Table of Contents

• A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention NetworksBiswadeep Chakraborty, Harshit Kumar, Saibal Mukhopadhyay. [doi]
• SKOLR: Structured Koopman Operator Linear RNN for Time-Series ForecastingYitian Zhang, Liheng Ma, Antonios Valkanas, Boris N. Oreshkin, Mark Coates. [doi]
• Preference-CFR: Beyond Nash Equilibrium for Better Game StrategiesQi Ju 0001, Thomas Tellier, Meng Sun, Zhemei Fang, Yunfeng Luo. [doi]
• An Optimistic Algorithm for online CMDPS with Anytime Adversarial ConstraintsJiahui Zhu, Kihyun Yu, Dabeen Lee, Xin Liu, Honghao Wei. [doi]
• Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order OptimizationHiroshi Sawada, Kazuo Aoyama, Yuya Hikima. [doi]
• Inverse problems with experiment-guided AlphaFoldSai Advaith Maddipatla, Nadav Bojan Sellam, Meital Bojan, Sanketh Vedula, Paul Schanda, Ailie Marx, Alexander M. Bronstein. [doi]
• A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form GamesYudong Hu, Haoran Li 0027, Congying Han, Tiande Guo, Bonan Li, Mingqiang Li. [doi]
• Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?Kexin Huang, Junkang Wu, Ziqian Chen, Xue Wang 0010, Jinyang Gao, Bolin Ding, Jiancan Wu, Xiangnan He 0001, Xiang Wang 0010. [doi]
• Provably Improving Generalization of Few-shot models with Synthetic DataLan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh, Dung D. Le, Long Tran-Thanh, Khoat Than. [doi]
• Let LLM Tell What to Prune and How Much to PruneMingzhe Yang, Sihao Lin, Changlin Li, Xiaojun Chang. [doi]
• LADA: Scalable Label-Specific CLIP Adapter for Continual LearningMao-Lin Luo, Zi-Hao Zhou, Tong Wei 0001, Min-Ling Zhang. [doi]
• RepoAudit: An Autonomous LLM-Agent for Repository-Level Code AuditingJinyao Guo, Chengpeng Wang 0001, Xiangzhe Xu, Zian Su, Xiangyu Zhang 0001. [doi]
• Provable Length Generalization in Sequence Prediction via Spectral FilteringAnnie Marsden, Evan Dogariu, Naman Agarwal, Xinyi Chen 0001, Daniel Suo, Elad Hazan. [doi]
• Accurate Identification of Communication Between Multiple Interacting Neural PopulationsBelle Liu, Jacob Sacks, Matthew D. Golub. [doi]
• Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time PointsJustin Lee, Behnaz Moradijamei, Heman Shakeri. [doi]
• MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spacesLoris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer. [doi]
• Dynamic Sparse Training of Diagonally Sparse NetworksAbhishek Tyagi, Arjun Iyer, William H. Renninger, Christopher Kanan, Yuhao Zhu 0001. [doi]
• Accelerating PDE-Constrained Optimization by the Derivative of Neural OperatorsZe Cheng, Zhuoyu Li, Xiaoqiang Wang, Jianing Huang, Zhizhou Zhang, Zhongkai Hao, Hang Su 0006. [doi]
• The Lock-in Hypothesis: Stagnation by AlgorithmTianyi Qiu, Zhonghao He, Tejasveer Chugh, Max Kleiman-Weiner. [doi]
• Polynomial-Delay MAG Listing with Novel Locally Complete Orientation RulesTian-Zuo Wang, Wen-Bo Du 0002, Zhi-Hua Zhou. [doi]
• Masked Generative Nested Transformers with Decode Time ScalingSahil Goyal, Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain 0002, Sujoy Paul. [doi]
• Sundial: A Family of Highly Capable Time Series Foundation ModelsYong Liu, Guo Qin, Zhiyuan Shi, Zhi Chen, Caiyin Yang, Xiangdong Huang 0001, Jianmin Wang 0001, Mingsheng Long. [doi]
• Maximum Coverage in Turnstile Streams with Applications to Fingerprinting MeasuresAlina Ene, Alessandro Epasto, Vahab Mirrokni, Hoai An Nguyen, Huy Nguyen, David P. Woodruff, Peilin Zhong. [doi]
• LIVS: A Pluralistic Alignment Dataset for Inclusive Public SpacesRashid Mushkani, Shravan Nayak, Hugo Berard, Allison Cohen, Shin Koseki, Hadrien Bertrand. [doi]
• Visual Abstraction: A Plug-and-Play Approach for Text-Visual RetrievalGuofeng Ding, Yiding Lu, Peng Hu 0002, Mouxing Yang, Yijie Lin 0001, Xi Peng 0001. [doi]
• Reward Modeling with Ordinal Feedback: Wisdom of the CrowdShang Liu, Yu Pan, Guanting Chen 0001, Xiaocheng Li. [doi]
• Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy DatasetsHaoye Lu, Qifan Wu, Yaoliang Yu. [doi]
• Unified Breakdown Analysis for Byzantine Robust GossipRenaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx. [doi]
• Aligned Multi Objective OptimizationYonathan Efroni, Ben Kretzu, Daniel Jiang 0002, Jalaj Bhandari, Zheqing Zhu, Karen Ullrich. [doi]
• Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema MatchingNabeel Seedat, Mihaela van der Schaar. [doi]
• Efficiently Vectorized MCMC on Modern AcceleratorsHugh Dance, Pierre Glaser, Peter Orbanz, Ryan P. Adams. [doi]
• No Task Left Behind: Isotropic Model Merging with Common and Task-Specific SubspacesDaniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer 0001. [doi]
• SKIM: Any-bit Quantization Pushing The Limits of Post-Training QuantizationRunsheng Bai, Bo Liu 0042, Qiang Liu 0001. [doi]
• Determinant Estimation under Memory Constraints and Neural Scaling LawsSiavash Ameli, Chris van der Heide, Liam Hodgkinson, Fred Roosta, Michael W. Mahoney. [doi]
• Smooth Interpolation for Improved Discrete Graph Generative ModelsYuxuan Song, Juntong Shi, Jingjing Gong, Minkai Xu, Stefano Ermon, Hao Zhou 0012, Wei-Ying Ma. [doi]
• WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation PredictionFanmeng Wang, Minjie Cheng, Hongteng Xu. [doi]
• Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference DataSiqi Guo 0003, Ilgee Hong, Vicente Balmaseda, Changlong Yu, Liang Qiu, Xin Liu, Haoming Jiang, Tuo Zhao, Tianbao Yang. [doi]
• Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge DistillationGuanglong Sun, Hongwei Yan, Liyuan Wang, Qian Li 0040, Bo Lei, Yi Zhong. [doi]
• Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive QueriesEdith Cohen, Mihir Singhal, Uri Stemmer. [doi]
• Core Context Aware Transformers for Long Context Language ModelingYaofo Chen, Zeng You, Shuhai Zhang, Haokun Li, Yirui Li, Yaowei Wang 0001, Mingkui Tan. [doi]
• Safety Reasoning with GuidelinesHaoyu Wang 0018, Zeyu Qin, Li Shen 0008, Xueqian Wang 0001, Dacheng Tao, Minhao Cheng. [doi]
• Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference PoliciesYuefan Cao, Xiaoyu Li 0001, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song 0002, Jiahao Zhang. [doi]
• On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature LearningThomas T. C. K. Zhang, Behrad Moniri, Ansh Nagwekar, Faraz Rahman, Anton Xue, Hamed Hassani, Nikolai Matni. [doi]
• Generalization and Robustness of the Tilted Empirical RiskGholamali Aminian, Amir R. Asadi, Tian Li 0005, Ahmad Beirami, Gesine Reinert, Samuel N. Cohen. [doi]
• Learning Multi-Level Features with Matryoshka Sparse AutoencodersBart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda. [doi]
• Generative Point Cloud RegistrationHaobo Jiang, Jin Xie 0001, Jian Yang 0003, Liang Yu, Jianmin Zheng. [doi]
• WeGeFT: Weight‑Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large ModelsChinmay Savadikar, Xi Song, Tianfu Wu 0001. [doi]
• RLTHF: Targeted Human Feedback for LLM AlignmentYifei Xu, Tusher Chakraborty, Emre Kiciman, Bibek Aryal, Srinagesh Sharma, Songwu Lu, Ranveer Chandra. [doi]
• AnyEdit: Edit Any Knowledge Encoded in Language ModelsHoucheng Jiang, Junfeng Fang, Ningyu Zhang 0001, Mingyang Wan, Guojun Ma, Xiang Wang 0010, Xiangnan He 0001, Tat-Seng Chua. [doi]
• Constrain Alignment with Sparse AutoencodersQingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang 0026, Yulan He 0001, Wenjie Li 0002, Jun Wang 0012, Yue Zhang 0004, Linyi Yang. [doi]
• Accelerated Diffusion Models via Speculative SamplingValentin De Bortoli, Alexandre Galashov, Arthur Gretton, Arnaud Doucet. [doi]
• Bipartite Ranking From Multiple Labels: On Loss Versus Label AggregationMichal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu, Sashank J. Reddi, Gang Fu, MohammadHossein Bateni, Sanjiv Kumar. [doi]
• Monte Carlo Tree Diffusion for System 2 PlanningJaesik Yoon, Hyeonseo Cho, Doojin Baek, Yoshua Bengio, Sungjin Ahn. [doi]
• Tackling Dimensional Collapse toward Comprehensive Universal Domain AdaptationHung-Chieh Fang, Po-Yi Lu, Hsuan-Tien Lin. [doi]
• Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAGWenbin Wang, Yongcheng Jing, Liang Ding 0006, Yingjie Wang, Li Shen 0008, Yong Luo 0002, Bo Du 0001, Dacheng Tao. [doi]
• Knowledge-Guided Wasserstein Distributionally Robust OptimizationZitao Wang, Ziyuan Wang, Molei Liu, Nian Si. [doi]
• Emotional Face-to-SpeechJiaxin Ye, Boyuan Cao, Hongming Shan. [doi]
• Ergodic Generative FlowsLeo Maxime Brunswic, Mateo Clémente, Rui-Heng Yang, Adam Sigal, Amir Rasouli, Yinchuan Li. [doi]
• Safe-EF: Error Feedback for Non-smooth Constrained OptimizationRustem Islamov, Yarden As, Ilyas Fatkhullin. [doi]
• Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through OptionsLakshmi Nair, Ian Trase, J. Mark Kim. [doi]
• Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse DatasetsNing Lu 0006, Shengcai Liu, Jiahao Wu 0004, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang 0012, Ke Tang 0001. [doi]
• Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via MixabilityYu-Jie Zhang, Peng Zhao 0006, Masashi Sugiyama. [doi]
• Sample-specific Noise Injection for Diffusion-based Adversarial PurificationYuhao Sun, Jiacheng Zhang, Zesheng Ye, Chaowei Xiao, Feng Liu. [doi]
• CAT Merging: A Training-Free Approach for Resolving Conflicts in Model MergingWenju Sun, Qingyong Li, Yangliao Geng, Boyang Li. [doi]
• Synthetic Text Generation for Training Large Language Models via Gradient MatchingDang Nguyen, Zeman Li, MohammadHossein Bateni, Vahab Mirrokni, Meisam Razaviyayn, Baharan Mirzasoleiman. [doi]
• GSM-∞: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian, Beidi Chen. [doi]
• CASE-Bench: Context-Aware SafEty Benchmark for Large Language ModelsGuangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such. [doi]
• Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled NewtonChengmei Niu, Zhenyu Liao 0001, Zenan Ling, Michael W. Mahoney. [doi]
• LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal DemonstrationsAnian Ruoss, Fabio Pardo, Harris Chan, Bonnie Li, Volodymyr Mnih, Tim Genewein. [doi]
• CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule GenerationThibaud Southiratn, Bonil Koo, Yijingxiu Lu, Sun Kim. [doi]
• Fleet of Agents: Coordinated Problem Solving with Large Language ModelsLars Henning Klein, Nearchos Potamitis, Roland Aydin, Robert West 0001, Caglar Gulcehre, Akhil Arora 0001. [doi]
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent SystemsShaokun Zhang, Ming Yin, Jieyu Zhang 0001, Jiale Liu, Zhiguang Han, Jingyang Zhang, Beibin Li, Chi Wang 0001, Huazheng Wang, Yiran Chen 0001, Qingyun Wu. [doi]
• What can large language models do for sustainable food?Anna T. Thomas, Adam Yee, Andrew Mayne, Maya B. Mathur, Dan Jurafsky, Kristina Gligoric. [doi]
• Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic WeightsSimone Moretti, Paolo Pellizzoni, Francesco Silvestri 0001. [doi]
• LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism IdentificationHang Gao 0004, Wenxuan Huang, Fengge Wu, Junsuo Zhao, Changwen Zheng, Huaping Liu 0001. [doi]
• Radio: Rate-Distortion Optimization for Large Language Model CompressionSean I. Young. [doi]
• David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-trainingWeijian Luo, Colin Zhang, Debing Zhang, Zhengyang Geng. [doi]
• PASS: Private Attributes Protection with Stochastic Data SubstitutionYizhuo Chen, Chun-Fu Chen 0001, Hsiang Hsu, Shaohan Hu, Tarek F. Abdelzaher. [doi]
• Confidence Difference Reflects Various Supervised Signals in Confidence-Difference ClassificationYuanchao Dai, Ximing Li 0002, Changchun Li. [doi]
• "Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance DriftHarvineet Singh, Fan Xia, Alexej Gossmann, Andrew Chuang, Julian C. Hong, Jean Feng. [doi]
• Redundancy Undermines the Trustworthiness of Self-Interpretable GNNsWenxin Tai, Ting Zhong, Goce Trajcevski, Fan Zhou 0002. [doi]
• NICE Data Selection for Instruction Tuning in LLMs with Non-differentiable Evaluation MetricJingtan Wang 0001, Xiaoqiang Lin, Rui Qiao 0006, Pang Wei Koh, Chuan-Sheng Foo, Bryan Kian Hsiang Low. [doi]
• ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM InferenceHanshi Sun, Li-Wen Chang, Wenlei Bao, Size Zheng 0001, Ningxin Zheng, Xin Liu 0086, Harry Dong, Yuejie Chi, Beidi Chen. [doi]
• RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of ExpertsTuan Truong, Chau Nguyen, Huy Nguyen, Minh Le, Trung Le 0001, Nhat Ho. [doi]
• DiTAR: Diffusion Transformer Autoregressive Modeling for Speech GenerationDongya Jia, Zhuo Chen 0006, Jiawei Chen, Chenpeng Du, Jian Wu, Jian Cong, Xiaobin Zhuang, Chumin Li 0002, Zhen Wei, Yuping Wang 0005, Yuxuan Wang 0002. [doi]
• When can in-context learning generalize out of task distribution?Page C. Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn, David J. Schwab. [doi]
• Diving into Self-Evolving Training for Multimodal ReasoningWei Liu 0131, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng 0001, Junxian He. [doi]
• Stream-level Flow Matching with Gaussian ProcessesGanchao Wei, Li Ma. [doi]
• SAE-V: Interpreting Multimodal Models for Enhanced AlignmentHantao Lou, Changye Li 0003, Jiaming Ji, Yaodong Yang 0001. [doi]
• Tractable Transformers for Flexible Conditional GenerationAnji Liu, Xuejie Liu, Dayuan Zhao, Mathias Niepert, Yitao Liang, Guy Van den Broeck. [doi]
• DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data ContaminationSimin Chen, Pranav Pusarla, Baishakhi Ray. [doi]
• 3D Question Answering via only 2D Vision-Language ModelsFengyun Wang, Sicheng Yu, Jiawei Wu, Jinhui Tang 0001, Hanwang Zhang, Qianru Sun. [doi]
• Enhancing Foundation Models with Federated Domain Knowledge InfusionJiaqi Wang 0002, Jingtao Li, Weiming Zhuang, Chen Chen 0043, Lingjuan Lyu, Fenglong Ma. [doi]
• Great Models Think Alike and this Undermines AI OversightShashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping. [doi]
• Advancing Personalized Learning with Neural Collapse for Long-Tail ChallengeHanglei Hu, Yingying Guo, Zhikang Chen, Sen Cui, Fei Wu 0001, Kun Kuang, Min Zhang 0005, Bo Jiang 0016. [doi]
• Interpreting the Repeated Token Phenomenon in Large Language ModelsItay Yona, Ilia Shumailov, Jamie Hayes, Yossi Gandelsman. [doi]
• The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model TrainingFabian Schaipp, Alexander Hägele, Adrien B. Taylor, Umut Simsekli, Francis Bach 0001. [doi]
• Universal Approximation of Mean-Field Models via TransformersShiba Biswal, Karthik Elamvazhuthi, Rishi Sonthalia. [doi]
• A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled EnvironmentRaanan Yehezkel Rohekar, Yaniv Gurwicz, Sungduk Yu, Estelle Aflalo, Vasudev Lal. [doi]
• EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission GraphGuancheng Wan, Zewen Liu 0005, Xiaojun Shan, Max S. Y. Lau, B. Aditya Prakash, Wei Jin 0009. [doi]
• Cross-City Latent Space Alignment for Consistency Region EmbeddingMeng Chen 0003, Hongwei Jia, Zechen Li 0003, Wenzhen Jia, Kai Zhao 0011, Hongjun Dai, Weiming Huang 0001. [doi]
• Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational AutoencodersKuheli Pratihar, Debdeep Mukhopadhyay. [doi]
• Causal Abstraction Learning based on the Semantic Embedding PrincipleGabriele D'Acunto, Fabio Massimo Zennaro, Yorgos Felekis, Paolo Di Lorenzo. [doi]
• Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical SpaceXihang Yue, Yi Yang 0001, Linchao Zhu. [doi]
• Universal Biological Sequence Reranking for Improved De Novo Peptide SequencingZijie Qiu, Jiaqi Wei, Xiang Zhang 0011, Sheng Xu, Kai Zou, Zhi Jin, Zhiqiang Gao, Nanqing Dong, Siqi Sun. [doi]
• Automated Hypothesis Validation with Agentic Sequential FalsificationsKexin Huang, Ying Jin, Ryan Li, Michael Y. Li, Emmanuel J. Candès, Jure Leskovec. [doi]
• Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of GraphsSiddharth Gollapudi, Ravishankar Krishnaswamy, Kirankumar Shiragur, Harsh Wardhan. [doi]
• Understanding and Improving Length Generalization in Recurrent ModelsRicardo Buitrago Ruiz, Albert Gu. [doi]
• Beyond Entropy: Region Confidence Proxy for Wild Test-Time AdaptationZixuan Hu, Yichun Hu, Xiaotong Li, Shixiang Tang, Lingyu Duan. [doi]
• Efficient ANN-SNN Conversion with Error Compensation LearningChang Liu, Jiangrong Shen, Xuming Ran, Mingkun Xu, Qi Xu 0008, Yi Xu 0008, Gang Pan 0001. [doi]
• A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural NetworksVarshita Kolipaka, Akshit Sinha, Debangan Mishra, Sumit Kumar, Arvindh Arun, Shashwat Goel, Ponnurangam Kumaraguru. [doi]
• Transformer-Based Spatial-Temporal Counterfactual Outcomes EstimationHe Li, Haoang Chi, Mingyu Liu, Wanrong Huang, Liyang Xu, Wenjing Yang 0002. [doi]
• Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical CovariateYingzhen Yang. [doi]
• Prior Knowledge Guided Neural Architecture GenerationJingrong Xie, Han Ji, Yanan Sun 0001. [doi]
• T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingZhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang, Yujiang Li, Zijun Yao 0002, Juanzi Li, Jie Tang 0001, Yuxiao Dong. [doi]
• An All-Atom Generative Model for Designing Protein ComplexesRuizhe Chen, Dongyu Xue, Xiangxin Zhou, Zaixiang Zheng, Xiangxiang Zeng, Quanquan Gu. [doi]
• NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health DisordersJun-En Ding, Dongsheng Luo, Chenwei Wu 0006, Feng Liu 0011. [doi]
• Direct Prediction Set Minimization via Bilevel Conformal Classifier TrainingYuanjie Shi, Hooman Shahrokhi, Xuesong Jia, Xiongzhi Chen, Jana Doppa, Yan Yan 0006. [doi]
• Breaking the n1.5 Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander DecompositionAnders Aamand, Justin Y. Chen, Mina Dalirrooyfard, Slobodan Mitrovic, Yuriy Nevmyvaka, Sandeep Silwal, Yinzhan Xu. [doi]
• GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated CodeSamidha Verma, Arushi Goyal, Ananya Mathur, Ankit Anand, Sayan Ranu. [doi]
• PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward ModelBaijiong Lin, Weisen Jiang, Yuancheng Xu, Hao Chen, Ying-Cong Chen. [doi]
• On Teacher Hacking in Language Model DistillationDaniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel. [doi]
• Zero-Shot Cyclic Peptide Design via Composable Geometric ConstraintsDapeng Jiang, Xiangzhe Kong, Jiaqi Han, Mingyu Li, Rui Jiao, Wenbing Huang 0001, Stefano Ermon, Jianzhu Ma, Yang Liu 0005. [doi]
• Inductive Moment MatchingLinqi Zhou, Stefano Ermon, Jiaming Song. [doi]
• LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and ModelsLukas Helff, Felix Friedrich, Manuel Brack, Kristian Kersting, Patrick Schramowski. [doi]
• One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual RepresentationXiaoyu Yang 0007, Lijian Xu, Hongsheng Li 0001, Shaoting Zhang 0001. [doi]
• Topology-aware Neural Flux Prediction Guided by PhysicsHaoyang Jiang, Jindong Wang, Xingquan Zhu 0001, Yi He 0007. [doi]
• A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak FeaturesKosuke Sugiyama, Masato Uchida. [doi]
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMsShenao Zhang, Zhihan Liu, Boyi Liu 0001, Yufeng Zhang 0007, Yingxiang Yang, Yongfei Liu, Liyu Chen, Tao Sun, Zhaoran Wang 0001. [doi]
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation ModelsJiawei Zhang 0013, Xuan Yang, Taiqi Wang, Yu Yao, Aleksandr Petiushko, Bo Li 0026. [doi]
• Selective Response Strategies for GenAIBoaz Taitler, Omer Ben-Porat. [doi]
• Modified K-means Algorithm with Local Optimality GuaranteesMingyi Li, Michael R. Metel, Akiko Takeda. [doi]
• Linear Q-Learning Does Not Diverge in L2: Convergence Rates to a Bounded SetXinyu Liu, Zixuan Xie, Shangtong Zhang. [doi]
• Diverging Preferences: When do Annotators Disagree and do Models Know?Michael J. Q. Zhang, Zhilin Wang, Jena D. Hwang, Yi Dong, Olivier Delalleau, Yejin Choi 0001, Eunsol Choi, Xiang Ren 0001, Valentina Pyatkin. [doi]
• Towards Attributions of Input Variables in a CoalitionXinhao Zheng, Huiqi Deng, Quanshi Zhang. [doi]
• Calibrated Physics-Informed Uncertainty QuantificationVignesh Gopakumar, Ander Gray, Lorenzo Zanisi, Timothy Nunn, Daniel Giles, Matt J. Kusner, Stanislas Pamela, Marc Peter Deisenroth. [doi]
• PINNsAgent: Automated PDE Surrogation with Large Language ModelsQingpo Wuwu, Chonghan Gao, Tianyu Chen, Yihang Huang, Yuekai Zhang, Jianing Wang, Jianxin Li 0002, Haoyi Zhou, Shanghang Zhang. [doi]
• EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization FormulationsHaotian Zhai, Connor Lawless, Ellen Vitercik, Liu Leqi. [doi]
• Testing Conditional Mean Independence Using Generative Neural NetworksYi Zhang, Linjun Huang, Yun Yang, Xiaofeng Shao. [doi]
• Kinetic Langevin Diffusion for Crystalline Materials GenerationFrançois R. J. Cornet, Federico Bergamin, Arghya Bhowmik, Juan Maria Garcia Lastra, Jes Frellsen, Mikkel N. Schmidt. [doi]
• SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph RetrievalNikolaos Chaidos, Angeliki Dimitriou, Maria Lymperaiou, Giorgos Stamou. [doi]
• Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss FunctionChristopher Subich, Syed Zahid Husain, Leo Separovic, Jing Yang. [doi]
• DIS-CO: Discovering Copyrighted Content in VLMs Training DataAndré V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei Li 0005. [doi]
• Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference TimeXiaoxuan Han, Songlin Yang, Wei Wang 0025, Yang Li, Jing Dong 0003. [doi]
• Time Series Representations with Hard-Coded InvariancesThibaut Germain, Chrysoula Kosma, Laurent Oudre. [doi]
• Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning TreesNate Veldt, Thomas Stanley, Benjamin W. Priest, Trevor Steil, Keita Iwabuchi, T. S. Jayram, Geoffrey Sanders. [doi]
• CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal LearningQingqing Cao, Mahyar Najibi, Sachin Mehta. [doi]
• Simple Policy OptimizationZhengpeng Xie, Qiang Zhang 0029, Fan Yang 0092, Marco Hutter 0001, Renjing Xu. [doi]
• Retrieval Augmented Time Series ForecastingSungwon Han 0001, SeungEon Lee 0001, Meeyoung Cha, Sercan Ö. Arik, Jinsung Yoon. [doi]
• Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance EstimationJingyu Liu, Beidi Chen, Ce Zhang 0001. [doi]
• XAttnMark: Learning Robust Audio Watermarking with Cross-AttentionYixin Liu 0002, Lie Lu, Jihui Jin, Lichao Sun 0001, Andrea Fanelli. [doi]
• Cross-environment Cooperation Enables Zero-shot Multi-agent CoordinationKunal Jha, Wilka Carvalho, Yancheng Liang, Simon Shaolei Du, Max Kleiman-Weiner, Natasha Jaques. [doi]
• Unpaired Point Cloud Completion via Unbalanced Optimal TransportTaekyung Lee, Jaemoo Choi, Jaewoong Choi, Myungjoo Kang. [doi]
• Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional CoverageKonstantina Bairaktari, Jiayun Wu, Steven Wu 0001. [doi]
• Function Encoders: A Principled Approach to Transfer Learning in Hilbert SpacesTyler Ingebrand, Adam J. Thorpe, Ufuk Topcu. [doi]
• Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic ProgramsZiang Chen, Xiaohan Chen 0001, Jialin Liu 0003, Xinshang Wang, Wotao Yin. [doi]
• Meta Optimality for Demographic Parity Constrained Regression via Post-ProcessingKazuto Fukuchi. [doi]
• A Checks-and-Balances Framework for Context-Aware Ethical AI AlignmentEdward Y. Chang. [doi]
• EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image ModelingTheodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis. [doi]
• Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-JudgeSwarnadeep Saha, Xian Li 0003, Marjan Ghazvininejad, Jason E. Weston, Tianlu Wang. [doi]
• Organize the Web: Constructing Domains Enhances Pre-Training Data CurationAlexander Wettig, Kyle Lo, Sewon Min, Hannaneh Hajishirzi, Danqi Chen 0001, Luca Soldaini. [doi]
• Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained ModelsDaiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Susumu Takeuchi. [doi]
• Ranking with Multiple Oracles: From Weak to Strong Stochastic TransitivityTao Jin 0002, Yue Wu, Quanquan Gu, Farzad Farnoud. [doi]
• Strategic Planning: A Top-Down Approach to Option GenerationMax Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar. [doi]
• The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity DataThomas Pouplin, Kasia Kobalczyk, Hao Sun 0017, Mihaela van der Schaar. [doi]
• On Temperature Scaling and Conformal Prediction of Deep ClassifiersLahav Dabah, Tom Tirer. [doi]
• scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell DataOlga Ovcharenko, Florian Barkmann, Philip Toma, Imant Daunhawer, Julia E. Vogt, Sebastian Schelter, Valentina Boeva. [doi]
• Ranked Entropy Minimization for Continual Test-Time AdaptationJisu Han, Jaemin Na, Wonjun Hwang. [doi]
• On the Interplay between Graph Structure and Learning Algorithms in Graph Neural NetworksJunwei Su, Chuan Wu 0001. [doi]
• Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version MatchingJoan Serrà, Recep Oguz Araz, Dmitry Bogdanov, Yuki Mitsufuji. [doi]
• Exact Recovery of Sparse Binary Vectors from Generalized Linear MeasurementsArya Mazumdar, Neha Sangwan. [doi]
• Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D StructuresYingzhao Jian, Yue Zhang 0004, Ying Wei 0001, Hehe Fan, Yi Yang 0001. [doi]
• Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving SparsificationLangzhang Liang, Fanchen Bu, Zixing Song, Zenglin Xu, Shirui Pan, Kijung Shin. [doi]
• Adaptive Elicitation of Latent Information Using Natural LanguageJimmy Wang, Thomas P. Zollo, Richard S. Zemel, Hongseok Namkoong. [doi]
• Contextual Linear Bandits with Delay as PayoffMengxiao Zhang, Yingfei Wang, Haipeng Luo. [doi]
• I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-ExpertsJiayi Xin, Sukwon Yun, Jie Peng 0002, Inyoung Choi, Jenna l. Ballard, Tianlong Chen 0001, Qi Long. [doi]
• A Bregman Proximal Viewpoint on Neural OperatorsAbdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo, Amaury Habrard, Massimiliano Pontil, Rémi Emonet, Marc Sebban. [doi]
• TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut OptimizationHaowen Ma, Zhiguo Long, Hua Meng 0001. [doi]
• Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal TransportMingyang Sun, Pengxiang Ding, Weinan Zhang 0001, Donglin Wang. [doi]
• Geometric and Physical Constraints Synergistically Enhance Neural PDE SurrogatesYunfei Huang, David S. Greenberg. [doi]
• SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from PixelsMalte Mosbach, Jan Niklas Ewertz, Angel Villar-Corrales, Sven Behnke. [doi]
• Inference-Time Alignment of Diffusion Models with Direct Noise OptimizationZhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong 0001, Fan Wang 0019, Tsung-Hui Chang. [doi]
• FedECADO: A Dynamical System Model of Federated LearningAayushya Agarwal, Gauri Joshi, Lawrence T. Pileggi. [doi]
• Dynamic Similarity Graph Construction with Kernel Density EstimationSteinar Laenen, Peter Macgregor, He Sun 0001. [doi]
• PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel SimilarityMustafa Burak Gurbuz, Xingyu Zheng, Constantine Dovrolis. [doi]
• How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality ReductionJun Chen, Hong Chen, Yonghua Yu, Yiming Ying. [doi]
• 3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric PriorsYujun Huang, Bin Chen 0011, Niu Lian, Xin Wang 0001, Baoyi An, Tao Dai 0001, Shu-Tao Xia. [doi]
• A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPOXingyu Zhou 0001, Yulian Wu, Francesco Orabona. [doi]
• One-Step Generalization Ratio Guided Optimization for Domain GeneralizationSumin Cho, Dongwon Kim, Kwangsu Kim. [doi]
• Defending LVLMs Against Vision Attacks Through Partial-Perception SupervisionQi Zhou 0012, Dongxia Wang 0002, Tianlin Li, Yun Lin 0001, Yang Liu 0003, Jin Song Dong 0001, Qing Guo 0005. [doi]
• Rethinking the Bias of Foundation Model under Long-tailed DistributionJiahao Chen, Bin Qin 0001, Jiangmeng Li, Hao Chen 0102, Bing Su 0001. [doi]
• Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement LearningZhihe Yang, Yunjian Xu, Yang Zhang. [doi]
• The impact of uncertainty on regularized learning in gamesPierre-Louis Cauvin, Davide Legacci, Panayotis Mertikopoulos. [doi]
• Reliable and Efficient Amortized Model-based EvaluationSang T. Truong, Yuheng Tu, Percy Liang, Bo Li 0026, Sanmi Koyejo. [doi]
• Stable Fair Graph Representation Learning with Lipschitz ConstraintQiang Chen, Zhongze Wu, Xiu Su, Xi Lin 0003, Zhe Qu, Shan You, Shuo Yang 0006, Chang Xu 0002. [doi]
• Large Language Models to Diffusion FinetuningEdoardo Cetin, Tianyu Zhao 0001, Yujin Tang. [doi]
• Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of InvarianceYusong Wang, Shiyin Tan, Jialun Shen, Yicheng Xu, Haobo Song, Qi Xu 0008, Prayag Tiwari, Mingkun Xu. [doi]
• Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow ModelsRafal Karczewski, Markus Heinonen, Vikas K. Garg 0001. [doi]
• Primal-Dual Neural Algorithmic ReasoningYu He, Ellen Vitercik. [doi]
• Topological Signatures of Adversaries in Multimodal AlignmentsMinh N. Vu, Geigh Zollicoffer, Huy Mai, Ben Nebgen, Boian S. Alexandrov, Manish Bhattarai. [doi]
• Closed-form Solutions: A New Perspective on Solving Differential EquationsShu Wei, Yanjie Li, Lina Yu, Weijun Li 0002, Min Wu, Linjun Sun, Jingyi Liu, Hong Qin 0007, Yusong Deng, Jufeng Han, Yan Pang. [doi]
• Taming Rectified Flow for Inversion and EditingJiangshan Wang, Junfu Pu, Zhongang Qi, Jiayi Guo, Yue Ma 0016, Nisha Huang, Yuxin Chen, Xiu Li 0001, Ying Shan. [doi]
• MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property PredictionYeyun Chen, Jiangming Shi. [doi]
• Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian ApproximationDahun Shin, Dongyeop Lee, Jinseok Chung, Namhoon Lee. [doi]
• Mechanistic PDE Networks for Discovery of Governing EquationsAdeel Pervez, Efstratios Gavves, Francesco Locatello. [doi]
• RAPID: Long-Context Inference with Retrieval-Augmented Speculative DecodingGuanzheng Chen, Qilong Feng, Jinjie Ni, Xin Li 0056, Michael Qizhe Shieh. [doi]
• ZipAR: Parallel Autoregressive Image Generation through Spatial LocalityYefei He, Feng Chen, Yuanyu He, Shaoxuan He, Hong Zhou, Kaipeng Zhang, Bohan Zhuang. [doi]
• Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-BatchingAmit Attia, Ofir Gaash, Tomer Koren. [doi]
• Targeted control of fast prototyping through domain-specific interfaceYu-Zhe Shi, Mingchen Liu, Hanlu Ma, Qiao Xu, Huamin Qu, Kun He 0001, Lecheng Ruan, Qining Wang. [doi]
• Stealix: Model Stealing via Prompt EvolutionZhixiong Zhuang, Hui-Po Wang, Maria-Irina Nicolae, Mario Fritz. [doi]
• Active Reward Modeling: Adaptive Preference Labeling for Large Language Model AlignmentYunyi Shen, Hao Sun 0017, Jean-Francois Ton. [doi]
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMsYinong Oliver Wang, Nivedha Sivakumar, Falaah Arif Khan, Katherine Metcalf, Adam Golinski, Natalie Mackraz, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff. [doi]
• Weakly-Supervised Contrastive Learning for Imprecise Class LabelsZi-Hao Zhou, Jun-Jie Wang, Tong Wei 0001, Min-Ling Zhang. [doi]
• Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut ApproachJin Zhu, Jingyi Li, Hongyi Zhou, Yinan Lin, Zhenhua Lin, Chengchun Shi. [doi]
• The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic TextMatthieu Meeus, Lukas Wutschitz, Santiago Zanella Béguelin, Shruti Tople, Reza Shokri. [doi]
• Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement LearningCheol Woo Kim, Jai Moondra, Shresth Verma, Madeleine Pollack, Lingkai Kong, Milind Tambe, Swati Gupta 0001. [doi]
• Fixed-Confidence Multiple Change Point Identification under Bandit FeedbackJoseph Lazzaro, Ciara Pike-Burke. [doi]
• When Do LLMs Help With Node Classification? A Comprehensive AnalysisXixi Wu, Yifei Shen, Fangzhou Ge, Caihua Shan, Yizhu Jiao, Xiangguo Sun, Hong Cheng 0001. [doi]
• Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density ClustersLixin Yuan, Yirui Wu, Wenxiao Zhang, Minglei Yuan, Jun Liu 0036. [doi]
• PhantomWiki: On-Demand Datasets for Reasoning and Retrieval EvaluationAlbert Gong, Kamile Stankeviciute, Chao Wan, Anmol Kabra, Raphael Thesmar, Johann Lee, Julius Klenke, Carla P. Gomes, Kilian Q. Weinberger. [doi]
• Dequantified Diffusion-Schrödinger Bridge for Density Ratio EstimationWei Chen 0165, Shigui Li, Jiacheng Li, Junmei Yang, John Paisley, Delu Zeng. [doi]
• Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG AnalysisWeiyu Guo, Ziyue Qiao, Ying Sun 0006, Yijie Xu, Hui Xiong 0001. [doi]
• Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit EmergenceGouki Minegishi, Hiroki Furuta, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo. [doi]
• Equivariant Neural Tangent KernelsPhilipp Misof, Pan Kessel, Jan E. Gerken. [doi]
• RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph ExplanationJingxiang Qu, Wenhan Gao 0002, Jiaxing Zhang, Xufeng Liu, Hua Wei, Haibin Ling, Yi Liu 0059. [doi]
• Clustering Items through Bandit Feedback: Finding the Right Feature out of ManyMaximilian Graf, Victor Thuot, Nicolas Verzelen. [doi]
• On the Learnability of Distribution Classes with Adaptive AdversariesTosca Lechner, Alex Bie, Gautam Kamath 0001. [doi]
• SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust ClassificationShuo Yang, Bardh Prenkaj, Gjergji Kasneci. [doi]
• Three-Dimensional Trajectory Prediction with 3DMoTraj DatasetHao Zhou 0014, Xu Yang 0004, Mingyu Fan, Lu Qi, Xiangtai Li, Ming-Hsuan Yang 0001, Fei Luo. [doi]
• On the Impact of Performative Risk Minimization for Binary Random VariablesNikita Tsoy, Ivan Kirev, Negin Rahimiyazdi, Nikola Konstantinov. [doi]
• Tensor-Var: Efficient Four-Dimensional Variational Data AssimilationYiming Yang, Xiaoyuan Cheng, Daniel Giles, Sibo Cheng, Yi He, Xiao Xue, Boli Chen, Yukun Hu. [doi]
• Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit ProblemsBotao Chen, Jongyeong Lee, Junya Honda. [doi]
• Causal Discovery from Conditionally Stationary Time SeriesCarles Balsells Rodas, Xavier Sumba, Tanmayee Narendra, Ruibo Tu, Gabriele Beate Schweikert, Hedvig Kjellström, Yingzhen Li. [doi]
• BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM InferenceWonsuk Jang, Thierry Tambe. [doi]
• STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector QuantizationHao Li, Qi Lv 0001, Rui Shao 0001, Xiang Deng 0002, Yinchuan Li, Jianye Hao, Liqiang Nie. [doi]
• Kernel Quantile Embeddings and Associated Probability MetricsMasha Naslidnyk, Siu Lun Chau, François-Xavier Briol, Krikamol Muandet. [doi]
• RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal ControlMingyuan Li 0006, Jiahao Wang, Guangsheng Yu, Xu Wang 0004, Qianrun Chen, Wei Ni 0001, Lixiang Li 0001, Haipeng Peng. [doi]
• Agent Workflow MemoryZora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig. [doi]
• CollabLLM: From Passive Responders to Active CollaboratorsShirley Wu, Michel Galley, Baolin Peng, Hao Cheng 0002, Gavin Li, Yao Dou, Weixin Cai, James Zou 0001, Jure Leskovec, Jianfeng Gao 0001. [doi]
• Optimizing Language Models for Inference Time Objectives using Reinforcement LearningYunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos. [doi]
• GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric AlgebrasEkaterina Filimoshina, Dmitry Shirokov. [doi]
• Token Assorted: Mixing Latent and Text Tokens for Improved Language Model ReasoningDijia Su, Hanlin Zhu, Yingchen Xu, Jiantao Jiao, Yuandong Tian, Qinqing Zheng. [doi]
• Active Treatment Effect Estimation via Limited SamplesZhiheng Zhang, Haoxiang Wang, Haoxuan Li 0001, Zhouchen Lin. [doi]
• Disentangled Graph Spectral Domain AdaptationLiang Yang 0002, Xin Chen, Jiaming Zhuo, Di Jin 0001, Chuan Wang 0002, Xiaochun Cao, Zhen Wang 0004, Yuanfang Guo. [doi]
• On the Provable Separation of Scales in Maximal Update ParameterizationLetong Hong, Zhangyang Wang. [doi]
• Adaptive Self-improvement LLM Agentic System for ML Library DevelopmentGenghan Zhang, Weixin Liang, Olivia Hsu, Kunle Olukotun. [doi]
• Compositional Causal Reasoning Evaluation in Language ModelsJacqueline R. M. A. Maasch, Alihan Hüyük, Xinnuo Xu, Aditya V. Nori, Javier González 0002. [doi]
• A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGDRuinan Jin, Xiao Li, Yaoliang Yu, Baoxiang Wang 0001. [doi]
• Hierarchical Reinforcement Learning with Targeted Causal InterventionsMohammadsadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Matthias Grossglauser. [doi]
• Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution RegularizationDuo Liu, Zhiquan Tan, Linglan Zhao, Zhongqiang Zhang, Xiangzhong Fang, Weiran Huang 0001. [doi]
• Importance Corrected Neural JKO SamplingJohannes Hertrich, Robert Gruhlke. [doi]
• Memorization Sinks: Isolating Memorization during LLM TrainingGaurav Rohit Ghosal, Pratyush Maini, Aditi Raghunathan. [doi]
• Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset DistillationRihong Qiu, Xinke Jiang, Yuchen Fang 0001, Hongbin Lai, Hao Miao 0001, Xu Chu, Junfeng Zhao 0001, Yasha Wang. [doi]
• Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without ForgettingChen Huang 0001, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Joshua M. Susskind. [doi]
• The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large DeviationsWaïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. [doi]
• Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced DataCorinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong 0002. [doi]
• Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated LearningHongyao Chen, Tianyang Xu, Xiaojun Wu 0001, Josef Kittler. [doi]
• "Why Is There a Tumor?": Tell Me the Reason, Show Me the EvidenceMengmeng Ma 0002, Tang Li 0005, Yunxiang Peng, Lu Lin, Volkan Beylergil, Binsheng Zhao, Oguz Akin, Xi Peng 0005. [doi]
• Divide and Conquer: Learning Label Distribution with SubtasksHaitao Wu, Weiwei Li 0001, Xiuyi Jia. [doi]
• Label Distribution Propagation-based Label Completion for CrowdsourcingTong Wu, Liangxiao Jiang, Wenjun Zhang 0012, Chaoqun Li 0001. [doi]
• GCAL: Adapting Graph Models to Evolving Domain ShiftsZiyue Qiao, Qianyi Cai, Hao Dong 0010, Jiawei Gu, Pengyang Wang, Meng Xiao 0001, Xiao Luo 0001, Hui Xiong 0001. [doi]
• OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature ExtractionHuang Huang, Fangchen Liu, Letian Fu, Tingfan Wu, Mustafa Mukadam, Jitendra Malik, Ken Goldberg, Pieter Abbeel. [doi]
• Graph Adaptive Autoregressive Moving Average ModelsMoshe Eliasof, Alessio Gravina, Andrea Ceni, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schönlieb. [doi]
• DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelSiwei Xia, Li Sun 0012, Tiantian Sun, Qingli Li. [doi]
• Shielded Diffusion: Generating Novel and Diverse Images using Sparse RepellencyMichael Kirchhof, James Thornton, Louis Béthune, Pierre Ablin, Eugène Ndiaye, Marco Cuturi. [doi]
• Simplifying DINO via Coding Rate RegularizationZiyang Wu, Jingyuan Zhang, Druv Pai, Xudong Wang, Chandan Singh, Jianwei Yang, Jianfeng Gao 0001, Yi Ma 0001. [doi]
• La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse ActivationKai Liu, Bowen Xu, Shaoyu Wu, Xin Chen, Hao Zhou, Yongliang Tao, Lulu Hu. [doi]
• What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent CapabilitiesWendong Bu, Yang Wu, Qifan Yu, Minghe Gao, Bingchen Miao, Zhenkui Zhang, Kaihang Pan, Liyunfei, Mengze Li 0001, Wei Ji 0008, Juncheng Li 0006, Siliang Tang, Yueting Zhuang. [doi]
• Low-Rank Tensor Transitions (LoRT) for Transferable Tensor RegressionAndong Wang, Yuning Qiu, Zhong Jin, GuoXu Zhou, Qibin Zhao. [doi]
• Demystifying Catastrophic Forgetting in Two-Stage Incremental Object DetectorQirui Wu, Shizhou Zhang, De Cheng, Yinghui Xing, Di Xu, Peng Wang 0015, Yanning Zhang 0001. [doi]
• Adaptive Flow Matching for Resolving Small-Scale PhysicsStathi Fotiadis, Noah D. Brenowitz, Tomas Geffner, Yair Cohen, Michael S. Pritchard, Arash Vahdat, Morteza Mardani. [doi]
• Focus On This, Not That! Steering LLMs with Adaptive Feature SpecificationTom A. Lamb, Adam Davies, Alasdair Paren, Philip Torr 0001, Francesco Pinto. [doi]
• Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data SilosTianyi Zhang, Yu Cao 0001, Dianbo Liu. [doi]
• Quadruple Attention in Many-body Systems for Accurate Molecular Property PredictionsJiahua Rao, Dahao Xu, Wentao Wei, Yicong Chen, Mingjun Yang, Yuedong Yang. [doi]
• Robust Multi-bit Text Watermark with LLM-based ParaphrasersXiaojun Xu, Jinghan Jia, Yuanshun Yao, Yang Liu, Hang Li 0001. [doi]
• Doubly Protected Estimation for Survival Outcomes Utilizing External Controls for Randomized Clinical TrialsChenyin Gao, Shu Yang, Mingyang Shan, Wenyu Ye, Ilya Lipkovich, Douglas Faries. [doi]
• Online Learning in the Random-Order ModelMartino Bernasconi, Andrea Celli, Riccardo Colini-Baldeschi, Federico Fusco 0001, Stefano Leonardi 0001, Matteo Russo 0002. [doi]
• Channel Normalization for Time Series Channel IdentificationSeunghan Lee, Taeyoung Park, Kibok Lee 0003. [doi]
• Reward-free World Models for Online Imitation LearningShangzhe Li, Zhiao Huang, Hao Su 0001. [doi]
• GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language ModelsZhaohong Huang, Yuxin Zhang 0002, Jingjing Xie, Fei Chao 0001, Rongrong Ji. [doi]
• Rapid Overfitting of Multi-Pass SGD in Stochastic Convex OptimizationShira Vansover-Hager, Tomer Koren, Roi Livni. [doi]
• Scalable Gaussian Processes with Latent Kronecker StructureJihao Andreas Lin, Sebastian Ament, Maximilian Balandat, David Eriksson, José Miguel Hernández-Lobato, Eytan Bakshy. [doi]
• TimeBase: The Power of Minimalism in Efficient Long-term Time Series ForecastingQihe Huang, Zhengyang Zhou, Kuo Yang, Zhongchao Yi, Xu Wang, Yang Wang 0015. [doi]
• Implicit Language Models are RNNs: Balancing Parallelization and ExpressivityMark Schöne, Babak Rahmani, Heiner Kremer, Fabian Falck, Hitesh Ballani, Jannes Gladrow. [doi]
• Preference Optimization for Combinatorial Optimization ProblemsMingjun Pan, Guanquan Lin, You-Wei Luo, Bin Zhu, Zhien Dai, Lijun Sun, Chun Yuan. [doi]
• Textual Unlearning Gives a False Sense of UnlearningJiacheng Du, Zhibo Wang 0001, Jie Zhang 0081, Xiaoyi Pang, Jiahui Hu, Kui Ren 0001. [doi]
• Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-developmentDaoyuan Chen, Haibin Wang, Yilun Huang 0004, Ce Ge, Yaliang Li, Bolin Ding, Jingren Zhou 0001. [doi]
• Sample Complexity of Correlation Detection in the Gaussian Wigner ModelDong Huang, Pengkun Yang. [doi]
• ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain ShiftsSamar Khanna, Medhanie Irgau, David B. Lobell, Stefano Ermon. [doi]
• IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series PredictionZhangyi Hu, Jiemin Wu, Hua Xu, Mingqian Liao, Ninghui Feng, Bo Gao, Songning Lai, Yutao Yue. [doi]
• Polynomial-Time Approximability of Constrained Reinforcement LearningJeremy McMahan. [doi]
• Spherical-Nested Diffusion Model for Panoramic Image OutpaintingXiancheng Sun, Senmao Ma, Shengxi Li, Mai Xu, Jingyuan Xia, Lai Jiang 0004, Xin Deng 0002, Jiali Wang. [doi]
• Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence MinimizationKyurae Kim, Zuheng Xu, Jacob R. Gardner, Trevor Campbell. [doi]
• Fully Heteroscedastic Count Regression with Deep Double Poisson NetworksSpencer Young, Porter Jenkins, Longchao Da, Jeffrey Dotson, Hua Wei 0001. [doi]
• Joint Localization and Activation Editing for Low-Resource Fine-TuningWen Lai, Alexander Fraser 0001, Ivan Titov 0001. [doi]
• LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy OptimizationWenzhe Niu, Zongxia Xie, Yanru Sun, Wei He, Man Xu, Chao Hao. [doi]
• Temperature-Annealed Boltzmann GeneratorsHenrik Schopmans, Pascal Friederich. [doi]
• The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor ProductsYuqing Xie 0006, Ameya Daigavane, Mit Kotak, Tess E. Smidt. [doi]
• Tensor Product Neural Networks for Functional ANOVA ModelSeokhun Park, Insung Kong, Yongchan Choi, Chanmoo Park, Yongdai Kim. [doi]
• EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic EncryptionLeo de Castro, Daniel Escudero 0001, Adya Agrawal, Antigoni Polychroniadou, Manuela Veloso. [doi]
• ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output SpacesJinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar. [doi]
• Learning Monotonic Probabilities with a Generative Cost ModelYongxiang Tang, Yanhua Cheng, Xiaocheng Liu, Jiaochen Chen, Yanxiang Zeng, Ning Luo, Pengjia Yuan, Xialong Liu, Peng Jiang 0002. [doi]
• Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?Tom Jacobs, Chao Zhou, Rebekka Burkholz. [doi]
• Fast Exact Unlearning for In-Context Learning Data for LLMsAndrei Ioan Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot. [doi]
• Cradle: Empowering Foundation Agents towards General Computer ControlWeihao Tan, Wentao Zhang 0007, Xinrun Xu, Haochong Xia, Ziluo Ding, Boyu Li 0003, Bohan Zhou, Junpeng Yue, Jiechuan Jiang, Yewen Li, Ruyi An, Molei Qin, Chuqiao Zong, Longtao Zheng, Yujie Wu, Xiaoqiang Chai, Yifei Bi, Tianbao Xie, Pengjie Gu, Xiyun Li, Ceyao Zhang, Long Tian, Chaojie Wang 0001, Xinrun Wang, Börje F. Karlsson, Bo An 0001, Shuicheng Yan, Zongqing Lu 0002. [doi]
• R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement LearningHarsh Goel, Mohammad Omama, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi-Pari, Sandeep P. Chinchali. [doi]
• High-Fidelity Simultaneous Speech-To-Speech TranslationTom Labiausse, Laurent Mazaré, Edouard Grave, Alexandre Défossez, Neil Zeghidour. [doi]
• Layer-wise Quantization for Quantized Optimistic Dual AveragingAnh-Duc Nguyen, Ilia Markov, Frank Zhengqing Wu, Ali Ramezani-Kebrya, Kimon Antonakopoulos, Dan Alistarh, Volkan Cevher. [doi]
• Distillation Scaling LawsDan Busbridge, Amitis Shidani, Floris Weers, Jason Ramapuram, Etai Littwin, Russell Webb. [doi]
• Generative Social Choice: The Next GenerationNiclas Boehmer, Sara Fish, Ariel D. Procaccia. [doi]
• Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian InferenceYusuke Yamasaki, Kenta Niwa, Daiki Chijiwa, Takumi Fukami, Takayuki Miura. [doi]
• On the Private Estimation of Smooth Transport MapsClément Lalanne, Franck Iutzeler, Jean-Michel Loubes, Julien Chhor. [doi]
• Towards Learning to Complete Anything in LidarAyça Takmaz, Cristiano Saltori, Neehar Peri, Tim Meinhardt, Riccardo de Lutio, Laura Leal-Taixé, Aljosa Osep. [doi]
• SBGD: Improving Graph Diffusion Generative Model via Stochastic Block DiffusionJunwei Su, Shan Wu. [doi]
• Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter TransferBlake Bordelon, Cengiz Pehlevan. [doi]
• A Meta-learner for Heterogeneous Effects in Difference-in-DifferencesHui Lan, Haoge Chang, Eleanor Wiske Dillon, Vasilis Syrgkanis. [doi]
• Is Complex Query Answering Really Complex?Cosimo Gregucci, Bo Xiong, Daniel Hernández 0002, Lorenzo Loconte, Pasquale Minervini, Steffen Staab, Antonio Vergari. [doi]
• Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model InferenceJixian Zhou, Fang Dong, Ruijun Huang, Hengjie Cao, Mengyi Chen, Yifeng Yang, Anrui Chen, Mingzhi Dong, Yujiang Wang 0001, Dongsheng Li 0002, David A. Clifton, Qin Lv, Rui Zhu 0006, Chun Zhang, Fan Yang 0001, Tun Lu, Ning Gu 0001, Li Shang. [doi]
• Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image GenerationHoigi Seo, Wongi Jeong, Jae-sun Seo, Se Young Chun. [doi]
• Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion TransformersWeilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An, Libo Huang, Boyu Diao, Zixiang Zhao, Yongjun Xu 0001, Michele Magno. [doi]
• QuanONet: Quantum Neural Operator with Application to Differential EquationRuocheng Wang, Zhuo Xia, Ge Yan 0001, Junchi Yan. [doi]
• Sparsing Law: Towards Large Language Models with Greater Activation SparsityYuqi Luo, Chenyang Song, Xu Han 0007, Yingfa Chen, Chaojun Xiao, Xiaojun Meng, Liqun Deng, Jiansheng Wei, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space ModelsHung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu. [doi]
• Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement LearningZhiyao Zhang, Myeung Suk Oh, Hairi, Ziyue Luo, Alvaro Velasquez, Jia Liu 0002. [doi]
• Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal DataDavid Heurtel-Depeiges, Anian Ruoss, Joel Veness, Tim Genewein. [doi]
• Ferret: Federated Full-Parameter Tuning at Scale for Large Language ModelsYao Shu, Wenyang Hu, See-Kiong Ng, Bryan Kian Hsiang Low, Fei Richard Yu. [doi]
• Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time SeriesYicheng Luo, Bowen Zhang, Zhen Liu 0023, Qianli Ma 0001. [doi]
• Flopping for FLOPs: Leveraging Equivariance for Computational EfficiencyGeorg Bökman, David Nordström, Fredrik Kahl. [doi]
• Language Models May Verbatim Complete Text They Were Not Explicitly Trained OnKen Liu, Christopher A. Choquette-Choo, Matthew Jagielski, Peter Kairouz, Sanmi Koyejo, Percy Liang, Nicolas Papernot. [doi]
• Integration-free Kernels for Equivariant Gaussian Process ModellingTim Steinert, David Ginsbourger, August Lykke-Møller, Ove Christiansen, Henry Moss. [doi]
• Fast and Low-Cost Genomic Foundation Models via Outlier RemovalHaozheng Luo, Chenghao Qiu, Maojiang Su, Zhihan Zhou 0001, Zoe Mehta, Guo Ye, Jerry Yao-Chieh Hu, Han Liu 0001. [doi]
• Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning ModelsAnshuman Chhabra, Bo Li, Jian Chen 0016, Prasant Mohapatra, Hongfu Liu 0001. [doi]
• LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision TransformersBeom-Jin Kang, Nam-Joon Kim, Hyun Kim 0001. [doi]
• Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual LearningXinrui Wang, Shao-Yuan Li, Jiaqiang Zhang, Songcan Chen. [doi]
• Improving the Diffusability of AutoencodersIvan Skorokhodov, Sharath Girish, Benran Hu 0001, Willi Menapace, Yanyu Li, Rameen Abdal, Sergey Tulyakov, Aliaksandr Siarohin. [doi]
• Geometric Algebra Planes: Convex Implicit Neural VolumesIrmak Sivgin, Sara Fridovich-Keil, Gordon Wetzstein, Mert Pilanci. [doi]
• DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic predictionRudy Morel, Jiequn Han, Edouard Oyallon. [doi]
• BECAME: Bayesian Continual Learning with Adaptive Model MergingMei Li, Yuxiang Lu, Qinyan Dai, Suizhi Huang, Yue Ding 0001, Hongtao Lu 0001. [doi]
• SparseLoRA: Accelerating LLM Fine-Tuning with Contextual SparsitySamir Khaki, Xiuyu Li, Junxian Guo, Ligeng Zhu, Konstantinos N. Plataniotis, Amir Yazdanbakhsh, Kurt Keutzer, Song Han 0003, Zhijian Liu. [doi]
• Does learning the right latent variables necessarily improve in-context learning?Sarthak Mittal, Eric Elmoznino, Léo Gagnon, Sangnie Bhardwaj, Guillaume Lajoie, Dhanya Sridhar. [doi]
• ARS: Adaptive Reward Scaling for Multi-Task Reinforcement LearningMyungsik Cho, Jongeui Park, Jeonghye Kim, Youngchul Sung. [doi]
• D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent SamplesZijing Hu, Fengda Zhang, Kun Kuang. [doi]
• Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré-Hopf TheoremIn Huh, Changwook Jeong, Muhammad Alam. [doi]
• Generalized additive models via direct optimization of regularized decision stump forestsMagzhan Gabidolla, Miguel Á. Carreira-Perpiñán. [doi]
• IBCircuit: Towards Holistic Circuit Discovery with Information BottleneckTian Bian, Yifan Niu, Chaohao Yuan, Chengzhi Piao, Bingzhe Wu, Long-Kai Huang, Yu Rong 0001, Tingyang Xu, Hong Cheng 0001, Jia Li 0009. [doi]
• FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt LearningGanyu Wang, Jinjie Fang, Maxwell J. Yin, Bin Gu 0001, Xi Chen 0009, Boyu Wang 0004, Yi Chang 0001, Charles Ling 0001. [doi]
• Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe MethodKiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari, Shoham Sabach, Branislav Kveton. [doi]
• video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language ModelGuangzhi Sun, Yudong Yang, Jimin Zhuang, Changli Tang, Yixuan Li, Wei Li 0119, Zejun Ma 0001, Chao Zhang 0031. [doi]
• Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μ ParametrizationZixiang Chen, Greg Yang, Qingyue Zhao 0001, Quanquan Gu. [doi]
• An analytic theory of creativity in convolutional diffusion modelsMason Kamb, Surya Ganguli. [doi]
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at ScaleRogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Keunho Jang, Zheng Hui. [doi]
• Aequa: Fair Model Rewards in Collaborative Learning via Slimmable NetworksNurbek Tastan, Samuel Horváth, Karthik Nandakumar. [doi]
• PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIsJianqing Zhang, Yang Liu 0165, Jie Fu, Yang Hua 0001, Tianyuan Zou, Jian Cao, Qiang Yang 0001. [doi]
• Self-supervised Adversarial Purification for Graph Neural NetworksWoohyun Lee, Hogun Park. [doi]
• Flexible, Efficient, and Stable Adversarial Attacks on Machine UnlearningZihan Zhou, Yang Zhou 0001, Zijie Zhang 0001, Lingjuan Lyu, Da Yan 0001, Ruoming Jin, Dejing Dou. [doi]
• Falcon: Fast Visuomotor Policies via Partial DenoisingHaojun Chen, Minghao Liu, Chengdong Ma, Xiaojian Ma 0001, Zailin Ma, Huimin Wu 0001, Yuanpei Chen, Yifan Zhong, Mingzhi Wang, Qing Li 0003, Yaodong Yang 0001. [doi]
• Model-Based Exploration in Monitored Markov Decision ProcessesAlireza Kazemipour, Matthew E. Taylor, Michael Bowling. [doi]
• Tree-Sliced Wasserstein Distance: A Geometric PerspectiveHoang V. Tran, Huyen-Trang Pham, Tho Tran Huu, Minh-Khoi Nguyen-Nhat, Thanh T. Chu, Tam Le, Tan Minh Nguyen. [doi]
• HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud EncoderQi Yang 0003, Le Yang 0001, Geert Van Der Auwera, Zhu Li 0001. [doi]
• M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed QualityZiyan Wang, Zhicheng Zhang, Fei Fang 0001, Yali Du 0001. [doi]
• Towards Cost-Effective Reward Guided Text GenerationAhmad Rashid, Ruotian Wu, Rongqi Fan, Hongliang Li, Agustinus Kristiadi, Pascal Poupart. [doi]
• Can Transformers Reason Logically? A Study in SAT SolvingLeyan Pan, Vijay Ganesh 0001, Jacob D. Abernethy, Chris Esposo, Wenke Lee. [doi]
• SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation LearningJunyou Zhu, Langzhou He, Chao Gao 0001, Dongpeng Hou, Zhen Su, Philip S. Yu, Jürgen Kurths, Frank Hellmann. [doi]
• Towards a General Time Series Forecasting Model with Unified Representation and Adaptive TransferYihang Wang 0004, Yuying Qiu, Peng Chen 0038, Kai Zhao 0009, Yang Shu 0001, Zhongwen Rao, Lujia Pan, Bin Yang 0002, Chenjuan Guo. [doi]
• Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identificationJan Blechschmidt, Tom-Christian Riemer, Max Winkler, Martin Stoll, Jan-Frederik Pietschmann. [doi]
• A Theoretical Justification for Asymmetric Actor-Critic AlgorithmsGaspard Lambrechts, Damien Ernst, Aditya Mahajan. [doi]
• Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving GraphZhiqiang Wang, Jianghao Wen, Jianqing Liang. [doi]
• Improving Diversity in Language Models: When Temperature Fails, Change the LossAlexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Négrevergne. [doi]
• The Power of Random Features and the Limits of Distribution-Free Gradient DescentAri Karchmer, Eran Malach. [doi]
• DLP: Dynamic Layerwise Pruning in Large Language ModelsYuli Chen 0001, Bo Cheng 0001, Jiale Han 0001, Yingying Zhang, Yingting Li, Shuhao Zhang 0011. [doi]
• Identifying Causal Direction via Variational Bayesian CompressionQuang Duy Tran, Bao Duong, Phuoc Nguyen, Thin Nguyen. [doi]
• Model Uncertainty Quantification by Conformal Prediction in Continual LearningRui Gao 0004, Weiwei Liu. [doi]
• DPCore: Dynamic Prompt Coreset for Continual Test-Time AdaptationYunbei Zhang, Akshay Mehra, Shuaicheng Niu, Jihun Hamm. [doi]
• Distributed Conformal Prediction via Message PassingHaifeng Wen, Hong Xing, Osvaldo Simeone. [doi]
• Optimal Fair Learning Robust to Adversarial Distribution ShiftSushant Agarwal, Amit Deshpande 0001, Rajmohan Rajaraman, Ravi Sundaram. [doi]
• Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual FeedbackYafu Li, Xuyang Hu, Xiaoye Qu, Linjie Li, Yu Cheng 0001. [doi]
• Hierarchical Refinement: Optimal Transport to Infinity and BeyondPeter Halmos, Julian Gold, Xinhao Liu 0009, Benjamin J. Raphael. [doi]
• On the Robustness of Reward Models for Language Model AlignmentJiwoo Hong, Noah Lee, Eunki Kim, Guijin Son, Woojin Chung, Aman Gupta, Shao Tang, James Thorne. [doi]
• Censor Dependent Variational InferenceChuanhui Liu, Xiao Wang. [doi]
• An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural NetworksMohsen Dehghankar, Mahdi Erfanian, Abolfazl Asudeh. [doi]
• DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial ExamplesZhengzhao Pan, Hua Chen, Xiaogang Zhang. [doi]
• Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model FusionBinchi Zhang, Zaiyi Zheng, Zhengzhang Chen, Jundong Li. [doi]
• All-atom inverse protein folding through discrete flow matchingKai Yi, Kiarash Jamali, Sjors H. W. Scheres. [doi]
• Prompt-based Depth Pruning of Large Language ModelsJuyun Wee, Minjae Park, Jaeho Lee. [doi]
• Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PCTyler Clark, Mark Towers, Christine Evers, Jonathon Hare. [doi]
• Exponential Family Variational Flow Matching for Tabular Data GenerationAndrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem van de Meent. [doi]
• EvoPress: Accurate Dynamic Model Compression via Evolutionary SearchOliver Sieberling, Denis Kuznedelev, Eldar Kurtic, Dan Alistarh. [doi]
• Towards Theoretical Understanding of Sequential Decision Making with Preference FeedbackSimone Drago, Marco Mussi, Alberto Maria Metelli. [doi]
• Towards a Formal Theory of Representational CompositionalityEric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie. [doi]
• K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series ForecastingXingjian Wu, Xiangfei Qiu, Hongfan Gao, Jilin Hu, Bin Yang 0002, Chenjuan Guo. [doi]
• Aguvis: Unified Pure Vision Agents for Autonomous GUI InteractionYiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu 0009, Caiming Xiong. [doi]
• LAST SToP for Modeling Asynchronous Time SeriesShubham Gupta, Thibaut Durand, Graham W. Taylor, Lilian W. Bialokozowicz. [doi]
• Rethinking Score Distilling Sampling for 3D Editing and GenerationXingyu Miao, Haoran Duan 0001, Yang Long 0001, Jungong Han. [doi]
• DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger BridgeLiangliang Shi, Shenhui Zhang, Xingbo Du, Nianzu Yang, Junchi Yan. [doi]
• DPO Meets PPO: Reinforced Token Optimization for RLHFHan Zhong 0001, Zikang Shan, Guhao Feng, Wei Xiong 0015, Xinle Cheng, Li Zhao 0007, Di He 0001, Jiang Bian 0002, Liwei Wang 0001. [doi]
• SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction TuningJinpeng Chen 0003, Runmin Cong, Yuzhi Zhao, Hongzheng Yang, Guangneng Hu, Horace H. S. Ip, Sam Kwong. [doi]
• MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse AttentionYucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li 0002, Jianfeng Gao 0001, Yuqing Yang 0001, Lili Qiu. [doi]
• An End-to-End Model for Logits-Based Large Language Models WatermarkingKahim Wong, Jicheng Zhou, Jiantao Zhou 0001, Yain-Whar Si. [doi]
• Ad Hoc Teamwork via Offline Goal-Based Decision TransformersXinzhi Zhang, Hohei Chan, Deheng Ye, Yi Cai 0001, Mengchen Zhao. [doi]
• Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn MoreXialie Zhuang, Zhikai Jia, Jianjin Li, Zhenyu Zhang 0015, Li Shen 0008, Zheng Cao, Shiwei Liu 0003. [doi]
• Rethinking the Temperature for Federated Heterogeneous DistillationFan Qi, Daxu Shi, Chuokun Xu, Shuai Li, Changsheng Xu. [doi]
• Attributes Shape the Embedding Space of Face Recognition ModelsPierrick Leroy, Antonio Mastropietro, Marco Nurisso, Francesco Vaccarino. [doi]
• PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal VerificationHongwei Li, Yuheng Tang, Shiqi Wang 0032, Wenbo Guo 0002. [doi]
• Quantifying Memory Utilization with Effective State-SizeRom N. Parnichkun, Neehal Tumma, Armin W. Thomas, Alessandro Moro, Qi An, Taiji Suzuki, Atsushi Yamashita, Michael Poli, Stefano Massaroli. [doi]
• CodeSteer: Symbolic-Augmented Language Models via Code/Text GuidanceYongchao Chen, Yilun Hao, Yueying Liu, Yang Zhang 0001, Chuchu Fan. [doi]
• Private Model Personalization RevisitedConor Snedeker, Xinyu Zhou, Raef Bassily. [doi]
• Rethinking Time Encoding via Learnable Transformation FunctionsXi Chen 0072, Yateng Tang, Jiarong Xu, Jiawei Zhang 0001, Siwei Zhang 0001, Sijia Peng, Xuehao Zheng, Yun Xiong. [doi]
• Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIJulien Pourcel, Cédric Colas, Pierre-Yves Oudeyer. [doi]
• IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion ModelsHanting Wang, Tao Jin 0004, Wang Lin, Shulei Wang, Hai Huang 0013, Shengpeng Ji, Zhou Zhao 0001. [doi]
• Towards Memorization Estimation: Fast, Formal and FreeDeepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy 0001. [doi]
• ROME is Forged in Adversity: Robust Distilled Datasets via Information BottleneckZheng Zhou 0007, Wenquan Feng, Qiaosheng Zhang, Shuchang Lyu, Qi Zhao 0037, Guangliang Cheng. [doi]
• All-atom Diffusion Transformers: Unified generative modelling of molecules and materialsChaitanya K. Joshi, Xiang Fu 0005, Yi-Lun Liao, Vahe Gharakhanyan, Benjamin Kurt Miller, Anuroop Sriram, Zachary W. Ulissi. [doi]
• Uncertainty Quantification for LLM-Based Survey SimulationsChengpiao Huang, Yuhang Wu, Kaizheng Wang. [doi]
• Maximum Entropy Reinforcement Learning with Diffusion PolicyXiaoyi Dong, Jian Cheng 0001, Xi Sheryl Zhang. [doi]
• MissScore: High-Order Score Estimation in the Presence of Missing DataWenqin Liu, Haoze Hou, Erdun Gao, Biwei Huang, Qiuhong Ke, Howard D. Bondell, Mingming Gong. [doi]
• AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion ModelsYaopei Zeng, Yuanpu Cao, Bochuan Cao, Yurui Chang, Jinghui Chen, Lu Lin 0001. [doi]
• Vision Graph Prompting via Semantic Low-Rank DecompositionZixiang Ai, Zichen Liu, Jiahuan Zhou. [doi]
• SafeMap: Robust HD Map Construction from Incomplete ObservationsXiaoshuai Hao, Lingdong Kong, Rong Yin 0001, Pengwei Wang 0004, Jing Zhang 0037, Yunfeng Diao, Shu Zhao 0006. [doi]
• Improved Online Confidence Bounds for Multinomial Logistic BanditsJoongkyu Lee, Min-hwan Oh. [doi]
• Optimizing Temperature for Language Models with Multi-Sample InferenceWeihua Du, Yiming Yang 0002, Sean Welleck. [doi]
• Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple InteractionsYik Siu Chan, Narutatsu Ri, Yuxin Xiao, Marzyeh Ghassemi. [doi]
• Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem SolvingYuxuan Zhou 0002, Xien Liu, Chenwei Yan, Chen Ning, Xiao Zhang 0001, Boxun Li, Xiangling Fu, Shijin Wang 0001, Guoping Hu, Yu Wang 0002, Ji Wu 0002. [doi]
• Behavioral Exploration: Learning to Explore via In-Context AdaptationAndrew Wagenmaker, Zhiyuan Zhou, Sergey Levine. [doi]
• Sub-Sequential Physics-Informed Learning with State Space ModelChenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li 0002, Ruiyang Qin, Qingxiao Zheng, Jinjun Xiong. [doi]
• Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained NetworksAnas Jnini, Lorenzo Breschi, Flavio Vella. [doi]
• Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural PerspectiveAojun Lu, Hangjie Yuan, Tao Feng 0014, Yanan Sun 0001. [doi]
• ConceptAttention: Diffusion Transformers Learn Highly Interpretable FeaturesAlec Helbling, Tuna Han Salih Meral, Benjamin Hoover, Pinar Yanardag, Duen Horng Chau. [doi]
• Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM ManipulationsLee Cohen 0003, Connie Hong, Jack Hsieh, Judy Hanwen Shen. [doi]
• Ad-Hoc Human-AI Coordination ChallengeTin Dizdarevic, Ravi Hammond, Tobias Gessler, Anisoara Calinescu, Jonathan Cook 0004, Matteo Gallici, Andrei Lupu, Jakob Nicolaus Foerster. [doi]
• CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp ModelingFeifei Kou, Jiahao Wang, Lei Shi 0030, Yuhan Yao 0001, Yawen Li 0001, Suguo Zhu, Zhongbao Zhang, Junping Du 0001. [doi]
• Contextual Bandits for Unbounded Context DistributionsPuning Zhao, Rongfei Fan, Shaowei Wang 0003, Li Shen 0008, Qixin Zhang 0001, Zong Ke, Tianhang Zheng. [doi]
• Griffin: Towards a Graph-Centric Relational Database Foundation ModelYanbo Wang, Xiyuan Wang, Quan Gan, Minjie Wang, Qibin Yang, David Wipf, Muhan Zhang. [doi]
• Implicit Regularization for Tubal Tensor Factorizations via Gradient DescentSanthosh Karnik, Anna Veselovska, Mark A. Iwen, Felix Krahmer. [doi]
• Adversarial Inputs for Linear Algebra BackendsJonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer, Konrad Rieck. [doi]
• HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge AdaptationTianwei Lin, Wenqiao Zhang, Sijing Li, Yuqian Yuan, Binhe Yu, Haoyuan Li 0002, Wanggui He, Hao Jiang 0014, Mengze Li 0001, Xiaohui Song, Siliang Tang, Jun Xiao 0001, Hui Lin, Yueting Zhuang, Beng Chin Ooi. [doi]
• Best of Both Worlds: Regret Minimization versus Minimax PlayAdrian Müller 0002, Jon Schneider, Stratis Skoulakis, Luca Viano, Volkan Cevher. [doi]
• Multi-agent Architecture Search via Agentic SupernetGuibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang 0056, Lei Bai 0001, Xiang Wang 0010. [doi]
• Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an ExampleYuhan Helena Liu, Guangyu Robert Yang, Christopher J. Cueva. [doi]
• Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?Zi Liang, Haibo Hu 0001, Qingqing Ye 0001, Yaxin Xiao, Ronghua Li. [doi]
• MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUsTommaso Mencattini, Adrian Robert Minut, Donato Crisostomi, Andrea Santilli, Emanuele Rodolà. [doi]
• Categorical Schrödinger Bridge MatchingGrigoriy Ksenofontov, Alexander Korotin. [doi]
• Scaling Trends in Language Model RobustnessNikolaus H. R. Howe, Ian R. McKenzie, Oskar John Hollinsworth, Michal Zajac 0005, Tom Tseng, Aaron David Tucker, Pierre-Luc Bacon, Adam Gleave. [doi]
• Scaling Probabilistic Circuits via Monarch MatricesHonghua Zhang, Meihua Dang, Benjie Wang 0001, Stefano Ermon, Nanyun Peng 0001, Guy Van den Broeck. [doi]
• QT-DoG: Quantization-Aware Training for Domain GeneralizationSaqib Javed, Hieu Le 0001, Mathieu Salzmann. [doi]
• Generalization of noisy SGD in unbounded non-convex settingsLeello Tadesse Dadi, Volkan Cevher. [doi]
• Teaching Language Models to Critique via Reinforcement LearningZhihui Xie 0002, Jie Chen, Liyu Chen, Weichao Mao, Jingjing Xu, Lingpeng Kong. [doi]
• IT3: Idempotent Test-Time TrainingNikita Durasov, Assaf Shocher, Doruk Öner, Gal Chechik, Alexei A. Efros, Pascal Fua. [doi]
• Generalized Venn and Venn-Abers Calibration with Applications in Conformal PredictionLars van der Laan, Ahmed M. Alaa. [doi]
• Learning to Quantize for Training Vector-Quantized NetworksPeijia Qin, Jianguo Zhang. [doi]
• CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application VulnerabilitiesYuxuan Zhu 0003, Antony Kellermann, Dylan Bowman, Philip Li, Akul Gupta, Adarsh Danda, Richard Fang, Conner Jensen, Eric Ihli, Jason Benn, Jet Geronimo, Avi Dhir, Sudhit Rao, Kaicheng Yu, Twm Stone, Daniel Kang. [doi]
• PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMsXiaoyan Hu 0003, Ho-Fung Leung, Farzan Farnia. [doi]
• LOGO - Long cOntext aliGnment via efficient preference OptimizationZecheng Tang, Zechen Sun, Juntao Li 0005, Qiaoming Zhu, Min Zhang 0005. [doi]
• Measuring Representational Shifts in Continual Learning: A Linear Transformation PerspectiveJoonKyu Kim, Yejin Kim, Jy-yong Sohn. [doi]
• Doubly Robust Conformalized Survival Analysis with Right-Censored DataMatteo Sesia, Vladimir Svetnik. [doi]
• Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive ExpertsKun Cheng, Xiao He 0014, Lei Yu, Zhijun Tu, Mingrui Zhu, Nannan Wang 0001, Xinbo Gao 0001, Jie Hu 0021. [doi]
• SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptationJiayue Liu, Zhongchao Yi, Zhengyang Zhou, Qihe Huang, Kuo Yang, Xu Wang 0029, Yang Wang 0015. [doi]
• X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPHanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey 0001. [doi]
• Residual TPP: A Unified Lightweight Approach for Event Stream Data AnalysisRuoxin Yuan, Guanhua Fang. [doi]
• Aligning Multimodal Representations through an Information BottleneckAntonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana, Ricard Marxer, Alfonso Ortega 0001. [doi]
• Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?Wendong Zheng, Junyang Chen, Husheng Guo, Wenjian Wang. [doi]
• QMamba: On First Exploration of Vision Mamba for Image Quality AssessmentFengbin Guan, Xin Li 0082, Zihao Yu, Yiting Lu, Zhibo Chen 0001. [doi]
• Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series ForecastingJan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka, Stephan Günnemann. [doi]
• Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation LearningNgoc Bui, Menglin Yang 0001, Runjin Chen, Leonardo Neves, Mingxuan Ju, Rex Ying, Neil Shah, Tong Zhao 0003. [doi]
• EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLMZhuofan Zong, Dongzhi Jiang, Bingqi Ma, Guanglu Song, Hao Shao, Dazhong Shen, Yu Liu 0015, Hongsheng Li 0001. [doi]
• What Makes In-context Learning Effective for Mathematical ReasoningJiayu Liu, Zhenya Huang, Chaokun Wang, Xunpeng Huang, ChengXiang Zhai, Enhong Chen. [doi]
• Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head MaskingSenyu Han, Hongchuan Zeng, Kai Yu 0004, Lu Chen 0002. [doi]
• MIB: A Mechanistic Interpretability BenchmarkAaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna 0001, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov. [doi]
• Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology AlignmentShuo Wang, Bokui Wang, Zhixiang Shen, Boyan Deng, Zhao Kang 0001. [doi]
• COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain AdaptationWenxu Wang, Rui Zhou, Jing Wang, Yun Zhou, Cheng Zhu, Ruichun Tang, Bo Han, Nevin L. Zhang. [doi]
• A Mathematical Framework for AI-Human Integration in WorkL. Elisa Celis, Lingxiao Huang, Nisheeth K. Vishnoi. [doi]
• Scalable Approximation Algorithms for p-Wasserstein Distance and Its VariantsNathaniel Lahn, Sharath Raghvendra, Emma Saarinen, Pouyan Shirzadian. [doi]
• Understanding Mode Connectivity via Parameter Space SymmetryBo Zhao 0028, Nima Dehmamy, Robin Walters 0001, Rose Yu. [doi]
• Segment Anyword: Mask Prompt Inversion for Open-Set Grounded SegmentationZhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy, Dino Oglic, Tom Diethe, Philip Alexander Teare, Huiyu Zhou 0001, Chen Jin. [doi]
• Features are fate: a theory of transfer learning in high-dimensional regressionJavan Tahir, Surya Ganguli, Grant M. Rotskoff. [doi]
• Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional NetworksJincheng Huang 0005, Yujie Mo, Xiaoshuang Shi, Lei Feng 0006, Xiaofeng Zhu 0001. [doi]
• Continuous Bayesian Model Selection for Multivariate Causal DiscoveryAnish Dhir, Ruby Sedgwick, Avinash Kori, Ben Glocker, Mark van der Wilk. [doi]
• PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation modelsAlejandro Velez-Arce, Marinka Zitnik. [doi]
• Safety Certificate against Latent Variables with Partially Unidentifiable DynamicsHaoming Jing, Yorie Nakahira. [doi]
• Models of Heavy-Tailed Mechanistic UniversalityLiam Hodgkinson, Zhichao Wang, Michael W. Mahoney. [doi]
• Targeted Unlearning with Single Layer Unlearning GradientZikui Cai, Yaoteng Tan, M. Salman Asif. [doi]
• On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM ServingYeonju Ro, Zhenyu Zhang 0015, Souvik Kundu 0009, Zhangyang Wang, Aditya Akella. [doi]
• A Trichotomy for List Transductive Online LearningSteve Hanneke, Amirreza Shaeiri. [doi]
• Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache SharingKaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang 0001, Jun Xiao 0001, Long Chen 0016. [doi]
• Active Fine-Tuning of Multi-Task PoliciesMarco Bagatella, Jonas Hübotter, Georg Martius, Andreas Krause 0001. [doi]
• Trajectory Inference with Smooth Schrödinger BridgesWanli Hong, Yuliang Shi, Jonathan Niles-Weed. [doi]
• GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation LearningXiangheng Wang, Ziquan Fang, Chenglong Huang, Danlei Hu, Lu Chen 0001, Yunjun Gao. [doi]
• Tokenized Bandit for LLM Decoding and AlignmentSuho Shin 0001, Chenghao Yang 0001, Haifeng Xu, MohammadTaghi Hajiaghayi. [doi]
• OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt TuningCong Hua, Qianqian Xu 0001, Zhiyong Yang 0001, Zitai Wang, Shilong Bao, Qingming Huang. [doi]
• BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary OptimizationDongmin Bang, Inyoung Sung, Yinhua Piao, Sangseon Lee, Sun Kim. [doi]
• Fast Estimation of Partial Dependence Functions using TreesJinyang Liu, Tessa Steensgaard, Marvin N. Wright, Niklas Pfister, Munir Hiabu. [doi]
• Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image ManipulationMingyu Kang, Yong Suk Choi. [doi]
• Roll the dice & look before you leap: Going beyond the creative limits of next-token predictionVaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan. [doi]
• Cache Me If You Must: Adaptive Key-Value Quantization for Large Language ModelsAlina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Denis Mazur, Nikita Surkov, Ivan Ermakov, Dan Alistarh. [doi]
• Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them AllErmis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken. [doi]
• Understanding High-Dimensional Bayesian OptimizationLeonard Papenmeier, Matthias Poloczek, Luigi Nardi. [doi]
• Learning Smooth and Expressive Interatomic Potentials for Physical Property PredictionXiang Fu 0005, Brandon M. Wood, Luis Barroso-Luque, Daniel S. Levine 0003, Meng Gao, Misko Dzamba, C. Lawrence Zitnick. [doi]
• Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and BeyondChongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong 0001, Sijia Liu 0001. [doi]
• LightGTS: A Lightweight General Time Series Forecasting ModelYihang Wang 0004, Yuying Qiu, Peng Chen 0038, Yang Shu 0001, Zhongwen Rao, Lujia Pan, Bin Yang 0002, Chenjuan Guo. [doi]
• Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost ConstraintDan-Xuan Liu, Chao Qian 0001. [doi]
• ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language ModelsXinPeng Dong, Min Zhang 0005, Didi Zhu, Ye Jun Jian, Keli Zhang, Aimin Zhou, Fei Wu 0001, Kun Kuang. [doi]
• Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID SettingsNong Minh Hieu, Antoine Ledent. [doi]
• Commute Graph Neural NetworksWei Zhuo 0006, Han Yu 0001, Guang Tan, Xiaoxiao Li. [doi]
• Leveraging Skills from Unlabeled Prior Data for Efficient Online ExplorationMax Wilcoxson, Qiyang Li, Kevin Frans, Sergey Levine. [doi]
• Robust Multimodal Large Language Models Against Modality ConflictZongmeng Zhang, Wengang Zhou 0001, Jie Zhao, Houqiang Li. [doi]
• Near Optimal Best Arm Identification for Clustered BanditsYash, Avishek Ghosh, Nikhil Karamchandani. [doi]
• VinePPO: Refining Credit Assignment in RL Training of LLMsAmirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron C. Courville, Nicolas Le Roux. [doi]
• Equivariant Polynomial Functional NetworksThieu Vo, Hoang V. Tran, Tho Tran Huu, An Nguyen The, Thanh Tran, Minh-Khoi Nguyen-Nhat, Duy-Tung Pham, Tan Minh Nguyen. [doi]
• Transfer Q-Learning with Composite MDP StructuresJinhang Chai, Elynn Y. Chen, Lin Yang. [doi]
• Training Software Engineering Agents and Verifiers with SWE-GymJiayi Pan, Xingyao Wang 0002, Graham Neubig, Navdeep Jaitly, Heng Ji 0001, Alane Suhr, Yizhe Zhang 0002. [doi]
• OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation BalanceYongqiang Yao, Jingru Tan, Feizhao Zhang, Jiahao Hu, Yazhe Niu, Xin Jin 0008, Bo Li 0126, Pengfei Liu 0003, Ruihao Gong, Dahua Lin, Ningyi Xu. [doi]
• BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference OptimizationZijun Liao, Jinbiao Chen, Debing Wang, Zizhen Zhang, Jiahai Wang. [doi]
• Neural Genetic Search in Discrete SpacesHyeonah Kim, Sanghyeok Choi, Jiwoo Son, Jinkyoo Park, Changhyun Kwon 0001. [doi]
• EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation GraphKaicheng Fu, Changde Du, Jie Peng, Kunpeng Wang, Shuangchen Zhao, Xiaoyu Chen, Huiguang He. [doi]
• LieRE: Lie Rotational Positional EncodingsSophie Ostmeier, Brian Axelrod, Maya Varma, Michael E. Moseley, Akshay S. Chaudhari, Curtis Langlotz. [doi]
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityZicheng Lin, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xing Wang 0007, Ruilin Luo, Chufan Shi, Siheng Li, Yujiu Yang 0001, Zhaopeng Tu. [doi]
• Adaptive Sample Sharing for Multi Agent Linear BanditsHamza Cherkaoui, Merwan Barlier, Igor Colin. [doi]
• SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse ProblemsIsmail Alkhouri, Shijun Liang 0001, Cheng-Han Huang, Jimmy Dai, Qing Qu 0001, Saiprasad Ravishankar, Rongrong Wang. [doi]
• Self-supervised Masked Graph Autoencoder via Structure-aware CurriculumHaoyang Li 0001, Xin Wang 0019, Zeyang Zhang 0001, Zongyuan Wu, Linxin Xiao, Wenwu Zhu 0001. [doi]
• Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form GamesLinjian Meng, Wubing Chen, Wenbin Li 0006, Tianpei Yang, Youzhi Zhang 0001, Yang Gao 0001. [doi]
• Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic DesignZhi Zheng 0009, Zhuoliang Xie, Zhenkun Wang 0001, Bryan Hooi. [doi]
• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated AttentionDejia Xu, Yifan Jiang 0001, Chen Huang, Liangchen Song, Thorsten Gernoth, Liangliang Cao, Zhangyang Wang, Hao Tang 0001. [doi]
• NegMerge: Sign-Consensual Weight Merging for Machine UnlearningHyoseo Kim, Dongyoon Han, Junsuk Choe. [doi]
• Inverse Problem Sampling in Latent Space Using Sequential Monte CarloIdan Achituve, Hai Victor Habi, Amir Rosenfeld, Arnon Netzer, Idit Diamant, Ethan Fetaya. [doi]
• On the Importance of Embedding Norms in Self-Supervised LearningAndrew Draganov, Sharvaree Vadgama, Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, Erik J. Bekkers. [doi]
• Statistical Test for Feature Selection Pipelines by Selective InferenceTomohiro Shiraishi, Tatsuya Matsukawa, Shuichi Nishino, Ichiro Takeuchi. [doi]
• A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box EmbeddingsShib Sankar Dasgupta, Michael Boratko, Andrew McCallum. [doi]
• MiraGe: Editable 2D Images using Gaussian SplattingJoanna Waczynska, Tomasz Szczepanik, Piotr Borycki, Slawomir Konrad Tadeja, Thomas Bohné, Przemyslaw Spurek. [doi]
• RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement LearningJonas Gehring, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, Gabriel Synnaeve. [doi]
• Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe ExplorationShiQing Gao, Jiaxin Ding 0001, Luoyi Fu, Xinbing Wang. [doi]
• Learning from others' mistakes: Finetuning machine translation models with span-level error annotationsLily H. Zhang, Hamid Dadkhahi, Mara Finkelstein, Firas Trabelsi, Jiaming Luo, Markus Freitag. [doi]
• Improving LLM Safety Alignment with Dual-Objective OptimizationXuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song. [doi]
• Latent Variable Estimation in Bayesian Black-Litterman ModelsThomas Yuan-Lung Lin, Jerry Yao-Chieh Hu, Paul W. Chiou, Peter Lin. [doi]
• SPHINX: Structural Prediction using Hypergraph Inference NetworkIulia Duta, Pietro Lio. [doi]
• Distilling the Knowledge in Data PruningEmanuel Ben Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, Gérard G. Medioni. [doi]
• Efficient Motion Prompt Learning for Robust Visual TrackingJie Zhao 0014, Xin Chen 0032, Yongsheng Yuan, Michael Felsberg, Dong Wang 0004, Huchuan Lu. [doi]
• Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured DataZhong Guan, Likang Wu, Hongke Zhao, Ming He, Jianping Fan 0007. [doi]
• Mixture of Lookup ExpertsShibo Jie, Yehui Tang, Kai Han 0002, Yitong Li, Duyu Tang, Zhi-Hong Deng 0001, Yunhe Wang 0001. [doi]
• PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement LearningDongchi Huang, Jiaqi Wang, Yang Li 0222, Chunhe Xia, Tianle Zhang, Kaige Zhang. [doi]
• Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic VariablesArhit Chakrabarti, Yang Ni, Debdeep Pati, Bani K. Mallick. [doi]
• Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and InferenceCe Zhang, Yixin Han, Yafei Wang, Xiaodong Yan, Linglong Kong, Ting Li, Bei Jiang. [doi]
• Arrow: Accelerator for Time Series Causal Discovery with Time WeavingYuanyuan Yao 0002, Yuan Dong, Lu Chen 0001, Kun Kuang, Ziquan Fang, Cheng Long, Yunjun Gao, Tianyi Li 0005. [doi]
• Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing DataKosuke Sugiyama, Masato Uchida. [doi]
• Banyan: Improved Representation Learning with Explicit StructureMattia Opper, N. Siddharth 0001. [doi]
• Learning from True-False Labels via Multi-modal Prompt RetrievingZhongnian Li, Jinghao Xu, Peng Ying, Meng Wei 0006, Xinzheng Xu. [doi]
• GuidedQuant: Large Language Model Quantization via Exploiting End Loss GuidanceJinuk Kim, Marwa El Halabi, Wonpyo Park, Clemens J. S. Schaefer, Deokjae Lee, Yeonhong Park, Jae W. Lee, Hyun Oh Song. [doi]
• Secant Line Search for Frank-Wolfe AlgorithmsDeborah Hendrych, Sebastian Pokutta, Mathieu Besançon, David Martínez-Rubio. [doi]
• Validating Mechanistic Interpretations: An Axiomatic ApproachNils Palumbo, Ravi Mangal, Zifan Wang 0001, Saranya Vijayakumar, Corina S. Pasareanu, Somesh Jha. [doi]
• From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language ModelsEtowah Adams, Liam Bai, Minji Lee, Yiyang Yu, Mohammed AlQuraishi. [doi]
• Algorithms and Hardness for Active Learning on GraphsVincent Cohen-Addad, Silvio Lattanzi, Simon Meierhans. [doi]
• Eigen Analysis of Conjugate Kernel and Neural Tangent KernelXiangchao Li, Xiao Han, Qing Yang. [doi]
• Towards Black-Box Membership Inference Attack for Diffusion ModelsJingwei Li, Jing Dong 0008, Tianxing He, Jingzhao Zhang. [doi]
• AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series ForecastingAbdelhakim Benechehab, Vasilii Feofanov, Giuseppe Paolo, Albert Thomas 0001, Maurizio Filippone, Balázs Kégl. [doi]
• Policy Guided Tree Search for Enhanced LLM ReasoningYang Li. [doi]
• POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalYaoyang Liu, Junlin Li, Yinjun Wu, Zhen Chen. [doi]
• A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal RegressionVictor Dheur, Matteo Fontana, Yorick Estievenart, Naomi Desobry, Souhaib Ben Taieb. [doi]
• PDE-Controller: LLMs for Autoformalization and Reasoning of PDEsMauricio Soroco, Jialin Song, Mengzhou Xia, Kye Emond, Weiran Sun, Wuyang Chen 0001. [doi]
• When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You NeedZiming Hong, Runnan Chen, Zengmao Wang, Bo Han 0003, Bo Du 0001, Tongliang Liu. [doi]
• Retrieval-Augmented Language Model for Knowledge-aware Protein EncodingJiasheng Zhang, Delvin Ce Zhang, Shuang Liang 0002, Zhengpin Li, Rex Ying, Jie Shao 0001. [doi]
• PARQ: Piecewise-Affine Regularized QuantizationLisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao. [doi]
• EasyInv: Toward Fast and Better DDIM InversionZiyue Zhang, Mingbao Lin, Shuicheng Yan, Rongrong Ji. [doi]
• LAuReL: Learned Augmented Residual LayerGaurav Menghani, Ravi Kumar, Sanjiv Kumar. [doi]
• The Logical Implication Steering Method for Conditional Interventions on Transformer GenerationDamjan Kalajdzievski. [doi]
• Learning-Order Autoregressive Models with Application to Molecular Graph GenerationZhe Wang 0055, Jiaxin Shi, Nicolas Heess, Arthur Gretton, Michalis K. Titsias. [doi]
• Binary Hypothesis Testing for Softmax Models and Leverage Score ModelsYuzhou Gu, Zhao Song 0002, Junze Yin. [doi]
• The dark side of the forces: assessing non-conservative force models for atomistic machine learningFilippo Bigi, Marcel F. Langer, Michele Ceriotti. [doi]
• Online Episodic Convex Reinforcement LearningBianca Marin Moreno, Khaled Eldowa, Pierre Gaillard, Margaux Brégère, Nadia Oudjane. [doi]
• FuseUNet: A Multi-Scale Feature Fusion Method for U-like NetworksQuansong He, Xiangde Min, Kaishen Wang, Tao He 0016. [doi]
• ParallelComp: Parallel Long-Context Compressor for Length ExtrapolationJing Xiong, Jianghan Shen, Chuanyang Zheng, Zhongwei Wan, Chenyang Zhao, Chiwun Yang, Fanghua Ye 0001, Hongxia Yang, Lingpeng Kong, Ngai Wong 0001. [doi]
• Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment SettingsAngéline Pouget, Mohammad Yaghini, Stephan Rabanser, Nicolas Papernot. [doi]
• Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-TuningMahavir Dabas, Si Chen 0008, Charles Fleming, Ming Jin 0002, Ruoxi Jia 0001. [doi]
• CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD EditingYu Yuan, Shizhao Sun, Qi Liu 0003, Jiang Bian 0002. [doi]
• Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise ModelsMingjia Li 0002, Hong Qian, Tian-Zuo Wang, Shujun Li, Min Zhang, Aimin Zhou. [doi]
• Prediction via Shapley Value RegressionAmr Alkhatib, Roman Bresson, Henrik Boström, Michalis Vazirgiannis. [doi]
• Thickness-aware E(3)-Equivariant 3D Mesh Neural NetworksSungwon Kim, Namkyeong Lee, Yunyoung Doh, Seungmin Shin, Guimok Cho, Seung-Won Jeon, Sangkook Kim, Chanyoung Park. [doi]
• Memory Layers at ScaleVincent-Pierre Berges, Barlas Oguz, Daniel Haziza, Wen-tau Yih, Luke Zettlemoyer, Gargi Ghosh. [doi]
• SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model InferenceJintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu 0001, Jianfei Chen 0001. [doi]
• MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense ConnectionsDa Xiao 0001, Qingye Meng, Shengping Li, Xingyuan Yuan. [doi]
• Statistical Query Hardness of Multiclass Linear Classification with Random Classification NoiseIlias Diakonikolas, Mingchen Ma, Lisheng Ren, Christos Tzamos. [doi]
• AtlasD: Automatic Local Symmetry DiscoveryManu Bhat, Jonghyun Park, Jianke Yang, Nima Dehmamy, Robin Walters 0001, Rose Yu. [doi]
• QLASS: Boosting Language Agent Inference via Q-Guided Stepwise SearchZongyu Lin, Yao Tang, Xingcheng Yao, Da Yin, Ziniu Hu, Yizhou Sun, Kai-Wei Chang. [doi]
• Learning Efficient Robotic Garment Manipulation with StandardizationChangshi Zhou, Feng Luan, hujiarui, Shaoqiang Meng, Zhipeng Wang 0006, Yanchao Dong, Yanmin Zhou, Bin He 0003. [doi]
• Tool Unlearning for Tool-Augmented LLMsJiali Cheng, Hadi Amiri. [doi]
• GenMol: A Drug Discovery Generalist with Discrete DiffusionSeul Lee, Karsten Kreis, Srimukh Prasad Veccham, Meng Liu 0015, Danny Reidenbach, Yuxing Peng 0005, Saee Gopal Paliwal, Weili Nie, Arash Vahdat. [doi]
• Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic TransformsJulius von Rohrscheidt, Bastian Rieck. [doi]
• Non-Asymptotic Length GeneralizationThomas Chen, Tengyu Ma 0001, Zhiyuan Li 0005. [doi]
• CellFlux: Simulating Cellular Morphology Changes via Flow MatchingYuhui Zhang, Yuchang Su, Chenyu Wang 0003, Tianhong Li, Zoe Wefers, Jeffrey J. Nirschl, James Burgess, Daisy Ding, Alejandro Lozano, Emma Lundberg, Serena Yeung-Levy. [doi]
• On Zero-Initialized Attention: Optimal Prompt and Gating Factor EstimationNghiem Tuong Diep, Huy Nguyen, Chau Nguyen, Minh Le, Duy Minh Ho Nguyen, Daniel Sonntag, Mathias Niepert, Nhat Ho. [doi]
• Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General GraphsJie Hu 0027, Yi-Ting Ma, Do Young Eun. [doi]
• Deep Sturm-Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis FunctionsDavid Vigouroux, Joseba Dalmau, Louis Béthune, Victor Boutin. [doi]
• Efficient LiDAR Reflectance Compression via Scanning SerializationJiahao Zhu, Kang You, Dandan Ding, Zhan Ma 0001. [doi]
• A Versatile Influence Function for Data Attribution with Non-Decomposable LossJunwei Deng, Weijing Tang, Jiaqi W. Ma. [doi]
• RAGGED: Towards Informed Design of Scalable and Stable RAG SystemsJennifer Hsia, Afreen Shaikh, Zora Zhiruo Wang, Graham Neubig. [doi]
• Solving Probabilistic Verification Problems of Neural Networks using Branch and BoundDavid Boetius, Stefan Leue, Tobias Sutter. [doi]
• GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision ModelZixiang Ai, Zichen Liu, Yuanhang Lei, Zhenyu Cui, Xu Zou 0002, Jiahuan Zhou. [doi]
• Learning dynamics in linear recurrent neural networksAlexandra Maria Proca, Clémentine Carla Juliette Dominé, Murray Shanahan, Pedro A. M. Mediano. [doi]
• SpikF: Spiking Fourier Network for Efficient Long-term PredictionWenjie Wu, Dexuan Huo, Hong Chen. [doi]
• Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality ConstraintsRuichuan Huang, Jiawei Zhang, Ahmet Alacaoglu. [doi]
• Maximum Total Correlation Reinforcement LearningBang You, Puze Liu, Huaping Liu, Jan Peters 0001, Oleg Arenz. [doi]
• Haste Makes Waste: A Simple Approach for Scaling Graph Neural NetworksRui Xue 0006, Tong Zhao 0003, Neil Shah, Xiaorui Liu. [doi]
• DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT SpaceMang Ning, Mingxiao Li 0002, Jianlin Su, Haozhe Jia, Lanmiao Liu, Martin Benes 0001, Wenshuo Chen, Albert Ali Salah, Itir Önal Ertugrul. [doi]
• Learning Survival Distributions with the Asymmetric Laplace DistributionDeming Sheng, Ricardo Henao. [doi]
• Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm IntelligenceShangbin Feng, Zifeng Wang 0002, Yike Wang 0002, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich, Achin Kulshrestha, Nathalie Rauschmayr, Yejin Choi 0001, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister. [doi]
• Probabilistic Group Mask Guided Discrete Optimization for Incremental LearningFengqiang Wan, Yang Yang 0074. [doi]
• Fast Video Generation with Sliding Tile AttentionPeiyuan Zhang, Yongqi Chen, Runlong Su, Hangliang Ding, Ion Stoica, Zhengzhong Liu 0001, Hao Zhang 0025. [doi]
• TopInG: Topologically Interpretable Graph Learning via Persistent Rationale FiltrationCheng Xin, Fan Xu, Xin Ding, Jie Gao 0001, Jiaxin Ding 0001. [doi]
• Probabilistic Interactive 3D Segmentation with Hierarchical Neural ProcessesJie Liu 0043, Pan Zhou, Zehao Xiao, Jiayi Shen, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves. [doi]
• Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold InterpolationAlessandro Palma, Sergei Rybakov, Leon Hetzel, Stephan Günnemann, Fabian J. Theis. [doi]
• ToMA: Token Merge with Attention for Diffusion ModelsWenbo Lu, Shaoyi Zheng, Yuxuan Xia, Shengjie Wang. [doi]
• Tree-Sliced Wasserstein Distance with Nonlinear ProjectionThanh Tran, Hoang V. Tran, Thanh T. Chu, Huyen-Trang Pham, Laurent El Ghaoui, Tam Le, Tan Minh Nguyen. [doi]
• The Ripple Effect: On Unforeseen Complications of Backdoor AttacksRui Zhang 0086, Yun Shen, Hongwei Li 0001, Wenbo Jiang 0001, Hanxiao Chen 0001, Yuan Zhang 0006, Guowen Xu, Yang Zhang 0016. [doi]
• Causal Attribution Analysis for Continuous OutcomesShanshan Luo, Yixuan Yu, Chunchen Liu, Feng Xie 0002, Zhi Geng. [doi]
• PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive CommunitiesDaniel Zilberg, Ron Levie. [doi]
• Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward LayersFreya Behrens, Luca Biggio, Lenka Zdeborová. [doi]
• Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement LearningBrett Barkley, David Fridovich-Keil. [doi]
• Learning to Match Unpaired Data with Minimum Entropy CouplingMustapha Bounoua, Giulio Franzese, Pietro Michiardi. [doi]
• DeepLayout: Learning Neural Representations of Circuit Placement LayoutYuxiang Zhao, Zhuomin Chai, Xun Jiang 0002, Qiang Xu 0001, Runsheng Wang, Yibo Lin. [doi]
• ENSUR: Equitable and Statistically Unbiased RecommendationNitin Bisht, Xiuwen Gong, Guandong Xu. [doi]
• K2IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson ProcessesHideaki Kim, Tomoharu Iwata, Akinori Fujino. [doi]
• Unified K-Means Clustering with Label-Guided Manifold LearningQianqian Wang 0001, Mengping Jiang, Zhengming Ding, Quanxue Gao. [doi]
• Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy BoundariesYuena Lin, Haichun Cai, Jun-Yi Hang, Haobo Wang 0001, Zhen Yang 0004, Gengyu Lyu. [doi]
• The Role of Sparsity for Length Generalization in LLMsNoah Golowich, Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach. [doi]
• Branches: Efficiently Seeking Optimal Sparse Decision Trees via AOAyman Chaouki, Jesse Read, Albert Bifet. [doi]
• WILTing Trees: Interpreting the Distance Between MPNN EmbeddingsMasahiro Negishi, Thomas Gärtner 0001, Pascal Welke. [doi]
• Optimizing Large Language Model Training Using FP4 QuantizationRuizhe Wang, Yeyun Gong, Xiao Liu 0029, Guoshuai Zhao, Ziyue Yang, Baining Guo, Zheng-Jun Zha, Peng Cheng 0005. [doi]
• Conservative Offline Goal-Conditioned Implicit V-LearningKaiqiang Ke, Qian Lin, Zongkai Liu, Shenghong He, Chao Yu 0004. [doi]
• Subgoal-Guided Policy Heuristic Search with Learned SubgoalsJake Tuero, Michael Buro, Levi Lelis. [doi]
• FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model UpdatesXinyi Lu, Hao Zhang, Chenglin Li, Weijia Lu, Zhifei Yang 0005, Wenrui Dai, Xiaodong Zhang, Xiaofeng Ma, Can Zhang, Junni Zou, Hongkai Xiong. [doi]
• Transfer Learning for Nonparametric Contextual Dynamic PricingFan Wang, Feiyu Jiang, Zifeng Zhao, Yi Yu. [doi]
• Optimal Task Order for Continual Learning of Multiple TasksZiyan Li, Naoki Hiratani. [doi]
• Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial TrainingBhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen 0001. [doi]
• An Efficient Pruner for Large Language Model with Theoretical GuaranteeCanhong Wen, Yihong Zuo, Wenliang Pan. [doi]
• Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-TuningNa Lee, Konstantinos Barmpas, Yannis Panagakis, Dimitrios A. Adamos, Nikolaos A. Laskaris, Stefanos Zafeiriou. [doi]
• ELITE: Enhanced Language-Image Toxicity Evaluation for SafetyWonjun Lee, Doehyeon Lee, Eugene Choi, Sangyoon Yu, Ashkan Yousefpour, Haon Park, Bumsub Ham, Suhyun Kim 0001. [doi]
• Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline DataJeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, Woohyung Lim. [doi]
• On the Local Complexity of Linear Regions in Deep ReLU NetworksNiket Patel, Guido Montúfar. [doi]
• Rethinking Chain-of-Thought from the Perspective of Self-TrainingZongqian Wu, Baoduo Xu, Ruochen Cui, Mengmeng Zhan, Xiaofeng Zhu 0001, Lei Feng 0006. [doi]
• Mixture of Experts Made Intrinsically InterpretableXingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr 0001. [doi]
• Online Learning in Risk Sensitive constrained MDPArnob Ghosh, Mehrdad Moharrami. [doi]
• An Architecture Search Framework for Inference-Time TechniquesJon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Kumar Guha, Estefany Kelly Buchanan, Mayee F. Chen, Neel Guha, Christopher Ré, Azalia Mirhoseini. [doi]
• CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-AttentionHan Li, Fei Liu 0044, Zhi Zheng 0009, Yu Zhang 0226, Zhenkun Wang 0001. [doi]
• Multi-Modal Object Re-identification via Sparse Mixture-of-ExpertsYingying Feng, Jie Li, Chi Xie, Lei Tan, Jiayi Ji. [doi]
• Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMMPenghao Wu, Lewei Lu, Ziwei Liu 0002. [doi]
• Algorithmic Recourse for Long-Term ImprovementKentaro Kanamori, Ken Kobayashi, Satoshi Hara 0001, Takuya Takagi. [doi]
• Speculate, then Collaborate: Fusing Knowledge of Language Models during DecodingZiyao Wang, Muneeza Azmat, Ang Li, Raya Horesh, Mikhail Yurochkin. [doi]
• TabFlex: Scaling Tabular Learning to Millions with Linear AttentionYuchen Zeng, Tuan Dinh, Wonjun Kang, Andreas C. Mueller. [doi]
• Morse: Dual-Sampling for Lossless Acceleration of Diffusion ModelsChao Li, Jiawei Fan, Anbang Yao. [doi]
• Towards Better-than-2 Approximation for Constrained Correlation ClusteringAndreas Kalavas, Evangelos Kipouridis, Nithin Varma. [doi]
• Test-time Adapted Reinforcement Learning with Action Entropy RegularizationShoukai Xu, Zihao Lian, Mingkui Tan, Liu Liu 0014, Zhong Zhang 0014, Peilin Zhao. [doi]
• The Four Color Theorem for Cell Instance SegmentationYe Zhang 0008, Yu Zhou, Yifeng Wang 0001, Jun Xiao, Ziyue Wang 0005, Yongbing Zhang 0002, Jianxu Chen 0001. [doi]
• Safety-Polarized and Prioritized Reinforcement LearningKe-fan, Jinpeng Zhang, Xuefeng Zhang, Yunze Wu, Jingyu Cao, Yuan Zhou 0007, Jianzhu Ma. [doi]
• Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep DeploymentChengting Yu, Xiaochen Zhao, Lei Liu, Shu Yang, Gaoang Wang, Erping Li 0001, Aili Wang 0002. [doi]
• Bayesian Inference for Correlated Human Experts and ClassifiersMarkelle Kelly, Alex James Boyd, Samuel Showalter, Mark Steyvers, Padhraic Smyth. [doi]
• Learning curves theory for hierarchically compositional data with power-law distributed featuresFrancesco Cagnetta, Hyunmo Kang, Matthieu Wyart. [doi]
• The Surprising Effectiveness of Test-Time Training for Few-Shot LearningEkin Akyürek, Mehul Damani, Adam Zweiger, Linlu Qiu, Han Guo, Jyothish Pari, Yoon Kim, Jacob Andreas. [doi]
• Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM ReasoningZhenni Bi, Kai Han 0002, Chuanjian Liu, Yehui Tang, Yunhe Wang 0001. [doi]
• Understanding and Mitigating Memorization in Diffusion Models for Tabular DataZhengyu Fang, Zhimeng Jiang, Huiyuan Chen, Xiao Li, Jing Li 0002. [doi]
• AdaSplash: Adaptive Sparse Flash AttentionNuno Gonçalves, Marcos V. Treviso, André F. T. Martins. [doi]
• Towards Rationale-Answer Alignment of LVLMs via Self-Rationale CalibrationYuanchen Wu, Ke Yan, Shouhong Ding, Ziyin Zhou, Xiaoqiang Li. [doi]
• Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability QueriesXuening Feng, Zhaohui Jiang, Timo Kaufmann, Eyke Hüllermeier, Paul Weng, Yifei Zhu. [doi]
• PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative ModelsFanmeng Wang, Wentao Guo 0004, Qi Ou, Hongshuai Wang, Haitao Lin, Hongteng Xu, Zhifeng Gao. [doi]
• Permutation Equivariant Neural Networks for Symmetric TensorsEdward Pearce-Crump. [doi]
• Conformal Anomaly Detection in Event SequencesShuai Zhang, Chuan Zhou 0001, Yang Liu 0320, Peng Zhang 0001, Xixun Lin, Shirui Pan. [doi]
• Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and FinetuningWanyun Xie, Francesco Tonin, Volkan Cevher. [doi]
• STAIR: Improving Safety Alignment with Introspective ReasoningYichi Zhang 0012, Siyuan Zhang, Yao Huang, Zeyu Xia 0003, Zhengwei Fang, Xiao Yang 0028, Ranjie Duan, Dong Yan, Yinpeng Dong, Jun Zhu 0001. [doi]
• Empowering World Models with Reflection for Embodied Video PredictionXiaowei Chi, Chun-Kai Fan, Hengyuan Zhang, Xingqun Qi, Rongyu Zhang, Anthony Chen, Chi-Min Chan, Wei Xue 0002, Qifeng Liu, Shanghang Zhang, Yike Guo. [doi]
• Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language ModelsYiyang Fang, Jian Liang 0001, Wenke Huang 0003, He Li 0054, Kehua Su, Mang Ye. [doi]
• The Disparate Benefits of Deep EnsemblesKajetan Schweighofer, Adrián Arnaiz-Rodríguez, Sepp Hochreiter, Nuria Oliver. [doi]
• Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in SuperpositionZheyang Xiong, Ziyang Cai, John Cooper, Albert Ge, Vasilis Papageorgiou, Zack Sifakis, Angeliki Giannou, Ziqian Lin, Liu Yang 0001, Saurabh Agarwal, Grigorios Chrysos 0002, Samet Oymak, Kangwook Lee 0001, Dimitris Papailiopoulos. [doi]
• AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph ModelingJian Gao, Weidong Cao 0001, Xuan Zhang 0001. [doi]
• When do neural networks learn world models?Tianren Zhang, Guanyu Chen, Feng Chen 0007. [doi]
• MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parametersArsalan Sharifnassab, Saber Salehkaleybar, Richard S. Sutton. [doi]
• ADDQ: Adaptive distributional double Q-learningLeif Döring, Benedikt Wille, Maximilian Birr, Mihail Bîrsan, Martin Slowik. [doi]
• Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization ChallengesNayoung Lee, Ziyang Cai, Avi Schwarzschild, Kangwook Lee 0001, Dimitris Papailiopoulos. [doi]
• Potemkin Understanding in Large Language ModelsMarina Mancoridis, Bec Weeks, Keyon Vafa, Sendhil Mullainathan. [doi]
• Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle MattersHongyi Wang, Shiyuan Ren, Wei Huang 0034, Miao Zhang 0001, Xiang Deng 0002, Yixin Bao, Liqiang Nie. [doi]
• A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive LearningYingzhen Yang. [doi]
• Temporal Query Network for Efficient Multivariate Time Series ForecastingShengsheng Lin, Haojun Chen, Haijie Wu, Chunyun Qiu, Weiwei Lin. [doi]
• Structure-Guided Large Language Models for Text-to-SQL GenerationQinggang Zhang, Hao Chen 0062, Junnan Dong, Shengyuan Chen, Feiran Huang, Xiao Huang 0001. [doi]
• SeedLoRA: A Fusion Approach to Efficient LLM Fine-TuningYong Liu 0020, Di Fu, Shenggan Cheng, Zirui Zhu, Yang Luo, Minhao Cheng, Cho-Jui Hsieh, Yang You 0001. [doi]
• LLMs can see and hear without any trainingKumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar. [doi]
• iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object DetectionHuahui Yi, Wei Xu 0046, Ziyuan Qin 0001, Xi Chen, Xiaohu Wu, Kang Li 0004, Qicheng Lao. [doi]
• SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMsXin Su 0008, Man Luo, Kris W. Pan, Tien Pei Chou, Vasudev Lal, Phillip Howard. [doi]
• Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding ApproachZhigaoyuan Wang, Ying Sun 0006, Hengshu Zhu. [doi]
• Steer LLM Latents for Hallucination DetectionSeongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang 0001, Yixuan Li 0001. [doi]
• Statistical Hypothesis Testing for Auditing Robustness in Language ModelsPaulius Rauba, Qiyao Wei, Mihaela van der Schaar. [doi]
• Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic RegressionsSupratim Shit, Gurmehak Kaur Chadha, Surendra Kumar, Bapi Chatterjee. [doi]
• CoDy: Counterfactual Explainers for Dynamic GraphsZhan Qu, Daniel Gomm, Michael Färber 0001. [doi]
• Revisiting Cooperative Off-Policy Multi-Agent Reinforcement LearningYueheng Li, Guangming Xie, Zongqing Lu 0002. [doi]
• NeuronTune: Towards Self-Guided Spurious Bias MitigationGuangtao Zheng, Wenqian Ye, Aidong Zhang. [doi]
• Can Transformers Learn Full Bayesian Inference in Context?Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David Rügamer. [doi]
• Simple Path Structural Encoding for Graph TransformersLouis Airale, Antonio Longa, Mattia Rigon, Andrea Passerini, Roberto Passerone. [doi]
• An Expressive and Self-Adaptive Dynamical System for Efficient Function LearningChuan Liu 0001, Chunshu Wu, Ruibing Song, Ang Li 0006, Ying Nian Wu, Tong Geng. [doi]
• Enforcing Idempotency in Neural NetworksNikolaj Banke Jensen, Jamie Vicary. [doi]
• Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack ProblemsMohammadreza Daneshvaramoli, Helia Karisani, Adam Lechowicz, Bo Sun 0004, Cameron Musco, Mohammad Hajiesmaili. [doi]
• Predictive Data Selection: The Data That Predicts Is the Data That TeachesKashun Shum, Yuzhen Huang, Hongjian Zou, Qi Ding, Yixuan Liao, Xiaoxin Chen, Qian Liu 0012, Junxian He. [doi]
• DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation ApplicationsIbrahim Fayad, Max Zimmer, Martin Schwartz, Fabian Gieseke, Philippe Ciais, Gabriel Belouze, Sarah Brood, Aurélien de Truchis, Alexandre d'Aspremont. [doi]
• Test-Time Adaptation with Binary FeedbackTaeckyung Lee, Sorn Chottananurak, Junsu Kim, Jinwoo Shin, Taesik Gong, Sung-Ju Lee. [doi]
• Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm IdentificationKapilan Balagopalan, Tuan Ngo Nguyen, Yao Zhao, Kwang-Sung Jun. [doi]
• Pareto-frontier Entropy Search with Variational Lower Bound MaximizationMasanori Ishikura, Masayuki Karasuyama. [doi]
• P(all-atom) Is Unlocking New Path For Protein DesignWei Qu, Jiawei Guan, Rui Ma, Ke Zhai, Weikun Wu, Haobo Wang. [doi]
• AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse AutoencodersZhengxuan Wu, Aryaman Arora, Atticus Geiger, Zheng Wang 0078, Jing Huang 0014, Dan Jurafsky, Christopher D. Manning, Christopher Potts. [doi]
• Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement LearningHanyang Zhao, Haoxian Chen 0002, Ji Zhang, David D. Yao, Wenpin Tang. [doi]
• ZebraLogic: On the Scaling Limits of LLMs for Logical ReasoningBill Yuchen Lin, Ronan Le Bras 0001, Kyle Richardson 0001, Ashish Sabharwal, Radha Poovendran, Peter Clark, Yejin Choi 0001. [doi]
• Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image FusionYiming Sun 0003, Xin Li, Pengfei Zhu 0001, Qinghua Hu, Dongwei Ren, Huiying Xu, Xinzhong Zhu. [doi]
• Monte-Carlo Tree Search with Uncertainty Propagation via Optimal TransportTuan Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard. [doi]
• Progressive Tempering Sampler with DiffusionSeveri Rissanen, Ruikang Ouyang, Jiajun He 0003, Wenlin Chen, Markus Heinonen, Arno Solin, José Miguel Hernández-Lobato. [doi]
• Quantum Algorithms for Finite-horizon Markov Decision ProcessesBin Luo, Yuwen Huang, Jonathan Allcock, Xiaojun Lin, Shengyu Zhang 0002, John C. S. Lui. [doi]
• A Unified Framework for Entropy Search and Expected Improvement in Bayesian OptimizationNuojin Cheng, Leonard Papenmeier, Stephen Becker, Luigi Nardi. [doi]
• An Online Statistical Framework for Out-of-Distribution DetectionXinsong Ma, Xin Zou 0002, Weiwei Liu 0003. [doi]
• A Market for Accuracy: Classification Under CompetitionOhad Einav, Nir Rosenfeld. [doi]
• From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE ControlPeiyan Hu, Xiaowei Qian, Wenhao Deng 0001, Rui Wang 0017, Haodong Feng, Ruiqi Feng, Tao Zhang 0033, Long Wei, Yue Wang 0017, Zhi-Ming Ma, Tailin Wu. [doi]
• Activation Space Interventions Can Be Transferred Between Large Language ModelsNarmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Michael Lan, Abir Harrasse, Amir Abdullah. [doi]
• Compressing tree ensembles through Level-wise Optimization and PruningLaurens Devos, Timo Martens, Deniz Can Oruc, Wannes Meert, Hendrik Blockeel, Jesse Davis. [doi]
• TimeBridge: Non-Stationarity Matters for Long-term Time Series ForecastingPeiyuan Liu, Beiliang Wu, Yifan Hu, Naiqi Li, Tao Dai 0001, Jigang Bao, Shu-Tao Xia. [doi]
• Improving Generalization with Flat Hilbert Bayesian InferenceTuan Truong, Quyen Tran, Ngoc-Quan Pham, Nhat Ho, Dinh Phung 0001, Trung Le 0001. [doi]
• Hyper-Transforming Latent Diffusion ModelsIgnacio Peis, Batuhan Koyuncu, Isabel Valera, Jes Frellsen. [doi]
• GeoPixel: Pixel Grounding Large Multimodal Model in Remote SensingAkashah Shabbir, Mohammed Zumri, Mohammed Bennamoun, Fahad Shahbaz Khan, Salman Khan 0001. [doi]
• UniSim: A Unified Simulator for Time-Coarsened Dynamics of BiomoleculesZiyang Yu 0002, Wenbing Huang 0001, Yang Liu 0005. [doi]
• Evolving Minds: Logic-Informed Inference from Temporal Action PatternsChao Yang, Shuting Cui, Yang Yang, Shuang Li 0002. [doi]
• Nonconvex Theory of M-estimators with Decomposable RegularizersWeiwei Liu 0003. [doi]
• Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMsAryan Gulati, Brando Miranda, Eric Chen, Emily Xia, Kai Fronsdal, Bruno de Moraes Dumont, Sanmi Koyejo. [doi]
• PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition ResidualsXinghe Fu, Zhiyuan Yan, Zheng Yang, Taiping Yao, Yandan Zhao, Shouhong Ding, Xi Li. [doi]
• Revisiting the Predictability of Performative, Social EventsJuan Carlos Perdomo. [doi]
• Federated Incomplete Multi-view Clustering with Globally Fused Graph GuidanceGuoqing Chao, Zhenghao Zhang, Lei Meng, Jie Wen, Dianhui Chu. [doi]
• In-Context Adaptation to Concept Drift for Learned Database OperationsJiaqi Zhu 0002, Shaofeng Cai, Yanyan Shen, Gang Chen 0001, Fang Deng, Beng Chin Ooi. [doi]
• MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible CostSen Xing, Muyan Zhong, Zeqiang Lai, Liangchen Li, Jiawen Liu, Yaohui Wang, Jifeng Dai, Wenhai Wang. [doi]
• Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language ModelsSamira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak. [doi]
• When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid NetworkDong Xiao, Guangyao Chen, Peixi Peng, Yangru Huang, Yifan Zhao 0002, Yongxing Dai, Yonghong Tian 0001. [doi]
• Adversarial Reasoning at Jailbreaking TimeMahdi Sabbaghi, Paul Kassianik, George J. Pappas, Amin Karbasi, Hamed Hassani. [doi]
• Symmetry-Driven Discovery of Dynamical Variables in Molecular SimulationsJeet Mohapatra, Nima Dehmamy, Csaba Both, Subhro Das, Tommi Jaakkola. [doi]
• Gandalf the Red: Adaptive Security for LLMsNiklas Pfister, Václav Volhejn, Manuel Knott 0003, Santiago Arias, Julia Bazinska, Mykhailo Bichurin, Alan Y. Commike, Janet Darling, Peter Dienes, Matthew Fiedler, David Haber, Matthias Kraft, Marco Lancini, Max Mathys, Damián Pascual-Ortiz, Jakub Podolak, Adrià Romero-López, Kyriacos Shiarlis, Andreas Signer, Zsolt Terek, Athanasios Theocharis, Daniel Timbrell, Samuel Trautwein, Samuel Watts, Yun-Han Wu, Mateo Rojas-Carulla. [doi]
• Certified Unlearning for Neural NetworksAnastasia Koloskova, Youssef Allouah, Animesh Jha, Rachid Guerraoui, Sanmi Koyejo. [doi]
• Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter SelectionMatteo Zecchin, Sangwoo Park 0002, Osvaldo Simeone. [doi]
• Generalized Random Forests Using Fixed-Point TreesDavid Fleischer, David A. Stephens, Archer Y. Yang. [doi]
• B-score: Detecting biases in large language models using response historyAn Vo, Mohammad Reza Taesiri, Daeyoung Kim 0001, Anh Totti Nguyen. [doi]
• ReferSplat: Referring Segmentation in 3D Gaussian SplattingShuting He, Guangquan Jie, Changshuo Wang 0001, Yun Zhou, Shuming Hu, Guanbin Li, Henghui Ding. [doi]
• Self-Supervised Learning of Intertwined Content and Positional Features for Object DetectionKang-Jun Liu, Masanori Suganuma, Takayuki Okatani. [doi]
• Fragments to Facts: Partial-Information Fragment Inference from LLMsLucas Rosenblatt, Bin Han 0011, Robert Wolfe, Bill Howe. [doi]
• Improving Out-of-Distribution Detection with Markov Logic NetworksKonstantin Kirchheim, Frank Ortmeier. [doi]
• Distillation of Discrete Diffusion through Dimensional CorrelationsSatoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji. [doi]
• Rethink GraphODE Generalization within Coupled Dynamical SystemGuancheng Wan, Zijie Huang 0002, Wanjia Zhao, Xiao Luo 0001, Yizhou Sun, Wei Wang 0010. [doi]
• Tilted Sharpness-Aware MinimizationTian Li 0005, Tianyi Zhou 0001, Jeff A. Bilmes. [doi]
• General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimizationKwangjun Ahn, Gagik Magakyan, Ashok Cutkosky. [doi]
• Blink of an eye: a simple theory for feature localization in generative modelsMarvin Li, Aayush Karan, Sitan Chen. [doi]
• Pareto-Optimal Fronts for Benchmarking Symbolic Regression AlgorithmsKei Sen Fong, Mehul Motani. [doi]
• Deep Bayesian Filter for Bayes-Faithful Data AssimilationYuta Tarumi, Keisuke Fukuda, Shin-ichi Maeda. [doi]
• Active feature acquisition via explainability-driven rankingOsman Berke Güney, Ketan Suhaas Saichandran, Karim Elzokm, Ziming Zhang, Vijaya B. Kolachalama. [doi]
• HyperTree Planning: Enhancing LLM Reasoning via Hierarchical ThinkingRunquan Gui, Zhihai Wang, Jie Wang 0005, Chi Ma, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Defu Lian, Enhong Chen, Feng Wu 0001. [doi]
• Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language ModelsShizhan Gong, Yankai Jiang 0003, Qi Dou 0001, Farzan Farnia. [doi]
• Logits are All We Need to Adapt Closed ModelsGaurush Hiranandani, Haolun Wu, Subhojyoti Mukherjee, Sanmi Koyejo. [doi]
• Linear Contextual Bandits With InterferenceYang Xu 0089, Wenbin Lu, Rui Song 0006. [doi]
• InfAlign: Inference-aware language model alignmentAnanth Balashankar, Ziteng Sun, Jonathan Berant, Jacob Eisenstein, Michael Collins 0001, Adrian Hutter, Jong Lee, Chirag Nagpal, Flavien Prost, Aradhana Sinha, Ananda Theertha Suresh, Ahmad Beirami. [doi]
• Olica: Efficient Structured Pruning of Large Language Models without RetrainingJiujun He, Huazhen Lin. [doi]
• Preserving AUC Fairness in Learning with Noisy Protected GroupsMingyang Wu, Li Lin, Wenbin Zhang 0002, Xin Wang 0045, Zhenhuan Yang, Shu Hu 0001. [doi]
• Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian InferenceMahendra Singh Thapa, Rui Li. [doi]
• BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching ModelsSusan Liang, Dejan Markovic, Israel D. Gebru, Steven Krenn, Todd Keebler, Jacob Sandakly, Frank Yu, Samuel Hassel, Chenliang Xu, Alexander Richard. [doi]
• Signed Laplacians for Constrained Graph ClusteringJohn Stewart Fabila-Carrasco, He Sun 0001. [doi]
• Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-MakingHongling Zheng, Li Shen 0008, Yong Luo 0002, Deheng Ye, Bo Du 0001, Jialie Shen 0001, Dacheng Tao. [doi]
• BiAssemble: Learning Collaborative Affordance for Bimanual Geometric AssemblyYan Shen 0035, Ruihai Wu, Yubin Ke, XinYuan Song, Zeyi Li, Xiaoqi Li 0020, Hongwei Fan, Haoran Lu, Hao Dong 0003. [doi]
• Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning BenchmarkYunzhuo Hao, Jiawei Gu, Huichen Will Wang, Linjie Li, Zhengyuan Yang, Lijuan Wang, Yu Cheng 0001. [doi]
• S2FGL: Spatial Spectral Federated Graph LearningZihan Tan, Suyuan Huang 0003, Guancheng Wan, Wenke Huang 0003, He Li 0054, Mang Ye. [doi]
• SEMU: Singular Value Decomposition for Efficient Machine UnlearningMarcin Sendera, Lukasz Struski, Kamil Ksiazek, Kryspin Musiol, Jacek Tabor, Dawid Damian Rymarczyk. [doi]
• LLM Data Selection and Utilization via Dynamic Bi-level OptimizationYang Yu 0056, Kai Han 0002, Hang Zhou, Yehui Tang, Kaiqi Huang, Yunhe Wang 0001, Dacheng Tao. [doi]
• Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention LayersThiziri Nait Saada, Alireza Naderi, Jared Tanner. [doi]
• An Instrumental Value for Data Production and its Application to Data PricingRui Ai 0002, Boxiang Lyu, Zhaoran Wang 0001, Zhuoran Yang, Haifeng Xu. [doi]
• A Sample Efficient Conditional Independence Test in the Presence of DiscretizationBoyang Sun, Yu Yao 0005, Xinshuai Dong, Zongfang Liu, Tongliang Liu, Yumou Qiu, Kun Zhang 0001. [doi]
• Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without TrainingMozhi Zhang, Howe Tissue, Lu Wang, Xipeng Qiu. [doi]
• Improving Out-of-Distribution Detection via Dynamic Covariance CalibrationKaiyu Guo, Zijian Wang 0009, Tan Pan, Brian C. Lovell, Mahsa Baktashmotlagh. [doi]
• Balanced Learning for Domain Adaptive Semantic SegmentationWangkai Li, Rui Sun 0006, Bohao Liao, Zhaoyang Li, Tianzhu Zhang 0001. [doi]
• FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language ModelsXinting Liao, Weiming Liu 0005, Jiaming Qian, Pengyang Zhou, Jiahe Xu 0003, Wenjie Wang, Chaochao Chen 0001, Xiaolin Zheng, Tat-Seng Chua. [doi]
• The Diffusion DualitySubham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T. Chiu, Volodymyr Kuleshov. [doi]
• Aligning Protein Conformation Ensemble Generation with Physical FeedbackJiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Aurélie C. Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang 0005. [doi]
• Batch List-Decodable Linear Regression via Higher MomentsIlias Diakonikolas, Daniel Kane 0001, Sushrut Karmalkar, Sihan Liu, Thanasis Pittas. [doi]
• RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion TransformersMin Zhao, Guande He, Yixiao Chen, Hongzhou Zhu, Chongxuan Li, Jun Zhu. [doi]
• The Underlying Universal Statistical Structure of Natural DatasetsNoam Itzhak Levi, Yaron Oz. [doi]
• Revisiting Unbiased Implicit Variational InferenceTobias Pielok, Bernd Bischl, David Rügamer. [doi]
• LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3DPaul McVay, Sergio Arnaud, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula, Phillip Thomas, Ruslan Partsey, Daniel Dugas, Abha Gejji, Alexander Sax, Vincent-Pierre Berges, Mikael Henaff, Ayush Jain, Ang Cao, Ishita Prasad, Mrinal Kalakrishnan, Michael Rabbat, Nicolas Ballas, Mido Assran, Oleksandr Maksymets, Aravind Rajeswaran. [doi]
• In-Context Fine-Tuning for Time-Series Foundation ModelsMatthew Faw, Rajat Sen, Yichen Zhou, Abhimanyu Das. [doi]
• COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer LearningChamika Sudusinghe, Gerasimos Gerogiannis, Damitha Lenadora, Charles Block, Josep Torrellas, Charith Mendis. [doi]
• Volume-Aware Distance for Robust Similarity LearningShuo Chen 0003, Chen Gong 0002, Jun Li 0027, Jian Yang 0003. [doi]
• Concept Reachability in Diffusion Models: Beyond Dataset ConstraintsMarta Aparicio Rodriguez, Xenia Miscouridou, Anastasia Borovykh. [doi]
• TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMsFelipe Pinto Coelho Nuti, Tim Franzmeyer, João F. Henriques. [doi]
• On the Dynamic Regret of Following the Regularized Leader: Optimism with History PruningNaram Mhaisen, George Iosifidis. [doi]
• LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language ModelsTzu-Tao Chang, Shivaram Venkataraman. [doi]
• Deep Unsupervised Hashing via External GuidanceQihong Song, XitingLiu, Hongyuan Zhu 0002, Joey Tianyi Zhou, Xi Peng 0001, Peng Hu 0002. [doi]
• Correlation Clustering Beyond the Pivot AlgorithmSoheil Behnezhad, Moses Charikar, Vincent Cohen-Addad, Alma Ghafari, Weiyun Ma. [doi]
• Improving the Variance of Differentially Private Randomized Experiments through ClusteringAdel Javanmard, Vahab Mirrokni, Jean Pouget-Abadie. [doi]
• CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic InterventionSonglin Xu, Xinyu Zhang 0003. [doi]
• Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative DecodingJinze Li 0001, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li 0025, Edith C. H. Ngai, Emad Barsoum. [doi]
• Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement LearningZhiwei Xu 0005, Kun Hu, Xin Xin 0003, Weiliang Meng, Yiwei Shi, Hangyu Mao, Bin Zhang 0052, Dapeng Li 0001, Jiangjin Yin. [doi]
• Stochastic Layer-Wise Shuffle for Improving Vision Mamba TrainingZizheng Huang, Haoxing Chen, Jiaqi Li, Jun Lan, Huijia Zhu, Weiqiang Wang 0002, Limin Wang. [doi]
• Human Cognition-Inspired Hierarchical Fuzzy Learning MachineJunbiao Cui, Qin Yue 0002, Jianqing Liang, Jiye Liang. [doi]
• EgoPrivacy: What Your First-Person Camera Says About You?Yijiang Li, Genpei Zhang, Jiacheng Cheng, Yi Li 0051, Xiaojun Shan, Dashan Gao 0001, Jiancheng Lyu, Yuan Li, Ning Bi, Nuno Vasconcelos. [doi]
• HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement LearningChiqiang Liu, Dazi Li. [doi]
• Towards Robust Influence Functions with Flat Validation MinimaXichen Ye, Yifan Wu 0011, Weizhong Zhang, Cheng Jin 0001, Yifan Chen 0004. [doi]
• SPRI: Aligning Large Language Models with Context-Situated PrinciplesHongli Zhan, Muneeza Azmat, Raya Horesh, Junyi Jessy Li, Mikhail Yurochkin. [doi]
• Reward Translation via Reward Machine in Semi-Alignable MDPsYun Hua, Haosheng Chen, Wenhao Li 0001, Bo Jin 0003, Baoxiang Wang 0001, Hongyuan Zha, Xiangfeng Wang 0002. [doi]
• QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning BaselineTianyi Bao, Ruizhe Zhong, Xinyu Ye, Yehui Tang, Junchi Yan. [doi]
• Joint Learning of Energy-based Models and their Partition FunctionMichael Eli Sander, Vincent Roulet, Tianlin Liu, Mathieu Blondel. [doi]
• AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example DefensesNicholas Carlini, Edoardo Debenedetti, Javier Rando, Milad Nasr, Florian Tramèr. [doi]
• Policy-Regret Minimization in Markov Games with Function ApproximationThanh Nguyen-Tang, Raman Arora. [doi]
• TLLC: Transfer Learning-based Label Completion for CrowdsourcingWenjun Zhang 0012, Liangxiao Jiang, Chaoqun Li 0001. [doi]
• Ringmaster ASGD: The First Asynchronous SGD with Optimal Time ComplexityArto Maranjyan, Alexander Tyurin, Peter Richtárik. [doi]
• Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression HypernetworksBenjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain. [doi]
• Subspace Optimization for Large Language Models with Convergence GuaranteesYutong He, Pengrui Li, Yipeng Hu, Chuyan Chen, Kun Yuan 0001. [doi]
• Structured Preconditioners in Adaptive Optimization: A Unified AnalysisShuo Xie, Tianhao Wang, Sashank J. Reddi, Sanjiv Kumar, Zhiyuan Li 0005. [doi]
• COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel ClusteringWeixuan Liang, Xinwang Liu 0002, Ke Liang 0006, Jiyuan Liu 0003, En Zhu. [doi]
• EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuningDong Huang 0005, Guangtao Zeng, Jianbo Dai, Meng Luo, Han Weng, Yuhao Qing, Heming Cui, Zhijiang Guo, Jie Zhang 0050. [doi]
• CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement LearningHongtu Zhou, Ruiling Yang, Yakun Zhu, Haoqi Zhao, Hai Zhang, Di Zhang, Junqiao Zhao, Chen Ye 0002, Changjun Jiang. [doi]
• Learn Singularly Perturbed Solutions via Homotopy DynamicsChuqi Chen, Yahong Yang, Yang Xiang 0002, Wenrui Hao. [doi]
• Generalization Performance of Ensemble Clustering: From Theory to AlgorithmXu Zhang, Haoye Qiu, Weixuan Liang, Hui Liu 0032, Junhui Hou, Yuheng Jia. [doi]
• Optimization for Neural Operators can Benefit from WidthPedro Cisneros-Velarde, Bhavesh Shrimali, Arindam Banerjee 0001. [doi]
• Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal TransportJayadev Naram, Fredrik Hellström, Ziming Wang, Rebecka Jörnsten, Giuseppe Durisi. [doi]
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based TokenizationLuca Masserano, Abdul Fatir Ansari, Boran Han, Xiyuan Zhang, Christos Faloutsos, Michael W. Mahoney, Andrew Gordon Wilson, Youngsuk Park, Syama Sundar Rangapuram, Danielle C. Maddix, Bernie Wang 0001. [doi]
• Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problemsJiachen Guo, Xiaoyu Xie, Chanwook Park, Hantao Zhang, Matthew Politis, Gino Domel, Wing Kam Liu. [doi]
• NextCoder: Robust Adaptation of Code LMs to Diverse Code EditsTushar Aggarwal, Swayam Singh, Abhijeet Awasthi, Aditya Kanade 0001, Nagarajan Natarajan. [doi]
• Graph Generative Pre-trained TransformerXiaohui Chen, Yinkai Wang, Jiaxing He, Yuanqi Du, Soha Hassoun, Xiaolin Xu, Liping Liu 0001. [doi]
• Heterogeneous Label Shift: Theory and AlgorithmChao Xu 0008, Xijia Tang, Chenping Hou. [doi]
• Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic VerificationFlavio Petruzzellis, Cristina Cornelio, Pietro Lio. [doi]
• Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed DataXinshuai Dong, Ignavier Ng, Boyang Sun, Haoyue Dai, Guang-Yuan Hao, Shunxing Fan, Peter Spirtes, Yumou Qiu, Kun Zhang 0001. [doi]
• Competitively Consistent ClusteringNiv Buchbinder, Roie Levin, Yue Yang. [doi]
• When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural NetsChen Zeno, Hila Manor, Greg Ongie, Nir Weinberger, Tomer Michaeli, Daniel Soudry. [doi]
• Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic FlowsWillem Diepeveen, Georgios Batzolis, Zakhar Shumaylov, Carola-Bibiane Schönlieb. [doi]
• Optimal Transport Barycenter via Nonconvex-Concave Minimax OptimizationKaheon Kim, Rentian Yao, Changbo Zhu, Xiaohui Chen. [doi]
• Enhancing Logits Distillation with Plug&Play Kendall's τ Ranking LossYuchen Guan, Runxi Cheng, Kang Liu, Chun Yuan. [doi]
• Matrix Completion with Incomplete Side Information via Orthogonal Complement ProjectionGengshuo Chang, Wei Zhang 0012, Lehan Zhang. [doi]
• Learning Distances from Data with Normalizing Flows and Score MatchingPeter Sorrenson, Daniel Behrend-Uriarte, Christoph Schnörr, Ullrich Köthe. [doi]
• Improving the Statistical Efficiency of Cross-Conformal PredictionMatteo Gasparin, Aaditya Ramdas. [doi]
• COExpander: Adaptive Solution Expansion for Combinatorial OptimizationJiale Ma, Wenzheng Pan, Yang Li, Junchi Yan. [doi]
• LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and EfficientlyYuanhe Zhang, Fanghui Liu 0001, Yudong Chen 0001. [doi]
• Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion ModelsFarzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli. [doi]
• Learnable Spatial-Temporal Positional Encoding for Link PredictionKatherine Tieu, Dongqi Fu, Zihao Li 0006, Ross Maciejewski, Jingrui He. [doi]
• MTSTRec: Multimodal Time-Aligned Shared Token RecommenderMing-Yi Hong 0002, Yen-Jung Hsu, Miao-Chen Chiang, Che Lin. [doi]
• Training High Performance Spiking Neural Network by Temporal Model CalibrationJiaqi Yan, Changping Wang, De Ma, Huajin Tang, Qian Zheng, Gang Pan 0001. [doi]
• Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax OptimizationZhangyi Liu, Feng Liu, Rui Gao, Shuang Li. [doi]
• On the Generalization Ability of Next-Token-Prediction PretrainingZhihao Li, Xue Jiang, Liyuan Liu, Xuelin Zhang, Hong Chen 0004, Feng Zheng 0001. [doi]
• Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention TransformersAlireza Amiri Bavandpour, Xinting Huang, Mark Rofin, Michael Hahn 0001. [doi]
• Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic SpaceMax van Spengler, Pascal Mettes. [doi]
• De-mark: Watermark Removal in Large Language ModelsRuibo Chen, Yihan Wu, Junfeng Guo, Heng Huang. [doi]
• MOGIC: Metadata-infused Oracle Guidance for Improved Extreme ClassificationSuchith Chidananda Prabhu, Bhavyajeet Singh, Anshul Mittal, Siddarth Asokan, Shikhar Mohan, Deepak Saini, Yashoteja Prabhu, Lakshya Kumar, Jian Jiao 0007, Amit Singh 0003, Niket Tandon, Manish Gupta, Sumeet Agarwal, Manik Varma. [doi]
• On the Benefits of Active Data Collection in Operator LearningUnique Subedi, Ambuj Tewari. [doi]
• Text-to-LoRA: Instant Transformer AdaptionRujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange. [doi]
• Projection Pursuit Density Ratio EstimationMeilin Wang, Wei Huang, Mingming Gong, Zheng Zhang. [doi]
• Large Continual Instruction AssistantJingyang Qiao, Zhizhong Zhang 0001, Xin Tan 0002, Yanyun Qu, Shouhong Ding, Yuan Xie 0006. [doi]
• How Expressive are Knowledge Graph Foundation Models?Xingyue Huang, Pablo Barceló, Michael M. Bronstein, Ismail Ilkan Ceylan, Mikhail Galkin 0001, Juan L. Reutter, Miguel A. Romero Orth. [doi]
• Quadratic Upper Bound for Boosting RobustnessEuijin You, Hyang-Won Lee. [doi]
• Solving Satisfiability Modulo Counting Exactly with Probabilistic CircuitsJinzhao Li, Nan Jiang 0012, Yexiang Xue. [doi]
• Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct ReasoningZeyu Gan, Yun Liao, Yong Liu 0018. [doi]
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language ModelsMarwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine. [doi]
• Double Machine Learning for Causal Inference under Shared-State InterferenceChris Hays, Manish Raghavan. [doi]
• Benchmarking Quantum Reinforcement LearningNico Meyer, Christian Ufrecht, George Yammine, Georgios D. Kontes, Christopher Mutschler, Daniel D. Scherer. [doi]
• EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance PredictionMing Li 0065, Yukang Cheng, Lu Bai 0001, Feilong Cao, Ke Lv, Jiye Liang, Pietro Lio. [doi]
• Mahalanobis++: Improving OOD Detection via Feature NormalizationMaximilian Müller, Matthias Hein 0001. [doi]
• Learning with Expected Signatures: Theory and ApplicationsLorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart. [doi]
• LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book DataPeer Nagy, Sascha Yves Frey, Kang Li, Bidipta Sarkar, Svitlana Vyetrenko, Stefan Zohren, Ani Calinescu, Jakob Nicolaus Foerster. [doi]
• Boosting Masked ECG-Text Auto-Encoders as Discriminative LearnersManh Pham Hung, Aaqib Saeed, Dong Ma 0001. [doi]
• Bridging Protein Sequences and Microscopy Images with Unified Diffusion ModelsDihan Zheng, Bo Huang. [doi]
• Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential EquationsJuwei Yue, Haikuo Li, Jiawei Sheng, Xiaodong Li 0012, Taoyu Su, Tingwen Liu, Li Guo 0001. [doi]
• Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex OptimizationZijian Liu 0003, Zhengyuan Zhou. [doi]
• Diffusion Adversarial Post-Training for One-Step Video GenerationShanchuan Lin, Xin Xia 0014, Yuxi Ren, Ceyuan Yang, Xuefeng Xiao 0001, Lu Jiang. [doi]
• Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov SamplingZhenyu Sun, Ermin Wei. [doi]
• Info-Coevolution: An Efficient Framework for Data Model CoevolutionZiheng Qin, Hailun Xu, Wei Chee Yew, Qi Jia, Yang Luo, Kanchan Sarkar, Danhui Guan, Kai Wang 0036, Yang You 0001. [doi]
• De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning AttacksWei Fan, Kejiang Chen, Chang Liu 0089, Weiming Zhang, Nenghai Yu. [doi]
• DIME: Diffusion-Based Maximum Entropy Reinforcement LearningOnur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters 0001, Georgia Chalvatzaki, Gerhard Neumann. [doi]
• Geometry Informed Tokenization of Molecules for Language Model GenerationXiner Li, Limei Wang, Youzhi Luo, Carl Edwards, Shurui Gui, Yuchao Lin, Heng Ji 0001, Shuiwang Ji. [doi]
• Efficient Long Context Fine-tuning with Chunk FlowXiulong Yuan, Hongtao Xu, Wenting Shen, Ang Wang, Xiafei Qiu, Jie Zhang 0135, Yuqiong Liu, Bowen Yu 0002, Junyang Lin, Mingzhen Li 0001, Weile Jia, Yong Li 0045, Wei Lin 0016. [doi]
• Nonparametric Modern Hopfield ModelsJerry Yao-Chieh Hu, Bo-Yu Chen, Dennis Wu, Feng Ruan, Han Liu 0001. [doi]
• Does Graph Prompt Work? A Data Operation Perspective with Theoretical AnalysisQunzhong Wang, Xiangguo Sun, Hong Cheng 0001. [doi]
• WMarkGPT: Watermarked Image Understanding via Multimodal Large Language ModelsSongbai Tan, Xuerui Qiu, Yao Shu, Gang Xu, Linrui Xu, Xiangyu Xu, Huiping Zhuang, Ming Li 0011, Fei Richard Yu. [doi]
• Falsification of Unconfoundedness by Testing Independence of Causal MechanismsRickard Karlsson, Jesse H. Krijthe. [doi]
• Tuning LLM Judge Design Decisions for 1/1000 of the CostDavid Salinas, Omar Swelam, Frank Hutter. [doi]
• Navigating Semantic Drift in Task-Agnostic Class-Incremental LearningFangwen Wu, Lechao Cheng, Shengeng Tang, Xiaofeng Zhu, Chaowei Fang, Dingwen Zhang, Meng Wang 0001. [doi]
• CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language ModelsJunbo Yin, Chao Zha, WenJia He, Chencheng Xu, Xin Gao 0001. [doi]
• Algorithm Development in Neural Networks: Insights from the Streaming Parity TaskLoek van Rossem, Andrew M. Saxe. [doi]
• Understanding Nonlinear Implicit Bias via Region Counts in Input SpaceJingwei Li, Jing Xu 0027, Zifan Wang, Huishuai Zhang, Jingzhao Zhang. [doi]
• Disentangling and Integrating Relational and Sensory Information in Transformer ArchitecturesAwni Altabaa, John Lafferty. [doi]
• Shifting Time: Time-series Forecasting with Khatri-Rao Neural OperatorsSrinath Dama, Kevin Course, Prasanth B. Nair. [doi]
• AutoEval Done Right: Using Synthetic Data for Model EvaluationPierre Boyeau, Anastasios Nikolas Angelopoulos, Tianle Li, Nir Yosef, Jitendra Malik, Michael I. Jordan. [doi]
• The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language ModelsShishir G. Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, Joseph E. Gonzalez. [doi]
• Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural NetworksJialin Zhao 0004, Yingtao Zhang, Xinghang Li, Huaping Liu 0001, Carlo Vittorio Cannistraci. [doi]
• Almost Optimal Fully Dynamic k-Center Clustering with RecourseSayan Bhattacharya, Martín Costa, Ermiya Farokhnejad, Silvio Lattanzi, Nikos Parotsidis. [doi]
• Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular ArithmeticEshika Saxena, Alberto Alfarano, Emily Wenger, Kristin E. Lauter. [doi]
• Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent EnvironmentsMikel Malagón, Josu Ceberio, José Antonio Lozano 0001. [doi]
• Learning-Augmented Algorithms for MTS with Bandit Access to Multiple PredictorsMatei Gabriel Cosa, Marek Eliás 0001. [doi]
• PTTA: Purifying Malicious Samples for Test-Time Model AdaptationJing Ma, Hanlin Li, Xiang Xiang 0001. [doi]
• Global Optimization with a Power-Transformed Objective and Gaussian SmoothingChen Xu. [doi]
• Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value IterationYan Chen, Qinxun Bai, Yiteng Zhang, Maria Dimakopoulou, Shi Dong, Qi Sun, Zhengyuan Zhou. [doi]
• Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information AcquisitionZichen Wang, Chuanhao Li, Huazheng Wang. [doi]
• Universal Approximation Theorem of Deep Q-NetworksQian Qi. [doi]
• FloE: On-the-Fly MoE Inference on Memory-constrained GPUYuxin Zhou, Zheng Li 0006, Jun Zhang 0069, Jue Wang 0019, Yiping Wang 0003, Zhongle Xie, Ke Chen 0005, Lidan Shou. [doi]
• Oscillation-Reduced MXFP4 Training for Vision TransformersYuxiang Chen, Haocheng Xi, Jun Zhu 0001, Jianfei Chen 0001. [doi]
• SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation ModelZhao Yang 0006, Jiwei Zhu, Bing Su 0001. [doi]
• Self-Discriminative Modeling for Anomalous Graph DetectionJinyu Cai, Yunhe Zhang 0001, Jicong Fan 0001. [doi]
• Instance-Optimal Pure Exploration for Linear Bandits on Continuous ArmsSho Takemori, Yuhei Umeda, Aditya Gopalan. [doi]
• STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery IdentificationHengrui Lou, Zunlei Feng, Jinsong Geng, Erteng Liu, Jie Lei 0002, Lechao Cheng, Jie Song 0011, Mingli Song, Yijun Bei. [doi]
• A Generalization Theory for Zero-Shot PredictionRonak Mehta, Zaïd Harchaoui. [doi]
• DeFoG: Discrete Flow Matching for Graph GenerationYiming Qin, Manuel Madeira, Dorina Thanou, Pascal Frossard. [doi]
• GraphCL: Graph-based Clustering for Semi-Supervised Medical Image SegmentationMengzhu Wang, Houcheng Su, Jiao Li, Chuan Li, Nan Yin, Li Shen 0008, Jingcai Guo. [doi]
• BaxBench: Can LLMs Generate Correct and Secure Backends?Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanovic 0001, Jingxuan He, Martin T. Vechev. [doi]
• Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality GuaranteesWilliam de Vazelhes, Xiaotong Yuan, Bin Gu 0001. [doi]
• Fast Incomplete Multi-view Clustering by Flexible Anchor LearningYalan Qin, Guorui Feng, Xinpeng Zhang 0001. [doi]
• Leveraging Offline Data in Linear Latent Contextual BanditsChinmaya Kausik, Kevin Tan, Ambuj Tewari. [doi]
• Action-Constrained Imitation LearningChia-Han Yeh, Tse-Sheng Nan, Risto Vuorio, Wei Hung, Hung-Yen Wu, Shao-Hua Sun, Ping-Chun Hsieh. [doi]
• sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language ModelsHongru Hu, Shuwen Zhang, Yongin Choi, Venkat S. Malladi, Gerald T. Quon. [doi]
• AdvPrompter: Fast Adaptive Adversarial Prompting for LLMsAnselm Paulus, Arman Zharmagambetov, Chuan Guo 0001, Brandon Amos, Yuandong Tian. [doi]
• BEST-Route: Adaptive LLM Routing with Test-Time Optimal ComputeDujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang 0001, Daniel Madrigal 0001, Mirian del Carmen Hipolito Garcia, Menglin Xia, Laks V. S. Lakshmanan, Qingyun Wu, Victor Rühle. [doi]
• The Complexity of Learning Sparse Superposed Features with FeedbackAkash Kumar. [doi]
• Robot-Gated Interactive Imitation Learning with Adaptive Intervention MechanismHaoyuan Cai, Zhenghao Peng, Bolei Zhou. [doi]
• Is Noise Conditioning Necessary for Denoising Generative Models?Qiao Sun, Zhicheng Jiang, Hanhong Zhao, Kaiming He. [doi]
• Understanding the difficulties of posterior predictive estimationAbhinav Agrawal 0001, Justin Domke. [doi]
• Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural NetworksShikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala. [doi]
• FedPHA: Federated Prompt Learning for Heterogeneous Client AdaptationChengying Fang, Wenke Huang 0003, Guancheng Wan, Yihao Yang, Mang Ye. [doi]
• Unbiased Evaluation of Large Language Models from a Causal PerspectiveMeilin Chen, Jian Tian, Liang Ma, Di Xie, Weijie Chen 0006, Jiang Zhu. [doi]
• Mixture of Hidden-Dimensions: Not All Hidden-States' Dimensions are Needed in TransformerYilong Chen, Junyuan Shang, Zhenyu Zhang 0006, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun 0029, Hua Wu 0003, Haifeng Wang 0001. [doi]
• A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing SolverSuyu Liu, Zhiguang Cao, Shanshan Feng 0001, Yew-Soon Ong. [doi]
• Multi-objective Linear Reinforcement Learning with Lexicographic RewardsBo Xue 0004, Dake Bu, Ji Cheng 0001, Yuanyu Wan, Qingfu Zhang 0001. [doi]
• Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMsBowen Tan, Zheng Xu, Eric P. Xing, Zhiting Hu, Shanshan Wu. [doi]
• Weight matrices compression based on PDB model in deep neural networksXiaoling Wu, Junpeng Zhu, Zeng Li. [doi]
• Adjustment for Confounding using Pre-Trained RepresentationsRickmer Schulte, David Rügamer, Thomas Nagler. [doi]
• No-Regret is not enough! Bandits with General Constraints through Adaptive Regret MinimizationMartino Bernasconi, Matteo Castiglioni, Andrea Celli. [doi]
• Graph Diffusion for Robust Multi-Agent CoordinationXianghua Zeng, Hang Su 0006, Zhengyi Wang, Zhiyuan Lin. [doi]
• Self-Organizing Visual Prototypes for Non-Parametric Representation LearningThalles Silva 0001, Hélio Pedrini, Adín Ramírez Rivera. [doi]
• Generative Human Trajectory Recovery via Embedding-Space Conditional DiffusionKaijun Liu, Sijie Ruan, Liang Zhang, Cheng Long 0001, Shuliang Wang 0001, Liang Yu 0005. [doi]
• Rethinking Benign Overfitting in Two-Layer Neural NetworksRuichen Xu, Kexin Chen. [doi]
• SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic ManipulationHaoquan Fang, Markus Grotz, Wilbert Pumacay, Yi Ru Wang, Dieter Fox, Ranjay Krishna, Jiafei Duan. [doi]
• Beyond Bradley-Terry Models: A General Preference Model for Language Model AlignmentYifan Zhang, Ge Zhang, Yue Wu, Kangping Xu, Quanquan Gu. [doi]
• Open Materials Generation with Stochastic InterpolantsPhilipp Höllmer, Thomas Egg, Maya M. Martirossyan, Eric Fuemmeler, Zeren Shui, Amit Gupta, Pawan Prakash, Adrian Roitberg, Mingjie Liu, George Karypis, Mark K. Transtrum, Richard G. Hennig, Ellad B. Tadmor, Stefano Martiniani. [doi]
• L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental LearningXiang Zhang, Run He, Chen Jiao, Di Fang 0004, Ming Li 0073, Ziqian Zeng, Cen Chen 0002, Huiping Zhuang. [doi]
• ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport PlansAshkan Shahbazi, Elaheh Akbari, Darian Salehi, Xinran Liu, Navid Naderializadeh, Soheil Kolouri. [doi]
• Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized EnvironmentsYun Qu 0002, Cheems Wang, Yixiu Mao, Yiqin Lv, Xiangyang Ji. [doi]
• UnHiPPO: Uncertainty-aware Initialization for State Space ModelsMarten Lienen, Abdullah Saydemir, Stephan Günnemann. [doi]
• A Reduction Framework for Distributionally Robust Reinforcement Learning under Average RewardZachary Roch, George K. Atia, Yue Wang 0068. [doi]
• Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference ModelYuzhong Hong, Hanshan Zhang, Junwei Bao 0001, Hongfei Jiang, Yang Song 0021. [doi]
• Toward Efficient Kernel-Based Solvers for Nonlinear PDEsZhitong Xu, Da Long, Yiming Xu, Guang Yang, Shandian Zhe, Houman Owhadi. [doi]
• Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse EnvironmentsBaohong Li, Yingrong Wang, Anpeng Wu, Ming Ma, Ruoxuan Xiong, Kun Kuang. [doi]
• Directly Forecasting Belief for Reinforcement Learning with DelaysQingyuan Wu, Yuhui Wang 0004, Simon Sinong Zhan, Yixuan Wang 0001, Chung-Wei Lin, Chen Lv 0001, Qi Zhu 0002, Jürgen Schmidhuber, Chao Huang 0015. [doi]
• EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance SegmentationJiawei Cao, Chaochen Gu, Hao Cheng 0004, Xiaofeng Zhang, Kaijie Wu 0002, Changsheng Lu. [doi]
• LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image SegmentationPiyush Tiwary, Kinjawl Bhattacharyya, Prathosh AP. [doi]
• Reinforcement Learning for Quantum Control under Physical ConstraintsJan Ole Ernst, Aniket Chatterjee, Tim Franzmeyer, Axel Kuhn. [doi]
• EEG-Language Pretraining for Highly Label-Efficient Clinical PhenotypingSam Gijsen, Kerstin Ritter. [doi]
• The Generalized Skew Spectrum of GraphsArmando Bellante, Martin Plávala, Alessandro Luongo. [doi]
• e-GAI: e-value-based Generalized α-Investing for Online False Discovery Rate ControlYifan Zhang, Zijian Wei, Haojie Ren, Changliang Zou. [doi]
• Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding ExplorationQinglin Zhu, Runcong Zhao, Hanqi Yan, Yulan He 0001, Yudong Chen, Lin Gui 0003. [doi]
• Matryoshka QuantizationPranav Ajit Nair, Puranjay Datta, Jeff Dean, Prateek Jain 0002, Aditya Kusupati. [doi]
• Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous VocabulariesNadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel. [doi]
• Provable Policy Gradient for Robust Average-Reward MDPs Beyond RectangularityQiuhao Wang, Yuqi Zha, Chin Pang Ho, Marek Petrik. [doi]
• Aggregation Buffer: Revisiting DropEdge with a New Parameter BlockDooho Lee, Myeong Kong, Sagad Hamid, Cheonwoo Lee, Jaemin Yoo. [doi]
• Identifying biological perturbation targets through causal differential networksMenghua Wu, Umesh Padia, Sean H. Murphy, Regina Barzilay, Tommi S. Jaakkola. [doi]
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-TimeMohamad Fares El Hajj Chehade, Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Dinesh Manocha, Hao Zhu, Amrit Singh Bedi. [doi]
• Proactive Agents for Multi-Turn Text-to-Image Generation Under UncertaintyMeera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, Been Kim, Zi Wang. [doi]
• Parallel Simulation for Log-concave Sampling and Score-based Diffusion ModelsHuanjian Zhou, Masashi Sugiyama. [doi]
• Boosting Protein Graph Representations through Static-Dynamic FusionPengkang Guo, Bruno E. Correia, Pierre Vandergheynst, Daniel Probst. [doi]
• Generative Intervention Models for Causal Perturbation ModelingNora Schneider, Lars Lorch, Niki Kilbertus, Bernhard Schölkopf, Andreas Krause 0001. [doi]
• Instance Correlation Graph-based Naive BayesChengyuan Li, Liangxiao Jiang, Wenjun Zhang 0012, Liangjun Yu, Huan Zhang 0007. [doi]
• MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference OptimizationKangyu Zhu, Peng Xia 0005, Yun Li 0010, Hongtu Zhu, Sheng Wang, Huaxiu Yao. [doi]
• Mitigating Heterogeneous Token Overfitting in LLM Knowledge EditingTianci Liu 0003, Ruirui Li 0002, Zihan Dong, Hui Liu 0031, Xianfeng Tang, Qingyu Yin, Linjun Zhang, Haoyu Wang 0004, Jing Gao 0004. [doi]
• Proxsparse: Regularized Learning of Semi-Structured Sparsity masks for Pretrained LLMSHongyi Liu, Rajarshi Saha, Zhen Jia, Youngsuk Park, Jiaji Huang, Shoham Sabach, Yu-Xiang Wang 0003, George Karypis. [doi]
• Analyze Feature Flow to Enhance Interpretation and Steering in Language ModelsDaniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov. [doi]
• Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in FairnessYuntao Wang, Yuxuan Li, Qingyuan Yang, Hu Ding. [doi]
• GRAM: A Generative Foundation Reward Model for Reward GeneralizationChenglong Wang 0002, Yang Gan, Yifu Huo, Yongyu Mu, Qiaozhi He, Murun Yang, Bei Li, Tong Xiao, Chunliang Zhang, Tongran Liu, Jingbo Zhu. [doi]
• Distributed Nonparametric Estimation: from Sparse to Dense Samples per TerminalDeheng Yuan, Tao Guo 0003, Zhongyi Huang. [doi]
• Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial ErrorsShuangpeng Han, Mengmi Zhang. [doi]
• Causal Logistic Bandits with Counterfactual Fairness ConstraintsJiajun Chen, Jin Tian, Christopher John Quinn. [doi]
• Bridging Layout and RTL: Knowledge Distillation based Timing PredictionMingjun Wang, Yihan Wen, Bin Sun, Jianan Mu, Juan Li, Xiaoyi Wang, Jing Justin Ye, Bei Yu 0001, Huawei Li 0001. [doi]
• Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication OverlappingMuru Zhang, Mayank Mishra, Zhongzhu Zhou, William Brandon, Jue Wang, Yoon Kim, Jonathan Ragan-Kelley, Shuaiwen Leon Song, Ben Athiwaratkun, Tri Dao. [doi]
• Navigating Conflicting Views: Harnessing Trust for LearningJueqing Lu, Wray L. Buntine, Yuanyuan Qi, Joanna Dipnall, Belinda Gabbe, Lan Du 0002. [doi]
• MindCustomer: Multi-Context Image Generation Blended with Brain SignalMuzhou Yu, Shuyun Lin, Lei Ma 0008, Bo Lei, Kaisheng Ma. [doi]
• Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain TransferYabo Liu, Waikeung Wong, Chengliang Liu 0003, Xiaoling Luo 0001, Yong Xu 0001, Jinghua Wang. [doi]
• Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific HeadsSiqi Kou, Jiachun Jin, Zhihong Liu, Chang Liu, Ye Ma, Jian Jia, Quan Chen 0006, Peng Jiang 0002, Zhijie Deng. [doi]
• Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language ModelsXin Cheng 0007, Jiabo Ye, Haiyang Xu 0001, Ming Yan 0008, Ji Zhang 0011, Feng Liu 0003, Fei Huang 0002, Lei Feng 0006. [doi]
• Accelerating Spectral Clustering under Fairness ConstraintsFrancesco Tonin, Alex Lambert, Johan A. K. Suykens, Volkan Cevher. [doi]
• FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable TrainingPhilip Zmushko, Aleksandr Beznosikov, Martin Takác 0001, Samuel Horváth. [doi]
• Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancingJie Peng 0002, Jenna l. Ballard, Mohan Zhang, Sukwon Yun, Jiayi Xin, Qi Long, Yanyong Zhang, Tianlong Chen 0001. [doi]
• Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus AreasShiqi Chen 0002, Tongyao Zhu, Ruochen Zhou, Jinghan Zhang 0006, Siyang Gao, Juan Carlos Niebles, Mor Geva, Junxian He, Jiajun Wu 0001, Manling Li. [doi]
• Simplicity Bias and Optimization Threshold in Two-Layer ReLU NetworksEtienne Boursier, Nicolas Flammarion. [doi]
• When to retrain a machine learning modelFlorence Regol, Leo Schwinn, Kyle Sprague, Mark Coates, Thomas Markovich. [doi]
• The Role of Randomness in StabilityMax Hopkins, Shay Moran. [doi]
• Learning Robust Neural Processes with Risk-Averse Stochastic OptimizationHuafeng Liu, Yiran Fu, Liping Jing, Hui Li, Shuyang Lin, Jingyue Shi, Deqiang Ouyang, Jian Yu. [doi]
• Active Learning with Selective Time-Step Acquisition for PDEsYegon Kim, Hyunsu Kim, Gyeonghoon Ko, Juho Lee 0001. [doi]
• Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation ModelsUlzee An, Moonseong Jeong, Simon A. Lee, Aditya Gorla, Yuzhe Yang, Sriram Sankararaman. [doi]
• Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction TuningChendi Ge, Xin Wang 0019, Zeyang Zhang 0001, Hong Chen 0011, Jiapei Fan, Longtao Huang, Hui Xue 0001, Wenwu Zhu 0001. [doi]
• Variational Learning of Fractional PosteriorsKian Ming A. Chai, Edwin V. Bonilla. [doi]
• Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer LearningMd Yousuf Harun, Jhair Gallardo, Christopher Kanan. [doi]
• The Geometry of Refusal in Large Language Models: Concept Cones and Representational IndependenceTom Wollschläger, Jannes Elstner, Simon Geisler, Vincent Cohen-Addad, Stephan Günnemann, Johannes Gasteiger. [doi]
• Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy EvaluationKosuke Nakanishi, Akihiro Kubo, Yuji Yasui, Shin Ishii. [doi]
• AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement LearningZhoufan Zhu, Ke Zhu. [doi]
• Catoni Contextual Bandits are Robust to Heavy-tailed RewardsChenlu Ye, Yujia Jin, Alekh Agarwal, Tong Zhang 0001. [doi]
• Active Learning for Efficient Discovery of Optimal Combinatorial PerturbationsJason Qin, Hans-Hermann Wessels, Carlos Fernandez-Granda, Yuhan Hao. [doi]
• A Lens into Interpretable Transformer Mistakes via Semantic DependencyRuo-Jing Dong, Yu Yao 0005, Bo Han 0003, Tongliang Liu. [doi]
• Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide SequencingXiang Zhang 0011, Jiaqi Wei, Zijie Qiu, Sheng Xu, Nanqing Dong, Zhiqiang Gao, Siqi Sun. [doi]
• Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and CoverageSaehyung Lee, Seunghyun Yoon 0002, Trung Bui, Jing Shi 0005, Sungroh Yoon. [doi]
• RUN: Reversible Unfolding Network for Concealed Object SegmentationChunming He, Rihan Zhang, Fengyang Xiao, Chengyu Fang 0001, Longxiang Tang, Yulun Zhang 0001, Linghe Kong, Deng-Ping Fan, Kai Li 0012, Sina Farsiu. [doi]
• Conditional Diffusion Model with Nonlinear Data Transformation for Time Series ForecastingJ. Rishi, GVS Mothish, Deepak Subramani. [doi]
• DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language ModelsChangyi He, Yifu Ding, Jinyang Guo, Ruihao Gong, Haotong Qin, Xianglong Liu 0001. [doi]
• Multi-band Frequency Reconstruction for Neural Psychoacoustic CodingDianwen Ng, Kun Zhou 0003, Yi-Wen Chao, Zhiwei Xiong, Bin Ma 0001, Engsiong Chng. [doi]
• AdaWorld: Learning Adaptable World Models with Latent ActionsShenyuan Gao, Siyuan Zhou, Yilun Du, Jun Zhang, Chuang Gan 0001. [doi]
• Measuring Diversity: Axioms and ChallengesMikhail Mironov, Liudmila Prokhorenkova. [doi]
• PDE-Transformer: Efficient and Versatile Transformers for Physics SimulationsBenjamin J. Holzschuh, Qiang Liu 0038, Georg Kohl, Nils Thuerey. [doi]
• Physics Aware Neural Networks for Unsupervised Binding Energy PredictionKe Liu 0012, Hao Cheng 0012, Chunhua Shen. [doi]
• Unisoma: A Unified Transformer-based Solver for Multi-Solid SystemsShilong Tao, Zhe Feng, Haonan Sun, Zhanxing Zhu, Yunhuai Liu. [doi]
• Neural Solver Selection for Combinatorial OptimizationChengrui Gao, Haopu Shang, Ke Xue 0001, Chao Qian 0001. [doi]
• Beyond Topological Self-Explainable GNNs: A Formal Explainability PerspectiveSteve Azzolin, Sagar Malhotra, Andrea Passerini, Stefano Teso. [doi]
• Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension ReductionYinfeng Chen, Jin Liu, Rui Qiu. [doi]
• Exploiting Similarity for Computation and Communication-Efficient Decentralized OptimizationYuki Takezawa, Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich. [doi]
• Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesJunhyuck Kim, Jongho Park, Jaewoong Cho, Dimitris Papailiopoulos. [doi]
• Reasoning Through Execution: Unifying Process and Outcome Rewards for Code GenerationZhuohao Yu 0001, Weizheng Gu, Yidong Wang 0003, Xingru Jiang, Zhengran Zeng, Jindong Wang 0001, Wei Ye 0004, Shikun Zhang. [doi]
• Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor CompletionYuanwei Zhang, Fengmiao Bian, Xiaoqun Zhang, Jian-Feng Cai 0001. [doi]
• Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized EquationsQuoc Tran-Dinh. [doi]
• Neurosymbolic World Models for Sequential Decision MakingLeonardo Hernandez Cano, Maxine Perroni-Scharf, Neil Dhir, Arun Ramamurthy, Armando Solar-Lezama. [doi]
• Universal Neural Optimal TransportJonathan Geuter, Gregor Kornhardt, Ingimar Tomasson, Vaios Laschos. [doi]
• Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical PerspectiveZeyu Jia, Alexander Rakhlin, Tengyang Xie. [doi]
• The Limits of Tractable MarginalizationOliver Broadrick, Sanyam Agarwal, Guy Van den Broeck, Markus Bläser. [doi]
• BAME: Block-Aware Mask Evolution for Efficient N: M Sparse TrainingChenyi Yang 0002, Wenjie Nie, Yuxin Zhang 0002, Yuhang Wu 0004, Xiawu Zheng, Guannan Jiang, Rongrong Ji. [doi]
• CALM: Consensus-Aware Localized Merging for Multi-Task LearningKunda Yan, Min Zhang 0005, Sen Cui, Zikun Qu, Bo Jiang 0016, Feng Liu, Changshui Zhang. [doi]
• A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-MakingYi Xie, Jaedong Hwang, Carlos D. Brody, David W. Tank, Ila R. Fiete. [doi]
• Provably Near-Optimal Federated Ensemble Distillation with Negligible OverheadWon Jun Jang, Hyeon-Seo Park, Si-Hyeon Lee. [doi]
• RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network LayersXuwei Xu, Yang Li 0184, Yudong Chen 0002, Jiajun Liu, Sen Wang 0001. [doi]
• UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything ModelTimo Kaiser, Thomas Norrenbrock, Bodo Rosenhahn. [doi]
• Gradient Inversion of Multimodal ModelsOmri Ben Hemo, Alon Zolfi, Oryan Yehezkel, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Yuval Elovici, Asaf Shabtai. [doi]
• QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model PredictionsZhun Deng, Thomas P. Zollo, Benjamin Eyre, Amogh Inamdar, David Madras, Richard S. Zemel. [doi]
• Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects ModelsXichen Guo, Feng Xie 0002, Yan Zeng 0002, Hao Zhang 0079, Zhi Geng. [doi]
• Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal ExamplesFangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, Lianhui Qin. [doi]
• An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical DataNikita Lagrange, Hervé Isambert. [doi]
• On Understanding Attention-Based In-Context Learning for Categorical DataAaron T. Wang, William Convertino, Xiang Cheng, Ricardo Henao, Lawrence Carin. [doi]
• Improving Consistency Models with Generator-Augmented FlowsThibaut Issenhuth, SangChul Lee, Ludovic Dos Santos, Jean-Yves Franceschi, Chansoo Kim, Alain Rakotomamonjy. [doi]
• On-Device Collaborative Language Modeling via a Mixture of Generalists and SpecialistsDongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi. [doi]
• Efficient Skill Discovery via Regret-Aware OptimizationHe Zhang 0030, Ming Zhou, Shaopeng Zhai, Ying Sun 0006, Hui Xiong 0001. [doi]
• Towards Escaping from Class Dependency Modeling for Multi-Dimensional ClassificationTeng Huang 0003, Bin-Bin Jia 0001, Min-Ling Zhang. [doi]
• Learning Distribution-wise Control in Representation Space for Language ModelsChunyuan Deng, Ruidi Chang, Hanjie Chen. [doi]
• De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain GraphsSamantha Chen 0001, Pankaj K. Agarwal, Yusu Wang 0001. [doi]
• Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration StoryVincenzo De Paola, Riccardo Zamboni, Mirco Mutti, Marcello Restelli. [doi]
• Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-MeansMikael Møller Høgsgaard, Andrea Paudice. [doi]
• Continuously Updating Digital Twins using Large Language ModelsHarry Amad, Nicolás Astorga, Mihaela van der Schaar. [doi]
• Optimal Survey Design for Private Mean EstimationYu-Wei Chen, Raghu Pasupathy, Jordan Awan. [doi]
• Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate SystemsHongyuan Su, Yu Zheng 0010, Yuan Yuan 0032, Yuming Lin 0003, Depeng Jin, Yong Li 0008. [doi]
• Understanding Generalization in Quantum Machine Learning with MarginsTak Hur, Daniel K. Park. [doi]
• Robust Spatio-Temporal Centralized Interaction for OOD LearningJiaming Ma, Binwu Wang, Pengkun Wang 0001, Zhengyang Zhou, Xu Wang 0029, Yang Wang 0015. [doi]
• TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical ImagingChuang Liu, Hongyan Xu 0002, Yichao Cao, Xiu Su, Zhe Qu, Tianfa Li, Shan An, Haogang Zhu. [doi]
• am-ELO: A Stable Framework for Arena-based LLM EvaluationZirui Liu 0010, Jiatong Li 0002, Yan Zhuang, Qi Liu 0003, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang 0001. [doi]
• A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics TasksThomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter. [doi]
• SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite ProgrammingHong Ming Chiu, Hao Chen, Huan Zhang, Richard Y. Zhang. [doi]
• LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from VideosYujun Shi, Jun Hao Liew, Hanshu Yan, Vincent Y. F. Tan, Jiashi Feng. [doi]
• An Interpretable N-gram Perplexity Threat Model for Large Language Model JailbreaksValentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping. [doi]
• Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph GenerationGuoqing Zhang, Shichao Kan, Fanghui Zhang, Wanru Xu, Yue Zhang 0065, Yigang Cen. [doi]
• Deep Reinforcement Learning from Hierarchical Preference DesignAlexander Bukharin, Yixiao Li, Pengcheng He, Tuo Zhao. [doi]
• On Explaining Equivariant Graph Networks via Improved Relevance PropagationHongyi Ling, Haiyang Yu 0005, Zhimeng Jiang, Na Zou 0001, Shuiwang Ji. [doi]
• Efficient Diffusion Models for Symmetric ManifoldsOren Mangoubi, Neil He, Nisheeth K. Vishnoi. [doi]
• Online Linear Classification with Massart NoiseIlias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis. [doi]
• SPMC: Self-Purifying Federated Backdoor Defense via Margin ContributionWenwen He, Wenke Huang 0003, Bin Yang 0026, Shukan Liu, Mang Ye. [doi]
• Optimizing Adaptive Attacks against Watermarks for Language ModelsAbdulrahman Diaa, Toluwani Aremu, Nils Lukas. [doi]
• Near-optimal Sketchy Natural Gradients for Physics-Informed Neural NetworksMaricela Best McKay, Avleen Kaur, Chen Greif, Brian Wetton. [doi]
• Convergence of Consistency Model with Multistep Sampling under General Data AssumptionsYiding Chen, Yiyi Zhang, Owen Oertell, Wen Sun 0002. [doi]
• Learning Imbalanced Data with Beneficial Label NoiseGuangzheng Hu, Feng Liu 0003, Mingming Gong, Guanghui Wang, Liuhua Peng. [doi]
• Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance TraceabilityYunshu Dai, Jianwei Fei, Fangjun Huang, Chip-Hong Chang. [doi]
• Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile ModelRachel Cummings, Alessandro Epasto, Jieming Mao, Tamalika Mukherjee, Tingting Ou, Peilin Zhong. [doi]
• Hybrid Quantum-Classical Multi-Agent PathfindingThore Gerlach, Loong Kuan Lee, Frédéric Barbaresco, Nico Piatkowski. [doi]
• On the Diversity of Adversarial Ensemble LearningJun-Qi Guo, Meng-Zhang Qian, Wei Gao 0008, Zhi-Hua Zhou. [doi]
• Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold MethodAndi Han, Pierre-Louis Poirion, Akiko Takeda. [doi]
• Probing Visual Language Priors in VLMsTiange Luo, Ang Cao, Gunhee Lee, Justin Johnson 0001, Honglak Lee. [doi]
• EPIC: Efficient Position-Independent Caching for Serving Large Language ModelsJunhao Hu, Wenrui Huang, Weidong Wang, Haoyi Wang, Tiancheng Hu, Qin Zhang, Hao Feng, Xusheng Chen, Yizhou Shan, Tao Xie 0001. [doi]
• Large Displacement Motion Transfer with Unsupervised Anytime InterpolationGuixiang Wang, Jianjun Li. [doi]
• In-Context Learning as Conditioned Associative Memory RetrievalWeimin Wu, Teng-Yun Hsiao, Jerry Yao-Chieh Hu, Wenxin Zhang, Han Liu 0001. [doi]
• MoH: Multi-Head Attention as Mixture-of-Head AttentionPeng Jin 0001, Bo Zhu, Li Yuan 0007, Shuicheng Yan. [doi]
• DS-VLM: Diffusion Supervision Vision Language ModelZhen Sun, Yunhang Shen, Jie Li 0052, Xing Sun 0001, Pingyang Dai, Liujuan Cao, Rongrong Ji. [doi]
• SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language ModelsSaman Forouzandeh, Parham Moradi, Mahdi Jalili. [doi]
• Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate MechanismAviv Bick, Eric P. Xing, Albert Gu. [doi]
• Automated Red Teaming with GOAT: the Generative Offensive Agent TesterMaya Pavlova, Erik Brinkman, Krithika Iyer, Vítor Albiero, Joanna Bitton, Hailey Nguyen, Cristian Canton-Ferrer, Ivan Evtimov, Aaron Grattafiori. [doi]
• Learning Cascade Ranking as One NetworkYunli Wang, Zhen Zhang, Zhiqiang Wang, Zixuan Yang, Yu Li, Jian Yang 0003, Shiyang Wen, Peng Jiang 0002, Kun Gai. [doi]
• FG-CLIP: Fine-Grained Visual and Textual AlignmentChunyu Xie, Bin Wang 0071, Fanjing Kong, Jincheng Li 0002, Dawei Liang, Gengshen Zhang, Dawei Leng, Yuhui Yin. [doi]
• SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential EquationsGrigory Bartosh, Dmitry P. Vetrov, Christian A. Naesseth. [doi]
• Vision-Language Models Create Cross-Modal Task RepresentationsGrace Luo, Trevor Darrell, Amir Bar. [doi]
• Improved Sample Complexity for Private Nonsmooth Nonconvex OptimizationGuy Kornowski, Daogao Liu, Kunal Talwar. [doi]
• EvoMesh: Adaptive Physical Simulation with Hierarchical Graph EvolutionsHuayu Deng, Xiangming Zhu 0002, Yunbo Wang, Xiaokang Yang 0001. [doi]
• Private Lossless Multiple ReleaseJoel Daniel Andersson, Lukas Retschmeier, Boel Nelson, Rasmus Pagh. [doi]
• Privacy Amplification Through Synthetic Data: Insights from Linear RegressionClément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard. [doi]
• Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial TransferabilityRenpu Liu, Hao Wu 0078, Jiawei Zhang 0011, Xin Cheng 0018, Xiangyang Luo 0001, Bin Ma 0003, Jinwei Wang. [doi]
• MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement LearningSuning Huang, Zheyu Aqa Zhang, Tianhai Liang, Yihan Xu, Zhehao Kou, Chenhao Lu, Guowei Xu 0001, Zhengrong Xue, Huazhe Xu. [doi]
• Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity LossSangyeon Park, Isaac Han, Seungwon Oh, Kyung-Joong Kim 0001. [doi]
• Fraud-Proof Revenue Division on Subscription PlatformsAbheek Ghosh, Tzeh Yuan Neoh, Nicholas Teh, Giannis Tyrovolas. [doi]
• Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite ImageryPratinav Seth, Michelle P. Lin, Brefo Yaw Dwamena, Jade Boutot, Mary Kang, David Rolnick. [doi]
• POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference OptimizationBatuhan K. Karaman, Ishmam Zabir, Alon Benhaim, Vishrav Chaudhary, Mert R. Sabuncu, Xia Song. [doi]
• Impossible VideosZechen Bai, Hai Ci, Mike Zheng Shou. [doi]
• Novelty Detection in Reinforcement Learning with World ModelsGeigh Zollicoffer, Kenneth Eaton, Jonathan C. Balloch, Julia M. Kim, Wei Zhou, Robert Wright, Mark O. Riedl. [doi]
• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion DistillationZhendong Wang 0005, Max Li, Ajay Mandlekar, Zhenjia Xu, JiaoJiao Fan, Yashraj Narang, Linxi Fan, Yuke Zhu, Yogesh Balaji, Mingyuan Zhou, Ming-Yu Liu 0001, Yu Zeng 0001. [doi]
• Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering AgentsKarina Zainullina, Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Daria Litvintseva, Simon Karasik, Filipp Fisin, Sergei Skvortsov, Maksim Nekrashevich, Anton Shevtsov, Boris Yangel. [doi]
• Controllable Data Generation with Hierarchical Neural RepresentationsSheyang Tang, Xiaoyu Xu, Jiayan Qiu, Zhou Wang. [doi]
• WAVE: Weighted Autoregressive Varying Gate for Time Series ForecastingJiecheng Lu, Xu Han, Yan Sun, Shihao Yang 0002. [doi]
• Policy-labeled Preference Learning: Is Preference Enough for RLHF?Taehyun Cho, Seokhun Ju, Seungyub Han, Dohyeong Kim, Kyungjae Lee 0001, Jungwoo Lee 0001. [doi]
• Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional SubgoalsVivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen. [doi]
• Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance LearningBoyuan Wu, Zefeng Wang, Xianwei Lin, Jiachun Xu, Jikai Yu, Shicheng Zhou, Hongda Chen, Lianxin Hu. [doi]
• Pfeife: Automatic Pipeline Parallelism for PyTorchHo Young Jhoo, Chung-Kil Hur, Nuno P. Lopes. [doi]
• Earley-Driven Dynamic Pruning for Efficient Structured DecodingXintong Sun, Chi Wei, Minghao Tian, Shiwen Ni. [doi]
• Runtime Analysis of Evolutionary NAS for Multiclass ClassificationZeqiong Lv, Chao Qian 0001, Yun Liu, Jiahao Fan, Yanan Sun 0001. [doi]
• Auditing Prompt Caching in Language Model APIsChenChen Gu, Xiang Lisa Li, Rohith Kuditipudi, Percy Liang, Tatsunori Hashimoto. [doi]
• Optimistic Algorithms for Adaptive Estimation of the Average Treatment EffectOjash Neopane, Aaditya Ramdas, Aarti Singh. [doi]
• Nesterov Method for Asynchronous Pipeline Parallel OptimizationThalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo, Gil Avraham, Alexander Long. [doi]
• Latent Action Learning Requires Supervision in the Presence of DistractorsAlexander Nikulin, Ilya Zisman, Denis Tarasov, Nikita Lyubaykin, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov. [doi]
• How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical PerspectiveJing Qiao, Yu Liu 0085, Yuan Yuan 0040, Xiao Zhang 0015, Zhipeng Cai 0001, Dongxiao Yu. [doi]
• Which Attention Heads Matter for In-Context Learning?Kayo Yin, Jacob Steinhardt. [doi]
• Hessian Geometry of Latent Space in Generative ModelsAlexander Lobashev, Dmitry Guskov, Maria A. Larchenko, Mikhail V. Tamm. [doi]
• Enhancing Parallelism in Decentralized Stochastic Convex OptimizationOfri Eisen, Ron Dorfman, Kfir Yehuda Levy. [doi]
• Whitened CLIP as a Likelihood Surrogate of Images and CaptionsRoy Betser, Meir Yossef Levi, Guy Gilboa. [doi]
• Exploring Vision Semantic Prompt for Efficient Point Cloud UnderstandingYixin Zha, Chuxin Wang, Wenfei Yang, Tianzhu Zhang 0001, Feng Wu 0001. [doi]
• Integer Programming for Generalized Causal Bootstrap DesignsJennifer Rogers Brennan, Sébastien Lahaie, Adel Javanmard, Nick Doudchenko, Jean Pouget-Abadie. [doi]
• Eigenspectrum Analysis of Neural Networks without Aspect Ratio BiasYuanzhe Hu, Kinshuk Goel, Vlad Killiakov, Yaoqing Yang. [doi]
• BCE vs. CE in Deep Feature LearningQiufu Li, Huibin Xiao, LinLin Shen. [doi]
• How Far Is Video Generation from World Model: A Physical Law PerspectiveBingyi Kang, Yang Yue, Rui Lu, Zhijie Lin 0001, Yang Zhao 0003, Kaixin Wang, Gao Huang 0001, Jiashi Feng. [doi]
• Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided DiffusionXingpei Ma, Jiaran Cai, Yuansheng Guan, Shenneng Huang, Qiang Zhang, Shunsi Zhang. [doi]
• Deep Neural Cellular Potts ModelsKoen Minartz, Tim D'Hondt, Leon Hillmann, Jörn Starruß, Lutz Brusch, Vlado Menkovski. [doi]
• LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision ModelsFanfei Li, Thomas Klein, Wieland Brendel, Robert Geirhos, Roland S. Zimmermann. [doi]
• No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning DatasetsCorinna Coupette, Jeremy Wayland, Emily Simons, Bastian Rieck. [doi]
• QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image RetrievalJaehyun Kwak, Ramahdani Muhammad Izaaz Inhar, Se-Young Yun, Sung-Ju Lee. [doi]
• Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning ModelsXingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He 0002, Jianhui Pang, Dian Yu 0001, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang 0001, Rui Wang 0015, Zhaopeng Tu, Haitao Mi, Dong Yu 0001. [doi]
• Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic NetworksLiyuan Liang, Xinyi Chen, Gan Luo, Kun Yuan. [doi]
• BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer SharingYuhua Zhou, Ruifeng Li, Changhai Zhou, Fei Yang, Aimin Pan. [doi]
• Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint MatchingAaron J. Havens, Benjamin Kurt Miller, Bing Yan, Carles Domingo-Enrich, Anuroop Sriram, Daniel S. Levine 0003, Brandon M. Wood, Bin Hu, Brandon Amos, Brian Karrer, Xiang Fu 0005, Guan-Horng Liu, Ricky T. Q. Chen. [doi]
• Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy RegularizationJunyi Liao, Zihan Zhu, Ethan X. Fang, Zhuoran Yang, Vahid Tarokh. [doi]
• Variational Rectified Flow MatchingPengsheng Guo, Alex Schwing 0001. [doi]
• Tightening Causal Bounds via Covariate-Aware Optimal TransportSirui Lin, Zijun Gao, Jose H. Blanchet, Peter W. Glynn. [doi]
• Differentiable Solver Search for Fast Diffusion SamplingShuai Wang, Zexian Li, Qipeng Zhang, Tianhui Song, Xubin Li, Tiezheng Ge, Bo Zheng 0007, Limin Wang 0002. [doi]
• Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data StreamsYuan Feng, Yukun Cao, Hairu Wang 0002, Xike Xie, S. Kevin Zhou. [doi]
• Conditioning Diffusions Using Malliavin CalculusJakiw Pidstrigach, Elizabeth Louise Baker, Carles Domingo-Enrich, George Deligiannidis, Nikolas Nüsken. [doi]
• A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPsKihyuk Hong, Ambuj Tewari. [doi]
• Enhancing Decision-Making of Large Language Models via Actor-CriticHeng Dong, Kefei Duan, Chongjie Zhang. [doi]
• Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsTung Minh Luu, Younghwan Lee, Donghoon Lee, Sunho Kim, Min Jun Kim, Chang D. Yoo. [doi]
• Understanding the Kronecker Matrix-Vector Complexity of Linear AlgebraRaphael A. Meyer, William J. Swartworth, David P. Woodruff. [doi]
• Scaling Large Motion Models with Million-Level Human MotionsYe Wang, Sipeng Zheng, Bin Cao, Qianshan Wei, Weishuai Zeng, Qin Jin, Zongqing Lu 0002. [doi]
• Robust Reward Alignment via Hypothesis Space Batch CuttingZhixian Xie, Haode Zhang, Yizhe Feng, Wanxin Jin. [doi]
• Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision ModelsQuan Minh Nguyen, Minh N. Vu, Truc Nguyen, My T. Thai. [doi]
• PipeOffload: Improving Scalability of Pipeline Parallelism with Memory OptimizationXinyi Wan, Penghui Qi, Guangxing Huang, Min Lin, Jialin Li. [doi]
• Quantum Speedup for Hypergraph SparsificationChenghua Liu, Minbo Gao, Zhengfeng Ji, Mingsheng Ying. [doi]
• Optimizing Test-Time Compute via Meta Reinforcement FinetuningYuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar. [doi]
• SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI BehaviorJing-jing Li, Valentina Pyatkin, Max Kleiman-Weiner, Liwei Jiang, Nouha Dziri, Anne Collins, Jana Schaich Borg, Maarten Sap, Yejin Choi 0001, Sydney Levine. [doi]
• Covered Forest: Fine-grained generalization analysis of graph neural networksAntonis Vasileiou, Ben Finkelshtein, Floris Geerts, Ron Levie, Christopher Morris 0001. [doi]
• Low-Rank ThinningAnnabelle Michael Carrell, Albert Gong, Abhishek Shetty, Raaz Dwivedi, Lester Mackey. [doi]
• A Model of Place Field Reorganization During Reward MaximizationM. Ganesh Kumar, Blake Bordelon, Jacob A. Zavatone-Veth, Cengiz Pehlevan. [doi]
• Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial ExplorationAndreas Kontogiannis, Konstantinos Papathanasiou, Yi Shen 0011, Giorgos Stamou, Michael M. Zavlanos, George A. Vouros. [doi]
• Elucidating the design space of language models for image generationXuantong Liu, Shaozhe Hao, Xianbiao Qi, Tianyang Hu, Jun Wang, Rong Xiao 0003, Yuan Yao. [doi]
• Lightweight Protocols for Distributed Private Quantile EstimationAnders Aamand, Fabrizio Boninsegna, Abigail Gentle, Jacob Imola, Rasmus Pagh. [doi]
• Grammar-Forced Translation of Natural Language to Temporal Logic using LLMsWilliam H. English, Dominic Simon, Sumit Kumar Jha 0001, Rickard Ewetz. [doi]
• BSO: Binary Spiking Online Optimization AlgorithmYu Liang, Yu Yang, Wenjie Wei, Ammar Belatreche, Shuai Wang 0058, Malu Zhang, Yang Yang 0002. [doi]
• Dendritic Localized Learning: Toward Biologically Plausible AlgorithmChangze Lv, Jingwen Xu, Yiyang Lu, Xiaohua Wang, Zhenghua Wang, Zhibo Xu, Di Yu 0001, Xin Du 0002, Xiaoqing Zheng, Xuanjing Huang 0001. [doi]
• Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised LearningJungtaek Kim. [doi]
• Clone-Robust AI AlignmentAriel D. Procaccia, Benjamin Schiffer, Shirley Zhang 0001. [doi]
• Differentiable Quadratic Optimization For the Maximum Independent Set ProblemIsmail Alkhouri, Cedric Le Denmat, Yingjie Li, Cunxi Yu, Jia Liu, Rongrong Wang, Alvaro Velasquez. [doi]
• Learning Fused State Representations for Control from Multi-View ObservationsZeyu Wang, Yao-Hui Li, Xin Li 0033, Hongyu Zang, Romain Laroche, Riashat Islam. [doi]
• Identifying Metric Structures of Deep Latent Variable ModelsStas Syrota, Yevgen Zainchkovskyy, Johnny Xi, Benjamin Bloem-Reddy, Søren Hauberg. [doi]
• TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy DistillationZiang Zhou, Zhihao Ding, Jieming Shi 0001, Qing Li 0001, Shiqi Shen. [doi]
• Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic EnvironmentsJae Hong Lee. [doi]
• Zero Shot Generalization of Vision-Based RL Without Data AugmentationSumeet Batra, Gaurav S. Sukhatme. [doi]
• Copilot Arena: A Platform for Code LLM Evaluation in the WildWayne Chi, Valerie Chen, Anastasios Nikolas Angelopoulos, Wei-Lin Chiang, Aditya Mittal, Naman Jain, Tianjun Zhang, Ion Stoica, Chris Donahue, Ameet Talwalkar. [doi]
• Adaptive Localization of Knowledge Negation for Continual LLM UnlearningAbudukelimu Wuerkaixi, Qizhou Wang, Sen Cui, Wutong Xu, Bo Han 0003, Gang Niu 0001, Masashi Sugiyama, Changshui Zhang. [doi]
• Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During TrainingMax Milkert, David Hyde 0001, Forrest J. Laine. [doi]
• ExpProof : Operationalizing Explanations for Confidential Models with ZKPsChhavi Yadav, Evan Laufer, Dan Boneh, Kamalika Chaudhuri. [doi]
• Optimal transport-based conformal predictionGauthier Thurin, Kimia Nadjahi, Claire Boyer. [doi]
• Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution TasksJeongmo Kim, Yisak Park, Minung Kim, Seungyul Han. [doi]
• Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak ControlSepehr Elahi, Paula Mürmann, Patrick Thiran. [doi]
• AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and RestorationWenhao Sun, Rong-Cheng Tu, Jingyi Liao, Zhao Jin, Dacheng Tao. [doi]
• Locality Preserving Markovian Transition for Instance RetrievalJifei Luo, Wenzheng Wu, Hantao Yao, Lu Yu 0004, Changsheng Xu. [doi]
• Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible ScalesJiaze Xu, Shiyu Xia, Xu Yang 0021, Jiaqi Lv, Xin Geng 0001. [doi]
• Ensemble Distribution Distillation via Flow MatchingJonggeon Park, Giung Nam, Hyunsu Kim, Jongmin Yoon, Juho Lee 0001. [doi]
• Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit FeedbackTal Lancewicki, Yishay Mansour. [doi]
• Zero-Shot Offline Imitation Learning via Optimal TransportThomas Rupf, Marco Bagatella, Nico Gürtler, Jonas Frey, Georg Martius. [doi]
• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of ExpertsXu Liu 0014, Juncheng Liu, Gerald Woo, Taha Aksu, Yuxuan Liang 0002, Roger Zimmermann, Chenghao Liu, Junnan Li 0001, Silvio Savarese, Caiming Xiong, Doyen Sahoo. [doi]
• Liger: Linearizing Large Language Models to Gated Recurrent StructuresDisen Lan, Weigao Sun, Jiaxi Hu, Jusen Du, Yu Cheng 0001. [doi]
• Low-Rank Adapting Models for Sparse AutoencodersMatthew Chen, Joshua Engels, Max Tegmark. [doi]
• FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information GainRohan Deb, Kiran Koshy Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton. [doi]
• Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward OptimizationSeungbeom Lee, Munsun Jo, Jungseul Ok, Dongwoo Kim 0002. [doi]
• Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity DiffusionDavid Geissbühler, Hatef Otroshi-Shahreza, Sébastien Marcel. [doi]
• Minimum Width for Universal Approximation using Squashable Activation FunctionsJonghyun Shin, Namjun Kim, Geonho Hwang, Sejun Park. [doi]
• Intersectional Fairness in Reinforcement Learning with Large State and Constraint SpacesEric Eaton, Marcel Hussing, Michael Kearns, Aaron Roth 0001, Sikata Bela Sengupta, Jessica Sorrell. [doi]
• DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference OptimizationZhenglin Zhou, Xiaobo Xia, Fan Ma, Hehe Fan, Yi Yang 0001, Tat-Seng Chua. [doi]
• Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet AgentsYifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Li Erran Li. [doi]
• Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning DynamicsShiwei Li 0002, Xiandi Luo, Xing Tang 0007, Haozhao Wang, Hao Chen, Weihong Luo, Yuhua Li 0003, Xiuqiang He 0001, Ruixuan Li 0001. [doi]
• Supercharging Graph Transformers with Advective DiffusionQitian Wu, Chenxiao Yang, Kaipeng Zeng, Michael M. Bronstein. [doi]
• Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?Guiomar Pescador-Barrios, Sarah Filippi, Mark van der Wilk. [doi]
• DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and AutoregressionJunjie Wen, Yichen Zhu, Minjie Zhu, Zhibin Tang, Jinming Li, Zhongyi Zhou, Xiaoyu Liu, Chaomin Shen 0001, Yaxin Peng, Feifei Feng. [doi]
• Rethink the Role of Deep Learning towards Large-scale Quantum SystemsYusheng Zhao, Chi Zhang 0001, Yuxuan Du. [doi]
• Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture DistributionsTejas Jayashankar, Jongha Jon Ryu, Gregory W. Wornell. [doi]
• Conformity Score Averaging for ClassificationRui Luo 0002, Zhixin Zhou. [doi]
• MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger BridgesShixi Qin, Zhiyong Yang 0001, Shilong Bao, Shi Wang, Qianqian Xu 0001, Qingming Huang. [doi]
• Certification for Differentially Private Prediction in Gradient-Based TrainingMatthew Wicker, Philip Sosnin, Igor Shilov, Adrianna Janik, Mark Niklas Müller, Yves-Alexandre de Montjoye, Adrian Weller, Calvin Tsay. [doi]
• Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed LearningZe'ev Zukerman, Bassel Hamoud, Kfir Yehuda Levy. [doi]
• Constrained Belief Updates Explain Geometric Structures in Transformer RepresentationsMateusz Piotrowski, Paul M. Riechers, Daniel Filan, Adam S. Shai. [doi]
• Diverse Prototypical Ensembles Improve Robustness to Subpopulation ShiftMinh Nguyen Nhat To, Paul F. R. Wilson, Viet Nguyen, Mohamed Harmanani, Michael Cooper, Fahimeh Fooladgar, Purang Abolmaesumi, Parvin Mousavi, Rahul G. Krishnan. [doi]
• Sparse Autoencoders, Again?Yin Lu, Xuening Zhu, Tong He 0002, David Wipf. [doi]
• Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic ApproachChangdae Oh, Zhen Fang 0001, Shawn Im, Xuefeng Du, Yixuan Li 0001. [doi]
• G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural NetworksGuibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang 0056, Tianlong Chen 0001, Dawei Cheng. [doi]
• Inverse Optimization via Learning Feasible RegionsKe Ren, Peyman Mohajerin Esfahani, Angelos Georghiou. [doi]
• Over-Tokenized Transformer: Vocabulary is Generally Worth ScalingHongzhi Huang, Defa Zhu, Banggu Wu, Yutao Zeng, Ya Wang, Qiyang Min, Xun Zhou. [doi]
• Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional DataErez Peterfreund, Ofir Lindenbaum, Yuval Kluger, Boris Landa. [doi]
• CodeIO: Condensing Reasoning Patterns via Code Input-Output PredictionJunlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu 0024, Junxian He. [doi]
• Learning the Electronic Hamiltonian of Large Atomic StructuresChen Hao Xia, Manasa Kaniselvan, Alexandros Nikolaos Ziogas, Marko Mladenovic, Rayen Mahjoub, Alexander Maeder, Mathieu Luisier. [doi]
• Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling VerificationEric Zhao 0003, Pranjal Awasthi, Sreenivas Gollapudi. [doi]
• Learning Utilities from Demonstrations in Markov Decision ProcessesFilippo Lazzati, Alberto Maria Metelli. [doi]
• Residual Matrix Transformers: Scaling the Size of the Residual StreamBrian Mak, Jeffrey Flanigan. [doi]
• SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse AutoencodersBartosz Cywinski, Kamil Deja. [doi]
• Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language ModelsChao Huang 0008, Yushu Shi, Jie Wen 0001, Wei Wang 0169, Yong Xu 0001, Xiaochun Cao. [doi]
• GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language ModelsPengxiang Zhao, Xiaoming Yuan 0001. [doi]
• Multiobjective distribution matchingXiaoyuan Zhang, Peijie Li, Yingying Yu, Yichi Zhang, Han Zhao 0002, Qingfu Zhang 0001. [doi]
• Gap-Dependent Bounds for Federated Q-LearningHaochen Zhang, Zhong Zheng, Lingzhou Xue. [doi]
• Understanding Chain-of-Thought in LLMs through Information TheoryJean-Francois Ton, Muhammad Faaiz Taufiq, Yang Liu 0018. [doi]
• CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language ModelsQinsi Wang, Hancheng Ye, Ming-Yu Chung, Yudong Liu, Yueqian Lin, Martin Kuo, Mingyuan Ma, Jianyi Zhang, Yiran Chen 0001. [doi]
• Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index ModelsTaj Jones-McCormick, Aukosh Jagannath, Subhabrata Sen. [doi]
• Large Language-Geometry Model: When LLM meets EquivarianceZongzhao Li, Jiacheng Cen, Bing Su 0001, Tingyang Xu, Yu Rong 0001, Deli Zhao, Wenbing Huang 0001. [doi]
• Selective Prompt Anchoring for Code GenerationYuan Tian, Tianyi Zhang 0001. [doi]
• Reconstructing Cell Lineage Trees from Phenotypic Features with Metric LearningDa Kuang, Guanwen Qiu, Junhyong Kim. [doi]
• Preference Learning for AI Alignment: a Causal PerspectiveKasia Kobalczyk, Mihaela van der Schaar. [doi]
• LARM: Large Auto-Regressive Model for Long-Horizon Embodied IntelligenceZhuoling Li, Xiaogang Xu 0002, Zhenhua Xu 0003, Ser-Nam Lim, Hengshuang Zhao. [doi]
• Differential Privacy Under Class Imbalance: Methods and Empirical InsightsLucas Rosenblatt, Yuliia Lut, Ethan Turok, Marco Avella-Medina, Rachel Cummings. [doi]
• Test-Time Canonicalization by Foundation Models for Robust PerceptionUtkarsh Singhal, Ryan Feng, Stella X. Yu, Atul Prakash 0001. [doi]
• Towards Practical Defect-Focused Automated Code ReviewJunyi Lu, Lili Jiang, Xiaojia Li, Jianbing Fang, Fengjun Zhang, Li Yang 0015, Chun Zuo. [doi]
• Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-TreesZehong Wang, Zheyuan Zhang, Tianyi Ma, Nitesh V. Chawla, Chuxu Zhang, Yanfang Ye 0001. [doi]
• World Model Implanting for Test-time Adaptation of Embodied AgentsMinjong Yoo, Jinwoo Jang, Sihyung Yoon, Honguk Woo. [doi]
• Calibrated Language Models and How to Find Them with Label SmoothingJerry Huang, Peng Lu, Qiuhao Zeng. [doi]
• STP: Self-play LLM Theorem Provers with Iterative Conjecturing and ProvingKefan Dong, Tengyu Ma 0001. [doi]
• Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for InterventionKyle Heuton, F. Samuel Muench, Shikhar Shrestha, Thomas J. Stopka, Michael C. Hughes. [doi]
• BARNN: A Bayesian Autoregressive and Recurrent Neural NetworkDario Coscia, Max Welling, Nicola Demo, Gianluigi Rozza. [doi]
• PAC Learning with ImprovementsIdan Attias, Avrim Blum, Keziah Naggita, Donya Saless, Dravyansh Sharma, Matthew R. Walter. [doi]
• Topology-Aware Dynamic Reweighting for Distribution Shifts on GraphWeihuang Zheng, Jiashuo Liu, Jiaxing Li, Jiayun Wu, Peng Cui 0001, Youyong Kong. [doi]
• FireFlow: Fast Inversion of Rectified Flow for Image Semantic EditingYingying Deng, Xiangyu He, Changwang Mei, Peisong Wang, Fan Tang. [doi]
• Automatically Interpreting Millions of Features in Large Language ModelsGonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose. [doi]
• UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein DistanceFangchen Yu, Yanzhen Chen, Jiaxing Wei, Jianfeng Mao, Wenye Li 0001, Qiang Sun 0007. [doi]
• Going Deeper into Locally Differentially Private Graph Neural NetworksLongzhu He, Chaozhuo Li, Peng Tang, Sen Su. [doi]
• Understanding the Logic of Direct Preference Alignment through LogicKyle Richardson 0001, Vivek Srikumar, Ashish Sabharwal. [doi]
• Wait-Less Offline Tuning and Re-solving for Online Decision MakingJingruo Sun, Wenzhi Gao, Ellen Vitercik, Yinyu Ye 0001. [doi]
• SepLLM: Accelerate Large Language Models by Compressing One Segment into One SeparatorGuoxuan Chen, Han Shi, Jiawei Li, Yihang Gao, Xiaozhe Ren, Yimeng Chen, Xin Jiang, Zhenguo Li, Weiyang Liu, Chao Huang. [doi]
• Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties PredictionJiao Huang, Qianli Xing 0002, Jinglong Ji, Bo Yang 0002. [doi]
• Retraining with Predicted Hard Labels Provably Increases Model AccuracyRudrajit Das, Inderjit S. Dhillon, Alessandro Epasto, Adel Javanmard, Jieming Mao, Vahab Mirrokni, Sujay Sanghavi, Peilin Zhong. [doi]
• Simultaneous Multi-Robot Motion Planning with Projected Diffusion ModelsJinhao Liang, Jacob K. Christopher, Sven Koenig, Ferdinando Fioretto. [doi]
• Pareto Merging: Multi-Objective Optimization for Preference-Aware Model MergingWeiyu Chen, James T. Kwok. [doi]
• DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret ResharingAlexander Bienstock, Ujjwal Kumar, Antigoni Polychroniadou. [doi]
• KGMark: A Diffusion Watermark for Knowledge GraphsHongrui Peng, Haolang Lu, Yuanlong Yu, Weiye Fu, Kun Wang 0056, Guoshun Nan. [doi]
• TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic ScenesXingcheng Zhou, Konstantinos Larintzakis, Hao Guo, Walter Zimmer, Mingyu Liu, Hu Cao, Jiajie Zhang, Venkatnarayanan Lakshminarasimhan, Leah Strand, Alois Knoll. [doi]
• Cowpox: Towards the Immunity of VLM-based Multi-Agent SystemsYutong Wu 0009, Jie Zhang 0073, Yiming Li 0004, Chao Zhang 0008, Qing Guo 0005, Han Qiu 0001, Nils Lukas, Tianwei Zhang 0004. [doi]
• Teaching Transformers Causal Reasoning through Axiomatic TrainingAniket Vashishtha, Abhinav Kumar 0001, Atharva Pandey, Abbavaram Gowtham Reddy, Kabir Ahuja, Vineeth N. Balasubramanian, Amit Sharma 0007. [doi]
• CoMemo: LVLMs Need Image Context with Image MemoryShi Liu, Weijie Su 0002, Xizhou Zhu, Wenhai Wang, Jifeng Dai. [doi]
• Learning Invariant Causal Mechanism from Vision-Language ModelsZeen Song, Siyu Zhao, Xingyu Zhang, Jiangmeng Li, Changwen Zheng, Wenwen Qiang. [doi]
• Learning Minimum-Size BDDs: Towards Efficient Exact AlgorithmsChristian Komusiewicz, André Schidler, Frank Sommer, Manuel Sorge, Luca Pascal Staus. [doi]
• Semantics-aware Test-time Adaptation for 3D Human Pose EstimationQiuxia Lin, Rongyu Chen, Kerui Gu, Angela Yao. [doi]
• Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling EvaluatorsYilun Zhou, Austin Xu, PeiFeng Wang, Caiming Xiong, Shafiq Joty. [doi]
• Spectral-Aware Reservoir Computing for Fast and Accurate Time Series ClassificationShikang Liu, Chuyang Wei, Xiren Zhou, Huanhuan Chen 0001. [doi]
• Trust-Region Twisted Policy ImprovementJoery A. de Vries, Jinke He, Yaniv Oren, Matthijs T. J. Spaan. [doi]
• Measuring Diversity in Synthetic DatasetsYuchang Zhu, Huizhe Zhang, Bingzhe Wu, Jintang Li, Zibin Zheng, Peilin Zhao, Liang Chen 0001, Yatao Bian. [doi]
• Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement LearningJinmin He, Kai Li 0022, Yifan Zang 0001, Haobo Fu, Qiang Fu 0016, Junliang Xing, Jian Cheng 0001. [doi]
• High-Dimensional Prediction for Sequential Decision MakingGeorgy Noarov, Ramya Ramalingam, Aaron Roth 0001, Stephan Xie. [doi]
• MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow SimulationQi Wang, Yuan Mi, Haoyun Wang, Yi Zhang, Ruizhi Chengze, Hongsheng Liu 0002, Ji-Rong Wen, Hao Sun 0002. [doi]
• ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank ResidualsUtkarsh Saxena, Sayeh Sharify, Kaushik Roy 0001, Xin Wang. [doi]
• Provably Cost-Sensitive Adversarial Defense via Randomized SmoothingYuan Xin, Dingfan Chen, Michael Backes 0001, Xiao Zhang 0016. [doi]
• One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion ModelsMingzhao Yang, Shangchao Su, Bin Li 0015, Xiangyang Xue 0001. [doi]
• LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language ModelsDachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong 0009, Jan Kautz, Pavlo Molchanov 0001, Yingyan Celine Lin. [doi]
• Efficient Heterogeneity-Aware Federated Active Data SelectionYing-Peng Tang, Chao Ren 0006, Xiaoli Tang 0001, Sheng-Jun Huang, LiZhen Cui, Han Yu 0001. [doi]
• Reinforcement Learning with Random Time HorizonsEnric Ribera Borrell, Lorenz Richter, Christof Schütte. [doi]
• Event-Customized Image GenerationZhen Wang 0004, Yilei Jiang, Dong Zheng, Jun Xiao 0001, Long Chen 0016. [doi]
• Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of ExpertsYike Yuan, Ziyu Wang, Zihao Huang, Defa Zhu, Xun Zhou, Jingyi Yu, Qiyang Min. [doi]
• Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate ShiftChao Ying, Jun Jin, Yi Guo, Xiudi Li, Muxuan Liang, Jiwei Zhao. [doi]
• Adversarial Robust Generalization of Graph Neural NetworksChang Cao, Han Li, Yulong Wang, Rui Wu, Hong Chen. [doi]
• Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-trainingMinghao Xu, Jiaze Song, Keming Wu, Xiangxin Zhou, Bin Cui 0001, Wentao Zhang 0001. [doi]
• KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent SystemsJusheng Zhang, Zimeng Huang, Yijia Fan, Ningyuan Liu, Mingyan Li, Zhuojie Yang, Jiawei Yao, Jian Wang 0100, Keze Wang. [doi]
• Addressing Misspecification in Simulation-based Inference through Data-driven CalibrationAntoine Wehenkel, Juan L. Gamella, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Jörn-Henrik Jacobsen, Marco Cuturi. [doi]
• LLMs Can Reason Faster Only If We Let ThemBilgehan Sel, Lifu Huang, Naren Ramakrishnan, Ruoxi Jia 0001, Ming Jin 0002. [doi]
• A Manifold Perspective on the Statistical Generalization of Graph Neural NetworksZhiyang Wang, Juan Cerviño, Alejandro Ribeiro. [doi]
• When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time SeriesMin-Yeong Park, Won-Jeong Lee, Seong Tae Kim 0001, Gyeong-Moon Park. [doi]
• Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian OptimizationDeyuan Liu, Zecheng Wang, Bingning Wang, Weipeng Chen, Chunshan Li, Zhiying Tu, Dianhui Chu, Dianbo Sui. [doi]
• LLM-Augmented Chemical Synthesis and Design Decision ProgramsHaorui Wang, Jeff Guo, Lingkai Kong, Rampi Ramprasad, Philippe Schwaller, Yuanqi Du, Chao Zhang 0014. [doi]
• Does Data Scaling Lead to Visual Compositional Generalization?Arnas Uselis, Andrea Dittadi, Seong Joon Oh. [doi]
• Towards a Mechanistic Explanation of Diffusion Model GeneralizationMatthew Niedoba, Berend Zwartsenberg, Kevin Patrick Murphy, Frank Wood. [doi]
• Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient AligningLianbo Ma, Jianlun Ma, Yuee Zhou, Guoyang Xie, Qiang He, Zhichao Lu. [doi]
• SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment RegimesYishan Shen, Yuyang Ye 0002, Hui Xiong 0001, Yong Chen. [doi]
• FIC-TSC: Learning Time Series Classification with Fisher Information ConstraintXiwen Chen, Wenhui Zhu, Peijie Qiu, Hao Wang 0176, Huayu Li, Zihan Li, Yalin Wang 0001, Aristeidis Sotiras, Abolfazl Razi. [doi]
• SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large EmbeddingPeihua Mai, Youlong Ding, Ziyan Lyu, Minxin Du, Yan Pang. [doi]
• On the Emergence of Position Bias in TransformersXinyi Wu 0003, Yifei Wang 0001, Stefanie Jegelka, Ali Jadbabaie. [doi]
• Nonlinear transformers can perform inference-time feature learningNaoki Nishikawa, Yujin Song, Kazusato Oko, Denny Wu, Taiji Suzuki. [doi]
• Update Your Transformer to the Latest Release: Re-Basin of Task VectorsFilippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli, Donato Crisostomi, Federico Bolelli, Elisa Ficarra, Emanuele Rodolà, Simone Calderara, Angelo Porrello. [doi]
• Solving Zero-Sum Convex Markov GamesFivos Kalogiannis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ian Gemp, Georgios Piliouras. [doi]
• Scalable Meta-Learning via Mixed-Mode DifferentiationIurii Kemaev, Dan A. Calian, Luisa M. Zintgraf, Gregory Farquhar, Hado van Hasselt. [doi]
• Laplace Transform Based Low-Complexity Learning of Continuous Markov SemigroupsVladimir R. Kostic, Karim Lounici, Hélène Halconruy, Timothée Devergne, Pietro Novelli, Massimiliano Pontil. [doi]
• Improved Approximations for Hard Graph Problems using PredictionsAnders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao Wu. [doi]
• Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked DiffusionsJaeyeon Kim, Kulin Shah, Vasilis Kontonis, Sham M. Kakade, Sitan Chen. [doi]
• Efficient Time Series Processing for Transformers and State-Space Models through Token MergingLeon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn. [doi]
• FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge DistillationKei Sen Fong, Mehul Motani. [doi]
• BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model EditingDongliang Guo 0002, Mengxuan Hu, Zihan Guan 0001, Thomas Hartvigsen, Sheng Li 0001. [doi]
• On Differential Privacy for Adaptively Solving Search Problems via SketchingShiyuan Feng, Ying Feng, George Zhaoqi Li, Zhao Song 0002, David P. Woodruff, Lichen Zhang 0003. [doi]
• Improving Parallel Program Performance with LLM Optimizers via Agent-System InterfacesAnjiang Wei, Allen Nie, Thiago S. F. X. Teixeira, Rohan Yadav, Wonchan Lee, Ke Wang 0022, Alex Aiken. [doi]
• Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model GuidanceFan Li, Xuan Wang, Min Qi, Zhaoxiang Zhang 0002, Yuelei Xu. [doi]
• A Variational Framework for Improving Naturalness in Generative Spoken Language ModelsLi-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Alexander Rudnicky. [doi]
• Temporal Difference FlowsJesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Rémi Munos, Alessandro Lazaric, Ahmed Touati. [doi]
• N2GON: Neural Networks for Graph-of-Net with Position AwarenessYejiang Wang, Yuhai Zhao, Zhengkui Wang, Wen Shan, Ling Li, Qian Li 0043, Miaomiao Huang, Meixia Wang, Shirui Pan, Xingwei Wang 0001. [doi]
• Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence ModelingJinghan Li, Zhicheng Sun 0001, Yadong Mu. [doi]
• Discovering Spoofing Attempts on Language Model WatermarksThibaud Gloaguen, Nikola Jovanovic 0001, Robin Staab, Martin T. Vechev. [doi]
• LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology GenerationChen-Chia Chang, Wan-Hsuan Lin, Yikang Shen, Yiran Chen 0001, Xin Zhang 0025. [doi]
• Training a Generally Curious AgentFahim Tajwar, Yiding Jiang, Abitha Thankaraj, Sumaita Sadia Rahman, J. Zico Kolter, Jeff Schneider 0001, Russ Salakhutdinov. [doi]
• Score Matching with Missing DataJosh Givens, Song Liu, Henry W. J. Reeve. [doi]
• Unconstrained Robust Online Convex OptimizationJiujia Zhang, Ashok Cutkosky. [doi]
• Efficient Personalized Adaptation for Physiological Signal Foundation ModelChenrui Wu 0002, Haishuai Wang, Xiang Zhang 0012, Chengqi Zhang, Jiajun Bu. [doi]
• AlphaPO: Reward Shape Matters for LLM AlignmentAman Gupta, Shao Tang, Qingquan Song, Sirou Zhu, Jiwoo Hong, Ankan Saha, Viral Gupta, Noah Lee, Eunki Kim, Siyu Zhu, Parag Agrawal, Natesh S. Pillai, S. Sathiya Keerthi. [doi]
• AutoCATE: End-to-End, Automated Treatment Effect EstimationToon Vanderschueren, Tim Verdonck, Mihaela van der Schaar, Wouter Verbeke. [doi]
• Customizing the Inductive Biases of Softmax Attention using Structured MatricesYilun Kuang, Noah Amsel, Sanae Lotfi, Shikai Qiu, Andres Potapczynski, Andrew Gordon Wilson. [doi]
• AutoAL: Automated Active Learning with Differentiable Query Strategy SearchYifeng Wang, Xueying Zhan, Siyu Huang. [doi]
• Sample Complexity of Branch-length Estimation by Maximum LikelihoodDavid Clancy Jr., Hanbaek Lyu, Sebastien Roch. [doi]
• IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion ModelsHang Guo 0002, Yawei Li 0001, Tao Dai 0001, Shu-Tao Xia, Luca Benini. [doi]
• MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI AgentsKaijie Zhu, Xianjun Yang, Jindong Wang 0001, Wenbo Guo 0002, William Yang Wang. [doi]
• DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic ConvergenceYang Jiao, Kai Yang 0001, Chengtao Jian. [doi]
• Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query OptimizationPeng Wang 0107, Yong Li 0032, Lin Zhao 0003, Xiu-Shen Wei. [doi]
• Steerable Transformers for Volumetric DataSoumyabrata Kundu, Risi Kondor. [doi]
• The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information SteeringZhuowei Li 0002, Haizhou Shi, Yunhe Gao, Di Liu 0003, Zhenting Wang, Yuxiao Chen 0002, Ting Liu 0005, Long Zhao 0003, Hao Wang 0014, Dimitris N. Metaxas. [doi]
• SGD Jittering: A Training Strategy for Robust and Accurate Model-Based ArchitecturesPeimeng Guan, Mark A. Davenport. [doi]
• Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and DistillationJuno Kim, Denny Wu, Jason D. Lee, Taiji Suzuki. [doi]
• Autoencoder-Based Hybrid Replay for Class-Incremental LearningMilad Khademi Nori, Il-Min Kim 0001, Guanghui Wang. [doi]
• Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMsHancheng Min, René Vidal. [doi]
• Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution DiversityAtefeh Sohrabizadeh, Jialin Song, Mingjie Liu, Rajarshi Roy 0003, Chankyu Lee, Jonathan Raiman, Bryan Catanzaro. [doi]
• Average Sensitivity of Hierarchical k-Median ClusteringShijie Li, Weiqiang He, Ruobing Bai, Pan Peng 0001. [doi]
• MedRAX: Medical Reasoning Agent for Chest X-rayAdibvafa Fallahpour, Jun Ma 0016, Alif Munim, Hongwei Lyu, Bo Wang 0044. [doi]
• Point-Level Topological Representation Learning on Point CloudsVincent Peter Grande, Michael T. Schaub. [doi]
• Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual ReasoningFan Shi, Bin Li 0015, Xiangyang Xue 0001. [doi]
• Correlated Errors in Large Language ModelsElliot Myunghoon Kim, Avi Garg, Kenny Peng, Nikhil Garg 0001. [doi]
• AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology GenerationPrashanth Vijayaraghavan, Luyao Shi, Ehsan Degan, Vandana V. Mukherjee, Xin Zhang. [doi]
• Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert CurvesMykhailo Uss, Ruslan Yermolenko, Oleksii Shashko, Olena Kolodiazhna, Ivan Safonov, Volodymyr Savin, Yoon-Jae Yeo, Seo-Won Ji, Jaeyun Jeong. [doi]
• Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?Antonia Wüst, Tim Nelson Tobiasch, Lukas Helff, Inga Ibs, Wolfgang Stammer, Devendra Singh Dhami, Constantin A. Rothkopf, Kristian Kersting. [doi]
• TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in VisionShaobin Zhuang, Yiwei Guo, Yanbo Ding, Kunchang Li 0002, Xinyuan Chen, Yaohui Wang 0001, Fangyikang Wang, Ying Zhang, Chen Li 0031, Yali Wang 0001. [doi]
• Sleeping Reinforcement LearningSimone Drago, Marco Mussi, Alberto Maria Metelli. [doi]
• FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered InferenceStefano Cortinovis, Francois Caron. [doi]
• Expected Variational InequalitiesBrian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm. [doi]
• RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost StrategyZipeng Ji, Guanghui Zhu, Chunfeng Yuan, Yihua Huang 0001. [doi]
• Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language ModelingXiang Hu, Zhihao Teng, Jun Zhao, Wei Wu, Kewei Tu. [doi]
• Online Differentially Private Conformal Prediction for Uncertainty QuantificationQiangqiang Zhang, Ting Li, Xinwei Feng, Xiaodong Yan, Jinhan Xie. [doi]
• Human-Aligned Image Models Improve Visual Decoding from the BrainNona Rajabi, Antônio H. Ribeiro, Miguel Vasco, Farzaneh Taleb, Mårten Björkman, Danica Kragic. [doi]
• Robust Conformal Outlier Detection under Contaminated Reference DataMeshi Bashari, Matteo Sesia, Yaniv Romano. [doi]
• DipLLM: Fine-Tuning LLM for Strategic Decision-making in DiplomacyKaixuan Xu, Jiajun Chai, Sicheng Li, Yuqian Fu, Yuanheng Zhu, Dongbin Zhao. [doi]
• From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph TransformersYoon Hyeok Lee, Jaemin Park, Taejin Paik, Doyun Kim, Bosun Hwang. [doi]
• Toward Data-centric Directed Graph Learning: An Entropy-driven ApproachXunkai Li, Zhengyu Wu, Kaichi Yu, Hongchao Qin, Guang Zeng 0001, Rong-Hua Li, Guoren Wang. [doi]
• On the Statistical Mechanisms of Distributional Compositional GeneralizationJingwen Fu, Nanning Zheng 0001. [doi]
• Introducing 3D Representation for Dense Volume-to-Volume Translation via Score FusionXiyue Zhu, Dou Hoon Kwark, Ruike Zhu, Kaiwen Hong, Yiqi Tao, Shirui Luo, Yudu Li, Zhi-Pei Liang, Volodymyr V. Kindratenko. [doi]
• Graph Minimum Factorization Distance and Its Application to Large-Scale Graph Data ClusteringJicong Fan 0001. [doi]
• Variational Phylogenetic Inference with Products over BipartitionsEvan Sidrow, Alexandre Bouchard-Côté, Lloyd T. Elliott. [doi]
• Learning With Multi-Group Guarantees For Clusterable SubpopulationsJessica Dai, Nika Haghtalab, Eric Zhao 0003. [doi]
• Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓp-Smooth Nonconvex OptimizationXinyu Luo, Site Bai, Bolian Li, Petros Drineas, Ruqi Zhang, Brian Bullins. [doi]
• Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive SupervisionAnqi Lu, Junchi Yan. [doi]
• Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated MarginYuchen Wang, Xuefeng Bai 0001, Xiucheng Li, Weili Guan, Liqiang Nie, Xinyang Chen 0001. [doi]
• OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inferenceSeungjun Shin, Jaehoon Oh, Dokwan Oh. [doi]
• Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language ModelsKejia Chen 0007, Jiawen Zhang 0005, Jiacong Hu, Yu Wang 0176, Jian Lou 0001, Zunlei Feng, Mingli Song. [doi]
• INRFlow: Flow Matching for INRs in Ambient SpaceYuyang Wang, Anurag Ranjan, Joshua M. Susskind, Miguel Ángel Bautista 0001. [doi]
• Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed KernelCarlota Parés-Morlans, Michelle Yi, Claire Chen, Sarah A. Wu, Rika Antonova, Tobias Gerstenberg, Jeannette Bohg. [doi]
• Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model ScalesJu-Seung Byun, Andrew Perrault. [doi]
• LGDM: Latent Guidance in Diffusion Models for Perceptual EvaluationsShreshth Saini, Ru-Ling Liao, Yan Ye, Alan Bovik. [doi]
• Exploiting Curvature in Online Convex Optimization with Delayed FeedbackHao Qiu, Emmanuel Esposito, Mengxiao Zhang. [doi]
• Federated In-Context Learning: Iterative Refinement for Improved Answer QualityRuhan Wang, Zhiyong Wang, Chengkai Huang, Rui Wang, Tong Yu 0001, Lina Yao 0001, John C. S. Lui, Dongruo Zhou. [doi]
• Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS PerspectiveHaidong Kang. [doi]
• Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video GenerationFanqing Meng, Jiaqi Liao, Xinyu Tan, Quanfeng Lu, Wenqi Shao, Kaipeng Zhang, Yu Cheng 0001, Dianqi Li, Ping Luo 0002. [doi]
• Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized PrototypesYusheng Zhao, Qixin Zhang, Xiao Luo 0001, Junyu Luo 0002, Wei Ju 0001, Zhiping Xiao 0001, Ming Zhang 0004. [doi]
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity ExtrapolationJiashu He, Mingyu Derek Ma, Jinxuan Fan, Dan Roth 0001, Wei Wang 0010, Alejandro Ribeiro. [doi]
• VIP: Vision Instructed Pre-training for Robotic ManipulationZhuoling Li, Liangliang Ren, Jinrong Yang, Yong Zhao, Xiaoyang Wu 0002, Zhenhua Xu 0003, Xiang Bai, Hengshuang Zhao. [doi]
• Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary LearningAo Shen, Mingzhi Yuan, Yingfan Ma, Jie Du, Qiao Huang, Manning Wang. [doi]
• Relational Invariant Learning for Robust Solvation Free Energy PredictionYeyun Chen. [doi]
• Discriminative Policy Optimization for Token-Level Reward ModelsHongzhan Chen, Tao Yang 0033, Shiping Gao, Ruijun Chen 0001, Xiaojun Quan, Hongtao Tian, Ting Yao. [doi]
• MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State MachinesYaolun Zhang, Xiaogeng Liu, Chaowei Xiao. [doi]
• FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image GenerationZheng Fang, Lichuan Xiang, Xu Cai, Kaicheng Zhou, Hongkai Wen 0001. [doi]
• Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RLQin-Wen Luo, Ming-Kun Xie, Ye-Wen Wang, Sheng-Jun Huang. [doi]
• Phase and Amplitude-aware Prompting for Enhancing Adversarial RobustnessYibo Xu, Dawei Zhou 0004, Decheng Liu, Nannan Wang 0001. [doi]
• Competing Bandits in Matching Markets via Super StabilitySoumya Basu 0001. [doi]
• Robust Consensus Anchor Learning for Efficient Multi-view Subspace ClusteringYalan Qin, Nan Pu, Guorui Feng, Nicu Sebe. [doi]
• Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement LearningSungjune Kim, Gyeongrok Oh, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung Jun Lee, Sujin Jang, Sangpil Kim. [doi]
• Taming Knowledge Conflicts in Language ModelsGaotang Li, Yuzhong Chen 0004, Hanghang Tong. [doi]
• AlphaDPO: Adaptive Reward Margin for Direct Preference OptimizationJunkang Wu, Xue Wang 0010, Zhengyi Yang 0007, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang 0010, Xiangnan He 0001. [doi]
• A Reasoning-Based Approach to Cryptic Crossword Clue SolvingMartin Andrews, Sam Witteveen. [doi]
• Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion PlannerChenyou Fan, Chenjia Bai, Zhao Shan, Haoran He, Yang Zhang, Zhen Wang 0004. [doi]
• Optimal Auction Design in the Joint AdvertisingYang Li, Yuchao Ma, Qi Qi. [doi]
• Attention-Only Transformers via Unrolled Subspace DenoisingPeng Wang 0098, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu 0001, Yi Ma 0001. [doi]
• S4S: Solving for a Fast Diffusion Model SolverEric Frankel, Sitan Chen, Jerry Li 0001, Pang Wei Koh, Lillian J. Ratliff, Sewoong Oh. [doi]
• GRU: Mitigating the Trade-off between Unlearning and Retention for LLMsYue Wang, Qizhou Wang, Feng Liu 0003, Wei Huang 0034, Yali Du 0001, Xiaojiang Du, Bo Han 0003. [doi]
• Convergence Analysis of Policy Gradient Methods with Dynamic StochasticityAlessandro Montenegro, Marco Mussi, Matteo Papini, Alberto Maria Metelli. [doi]
• DiMa: Understanding the Hardness of Online Matching Problems via Diffusion ModelsBoyu Zhang, Aocheng Shen, Bing Liu, Qiankun Zhang, Bin Yuan, Jing Wang, Shenghao Liu, Xianjun Deng. [doi]
• Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language ModelsXin Zou 0001, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Kening Zheng, Sirui Huang, JunKai Chen, Peijie Jiang, Jia Liu, Chang Tang, Xuming Hu. [doi]
• Hybrid Spiking Vision Transformer for Object Detection with Event CamerasQi Xu 0008, Jie Deng, Jiangrong Shen, Biwu Chen, Huajin Tang, Gang Pan 0001. [doi]
• iN2V: Bringing Transductive Node Embeddings to Inductive GraphsNicolas Lell, Ansgar Scherp. [doi]
• ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure AnalysisHaoxiong Liu, Jiacheng Sun, Zhenguo Li, Andrew C. Yao. [doi]
• RATE: Causal Explainability of Reward Models with Imperfect CounterfactualsDavid Reber, Sean M. Richardson, Todd Nief, Cristina Garbacea, Victor Veitch. [doi]
• From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel ControlChi Zhang, Lianhai Ren, Jingpu Cheng, Qianxiao Li. [doi]
• Self-Supervised Transformers as Iterative Solution Improvers for Constraint SatisfactionYudong Xu 0001, Wenhao Li, Scott Sanner, Elias Boutros Khalil. [doi]
• Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data SourcesRenzhe Xu, Kang Wang, Bo Li 0064. [doi]
• Otter: Generating Tests from Issues to Validate SWE PatchesToufique Ahmed, Jatin Ganhotra, Rangeet Pan, Avraham Shinnar, Saurabh Sinha 0003, Martin Hirzel. [doi]
• Synthesizing Software Engineering Data in a Test-Driven MannerLei Zhang 0201, Jiaxi Yang 0004, Min Yang 0007, Jian Yang 0003, Mouxiang Chen, Jiajun Zhang 0012, Zeyu Cui, Binyuan Hui, Junyang Lin. [doi]
• Leveraging Per-Instance Privacy for Machine UnlearningNazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy 0001, Gintare Karolina Dziugaite. [doi]
• Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block ModelKaito Ariu, Alexandre Proutière, Se-Young Yun. [doi]
• Socialized Coevolution: Advancing a Better World through Cross-Task CollaborationXinjie Yao, Yu Wang 0106, Pengfei Zhu 0001, Wanyu Lin, Ruipu Zhao, Zhoupeng Guo, Weihao Li, Qinghua Hu. [doi]
• Multi-Session Budget Optimization for Forward Auction-based Federated LearningXiaoli Tang 0001, Han Yu 0001, Zengxiang Li, Xiaoxiao Li. [doi]
• Importance Sampling for Nonlinear ModelsPrakash Palanivelu Rajmohan, Fred Roosta. [doi]
• Curvature Enhanced Data Augmentation for RegressionIlya Kaufman, Omri Azencot. [doi]
• Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?Renbiao Liu, Anqi Li, Chaoding Yang, Hui Sun 0003, Ming Li 0005. [doi]
• Random Feature Representation BoostingNikita Zozoulenko, Thomas Cass, Lukas Gonon. [doi]
• SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking ServicesHongcheng Guo, Yue Wang, Shaosheng Cao, Fei Zhao 0012, Boyang Wang 0006, Lei Li 0039, Liang Chen 0024, Xinze Lyu, Zhe Xu, Yao Hu 0002, Zhoujun Li 0001. [doi]
• Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-TailedSavelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác 0001, Eduard Gorbunov. [doi]
• Time-Aware World Model for Adaptive Prediction and ControlAnh N. Nhu, Sanghyun Son 0003, Ming Lin. [doi]
• Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular DataYunze Tong, Fengda Zhang, Zihao Tang, Kaifeng Gao, Kai Huang, Pengfei Lyu, Jun Xiao 0001, Kun Kuang. [doi]
• Progressively Label Enhancement for Large Language Model AlignmentBiao Liu, Ning Xu 0009, Xin Geng 0001. [doi]
• ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language ModelingDongchao Yang, Songxiang Liu, Haohan Guo, Jiankun Zhao, Yuanyuan Wang, Helin Wang, Zeqian Ju, Xubo Liu, Xueyuan Chen, Xu Tan 0003, Xixin Wu, Helen M. Meng. [doi]
• Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic ImagesYan Zhong, Chenxi Yang 0004, Suyuan Zhao, Tingting Jiang 0001. [doi]
• TruthFlow: Truthful LLM Generation via Representation Flow CorrectionHanyu Wang, Bochuan Cao, Yuanpu Cao, Jinghui Chen. [doi]
• KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale DecouplingShimin Zhang, Ziyuan Ye, Yinsong Yan, Zeyang Song, Yujie Wu 0002, Jibin Wu. [doi]
• Towards Trustworthy Federated Learning with Untrusted ParticipantsYoussef Allouah, Rachid Guerraoui, John Stephan. [doi]
• Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine TranslationMuhammed Yusuf Kocyigit, Eleftheria Briakou, Daniel Deutsch, Jiaming Luo, Colin Cherry, Markus Freitag. [doi]
• Reflection-Window Decoding: Text Generation with Selective RefinementZeyu Tang 0002, Zhenhao Chen, Xiangchen Song, Loka Li, Yunlong Deng, Yifan Shen 0004, Guangyi Chen 0002, Peter Spirtes, Kun Zhang 0001. [doi]
• Energy-Based Flow Matching for Generating 3D Molecular StructureWenyin Zhou, Christopher Iliffe Sprague, Vsevolod Viliuga, Matteo Tadiello, Arne Elofsson, Hossein Azizpour. [doi]
• EpiCoder: Encompassing Diversity and Complexity in Code GenerationYaoxiang Wang, Haoling Li, Xin Zhang 0099, Jie Wu 0001, Xiao Liu 0029, Wenxiang Hu, Zhongxin Guo, Yangyu Huang, Ying Xin, Yujiu Yang 0001, Jinsong Su, Qi Chen 0009, Scarlett Li. [doi]
• Online Conformal Prediction via Online OptimizationFelipe Areces, Christopher Mohri, Tatsunori Hashimoto, John C. Duchi. [doi]
• LEVIS: Large Exact Verifiable Input Spaces for Neural NetworksMohamad Fares El Hajj Chehade, Wenting Li, Brian Wesley Bell, Russell Bent, Saif R. Kazi, Hao Zhu. [doi]
• Efficient Quantification of Multimodal Interaction at Sample LevelZequn Yang, Hongfa Wang, Di Hu 0001. [doi]
• Settling the Maximin Share Fairness for Scheduling among Groups of MachinesBo Li 0037, Fangxiao Wang 0002, Shiji Xing. [doi]
• How to Evaluate and Mitigate IP Infringement in Visual Generative AI?Zhenting Wang, Chen Chen 0043, Vikash Sehwag, Minzhou Pan, Lingjuan Lyu. [doi]
• Enhancing Visual Localization with Cross-Domain Image GenerationYuanze Wang, Yichao Yan, Shiming Song 0003, Songchang Jin, Yilan Huang, Xingdong Sheng, Dianxi Shi. [doi]
• NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic DemonstrationsMyunsoo Kim, Hayeong Lee, Seong-Woong Shim, Junho Seo, Byung Jun Lee. [doi]
• Parrot: Multilingual Visual Instruction TuningHai-Long Sun, Da-Wei Zhou 0001, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye. [doi]
• A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal ProcessingYu Chen, Jing Lian 0001, Zhaofei Yu, Jizhao Liu, Jisheng Dang, Gang Wang 0031. [doi]
• Principled Data Selection for Alignment: The Hidden Risks of Difficult ExamplesChengqian Gao, Haonan Li, Liu Liu 0014, Zeke Xie, Peilin Zhao, Zhiqiang Xu 0003. [doi]
• From RAG to Memory: Non-Parametric Continual Learning for Large Language ModelsBernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, Yu Su 0001. [doi]
• Calibrated Value-Aware Model Learning with Probabilistic Environment ModelsClaas Voelcker, Anastasiia Pedan, Arash Ahmadian, Romina Abachi, Igor Gilitschenski, Amir Massoud Farahmand. [doi]
• AAAR-1.0: Assessing AI's Potential to Assist ResearchRenze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun 0002, Yusen Zhang 0001, Jihyun Janice Ahn, Hongchao Fang, Zhuoyang Zou, Wenchao Ma, Xi Li, Kai Zhang 0033, Congying Xia, Lifu Huang, Wenpeng Yin 0001. [doi]
• DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit DifferentiationShuyuan Wang, Philip D. Loewen, Michael G. Forbes, R. Bhushan Gopaluni, Wei Pan. [doi]
• Generative Data Mining with Longtail-Guided DiffusionDavid S. Hayden, Mao Ye 0006, Timur Garipov, Gregory P. Meyer, Carl Vondrick, Zhao Chen, Yuning Chai, Eric M. Wolff, Siddhartha S. Srinivasa. [doi]
• PokéChamp: an Expert-level Minimax Language AgentSeth Karten, Andy Luu Nguyen, Chi Jin 0001. [doi]
• Multivariate Conformal SelectionTian Bai 0010, Yue Zhao, Xiang Yu, Archer Y. Yang. [doi]
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot PlanningGaoyue Zhou, Hengkai Pan, Yann LeCun, Lerrel Pinto. [doi]
• Soup-of-Experts: Pretraining Specialist Models via Parameters AveragingPierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier. [doi]
• TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference OptimizationMingkang Zhu, Xi Chen 0119, Zhongdao Wang, Bei Yu 0001, Hengshuang Zhao, Jiaya Jia. [doi]
• Are High-Quality AI-Generated Images More Difficult for Models to Detect?Yao Xiao, Binbin Yang, Weiyan Chen, Jiahao Chen, Zijie Cao, Ziyi Dong, Xiangyang Ji, Liang Lin, Wei Ke 0003, Pengxu Wei. [doi]
• Compress then Serve: Serving Thousands of LoRA Adapters with Little OverheadRickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan H. Greenewald, Mikhail Yurochkin, Justin Solomon 0001. [doi]
• Rethinking Aleatoric and Epistemic UncertaintyFreddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster 0001, Tom Rainforth. [doi]
• VerbalTS: Generating Time Series from TextsShuqi Gu, Chuyue Li, Baoyu Jing, Kan Ren. [doi]
• The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning NetworksWalter Mayor, Johan S. Obando-Ceron, Aaron C. Courville, Pablo Samuel Castro. [doi]
• From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and ApplicationsAjay Kumar Jaiswal, Yifan Wang, Lu Yin 0006, Shiwei Liu 0003, Runjin Chen, Jiawei Zhao, Ananth Grama, Yuandong Tian, Zhangyang Wang. [doi]
• Fusing Reward and Dueling Feedback in Stochastic BanditsXuchuang Wang, Qirun Zeng, Jinhang Zuo, Xutong Liu 0002, Mohammad Hajiesmaili, John C. S. Lui, Adam Wierman. [doi]
• Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared LossAbhijeet Mulgund, Chirag Pabbaraju. [doi]
• Scalable Private Partition Selection via Adaptive WeightingJustin Y. Chen, Vincent Cohen-Addad, Alessandro Epasto, Morteza Zadimoghaddam. [doi]
• Exogenous Isomorphism for Counterfactual IdentifiabilityYikang Chen, Dehui Du. [doi]
• OneForecast: A Universal Framework for Global and Regional Weather ForecastingYuan Gao, Hao Wu 0094, Ruiqi Shu, Huanshuo Dong, Fan Xu 0009, Rui Ray Chen, Yibo Yan, Qingsong Wen, Xuming Hu, Kun Wang 0056, Jiahao Wu 0004, Qing Li 0001, Hui Xiong 0001, Xiaomeng Huang. [doi]
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language ModelsWei Huang 0042, Haotong Qin, Yangdong Liu, Yawei Li 0001, Qinshuo Liu, Xianglong Liu 0001, Luca Benini, Michele Magno, Shiming Zhang, Xiaojuan Qi 0001. [doi]
• NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare AnalyticsChangshuo Liu, Lingze Zeng, Kaiping Zheng, Shaofeng Cai, Beng Chin Ooi, James Wei Luen Yip. [doi]
• Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability LandscapesDongjae Jeon, Dueun Kim, Albert No. [doi]
• Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow MatchingTinglin Huang 0001, Tianyu Liu 0005, Mehrtash Babadi, Wengong Jin, Rex Ying. [doi]
• From Kernels to Features: A Multi-Scale Adaptive Theory of Feature LearningNoa Rubin, Kirsten Fischer, Javed Lindner, Inbar Seroussi, Zohar Ringel, Michael Krämer, Moritz Helias. [doi]
• Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-TuningLiang Chen 0001, Xueting Han, Li Shen 0008, Jing Bai, Kam-Fai Wong. [doi]
• Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware DiffusionAnle Ke, Xu Zhang 0027, Tong Chen 0004, Ming Lu 0003, Chao Zhou, Jiawen Gu, Zhan Ma 0001. [doi]
• Conformal Prediction with Cellwise Outliers: A Detect-then-Impute ApproachQian Peng, Yajie Bao, Haojie Ren, Zhaojun Wang, Changliang Zou. [doi]
• Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic AdaptationYihao Yang, Wenke Huang 0003, Guancheng Wan, Bin Yang 0026, Mang Ye. [doi]
• In-Context Reinforcement Learning From Suboptimal Historical DataJuncheng Dong, Moyang Guo, Ethan X. Fang, Zhuoran Yang, Vahid Tarokh. [doi]
• PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language ModelsChenyang Zhang, Xiaoyu Zhang 0010, Jian Lou 0001, Kai Wu 0003, Zilong Wang 0001, Xiaofeng Chen 0001. [doi]
• FedClean: A General Robust Label Noise Correction for Federated LearningXiaoqian Jiang, Jing Zhang. [doi]
• Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best ResponseKexin Huang, Ziqian Chen, Xue Wang 0010, Chongming Gao, Jinyang Gao, Bolin Ding, Xiang Wang 0010. [doi]
• Contrastive Learning with Simplicial Convolutional Networks for Short-Text ClassificationHuang Liang, Benedict Lee, Daniel Hui Loong Ng, Kelin Xia. [doi]
• Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision ModelsThomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle. [doi]
• UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal ControlKaizhen Zhu, Mokai Pan, Yuexin Ma, Yanwei Fu 0001, Jingyi Yu 0001, Jingya Wang, Ye Shi 0001. [doi]
• Selective Preference AggregationShreyas Kadekodi, Hayden McTavish, Berk Ustun. [doi]
• Conformal Tail Risk Control for Large Language Model AlignmentCatherine Yu-Chi Chen, Jingyan Shen, Zhun Deng, Lihua Lei. [doi]
• Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution DetectionXiang Fang, Arvind Easwaran, Blaise Genest. [doi]
• Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement LearningChen-Xiao Gao, Chenyang Wu 0001, Mingjun Cao, Chenjun Xiao, Yang Yu 0001, Zongzhang Zhang. [doi]
• Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision ProcessesBhargav Ganguly, Yang Xu 0003, Vaneet Aggarwal. [doi]
• KV Shifting Attention Enhances Language ModelingMingyu Xu, Bingning Wang, Weipeng Chen. [doi]
• Theoretical Limitations of Ensembles in the Age of OverparameterizationNiclas Dern, John Patrick Cunningham, Geoff Pleiss. [doi]
• Revisiting Diffusion Models: From Generative Pre-training to One-Step GenerationBowen Zheng, Tianming Yang. [doi]
• Learning Safe Control via On-the-Fly Bandit ExplorationAlexandre Capone, Ryan Kazuo Cosner, Aaron D. Ames, Sandra Hirche. [doi]
• Learning Policy Committees for Effective Personalization in MDPs with Diverse TasksLuise Ge, Michael Lanier, Anindya Sarkar, Bengisu Guresti, Chongjie Zhang, Yevgeniy Vorobeychik. [doi]
• Efficient Online Reinforcement Learning for Diffusion PolicyHaitong Ma, Tianyi Chen, Kai Wang, Na Li 0002, Bo Dai 0001. [doi]
• DocVXQA: Context-Aware Visual Explanations for Document Question AnsweringMohamed Ali Souibgui, Changkyu Choi, Andrey Barsky, Kangsoo Jung, Ernest Valveny, Dimosthenis Karatzas. [doi]
• Diversity By Design: Leveraging Distribution Matching for Offline Model-Based OptimizationMichael S. Yao, James C. Gee, Osbert Bastani. [doi]
• LSCD: Lomb-Scargle Conditioned Diffusion for Time series ImputationElizabeth Fons, Alejandro Sztrajman, Yousef El-Laham, Luciana Ferrer, Svitlana Vyetrenko, Manuela Veloso. [doi]
• A Mixture-Based Framework for Guiding Diffusion ModelsYazid Janati, Badr Moufad, Mehdi Abou El Qassime, Alain Oliviero Durmus, Eric Moulines, Jimmy Olsson. [doi]
• BILBO: BILevel Bayesian OptimizationWan Theng Ruth Chew, Quoc Phong Nguyen, Bryan Kian Hsiang Low. [doi]
• Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language ModelsJialin Zhao 0004, Yingtao Zhang, Carlo Vittorio Cannistraci. [doi]
• BAnG: Bidirectional Anchored Generation for Conditional RNA DesignRoman Klypa, Alberto Bietti, Sergei Grudinin. [doi]
• A Classification View on Meta Learning BanditsMirco Mutti, Jeongyeol Kwon, Shie Mannor, Aviv Tamar. [doi]
• Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online InteractionYiting He, Zhishuai Liu, Weixin Wang, Pan Xu 0002. [doi]
• Hierarchical Graph Tokenization for Molecule-Language AlignmentYongqiang Chen 0002, Quanming Yao, Juzheng Zhang, James Cheng, Yatao Bian. [doi]
• Learnings from Scaling Visual Tokenizers for Reconstruction and GenerationPhilippe Hansen-Estruch, David Yan, Ching-Yao Chuang, Orr Zohar, Jialiang Wang 0001, Tingbo Hou, Tao Xu, Sriram Vishwanath, Peter Vajda, Xinlei Chen. [doi]
• CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data ImputationAditya Gorla, Ryan Wang, Zhengtong Liu, Ulzee An, Sriram Sankararaman. [doi]
• Scaling Laws for Forgetting during Finetuning with Pretraining Data InjectionLouis Béthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin. [doi]
• Knowledge Retention in Continual Model-Based Reinforcement LearningHaotian Fu, Yixiang Sun, Michael Littman 0002, George Konidaris 0001. [doi]
• TabFSBench: Tabular Benchmark for Feature Shifts in Open EnvironmentsZi-Jian Cheng, Ziyi Jia, Zhi Zhou 0007, Yufeng Li 0008, Lan-Zhe Guo. [doi]
• Optimal Information Retention for Time-Series ExplanationsJinghang Yue, Jing Wang 0060, Lu Zhang, Shuo Zhang 0015, Da Li, Zhaoyang Ma, Youfang Lin. [doi]
• Normalizing Flows are Capable Generative ModelsShuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao Gu, Huangjie Zheng, Tianrong Chen, Miguel Ángel Bautista 0001, Navdeep Jaitly, Joshua M. Susskind. [doi]
• Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy EvaluationHongyi Zhou, Josiah P. Hanna, Jin Zhu, Ying Yang, Chengchun Shi. [doi]
• Logarithmic Regret for Online KL-Regularized Reinforcement LearningHeyang Zhao, Chenlu Ye, Wei Xiong 0015, Quanquan Gu, Tong Zhang 0001. [doi]
• MTL-UE: Learning to Learn Nothing for Multi-Task LearningYi Yu 0011, Song Xia, Siyuan Yang 0001, Chenqi Kong, Wenhan Yang, Shijian Lu, Yap-Peng Tan, Alex C. Kot. [doi]
• AutoGFM: Automated Graph Foundation Model with Adaptive Architecture CustomizationHaibo Chen 0008, Xin Wang 0019, Zeyang Zhang 0001, Haoyang Li 0001, Ling Feng, Wenwu Zhu 0001. [doi]
• Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large pShengbin Ye, Meng Li 0002. [doi]
• How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization GuaranteesHaonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li 0002, Philip S. Yu. [doi]
• FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender SystemsArya Fayyazi, Mehdi Kamal, Massoud Pedram. [doi]
• Leveraging Randomness in Model and Data Partitioning for Privacy AmplificationAndy Dong, Wei-Ning Chen, Ayfer Özgür. [doi]
• Can We Predict Performance of Large Models across Vision-Language Tasks?Qinyu Zhao, Ming Xu 0015, Kartik Gupta, Akshay Asthana, Liang Zheng 0001, Stephen Gould. [doi]
• ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement LearningHongyin Zhang, Zifeng Zhuang, Han Zhao 0008, Pengxiang Ding, Hongchao Lu, Donglin Wang. [doi]
• A Near Linear Query Lower Bound for Submodular MaximizationBinghui Peng, Aviad Rubinstein. [doi]
• Enhancing Performance of Explainable AI Models with Constrained Concept RefinementGeyu Liang, Senne Michielssen, Salar Fattahi. [doi]
• An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques TransferLifu Liu, Shiyuan He, Jianhua Guo. [doi]
• Contrastive Visual Data AugmentationYu Zhou 0030, Bingxuan Li, Mohan Tang, Xiaomeng Jin, Te-Lin Wu, Kuan-Hao Huang, Heng Ji 0001, Kai-Wei Chang, Nanyun Peng 0001. [doi]
• Improving Memory Efficiency for Training KANs via Meta LearningZhangchi Zhao, Jun Shu, Deyu Meng, ZongBen Xu. [doi]
• SWAN: SGD with Normalization and Whitening Enables Stateless LLM TrainingChao Ma 0019, Wenbo Gong 0001, Meyer Scetbon, Edward Meeds. [doi]
• Self-Consuming Generative Models with Adversarially Curated DataXiukun Wei, Xueru Zhang. [doi]
• ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine LearningArto Maranjyan, El Mehdi Saad, Peter Richtárik, Francesco Orabona. [doi]
• Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensionsFabiola Ricci, Lorenzo Bardone, Sebastian Goldt. [doi]
• Contextures: Representations from ContextsRuntian Zhai, Kai Yang, Burak Varici, Che-Ping Tsai, J. Zico Kolter, Pradeep Kumar Ravikumar. [doi]
• Evaluating Neuron Explanations: A Unified Framework with Sanity ChecksTuomas P. Oikarinen, Ge Yan, Tsui-Wei Weng. [doi]
• Riemannian Diffusion Adaptation for Distributed Optimization on ManifoldsXiuheng Wang, Ricardo Augusto Borsoi, Cédric Richard, Ali H. Sayed. [doi]
• Provable Zero-Shot Generalization in Offline Reinforcement LearningZhiyong Wang, Chen Yang, John C. S. Lui, Dongruo Zhou. [doi]
• FeatSharp: Your Vision Model Features, SharperMike Ranzinger, Greg Heinrich, Pavlo Molchanov 0001, Bryan Catanzaro, Andrew Tao. [doi]
• Fast Min-ϵ Segmented Regression using Constant-Time Segment MergingAnsgar Lößer, Max Schlecht, Florian Schintke, Joel Witzke, Matthias Weidlich 0001, Björn Scheuermann 0001. [doi]
• Evolving Prompts In-Context: An Open-ended, Self-replicating PerspectiveJianyu Wang, Zhiqiang Hu, Lidong Bing. [doi]
• Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networksLukas Braun, Erin Grant, Andrew M. Saxe. [doi]
• LEAPS: A discrete neural sampler via locally equivariant networksPeter Holderrieth, Michael Samuel Albergo, Tommi S. Jaakkola. [doi]
• HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEsMingquan Feng, Weixin Liao, Yixin Huang, Yifan Fu, Qifu Zheng, Junchi Yan. [doi]
• Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal DataMingcai Chen, Baoming Zhang, Zongbo Han, Wenyu Jiang, Yanmeng Wang, Shuai Feng, Yuntao Du 0001, Bingkun Bao. [doi]
• Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation AlignmentYu Zhu, Chunfeng Song, Wanli Ouyang, Shan Yu, Tiejun Huang 0003. [doi]
• Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement LearningChi Zhang, Ziying Jia, George K. Atia, Sihong He, Yue Wang 0068. [doi]
• Adversarial Combinatorial Semi-bandits with Graph FeedbackYuxiao Wen. [doi]
• The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension ReductionAlex Kokot, Octavian-Vlad Murad, Marina Meila. [doi]
• Online Curvature-Aware Replay: Leveraging 2nd Order Information for Online Continual LearningEdoardo Urettini, Antonio Carta. [doi]
• Functional Alignment Can Mislead: Examining Model StitchingDamian Smith, Harvey Mannering, Antonia Marcu. [doi]
• TTFSFormer: A TTFS-based Lossless Conversion of Spiking TransformerLusen Zhao, Zihan Huang, Jianhao Ding, Zhaofei Yu. [doi]
• Extracting Rare Dependence Patterns via Adaptive Sample ReweightingYiqing Li, Yewei Xia, Xiaofei Wang, Zhengming Chen 0002, Liuhua Peng, Mingming Gong, Kun Zhang 0001. [doi]
• Fast Tensor Completion via Approximate Richardson IterationMehrdad Ghadiri, Matthew Fahrbach, Yunbum Kook, Ali Jadbabaie. [doi]
• Predicting mutational effects on protein binding from folding energyArthur Deng, Karsten D. Householder, Fang Wu 0002, K. Christopher Garcia, Brian L. Trippe. [doi]
• Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language ModelsLiangchen Liu 0001, Nannan Wang 0001, Xi Yang 0011, Xinbo Gao 0001, Tongliang Liu. [doi]
• SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMsShibo Jie, Yehui Tang, Kai Han 0002, Zhi-Hong Deng 0001, Jing Han. [doi]
• BoA: Attention-aware Post-training Quantization without BackpropagationJunhan Kim, Ho Young Kim, Eulrang Cho, Chungman Lee, Joonyoung Kim, Yongkweon Jeon. [doi]
• Flow-field inference from neural data using deep recurrent networksTimothy Doyeon Kim, Thomas Zhihao Luo, Tankut Can, Kamesh Krishnamurthy, Jonathan W. Pillow, Carlos D. Brody. [doi]
• CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image GenerationMinghao Fu 0001, Guo-Hua Wang, Liangfu Cao, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang. [doi]
• Automated Benchmark Generation for Repository-Level Coding TasksKonstantinos Vergopoulos, Mark Niklas Müller, Martin T. Vechev. [doi]
• MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward HackingSebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah. [doi]
• Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement LearningBryan Lincoln Marques de Oliveira, Luana Guedes Barros Martins, Bruno Brandão, Murilo Lopes da Luz, Telma Woerle de Lima Soares, Luckeciano Carvalho Melo. [doi]
• LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)Junsu Kim, Jaeyeon Kim, Ernest K. Ryu. [doi]
• Efficient Multivariate Robust Mean Estimation Under Mean-Shift ContaminationIlias Diakonikolas, Giannis Iakovidis, Daniel Kane 0001, Thanasis Pittas. [doi]
• Reinforcement Learning with Segment FeedbackYihan Du, Anna Winnicki, Gal Dalal, Shie Mannor, R. Srikant 0001. [doi]
• Zebra: In-Context Generative Pretraining for Solving Parametric PDEsLouis Serrano, Armand Kassaï Koupaï, Thomas X. Wang, Pierre Erbacher, Patrick Gallinari. [doi]
• Flow Matching for Few-Trial Neural Adaptation with Stable Latent DynamicsPuli Wang, Yu Qi, Yueming Wang 0001, Gang Pan 0001. [doi]
• Epsilon-VAE: Denoising as Visual DecodingLong Zhao 0003, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang 0010, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu 0005. [doi]
• Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate DescentDongHwa Kim, Jaewook Lee 0009, Chulhee Yun. [doi]
• Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority GenerationSoobin Um, Beomsu Kim, Jong Chul Ye. [doi]
• Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA DesignMasatoshi Uehara, Xingyu Su, Yulai Zhao 0002, Xiner Li, Aviv Regev, Shuiwang Ji, Sergey Levine, Tommaso Biancalani. [doi]
• G-Adaptivity: optimised graph-based mesh relocation for finite element methodsJames Rowbottom, Georg Maierhofer, Teo Deveney, Eike Hermann Müller, Alberto Paganini, Katharina Schratz, Pietro Lio, Carola-Bibiane Schönlieb, Chris J. Budd. [doi]
• Fast, Accurate Manifold Denoising by Tunneling Riemannian OptimizationShiyu Wang, Mariam Avagyan, Yihan Shen, Arnaud Lamy, Tingran Wang, Szabolcs Márka, Zsuzsa Márka, John Wright 0001. [doi]
• Universal Sparse Autoencoders: Interpretable Cross-Model Concept AlignmentHarrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos G. Derpanis. [doi]
• Can Large Language Models Understand Intermediate Representations in Compilers?Hailong Jiang, Jianfeng Zhu, Yao Wan 0001, Bo Fang 0002, Hongyu Zhang 0002, Ruoming Jin, Qiang Guan. [doi]
• TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian PredictionShi Yin, Xinyang Pan, Fengyan Wang, Lixin He. [doi]
• Stronger Neyman Regret Guarantees for Adaptive Experimental DesignGeorgy Noarov, Riccardo Fogliato, Martín Bertrán, Aaron Roth 0001. [doi]
• PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex DesignZhenqiao Song, Tianxiao Li 0001, Lei Li, Martin Renqiang Min. [doi]
• Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based LearningRyotaro Kawata, Kohsei Matsutani, Yuri Kinoshita, Naoki Nishikawa, Taiji Suzuki. [doi]
• From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction ModelsMingjia Yin, Junwei Pan, Hao Wang 0076, Ximei Wang, Shangyu Zhang, Jie Jiang 0015, Defu Lian, Enhong Chen. [doi]
• Test-Time Graph Neural Dataset Search With Generative ProjectionXin Zheng 0008, Wei Huang 0034, Chuan Zhou 0001, Ming Li 0065, Shirui Pan. [doi]
• Unlocking Post-hoc Dataset Inference with Synthetic DataBihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic. [doi]
• MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language ModelsJiazheng Li 0012, Lu Yu 0006, Qing Cui, Zhiqiang Zhang 0012, Jun Zhou 0011, Yanfang Ye 0001, Chuxu Zhang. [doi]
• Leveraging Predictive Equivalence in Decision TreesHayden McTavish, Zachery Boner, Jon Donnelly, Margo I. Seltzer, Cynthia Rudin. [doi]
• PIPA: Preference Alignment as Prior-Informed Statistical EstimationJunbo Li, Zhangyang Wang, Qiang Liu 0001. [doi]
• Retraining-free Merging of Sparse MoE via Hierarchical ClusteringI-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, Chen-Hao Chao, Yen-Chang Hsu, Chun-Yi Lee. [doi]
• Fairness on Principal Stratum: A New Perspective on Counterfactual FairnessHaoxuan Li 0001, Zeyu Tang 0002, Zhichao Jiang, Zhuangyan Fang, Yue Liu, Zhi Geng, Kun Zhang 0001. [doi]
• Offline Model-based Optimization for Real-World Molecular DiscoveryDong-Hee Shin, Young-Han Son, Hyun Jung Lee, Deok-Joong Lee, Tae-Eui Kam. [doi]
• From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash EquilibriumXie Yi, Zhanke Zhou, Chentao Cao, Qiyu Niu, Tongliang Liu, Bo Han 0003. [doi]
• Improving Transformer World Models for Data-Efficient RLAntoine Dedieu, Joseph Ortiz, Xinghua Lou, Carter Wendelken, J. Swaroop Guntupalli, Wolfgang Lehrach, Miguel Lázaro-Gredilla, Kevin Patrick Murphy. [doi]
• Contextual Online Decision Making with Infinite-Dimensional Functional RegressionHaichen Hu, Rui Ai 0004, Stephen Bates, David Simchi-Levi. [doi]
• TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change AwarenessCheng Huang, Pan Mu, Cong Bai, Peter AG Watson. [doi]
• Imitation Learning from a Single Temporally Misaligned VideoWilliam Huey, Huaxiaoyue Wang, Anne Wu, Yoav Artzi, Sanjiban Choudhury. [doi]
• Exploring Invariance in Images through One-way Wave EquationsYinpeng Chen, Dongdong Chen 0001, Xiyang Dai, Mengchen Liu, Yinan Feng, Youzuo Lin, Lu Yuan, Zicheng Liu 0001. [doi]
• Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative ModelsSiddarth Venkatraman, Mohsin Hasan, Minsu Kim 0004, Luca Scimeca, Marcin Sendera, Yoshua Bengio, Glen Berseth, Nikolay Malkin. [doi]
• Limitations of measure-first protocols in quantum machine learningCasper Gyurik, Riccardo Molteni, Vedran Dunjko. [doi]
• Imagine While Reasoning in Space: Multimodal Visualization-of-ThoughtChengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia 0005, Shaoguang Mao, Li Dong 0004, Ivan Vulic, Furu Wei. [doi]
• Efficient Noise Calculation in Deep Learning-based MRI ReconstructionsOnat Dalmaz, Arjun D. Desai, Reinhard Heckel, Tolga Çukur, Akshay S. Chaudhari, Brian A. Hargreaves. [doi]
• Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated LearningWenjing Yan, Xiangyu Zhong, Xiaolu Wang, Ying Jun Angela Zhang. [doi]
• Scaling Laws for Task-Optimized Models of the Primate Visual Ventral StreamAbdülkadir Gökce, Martin Schrimpf. [doi]
• ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-DivergenceGuanghui Wang 0001, Zhiyong Yang 0001, Zitai Wang, Shi Wang, Qianqian Xu 0001, Qingming Huang. [doi]
• How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary ObjectsWonkwang Lee, Jongwon Jeong, Taehong Moon, Hyeon-Jong Kim, Jaehyeon Kim, Gunhee Kim, Byeong-uk Lee. [doi]
• On the Role of Label Noise in the Feature Learning ProcessAndi Han, Wei Huang 0034, Zhanpeng Zhou, Gang Niu 0001, Wuyang Chen 0001, Junchi Yan, Akiko Takeda, Taiji Suzuki. [doi]
• Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization SchemeRuofeng Yang, Bo Jiang, Cheng Chen 0015, Shuai Li 0010. [doi]
• Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous DecodingTian Jin, Ellie Y. Cheng, Zachary Ankner, Nikunj Saunshi, Blake M. Elias, Amir Yazdanbakhsh, Jonathan Ragan-Kelley, Suvinay Subramanian, Michael Carbin. [doi]
• Field Matching: an Electrostatic Paradigm to Generate and Transfer DataAlexander Kolesov, S. I. Manukhov, Vladimir Vladimirovich Palyulin, Alexander Korotin. [doi]
• Modulated Diffusion: Accelerating Generative Modeling with Modulated QuantizationWeizhi Gao, Zhichao Hou, Junqi Yin, Feiyi Wang, Linyu Peng, Xiaorui Liu. [doi]
• Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit AlignmentCheryl Li, Tianyuan Xu, Steven Y. Guo. [doi]
• Autoformulation of Mathematical Optimization Models Using LLMsNicolás Astorga, Tennison Liu, Yuanzhang Xiao, Mihaela van der Schaar. [doi]
• Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMsFaisal Hamman, Pasan Dissanayake, Saumitra Mishra, Freddy Lécué, Sanghamitra Dutta. [doi]
• Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation ModelsNgoc-Quan Pham, Tuan Truong, Quyen Tran, Tan Minh Nguyen, Dinh Phung 0001, Trung Le 0001. [doi]
• Exploring Representations and Interventions in Time Series Foundation ModelsMichal Wilinski, Mononito Goswami, Willa Potosnak, Nina Zukowska, Artur Dubrawski. [doi]
• Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge DistillationYang Yang 0074, Haonan Xu. [doi]
• The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward HackingYuchun Miao, Sen Zhang 0006, Liang Ding 0006, Yuqi Zhang 0002, Lefei Zhang, Dacheng Tao. [doi]
• Effective and Efficient Masked Image Generation ModelsZebin You, Jingyang Ou, Xiaolu Zhang, Jun Hu, Jun Zhou 0011, Chongxuan Li. [doi]
• Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence GuaranteesThien Hang Nguyen, Huy Nguyen. [doi]
• An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying DistributionsYuhan Ye, Ying Cui, Jingyi Wang. [doi]
• NExtLong: Toward Effective Long-Context Training without Long DocumentsChaochen Gao, Xing Wu 0002, Zijia Lin, Debing Zhang, Songlin Hu 0001. [doi]
• Contrastive Private Data Synthesis via Weighted Multi-PLM FusionTianyuan Zou, Yang Liu 0165, Peng Li 0030, Yufei Xiong, Jianqing Zhang, Jingjing Liu, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang. [doi]
• Hyperspherical Normalization for Scalable Deep Reinforcement LearningHoJoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone 0001, Jaegul Choo. [doi]
• Demonstration Selection for In-Context Learning via Reinforcement LearningXubin Wang, Jianfei Wu, Yichen Yuan, Deyu Cai, Mingzhe Li, Weijia Jia 0001. [doi]
• MARS: Unleashing the Power of Variance Reduction for Training Large ModelsHuizhuo Yuan, Yifeng Liu 0004, Shuang Wu, Xun Zhou, Quanquan Gu. [doi]
• FairICP: Encouraging Equalized Odds via Inverse Conditional PermutationYuheng Lai, Leying Guan. [doi]
• SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityAdam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Demian Till, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda. [doi]
• CostFilter-AD: Enhancing Anomaly Detection through Matching Cost FilteringZhe Zhang, Mingxiu Cai, Hanxiao Wang, Gaochang Wu, Tianyou Chai, Xiatian Zhu. [doi]
• Non-stationary Diffusion For Probabilistic Time Series ForecastingWeiwei Ye, Zhuopeng Xu, Ning Gui. [doi]
• Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptionsLe-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello, Giovanni Conforti, Alain Oliviero Durmus. [doi]
• R.I.P.: Better Models by Survival of the Fittest PromptsPing Yu, Weizhe Yuan, Olga Golovneva, Tianhao Wu 0002, Sainbayar Sukhbaatar, Jason E. Weston, Jing Xu 0014. [doi]
• The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised LearningDulhan Jayalath, Gilad Landau, Brendan Shillingford, Mark W. Woolrich, Oiwi Parker Jones. [doi]
• The Elicitation Game: Evaluating Capability Elicitation TechniquesFelix Hofstätter, Teun van der Weij, Jayden Teoh, Rada Djoneva, Henning Bartsch, Francis Rhys Ward. [doi]
• SAFE: Finding Sparse and Flat Minima to Improve PruningDongyeop Lee, Kwanhee Lee, Jinseok Chung, Namhoon Lee. [doi]
• ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot LearningWei Xiao 0003, Tsun-Hsuan Wang, Chuang Gan 0001, Daniela Rus. [doi]
• Beyond Matryoshka: Revisiting Sparse Coding for Adaptive RepresentationTiansheng Wen, Yifei Wang, Zequn Zeng, Zhong Peng, Yudi Su, Xinyang Liu, Bo Chen 0001, Hongwei Liu, Stefanie Jegelka, Chenyu You. [doi]
• Improving Flow Matching by Aligning Flow DivergenceYuhao Huang, Taos Transue, Shih-Hsin Wang, William M. Feldman, Hong Zhang, Bao Wang 0001. [doi]
• Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans WorseRyan Liu 0001, Jiayi Geng, Addison J. Wu, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths 0001. [doi]
• Gridded Transformer Neural Processes for Spatio-Temporal DataMatthew Ashman, Cristiana Diaconu, Eric Langezaal, Adrian Weller, Richard E. Turner. [doi]
• DVI: A Derivative-based Vision Network for INRRunzhao Yang, Xiaolong Wu, Zhihong Zhang 0004, Fabian Zhang, Tingxiong Xiao, Zongren Li, Kunlun He, Jinli Suo. [doi]
• Mitigating over-Exploration in Latent Space Optimization using lesOmer Ronen, Ahmed Imtiaz Humayun, Richard G. Baraniuk, Randall Balestriero, Bin Yu 0001. [doi]
• Joint MoE Scaling Laws: Mixture of Experts Can Be Memory EfficientJan Ludziejewski, Maciej Pióro, Jakub Krajewski, Maciej Stefaniak, Michal Krutul, Jan Malasnicki, Marek Cygan, Piotr Sankowski, Kamil Adamczewski, Piotr Milos, Sebastian Jaszczur. [doi]
• Dimension-Independent Rates for Structured Neural Density EstimationRobert A. Vandermeulen, Wai Ming Tai, Bryon Aragam. [doi]
• Wasserstein Policy OptimizationDavid Pfau, Ian Davies, Diana L. Borsa, João Guilherme Madeira Araújo, Brendan D. Tracey, Hado van Hasselt. [doi]
• The Case for Learned Provenance-based System Behavior BaselineYao Zhu, Zhenyuan Li, Yangyang Wei, Shouling Ji. [doi]
• SAND: One-Shot Feature Selection with Additive Noise DistortionPedram Pad, Hadi Hammoud, Mohamad Dia, Nadim Maamari, Liza Andrea Dunbar. [doi]
• Communicating Activations Between Language Model AgentsVignav Ramesh, Kenneth Li 0002. [doi]
• Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion ModelsZheng Gong 0001, Ying Sun 0006. [doi]
• The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision ProcessesPedro P. Santos, Alberto Sardinha, Francisco S. Melo. [doi]
• Point Cloud Dataset DistillationDeyu Bo, Xinchao Wang. [doi]
• C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement LearningZifan Liu, Xinran Li, Jun Zhang 0004. [doi]
• LipsNet++: Unifying Filter and Controller into a Policy NetworkXujie Song, Liangfa Chen, Tong Liu, Wenxuan Wang 0004, Yinuo Wang, Shentao Qin, Yinsong Ma, Jingliang Duan, Shengbo Eben Li. [doi]
• Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback ExperimentsQianglin Wen, Chengchun Shi, Ying Yang, Niansheng Tang, Hongtu Zhu. [doi]
• How Effective Can Dropout Be in Multiple Instance Learning ?Wenhui Zhu, Peijie Qiu, Xiwen Chen, Zhangsihao Yang, Aristeidis Sotiras, Abolfazl Razi, Yalin Wang 0001. [doi]
• Text-to-CAD Generation Through Infusing Visual Feedback in Large Language ModelsRuiyu Wang, Yu Yuan, Shizhao Sun, Jiang Bian 0002. [doi]
• Beyond Message Passing: Neural Graph Pattern MachineZehong Wang, Zheyuan Zhang, Tianyi Ma, Nitesh V. Chawla, Chuxu Zhang, Yanfang Ye 0001. [doi]
• Scaling Laws for Upcycling Mixture-of-Experts Language ModelsSeng Pei Liew, Takuya Kato, Sho Takase. [doi]
• Test-Time Multimodal Backdoor Detection by Contrastive PromptingYuwei Niu, Shuo He 0001, Qi Wei 0004, Zongyu Wu 0001, Feng Liu 0003, Lei Feng 0006. [doi]
• AMPO: Active Multi Preference Optimization for Self-play Preference SelectionTaneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, Saravan Rajmohan. [doi]
• UP-VLA: A Unified Understanding and Prediction Model for Embodied AgentJianke Zhang, Yanjiang Guo, Yucheng Hu, Xiaoyu Chen, Xiang Zhu, Jianyu Chen 0002. [doi]
• Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted NetworksDongwoo Lee, Dong-Bok Lee, Steven Adriaensen, Juho Lee, Sung Ju Hwang, Frank Hutter, Seon Joo Kim, Hae Beom Lee. [doi]
• EraseAnything: Enabling Concept Erasure in Rectified Flow TransformersDaiheng Gao, Shilin Lu, Wenbo Zhou, Jiaming Chu, Jie Zhang 0073, Mengxi Jia, Bang Zhang, Zhaoxin Fan, Weiming Zhang 0001. [doi]
• Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-TuningWenke Huang 0003, Jian Liang 0003, Zekun Shi, Didi Zhu, Guancheng Wan, He Li 0054, Bo Du 0001, Dacheng Tao, Mang Ye. [doi]
• Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical SpaceZixing Song, Ziqiao Meng, José Miguel Hernández-Lobato. [doi]
• AdvAgent: Controllable Blackbox Red-teaming on Web AgentsChejian Xu, Mintong Kang, Jiawei Zhang 0013, Zeyi Liao, Lingbo Mo, Mengqi Yuan, Huan Sun 0001, Bo Li 0026. [doi]
• Causal Effect Identification in lvLiNGAM from Higher-Order CumulantsDaniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Negar Kiyavash, Mathias Drton. [doi]
• Counting atoms faster: policy-based nuclear magnetic resonance pulse sequencing for atomic abundance measurementRohan Shenoy, Evan Austen Coleman, Hans Gaensbauer, Elsa Olivetti. [doi]
• SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive DecodingWoohyeon Park, Woojin Kim, Jaeik Kim, Jaeyoung Do. [doi]
• Adversarial Robustness via Deformable Convolution with StochasticityYanxiang Ma, Zixuan Huang, Minjing Dong, Shan You, Chang Xu 0002. [doi]
• Local Manifold Approximation and Projection for Manifold-Aware Diffusion PlanningKyowoon Lee, Jaesik Choi. [doi]
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model ReasoningHan Zhong 0001, Yutong Yin, Shenao Zhang, Xiaojun Xu, Yuanxin Liu, Yifei Zuo, Zhihan Liu, Boyi Liu 0001, Sirui Zheng, Hongyi Guo, Liwei Wang 0001, Mingyi Hong 0001, Zhaoran Wang 0001. [doi]
• Deliberation in Latent Space via Differentiable Cache AugmentationLuyang Liu, Jonas Pfeiffer, Jiaxing Wu, Jun Xie, Arthur Szlam. [doi]
• Scaling Sparse Feature Circuits For Studying In-Context LearningDmitrii Kharlapenko, Stepan Shabalin, Arthur Conmy, Neel Nanda. [doi]
• Randomized Dimensionality Reduction for Euclidean Maximization and Diversity MeasuresJie Gao 0001, Rajesh Jayaram, Benedikt Kolbe, Shay Sapir, Chris Schwiegelshohn, Sandeep Silwal, Erik Waingarten. [doi]
• Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM AdaptationTianyi Zhang 0011, Junda Su, Aditya Desai, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava. [doi]
• I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion ModelsZhenxing Mi, Kuan-Chieh Wang, Guocheng Qian, Hanrong Ye, Runtao Liu, Sergey Tulyakov, Kfir Aberman, Dan Xu 0002. [doi]
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language UnderstandingXiaoqian Shen, Yunyang Xiong, Changsheng Zhao 0002, Lemeng Wu, Jun Chen 0021, Chenchen Zhu, Zechun Liu, Fanyi Xiao, Balakrishnan Varadarajan, Florian Bordes, Zhuang Liu, Hu Xu 0001, Hyunwoo J. Kim, Bilge Soran, Raghuraman Krishnamoorthi, Mohamed Elhoseiny, Vikas Chandra. [doi]
• Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field GamesAntonio Ocello, Daniil Tiapkin, Lorenzo Mancini, Mathieu Laurière, Eric Moulines. [doi]
• TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph CompletionJiujiang Guo, Mankun Zhao, Wenbin Zhang 0010, Tianyi Xu, Linying Xu, Jian Yu 0003, Mei Yu 0004, Ruiguo Yu. [doi]
• QuEST: Stable Training of LLMs with 1-Bit Weights and ActivationsAndrei Panferov, Jiale Chen 0004, Soroush Tabesh, Mahdi Nikdan, Dan Alistarh. [doi]
• Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight SymmetryMohammed Adnan, Rohan Jain, Ekansh Sharma, Rahul Krishnan, Yani Ioannou. [doi]
• NETS: A Non-equilibrium Transport SamplerMichael Samuel Albergo, Eric Vanden-Eijnden. [doi]
• Diversifying Policy Behaviors with Extrinsic Behavioral CuriosityZhenglin Wan, Xingrui Yu, David Mark Bossens, Yueming Lyu, Qing Guo 0005, Flint Xiaofeng Fan, Yew-Soon Ong, Ivor W. Tsang. [doi]
• BOOD: Boundary-based Out-Of-Distribution Data GenerationQilin Liao, Shuo Yang 0006, Bo Zhao 0038, Ping Luo 0002, Hengshuang Zhao. [doi]
• One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model TrajectoryYuhang Li, Tong Liu, Yangguang Cui, Ming Hu, Xiaoqiang Li. [doi]
• Latent Preference Coding: Aligning Large Language Models via Discrete Latent CodesZhuocheng Gong, Jian Guan 0002, Wei Wu 0014, Huishuai Zhang, Dongyan Zhao 0001. [doi]
• Improving Your Model Ranking on Chatbot Arena by Vote RiggingRui Min, Tianyu Pang, Chao Du, Qian Liu 0012, Minhao Cheng, Min Lin. [doi]
• Masked Autoencoders Are Effective Tokenizers for Diffusion ModelsHao Chen 0102, Yujin Han, Fangyi Chen, Xiang Li 0106, Yidong Wang 0003, Jindong Wang 0001, Ze Wang 0008, Zicheng Liu 0001, Difan Zou, Bhiksha Raj. [doi]
• LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k SelectionLukasz Struski, Michal B. Bednarczyk, Igor T. Podolak, Jacek Tabor. [doi]
• Exploring and Mitigating Adversarial Manipulation of Voting-Based LeaderboardsYangsibo Huang, Milad Nasr, Anastasios Nikolas Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Ken Liu, Ion Stoica, Florian Tramèr, Chiyuan Zhang. [doi]
• Aggregation of Dependent Expert Distributions in Multimodal Variational AutoencodersRogelio Andrade Mancisidor, Robert Jenssen, Shujian Yu, Michael Kampffmeyer. [doi]
• Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic LocalizationPhillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite. [doi]
• KinDEL: DNA-Encoded Library Dataset for Kinase InhibitorsBenson Chen, Tomasz Danel, Gabriel H. S. Dreiman, Patrick J. McEnaney, Nikhil Jain, Kirill Novikov, Spurti Umesh Akki, Joshua L. Turnbull, Virja Atul Pandya, Boris P. Belotserkovskii, Jared Bryce Weaver, Ankita Biswas, Dat Nguyen, Kent Gorday, Mohammad Sultan, Nathaniel Stanley, Daniel M. Whalen, Divya Kanichar, Christoph Klein 0006, Emily Fox, R. Edward Watts. [doi]
• Feedforward Few-shot Species Range EstimationChristian Lange 0004, Max Hamilton, Elijah Cole, Alexander Shepard, Samuel Heinrich, Angela Zhu, Subhransu Maji, Grant Van Horn, Oisin Mac Aodha. [doi]
• Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and DiffusionDoHoon Lee, Jaehyun Park, Hyunwoo J. Kim, Kyogu Lee. [doi]
• Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model EnsembleAtsushi Nitanda, Anzelle Lee, Damian Tan Xing Kai, Mizuki Sakaguchi, Taiji Suzuki. [doi]
• LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent CoordinationLihe Li, Lei Yuan 0005, Pengsen Liu, Tao Jiang, Yang Yu 0001. [doi]
• TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-stateXiaowen Ma, Zhen-Liang Ni, Shuai Xiao, Xinghao Chen 0001. [doi]
• SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) ComplexityShihao Zou, Qingfeng Li, Wei Ji, Jingjing Li, Yongkui Yang, Guoqi Li, Chao Dong. [doi]
• Scalable First-order Method for Certifying Optimal k-Sparse GLMsJiachang Liu 0001, Soroosh Shafiee, Andrea Lodi 0001. [doi]
• Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in TokamaksRohit Sonker, Alexandre Capone, Andrew Rothstein, Hiro Josep Farre Kaga, Egemen Kolemen, Jeff Schneider 0001. [doi]
• Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned ProblemsYujun Kim, Jaeyoung Cha, Chulhee Yun. [doi]
• When Bad Data Leads to Good ModelsKenneth Li 0002, Yida Chen, Fernanda B. Viégas, Martin Wattenberg. [doi]
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied AgentsRui Yang 0010, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian 0008, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji 0001, Huan Zhang 0001, Tong Zhang 0001. [doi]
• FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free GuaranteesFan Nie, Xiaotian Hou, Shuhang Lin, James Zou 0001, Huaxiu Yao, Linjun Zhang. [doi]
• Symmetry-Robust 3D Orientation EstimationChristopher Scarvelis, David Ben-Haim, Paul Zhang. [doi]
• Diffuse Everything: Multimodal Diffusion Models on Arbitrary State SpacesKevin Rojas, Yuchen Zhu, Sichen Zhu, Felix X.-F. Ye, Molei Tao. [doi]
• REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic ObjectiveSimon Geisler, Tom Wollschläger, M. H. I. Abdalla, Vincent Cohen-Addad, Johannes Gasteiger, Stephan Günnemann. [doi]
• Online Clustering of Dueling BanditsZhiyong Wang, Jiahang Sun, Mingze Kong, Jize Xie, Qinghua Hu, John C. S. Lui, Zhongxiang Dai. [doi]
• Ranked from Within: Ranking Large Multimodal Models Without LabelsWeijie Tu, Weijian Deng, Dylan Campbell, Yu Yao 0005, Jiyang Zheng, Tom Gedeon, Tongliang Liu. [doi]
• Complete-Tree Space Favors Data-Efficient Link PredictionChi Gao, Lukai Li, Yancheng Zhou, Shangqi Guo. [doi]
• Flexibility-conditioned protein structure design with flow matchingVsevolod Viliuga, Leif Seute, Nicolas Wolf, Simon Wagner, Arne Elofsson, Jan Stühmer, Frauke Gräter. [doi]
• Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and RegretBingshan Hu, Zhiming Huang 0002, Tianyue H. Zhang, Mathias Lécuyer, Nidhi Hegde 0001. [doi]
• How Compositional Generalization and Creativity Improve as Diffusion Models are TrainedAlessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart. [doi]
• Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness EvaluationChang Liu, Yixin Wang, Moontae Lee. [doi]
• EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security VulnerabilitiesTalor Abramovich, Meet Udeshi, Minghao Shao, Kilian Lieret, Haoran Xi, Kimberly Milner, Sofija Jancheska, John Yang 0002, Carlos E. Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique 0001, Karthik R. Narasimhan, Ramesh Karri, Ofir Press. [doi]
• Global curvature for second-order optimization of neural networksAlberto Bernacchia. [doi]
• A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?Ibrahim Alabdulmohsin, Andreas Peter Steiner. [doi]
• Learning Event Completeness for Weakly Supervised Video Anomaly DetectionYu Wang 0174, Shiwei Chen. [doi]
• Understanding Complexity in VideoQA via Visual Program GenerationCristóbal Eyzaguirre, Igor Vasiljevic, Achal Dave, Jiajun Wu 0001, Rares Andrei Ambrus, Thomas Kollar, Juan Carlos Niebles, Pavel Tokmakov. [doi]
• Avoiding spurious sharpness minimization broadens applicability of SAMSidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann N. Dauphin. [doi]
• CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous QueriesNi Mu, Hao Hu, Xiao Hu, Yiqin Yang, Bo Xu, Qing-Shan Jia. [doi]
• Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-TuningJinlong Pang, Na Di, Zhaowei Zhu, Jiaheng Wei, Hao Cheng, Chen Qian 0001, Yang Liu 0018. [doi]
• Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix FactorizationSuryanarayana Sankagiri, Jalal Etesami, Matthias Grossglauser. [doi]
• TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor LearningRon Shapira Weber, Shahar Ben Ishay, Andrey Lavrinenko, Shahaf E. Finder, Oren Freifeld. [doi]
• Algorithms with Calibrated Machine Learning PredictionsJudy Hanwen Shen, Ellen Vitercik, Anders Wikum. [doi]
• A Bayesian Model Selection Criterion for Selecting Pretraining CheckpointsMichael Munn, Susan Wei. [doi]
• On the Similarities of Embeddings in Contrastive LearningChungpa Lee, Sehee Lim, Kibok Lee 0003, Jy-yong Sohn. [doi]
• Improved Off-policy Reinforcement Learning in Biological Sequence DesignHyeonah Kim, Minsu Kim 0004, Taeyoung Yun, Sanghyeok Choi, Emmanuel Bengio, Alex Hernández-García, Jinkyoo Park. [doi]
• Decomposition of Graphic Design with Unified Multimodal ModelHui Nie 0001, Zhao Zhang, Yutao Cheng, Maoke Yang, Gonglei Shi, Qingsong Xie, Jie Shao, Xinglong Wu. [doi]
• Loss Functions and Operators Generated by f-DivergencesVincent Roulet, Tianlin Liu, Nino Vieillard, Michael Eli Sander, Mathieu Blondel. [doi]
• Deep Fuzzy Multi-view Learning for Reliable ClassificationSiyuan Duan, Yuan Sun 0016, Dezhong Peng, Guiduo Duan, Xi Peng 0001, Peng Hu 0002. [doi]
• On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal AlgorithmsEkaterina Borodich, Alexander V. Gasnikov, Dmitry Kovalev. [doi]
• Circumventing Backdoor Space via Weight SymmetryJie Peng, Hongwei Yang, Jing Zhao, Hengji Dong, Hui He, Weizhe Zhang, Haoyu He 0001. [doi]
• Improving LLM Video Understanding with 16 Frames Per SecondYixuan Li, Changli Tang, Jimin Zhuang, Yudong Yang, Guangzhi Sun, Wei Li 0119, Zejun Ma 0001, Chao Zhang 0031. [doi]
• When, Where and Why to Average Weights?Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping. [doi]
• Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed ClassificationSicong Li, Qianqian Xu 0001, Zhiyong Yang 0001, Zitai Wang, Linchao Zhang, Xiaochun Cao, Qingming Huang. [doi]
• Learning Configurations for Data-Driven Multi-Objective OptimizationZhiyang Chen, Hailong Yao, Xia Yin. [doi]
• Online Learning with Unknown ConstraintsKarthik Sridharan, Seung Won Wilson Yoo. [doi]
• Adaptive Estimation and Learning under Temporal Distribution ShiftDheeraj Baby, Yifei Tang, Hieu Duy Nguyen, Yu-Xiang Wang 0003, Rohit Pyati. [doi]
• ActionPiece: Contextually Tokenizing Action Sequences for Generative RecommendationYupeng Hou, Jianmo Ni, Zhankui He, Noveen Sachdeva, Wang-Cheng Kang, Ed H. Chi, Julian J. McAuley, Derek Zhiyuan Cheng. [doi]
• One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMsYinghui Li, Jiayi Kuang, Haojing Huang 0001, Zhikun Xu, Xinnian Liang, Yi Yu, Wenlian Lu, Yangning Li, Xiaoyu Tan, Chao Qu, Ying Shen 0001, Hai-Tao Zheng 0002, Philip S. Yu. [doi]
• LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution LearningXiuyi Jia, Jinchi Li, Yunan Lu 0002, Weiwei Li 0001. [doi]
• Learning to (Learn at Test Time): RNNs with Expressive Hidden StatesYu Sun 0020, Xinhao Li, Karan Dalal, Jiarui Xu, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang 0004, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin. [doi]
• ViTally Consistent: Scaling Biological Representation Learning for Cell MicroscopyKian Kenyon-Dean, Zitong Jerry Wang, John Urbanik, Konstantin Donhauser, Jason S. Hartford, Saber Saberian, Nil Sahin, Ihab Bendidi, Safiye Celik, Juan Sebastián Rodríguez Vera, Marta M. Fay, Imran S. Haque, Oren Kraus. [doi]
• G-Sim: Generative Simulations with Large Language Models and Gradient-Free CalibrationSamuel Holt, Max Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar. [doi]
• Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary VarianceShogo Iwazaki, Shion Takeno. [doi]
• The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge TransportabilityJiachen Hu, Rui Ai 0002, Han Zhong 0001, Xiaoyu Chen 0008, Liwei Wang 0001, Zhaoran Wang 0001, Zhuoran Yang. [doi]
• From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language ModelsXinyang Li, Siqi Liu, Bochao Zou, Jiansheng Chen, Huimin Ma 0001. [doi]
• BanditSpec: Adaptive Speculative Decoding via Bandit AlgorithmsYunlong Hou 0001, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang. [doi]
• A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex EnvironmentsYuchen Wang, Hongjue Zhao, Haohong Lin, Enze Xu, Lifang He 0001, Huajie Shao. [doi]
• Concept-Based Unsupervised Domain AdaptationXinyue Xu, Yueying Hu, Hui Tang, Yi Qin 0004, Lu Mi, Hao Wang 0014, Xiaomeng Li 0001. [doi]
• Overcoming Non-monotonicity in Transducer-based Streaming GenerationZhengrui Ma, Yang Feng 0004, Min Zhang 0005. [doi]
• EcoMapper: Generative Modeling for Climate-Aware Satellite ImageryMuhammed Goktepe, Amir Hossein Shamseddin, Erencan Uysal, Javier Muinelo Monteagudo, Lukas Drees, Aysim Toker, Senthold Asseng, Malte von Bloh. [doi]
• Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion ModelFei Shen, Cong Wang 0018, Junyao Gao 0002, Qin Guo, Jisheng Dang, Jinhui Tang 0001, Tat-Seng Chua. [doi]
• WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal MartingalesDrew Prinster, Xing Han, Anqi Liu, Suchi Saria. [doi]
• Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series ForecastingZhining Liu 0002, Ze Yang, Xiao Lin 0016, Ruizhong Qiu, Tianxin Wei, Yada Zhu, Hendrik F. Hamann, Jingrui He, Hanghang Tong. [doi]
• Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion ModelsYang Zheng, Wen Li, Zhaoqiang Liu. [doi]
• A General Representation-Based Approach to Multi-Source Domain AdaptationIgnavier Ng, Yan Li 0099, Zijian Li 0001, Yujia Zheng 0001, Guangyi Chen 0002, Kun Zhang 0001. [doi]
• Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly DetectionHyungi Kim, Jisoo Mok, Dongjun Lee, Jaihyun Lew, Sungjae Kim, Sungroh Yoon. [doi]
• Neutral residues: revisiting adapters for model extensionFranck Signe Talla, Edouard Grave, Hervé Jégou. [doi]
• DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic SegmentationChangshuo Wang 0001, Xiang Fang, Prayag Tiwari. [doi]
• FourierMamba: Fourier Learning Integration with State Space Models for Image DerainingDong Li 0055, Yidi Liu, Xueyang Fu, Jie Huang 0017, Senyan Xu, Qi Zhu 0010, Zheng-Jun Zha. [doi]
• What Makes a Good Feedforward Computational Graph?Alex Vitvitskyi, João Guilherme Madeira Araújo, Marc Lackenby, Petar Velickovic. [doi]
• SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language ModelsHan-Byul Kim, Duc N. M. Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho. [doi]
• Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy OptimizationZelai Xu, Wanjun Gu, Chao Yu 0005, Yi Wu 0013, Yu Wang 0002. [doi]
• An Asymptotically Optimal Approximation Algorithm for Multiobjective Submodular Maximization at ScaleFabian Christian Spaeh, Atsushi Miyauchi 0001. [doi]
• Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvgLike Jian, Dong Liu. [doi]
• Training Diffusion-based Generative Models with Limited DataZhaoyu Zhang, Yang Hua 0001, Guanxiong Sun, Hui Wang 0001, Seán F. McLoone. [doi]
• SADA: Stability-guided Adaptive Diffusion AccelerationTing Jiang, Yixiao Wang, Hancheng Ye, Zishan Shao, Jingwei Sun 0002, Jingyang Zhang, Zekai Chen, Jianyi Zhang, Yiran Chen 0001, Hai Li 0001. [doi]
• Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task EmbeddingSiyuan Xu, Minghui Zhu. [doi]
• Discovering a Zero (Zero-Vector Class of Machine Learning)Harikrishna Metta, Venkatesh Babu Radhakrishnan. [doi]
• Parameter-Efficient Fine-Tuning of State Space ModelsKevin Galim, Wonjun Kang, Yuchen Zeng, Hyung il Koo, Kangwook Lee 0001. [doi]
• Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix LearningAnkit Pratap Singh, Ahmed Ali Abbasi, Namrata Vaswani. [doi]
• Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block ModelsZhongtian Ma, Qiaosheng Zhang 0002, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang 0004. [doi]
• Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and SufficiencyZexu Sun, Qiyu Han, Hao Yang 0045, Anpeng Wu, Minqin Zhu, Dugang Liu, Chen Ma 0001, Yunpeng Weng, Xing Tang 0007, Xiuqiang He 0001. [doi]
• FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural NetworksLaines Schmalwasser, Niklas Penzel, Joachim Denzler, Julia Niebling. [doi]
• Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and RemediesQiang Li 0017, Michal Yemini, Hoi-To Wai. [doi]
• CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial CorrelationsHaotian Si, Changhua Pei, Jianhui Li, Dan Pei, Gaogang Xie. [doi]
• Federated Node-Level Clustering Network with Cross-Subgraph Link MendingJingxin Liu 0006, Renda Han, Wenxuan Tu, Haotian Wang, Junlong Wu, Jieren Cheng. [doi]
• Contract Design Under Approximate Best ResponsesFrancesco Bacchiocchi, Jiarui Gan, Matteo Castiglioni, Alberto Marchesi 0001, Nicola Gatti 0001. [doi]
• Causal Abstraction Inference under Lossy RepresentationsKevin Muyuan Xia, Elias Bareinboim. [doi]
• Ehrenfeucht-Haussler Rank and Chain of ThoughtPablo Barceló, Alexander Kozachinskiy, Tomasz Steifer. [doi]
• LensLLM: Unveiling Fine-Tuning Dynamics for LLM SelectionXinyue Zeng, Haohui Wang, Junhong Lin, Jun Wu 0019, Tyler Cody, Dawei Zhou 0003. [doi]
• PRIME: Deep Imbalanced Regression with ProxiesJongin Lim 0002, Sucheol Lee, Daeho Um, Sung Un Park, Jinwoo Shin. [doi]
• Schwarz-Schur Involution: Lightspeed Differentiable Sparse Linear SolversYu Wang 0103, S. Mazdak Abulnaga, Yaël Balbastre, Bruce Fischl. [doi]
• Symmetry-Aware GFlowNetsHohyun Kim, SeungGeun Lee, Min-hwan Oh. [doi]
• Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto SpeculationHengyuan Hu, Aniket Das, Dorsa Sadigh, Nima Anari. [doi]
• Measuring In-Context Computation Complexity via Hidden State PredictionVincent Herrmann, Róbert Csordás, Jürgen Schmidhuber. [doi]
• ProSec: Fortifying Code LLMs with Proactive Security AlignmentXiangzhe Xu, Zian Su, Jinyao Guo, Kaiyuan Zhang 0002, Zhenting Wang, Xiangyu Zhang 0001. [doi]
• Actor-Critics Can Achieve Optimal Sample EfficiencyKevin Tan, Wei Fan, Yuting Wei 0001. [doi]
• Robust Offline Reinforcement Learning with Linearly Structured f-Divergence RegularizationCheng Tang, Zhishuai Liu, Pan Xu 0002. [doi]
• Elucidating Flow Matching ODE Dynamics via Data Geometry and DenoisersZhengchao Wan, Qingsong Wang, Gal Mishne, Yusu Wang 0001. [doi]
• Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy DataAnish Acharya, Sujay Sanghavi, Alex Dimakis, Inderjit S. Dhillon. [doi]
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language ModelsQuan Wei 0001, Chung-Yiu Yau, Hoi-To Wai, Yang Zhao, Dongyeop Kang, Youngsuk Park, Mingyi Hong 0001. [doi]
• Rethinking Causal Ranking: A Balanced Perspective on Uplift Model EvaluationMinqin Zhu, Zexu Sun, Ruoxuan Xiong, Anpeng Wu, Baohong Li, Caizhi Tang, Jun Zhou 0011, Fei Wu 0001, Kun Kuang. [doi]
• RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHFXiaomin Li, Mingye Gao, Zhiwei Zhang, Jingxuan Fan, Weiyu Li. [doi]
• Accurate and Efficient World Modeling with Masked Latent TransformersMaxime Burchi, Radu Timofte. [doi]
• Few-Shot Learner Generalizes Across AI-Generated Image DetectionShiyu Wu, Jing Liu, Jing Li, Yequan Wang. [doi]
• Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health PredictionsEray Erturk, Fahad Kamran, Salar Abbaspourazad, Sean Jewell, Harsh Sharma, Yujie Li, Sinead Williamson, Nicholas J. Foti, Joseph Futoma. [doi]
• Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path SimplicesJunhao Dong 0001, Piotr Koniusz, Yifei Zhang, Hao Zhu 0010, Weiming Liu 0005, Xinghua Qu, Yew-Soon Ong. [doi]
• Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient AccumulatorYu Xin Li, Felix Dangel, Derek Tam, Colin Raffel. [doi]
• KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree SearchHaoran Luo 0001, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu 0001, Anh Tuan Luu. [doi]
• Robust Multi-Agent Reinforcement Learning with Stochastic AdversaryZiyuan Zhou, GuanJun Liu, MengChu Zhou, Weiran Guo. [doi]
• Learning to Route LLMs with Confidence TokensYu-Neng Chuang, Prathusha Kameswara Sarma, Parikshit Gopalan, John Boccio, Sara Bolouki, Xia Hu 0001, Helen Zhou. [doi]
• Maintaining Proportional Committees with Dynamic Candidate SetsChris Dong, Jannik Peters 0001. [doi]
• Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics DiscoveryNing Liu, Yue Yu. [doi]
• Primitive Vision: Improving Diagram Understanding in MLLMsShan Zhang 0002, Aotian Chen, Yanpeng Sun, Jindong Gu, Yi Yu Zheng, Piotr Koniusz, Kai Zou, Anton van den Hengel, Yuan Xue. [doi]
• InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information TheoryFeifei Li, Mi Zhang, Zhaoxiang Wang, Min Yang. [doi]
• SToFM: a Multi-scale Foundation Model for Spatial TranscriptomicsSuyuan Zhao, Yizhen Luo, Ganbo Yang, Yan Zhong, Hao Zhou 0012, Zaiqing Nie. [doi]
• Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model LearningAdrià López Escoriza, Nicklas Hansen 0001, Stone Tao, Tongzhou Mu, Hao Su 0001. [doi]
• Demystifying Long Chain-of-Thought ReasoningShiming Yang, Yuxuan Tong, Xinyao Niu, Graham Neubig, Xiang Yue. [doi]
• TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language ModelsKangjie Chen, Muyang Li, Guanlin Li, Shudong Zhang, Shangwei Guo, Tianwei Zhang 0004. [doi]
• FSTLLM: Spatio-Temporal LLM for Few Shot Time Series ForecastingYue Jiang 0005, Yile Chen 0001, Xiucheng Li, Qin Chao, Shuai Liu 0018, Gao Cong. [doi]
• Fair Clustering via AlignmentKunwoong Kim, Jihu Lee, Sangchul Park, Yongdai Kim. [doi]
• One-Pass Feature Evolvable Learning with Theoretical GuaranteesCun-Yuan Xing, Meng-Zhang Qian, Wuyang Chen 0003, Wei Gao 0008, Zhi-Hua Zhou. [doi]
• SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex OptimizationYan Liu, Mingjie Chen, Chaojie Ji, Hao Zhang, Ruxin Wang 0001. [doi]
• Approximating Latent Manifolds in Neural Networks via Vanishing IdealsNico Pelleriti, Max Zimmer, Elias Samuel Wirth, Sebastian Pokutta. [doi]
• BSemiFL: Semi-supervised Federated Learning via a Bayesian ApproachHaozhao Wang, Shengyu Wang, Jiaming Li, Hao Ren 0001, Xingshuo Han, Wenchao Xu 0001, Shangwei Guo, Tianwei Zhang 0004, Ruixuan Li 0001. [doi]
• Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised LearningHao Wang 0049, Zhichao Chen 0001, Haotian Wang 0001, Yanchao Tan, Pan Li 0005, Tianqiao Liu, Xu Chen 0017, Haoxuan Li 0001, Zhouchen Lin. [doi]
• How Do Transformers Learn Variable Binding in Symbolic Programs?Yiwei Wu, Atticus Geiger, Raphaël Millière. [doi]
• Explaining the role of Intrinsic Dimensionality in Adversarial TrainingEnes Altinisik, Safa Messaoud, Husrev Taha Sencar, Hassan Sajjad 0001, Sanjay Chawla. [doi]
• BackSlash: Rate Constrained Optimized Training of Large Language ModelsJun Wu, Jiangtao Wen, Yuxing Han 0001. [doi]
• SEAD: Unsupervised Ensemble of Streaming Anomaly DetectorsSaumya Gaurang Shah, Abishek Sankararaman, Balakrishnan Narayanaswamy, Vikramank Y. Singh. [doi]
• MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free RectificationTianchi Xing, Bonan Li, Congying Han, Xinmin Qiu, Zicheng Zhang, Tiande Guo. [doi]
• A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic ApproachSwetha Ganesh, Washim Uddin Mondal, Vaneet Aggarwal. [doi]
• HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural NetworksJulia Gusak, Xunyi Zhao, Théotime Le Hellard, Zhe Li, Lionel Eyraud-Dubois, Olivier Beaumont. [doi]
• SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song GenerationZihan Liu, Shuangrui Ding, Zhixiong Zhang, Xiaoyi Dong, Pan Zhang 0001, Yuhang Zang, Yuhang Cao, Dahua Lin, Jiaqi Wang 0003. [doi]
• RBench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning EvaluationMeng-Hao Guo, Jiajun Xu, Yi Zhang 0099, Jiaxi Song, Haoyang Peng, Yi-Xuan Deng, Xinzhi Dong, Kiyohiro Nakayama, Zhengyang Geng, Chen Wang 0049, Bolin Ni, Guo-Wei Yang, Yongming Rao, Houwen Peng, Han Hu 0001, Gordon Wetzstein, Shimin Hu 0001. [doi]
• Highly Compressed Tokenizer Can Generate Without TrainingLukas Lao Beyer, Tianhong Li, Xinlei Chen, Sertac Karaman, Kaiming He. [doi]
• Quantifying Treatment Effects: Estimating Risk Ratios via Observational StudiesAhmed Boughdiri, Julie Josse, Erwan Scornet. [doi]
• Calibrating Video Watch-time Predictions with Credible Prototype AlignmentChao Cui, Shisong Tang, Fan Li 0017, Jiechao Gao, Hechang Chen. [doi]
• Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit FeedbackCanzhe Zhao, Yutian Cheng, Jing Dong 0008, Baoxiang Wang 0001, Shuai Li 0010. [doi]
• Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide SequencingYe Du, Chen Yang, Nanxi Yu, Wanyu Lin, Qian Zhao, Shujun Wang. [doi]
• ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language ModelsKangjie Zheng, Junwei Yang, Siyue Liang, Bin Feng, Zequn Liu, Wei Ju 0001, Zhiping Xiao 0001, Ming Zhang 0004. [doi]
• Geometry-Informed Neural NetworksArturs Berzins, Andreas Radler, Eric Volkmann, Sebastian Sanokowski, Sepp Hochreiter, Johannes Brandstetter. [doi]
• Best of Both Worlds: Advantages of Hybrid Graph Sequence ModelsAli Behrouz, Ali Parviz, Mahdi Karami, Clayton Sanford, Bryan Perozzi, Vahab Mirrokni. [doi]
• A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample EstimatorsHan Zhou 0013, Jordy Van Landeghem, Teodora Popordanoska, Matthew B. Blaschko. [doi]
• Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language ModelKaiwen Tang, Zhanglu Yan, Weng-Fai Wong. [doi]
• The Missing Alignment Link of In-context Learning on SequencesHarshvardhan Agarwal, Sunita Sarawagi. [doi]
• Reinforce LLM Reasoning through Multi-Agent ReflectionYurun Yuan, Tengyang Xie. [doi]
• Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language ModelsPeijie Liu, Fengli Xu, Yong Li 0008. [doi]
• Revisiting Continuity of Image Tokens for Cross-domain Few-shot LearningShuai Yi, Yixiong Zou, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• Permutation-Free High-Order Interaction TestsZhaolu Liu, Robert L. Peach, Mauricio Barahona. [doi]
• Learning Joint Interventional Effects from Single-Variable Interventions in Additive ModelsArmin Kekic, Sergio Hernan Garrido Mejia, Bernhard Schölkopf. [doi]
• Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain AdaptationJunyu Luo 0002, Yuhao Tang, Yiwei Fu, Xiao Luo 0001, Zhizhuo Kou, Zhiping Xiao 0001, Wei Ju 0001, Wentao Zhang 0001, Ming Zhang 0004. [doi]
• Compressed Image Generation with Denoising Diffusion Codebook ModelsGuy Ohayon, Hila Manor, Tomer Michaeli, Michael Elad. [doi]
• UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition ConfirmationWangzhi Zhan, Jianpeng Chen, Dongqi Fu, Dawei Zhou 0003. [doi]
• EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous ControlSamuel Holt, Todor Davchev, Dhruva Tirumala, Ben Moran, Atil Iscen, Antoine Laurens, Yixin Lin, Erik Frey, Markus Wulfmeier, Francesco Romano, Nicolas Heess. [doi]
• Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distanceMarta Gentiloni Silveri, Antonio Ocello. [doi]
• Causality Inspired Federated Learning for OOD GeneralizationJiayuan Zhang 0001, Xuefeng Liu 0001, Jianwei Niu 0002, Shaojie Tang 0001, Haotian Yang, Xinghao Wu. [doi]
• The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)Zihao Wang, Yibo Jiang, Jiahao Yu, Heqing Huang. [doi]
• Feature Shift Localization NetworkMíriam Barrabés, Daniel Mas Montserrat, Kapal Dev, Alexander G. Ioannidis. [doi]
• DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt TuningXiaolong Xu 0001, Yibo Zhou, Haolong Xiang, Xiaoyong Li 0002, Xuyun Zhang, Lianyong Qi, Wanchun Dou. [doi]
• Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant MachinesSho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda. [doi]
• An Efficient Private GPT Never Autoregressively DecodesZhengyi Li 0002, Yue Guan 0003, Kang Yang 0002, Yu Feng 0007, Ning Liu, Yu Yu 0001, Jingwen Leng, Minyi Guo. [doi]
• Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained ModelsXuelin Shen, Jiayin Xu, Kangsheng Yin, Wenhan Yang. [doi]
• Implicit Subgraph Neural NetworkYongjian Zhong, Liao Zhu, Hieu Vu, Bijaya Adhikari. [doi]
• AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-NTianyu Zhang, Andrew Robert Williams, Phillip Wozny, Kai-Hendrik Cohrs, Koen Ponse, Marco Jiralerspong, Soham R. Phade, Sunil Srinivasa, Lu Li, Yang Zhang, Prateek Gupta, Erman Acar, Irina Rish, Yoshua Bengio, Stephan Zheng. [doi]
• Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time SeriesZachary C. Brown, David Carlson. [doi]
• Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and UnderreachingFederico Errica, Henrik Christiansen, Viktor Zaverkin, Takashi Maruyama, Mathias Niepert, Francesco Alesiani. [doi]
• Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare ClassesXuetong Li, Danyang Huang, Hansheng Wang 0002. [doi]
• On the Guidance of Flow MatchingRuiqi Feng, Chenglei Yu, Wenhao Deng 0001, Peiyan Hu, Tailin Wu. [doi]
• Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text SystemsTaejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, He Huang 0012, Nithin Rao Koluguri, Krishna C. Puvvada, Jagadeesh Balam, Boris Ginsburg. [doi]
• Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language ModelsLinhao Luo, ZiCheng Zhao, Gholamreza Haffari, Yuan-Fang Li, Chen Gong 0002, Shirui Pan. [doi]
• Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal SparsityHaocheng Xi, Shuo Yang, Yilong Zhao, Chenfeng Xu, Muyang Li, Xiuyu Li, Yujun Lin 0001, Han Cai, Jintao Zhang, Dacheng Li, Jianfei Chen 0001, Ion Stoica, Kurt Keutzer, Song Han 0003. [doi]
• Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse LayoutsGengluo Li, Huawen Shen, Yu Zhou 0015. [doi]
• EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided MutationJi Deng, Zhao Li, Ji Zhang, Jun Gao. [doi]
• Online Sparsification of Bipartite-Like Clusters in GraphsJoyentanuj Das, Suranjan De, He Sun. [doi]
• Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement LearningWenhao Zhao, Qiushui Xu, Linjie Xu, Lei Song 0001, Jinyu Wang, Chunlai Zhou, Jiang Bian 0002. [doi]
• Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism DesignVikram Kher, Manolis Zampetakis. [doi]
• GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement LearningHaoyuan Qin, Zhengzhu Liu, Chenxing Lin, Chennan Ma, Songzhu Mei, Siqi Shen, Cheng Wang 0003. [doi]
• Bayesian Optimization from Human Feedback: Near-Optimal Regret BoundsAya Kayal, Sattar Vakili, Laura Toni, Da-shan Shiu, Alberto Bernacchia. [doi]
• GraphGPT: Generative Pre-trained Graph Eulerian TransformerQifang Zhao, Weidong Ren, Tianyu Li 0007, Hong Liu, Xingsheng He, Xiaoxiao Xu. [doi]
• Finite-Time Analysis of Discrete-Time Stochastic InterpolantsYuhao Liu, Yu Chen 0074, Rui Hu, Longbo Huang. [doi]
• Partially Observable Reinforcement Learning with Memory TracesOnno Eberhard, Michael Muehlebach, Claire Vernade. [doi]
• EVOLvE: Evaluating and Optimizing LLMs For In-Context ExplorationAllen Nie, Yi Su 0008, Bo Chang 0002, Jonathan Lee 0002, Ed H. Chi, Quoc V. Le, Minmin Chen. [doi]
• LoRA-Gen: Specializing Large Language Model via Online LoRA GenerationYicheng Xiao, Lin Song 0002, Rui Yan 0001, Cheng Cheng, Yixiao Ge, Xiu Li 0001, Ying Shan. [doi]
• Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and MoreGeonhui Yoo, Minhak Song, Chulhee Yun. [doi]
• Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length GeneralizationErmo Hua, Che Jiang, Xingtai Lv, Kaiyan Zhang, Youbang Sun, Yuchen Fan, Xuekai Zhu, Biqing Qi, Ning Ding 0002, Bowen Zhou 0002. [doi]
• Subgroups Matter for Robust Bias MitigationAnissa Alloula, Charles Jones, Ben Glocker, Bartlomiej W. Papiez. [doi]
• The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit FeedbackCôme Fiegel, Pierre Ménard, Tadashi Kozuno, Michal Valko, Vianney Perchet. [doi]
• Synonymous Variational Inference for Perceptual Image CompressionZijian Liang, Kai Niu 0001, Changshuo Wang 0005, Jin Xu 0001, Ping Zhang 0003. [doi]
• Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholdsEmanuele Troiani, Hugo Cui, Yatin Dandi, Florent Krzakala, Lenka Zdeborová. [doi]
• FlipAttack: Jailbreak LLMs via FlippingYue Liu 0008, Xiaoxin He, Miao Xiong, JinLan Fu, Shumin Deng, Yingwei Ma, Jiaheng Zhang, Bryan Hooi. [doi]
• A Machine Learning Approach to Duality in Statistical PhysicsPrateek Gupta, Andrea E. V. Ferrari, Nabil Iqbal. [doi]
• TypyBench: Evaluating LLM Type Inference for Untyped Python RepositoriesHonghua Dong, Jiacheng Yang, Xun Deng, Yuhe Jiang, Gennady Pekhimenko, Fan Long, Xujie Si. [doi]
• Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed TreesTomer Meir, Uri Shalit, Malka Gorfine. [doi]
• Scaling Laws for Differentially Private Language ModelsRyan Mckenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar 0001, Ruibo Liu, Da Yu, Chiyuan Zhang. [doi]
• Learning Soft Sparse Shapes for Efficient Time-Series ClassificationZhen Liu 0023, Yicheng Luo, Boyuan Li, Emadeldeen Eldele, Min Wu 0008, Qianli Ma 0001. [doi]
• Enhancing Spectral GNNs: From Topology and Perturbation PerspectivesTaoyang Qin, Ke-Jia Chen 0001, Zheng Liu 0001. [doi]
• ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-k-Cut ProblemsYeqing Qiu, Ye Xue, Akang Wang, Yiheng Wang, Qingjiang Shi, Zhi-Quan Luo. [doi]
• Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent DistributionsYuya Hikima, Hiroshi Sawada, Akinori Fujino. [doi]
• Optimization Proxies using Limited Labeled Data and Training Time - A Semi-Supervised Bayesian Neural Network ApproachParikshit Pareek, Abhijith Jayakumar, Kaarthik Sundar, Sidhant Misra, Deepjyoti Deka. [doi]
• Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake DetectionPeipeng Yu, Jianwei Fei, Hui Gao, Xuan Feng 0002, Zhihua Xia, Chip-Hong Chang. [doi]
• GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory PredictionMuleilan Pei, Shaoshuai Shi, Lu Zhang 0047, Peiliang Li 0001, Shaojie Shen. [doi]
• Upcycling Text-to-Image Diffusion Models for Multi-Task CapabilitiesRuchika Chavhan, Abhinav Mehrotra, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Luca Morreale, Mehdi Noroozi, Sourav Bhattacharya. [doi]
• Eliciting Language Model Behaviors with Investigator AgentsXiang Lisa Li, Neil Chowdhury, Daniel D. Johnson 0001, Tatsunori Hashimoto, Percy Liang, Sarah Schwettmann, Jacob Steinhardt. [doi]
• Multiple-policy Evaluation via Density EstimationYilei Chen, Aldo Pacchiano, Ioannis Paschalidis. [doi]
• Galileo: Learning Global & Local Features of Many Remote Sensing ModalitiesGabriel Tseng, Anthony Fuller, Marlena Reil, Henry Herzog, Patrick Beukema, Favyen Bastani, James R. Green, Evan Shelhamer, Hannah Kerner, David Rolnick. [doi]
• Diffusion on Language Model Encodings for Protein Sequence GenerationViacheslav Meshchaninov, Pavel V. Strashnov, Andrey Shevtsov, Fedor Nikolaev, Nikita Ivanisenko, Olga L. Kardymon, Dmitry P. Vetrov. [doi]
• Programming Every Example: Lifting Pre-training Data Quality Like Experts at ScaleFan Zhou, Zengzhi Wang, Qian Liu, Junlong Li, Pengfei Liu 0003. [doi]
• MuseControlLite: Multifunctional Music Generation with Lightweight ConditionersFang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, Yi-Hsuan Yang. [doi]
• InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic PerspectiveYuanhong Zhang, Muyao Yuan, Weizhan Zhang, Tieliang Gong, Wen Wen, Jiangyong Ying, Weijie Shi. [doi]
• Preference Controllable Reinforcement Learning with Advanced Multi-Objective OptimizationYucheng Yang, Tianyi Zhou 0001, Mykola Pechenizkiy, Meng Fang. [doi]
• Capturing Temporal Dynamics in Large-Scale Canopy Tree Height EstimationJan Pauls, Max Zimmer, Berkant Turan, Sassan Saatchi, Philippe Ciais, Sebastian Pokutta, Fabian Gieseke. [doi]
• Open-Det: An Efficient Learning Framework for Open-Ended DetectionGuiping Cao, Tao Wang, Wenjian Huang 0001, Xiangyuan Lan, Jianguo Zhang 0001, Dongmei Jiang. [doi]
• Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking CalculationZecheng Hao, Qichao Ma, Kang Chen, Yi Zhang, Zhaofei Yu, Tiejun Huang 0003. [doi]
• Differential Coding for Training-Free ANN-to-SNN ConversionZihan Huang, Wei Fang 0006, Tong Bu, Peng Xue, Zecheng Hao, Wenxuan Liu 0008, Yuanhong Tang, Zhaofei Yu, Tiejun Huang 0001. [doi]
• Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion ModelsJiachen Yang, Yusong Wang, Yanmei Fang, Yunshu Dai, Fangjun Huang. [doi]
• Adversaries Can Misuse Combinations of Safe ModelsErik Jones, Anca D. Dragan, Jacob Steinhardt. [doi]
• Collapse-Proof Non-Contrastive Self-Supervised LearningEmanuele Sansone, Tim Lebailly, Tinne Tuytelaars. [doi]
• Learning the RoPEs: Better 2D and 3D Position Encodings with STRINGConnor Schenck, Isaac Reid, Mithun George Jacob, Alex Bewley, Joshua Ainslie, David Rendleman, Deepali Jain, Mohit Sharma 0001, Kumar Avinava Dubey, Ayzaan Wahid, Sumeet Singh, René Wagner, Tianli Ding, Chuyuan Fu, Arunkumar Byravan, Jake Varley, Alexey A. Gritsenko, Matthias Minderer, Dmitry Kalashnikov, Jonathan Tompson, Vikas Sindhwani, Krzysztof Marcin Choromanski. [doi]
• MP-Nav: Enhancing Data Poisoning Attacks against Multimodal LearningJingfeng Zhang, Prashanth Krishnamurthy, Naman Patel, Anthony Tzes, Farshad Khorrami. [doi]
• AdaDecode: Accelerating LLM Decoding with Adaptive Layer ParallelismZhepei Wei, Wei-Lin Chen, Xinyu Zhu, Yu Meng 0001. [doi]
• Don't Restart, Just Reuse: Reoptimizing MILPs with Dynamic ParametersSijia Zhang, Shuli Zeng, Shaoang Li, Feng Wu 0001, Shaojie Tang 0001, Xiangyang Li 0001. [doi]
• MGD3 : Mode-Guided Dataset Distillation using Diffusion ModelsJeffrey A. Chan-Santiago, Praveen Tirupattur, Gaurav Kumar Nayak, Gaowen Liu, Mubarak Shah. [doi]
• TokenSwift: Lossless Acceleration of Ultra Long Sequence GenerationTong Wu, Junzhe Shen, Zixia Jia, Yuxuan Wang 0004, Zilong Zheng. [doi]
• Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language ModelsZahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu. [doi]
• Implicit Bias of Gradient Descent for Non-Homogeneous Deep NetworksYuhang Cai, Kangjie Zhou, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett. [doi]
• Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel ManifoldYilong Song, Peijin Li, Bin Gao, Kun Yuan. [doi]
• Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-ParameterizationSimone Bombari, Marco Mondelli. [doi]
• AssistanceZero: Scalably Solving Assistance GamesCassidy Laidlaw, Eli Bronstein, Timothy Guo, Dylan Feng, Lukas Berglund, Justin Svegliato, Stuart Russell 0001, Anca D. Dragan. [doi]
• AffinityFlow: Guided Flows for Antibody Affinity MaturationCan Chen, Karla-Luise Herpoldt, Chenchao Zhao, Zichen Wang, Marcus D. Collins, Shang Shang, Ron Benson. [doi]
• Counterfactual Graphical Models: Constraints and InferenceJuan D. Correa, Elias Bareinboim. [doi]
• Learning Safety Constraints for Large Language ModelsXin Chen, Yarden As, Andreas Krause 0001. [doi]
• Hardware and Software Platform InferenceCheng Zhang, Hanna Foerster, Robert D. Mullins, Yiren Zhao, Ilia Shumailov. [doi]
• Large Language Models are Demonstration Pre-Selectors for ThemselvesJiarui Jin, Yuwei Wu, Haoxuan Li 0001, Xiaoting He, Weinan Zhang 0001, Yiming Yang, Yong Yu 0001, Jun Wang 0012, Mengyue Yang. [doi]
• H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained ModelsRushuang Zhou, Yuanting Zhang, Yining Dong. [doi]
• Principal-Agent Bandit Games with Self-Interested and Exploratory Learning AgentsJunyan Liu, Lillian J. Ratliff. [doi]
• Lightweight-Mark: Rethinking Deep Learning-Based WatermarkingYupeng Qiu, Han Fang, Ee-Chien Chang. [doi]
• Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher SamplingWalid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Théo Bontempelli, Thomas Bouabça, Tristan Cazenave. [doi]
• On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed LearningYi-Rui Yang, Chang-Wei Shi, Wu-Jun Li. [doi]
• Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask OptimizationXiuyuan Wang, Chaochao Chen 0001, Weiming Liu 0005, Xinting Liao, Fan Wang 0020, Xiaolin Zheng. [doi]
• UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image GenerationQin Guo, Ailing Zeng, Dongxu Yue, Ceyuan Yang, Yang Cao 0017, Hanzhong Guo, Fei Shen, Wei Liu 0005, Xihui Liu, Dan Xu 0002. [doi]
• Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication OptimizationGuopeng Lin, Ruisheng Zhou, Shuyu Chen, Weili Han, Jin Tan, Wenjing Fang, Lei Wang, Tao Wei. [doi]
• Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsJan Betley, Daniel Chee Hian Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, Owain Evans. [doi]
• Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?Yujin Han, Andi Han, Wei Huang, Chaochao Lu, Difan Zou. [doi]
• Mixed-curvature decision trees and random forestsPhilippe Chlenski, Quentin Chu, Raiyan R. Khan, Kaizhu Du, Antonio Khalil Moretti, Itsik Pe'er. [doi]
• An Analysis for Reasoning Bias of Language Models with Small InitializationJunjie Yao, Zhongwang Zhang, Zhi-Qin John Xu. [doi]
• S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object TrackingTao Tang, Lijun Zhou, Pengkun Hao, Zihang He, Kalok Ho, Shuo Gu, Zhihui Hao, Haiyang Sun, Kun Zhan, Peng Jia, Xianpeng Lang, Xiaodan Liang. [doi]
• Transolver++: An Accurate Neural Solver for PDEs on Million-Scale GeometriesHuakun Luo, Haixu Wu, Hang Zhou, Lanxiang Xing, Yichen Di, Jianmin Wang 0001, Mingsheng Long. [doi]
• Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View LearningXue Zhao, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye 0001. [doi]
• The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-TrainingJinbo Wang 0003, Mingze Wang, Zhanpeng Zhou, Junchi Yan, Weinan E, Lei Wu. [doi]
• Perceptually Constrained Precipitation Nowcasting ModelWenzhi Feng, Xutao Li 0003, Zhe Wu 0006, Kenghong Lin, Demin Yu, Yunming Ye, Yaowei Wang 0001. [doi]
• LASER: Attention with Exponential TransformationSai Surya Duvvuri, Inderjit S. Dhillon. [doi]
• GenZSL: Generative Zero-Shot Learning Via Inductive Variational AutoencoderShiming Chen 0002, Dingjie Fu, Salman Khan 0001, Fahad Shahbaz Khan. [doi]
• RollingQ: Reviving the Cooperation Dynamics in Multimodal TransformerHaotian Ni, Yake Wei, Hang Liu, Gong Chen, Chong Peng, Hao Lin, Di Hu 0001. [doi]
• Subobject-level Image TokenizationDelong Chen, Samuel Cahyawijaya, Jianfeng Liu 0002, Baoyuan Wang, Pascale Fung. [doi]
• Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General SetEnming Liang, Minghua Chen 0001. [doi]
• Reward-Guided Speculative Decoding for Efficient LLM ReasoningBaohao Liao, Yuhui Xu, Hanze Dong, Junnan Li 0001, Christof Monz, Silvio Savarese, Doyen Sahoo, Caiming Xiong. [doi]
• Metadata Conditioning Accelerates Language Model Pre-trainingTianyu Gao 0001, Alexander Wettig, Luxi He, Yihe Dong, Sadhika Malladi, Danqi Chen 0001. [doi]
• On the Adversarial Robustness of Multi-Kernel ClusteringHao Yu 0017, Weixuan Liang, Ke Liang 0006, Suyuan Liu, Meng Liu 0014, Xinwang Liu 0002. [doi]
• Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-TuningChangsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu 0001. [doi]
• On Fine-Grained Distinct Element EstimationIlias Diakonikolas, Daniel Kane 0001, Jasper C. H. Lee, Thanasis Pittas, David P. Woodruff, Samson Zhou. [doi]
• C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented GenerationGuoxin Chen, Minpeng Liao, Peiying Yu, Dingmin Wang, Zile Qiao, Chao Yang, Xin Zhao 0018, Kai Fan 0002. [doi]
• Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving TestingHan Jiang 0007, Xiaoyuan Yi, Zhihua Wei 0001, Ziang Xiao, Shu Wang, Xing Xie 0001. [doi]
• FlexTok: Resampling Images into 1D Token Sequences of Flexible LengthRoman Bachmann 0001, Jesse Allardice, David Mizrahi, Enrico Fini, Oguzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan. [doi]
• Joker: Joint Optimization Framework for Lightweight Kernel MachinesJunhong Zhang, Zhihui Lai 0001. [doi]
• Robust Noise Attenuation via Adaptive Pooling of Transformer OutputsGreyson Brothers. [doi]
• ML2-GCL: Manifold Learning Inspired Lightweight Graph Contrastive LearningJianqing Liang, Zhiqiang Li, Xinkai Wei, Yuan Liu, Zhiqiang Wang 0005. [doi]
• Learning Optimal Multimodal Information Bottleneck RepresentationsQilong Wu, Yiyang Shao, Jun Wang 0018, Xiaobo Sun. [doi]
• Aligning Spoken Dialogue Models from User InteractionsAnne Wu, Laurent Mazaré, Neil Zeghidour, Alexandre Défossez. [doi]
• Off-Policy Evaluation under Nonignorable Missing DataHan Wang, Yang Xu 0089, Wenbin Lu, Rui Song 0006. [doi]
• Self-cross Feature based Spiking Neural Networks for Efficient Few-shot LearningQi Xu 0008, Junyang Zhu, Dongdong Zhou, Hao Chen, Yang Liu, Jiangrong Shen, Qiang Zhang 0008. [doi]
• Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language ModelsTianjie Ju, Yi-Hua, Hao Fei 0001, Zhenyu Shao, Yubin Zheng, Haodong Zhao, Mong-Li Lee, Wynne Hsu, Zhuosheng Zhang 0001, Gongshen Liu. [doi]
• CTBench: A Library and Benchmark for Certified TrainingYuhao Mao, Stefan Balauca, Martin T. Vechev. [doi]
• Posterior Inference with Diffusion Models for High-dimensional Black-box OptimizationTaeyoung Yun, Kiyoung Om, Jaewoo Lee, Sujin Yun, Jinkyoo Park. [doi]
• Improved and Oracle-Efficient Online ℓ1-MulticalibrationRohan Ghuge, Vidya Muthukumar, Sahil Singla 0001. [doi]
• Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-SearchZiyad Benomar, Lorenzo Croissant, Vianney Perchet, Spyros Angelopoulos 0001. [doi]
• Data Mixing Optimization for Supervised Fine-Tuning of Large Language ModelsYuan Li 0032, Zhengzhong Liu 0001, Eric P. Xing. [doi]
• Ultra-Resolution Adaptation with EaseRuonan Yu, Songhua Liu, Zhenxiong Tan, Xinchao Wang. [doi]
• Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution ShiftsHaoyang Li 0001, Xin Wang 0019, Xueling Zhu, Weigao Wen, Wenwu Zhu 0001. [doi]
• DriveGPT: Scaling Autoregressive Behavior Models for DrivingXin Huang, Eric M. Wolff, Paul Vernaza, Tung Phan-Minh, Hongge Chen, David S. Hayden, Mark Edmonds, Brian Pierce, Xinxin Chen, Pratik Elias Jacob, Xiaobai Chen, Chingiz Tairbekov, Pratik Agarwal, Tianshi Gao, Yuning Chai, Siddhartha S. Srinivasa. [doi]
• TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular DataHengrui Zhang, Liancheng Fang, Qitian Wu, Philip S. Yu. [doi]
• Learning Latent Graph Structures and their UncertaintyAlessandro Manenti, Daniele Zambon, Cesare Alippi. [doi]
• Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMsSagnik Mukherjee, Abhinav Chinta, Takyoung Kim, Tarun Anoop Sharma, Dilek Hakkani-Tur. [doi]
• Relational Conformal Prediction for Correlated Time SeriesAndrea Cini, Alexander Jenkins, Danilo P. Mandic, Cesare Alippi, Filippo Maria Bianchi. [doi]
• Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering PerspectiveHechuan Wen, Tong Chen 0005, Mingming Gong, Li Kheng Chai, Shazia Sadiq, Hongzhi Yin. [doi]
• Compute or Load KV Cache? Why Not Both?Shuowei Jin, Xueshen Liu, Qingzhao Zhang, Zhuoqing Mao 0001. [doi]
• Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality MetricsAleksandr Gushchin, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Anna Chistyakova, Sergey Lavrushkin, Bader Rasheed, Kirill Malyshev, Dmitriy S. Vatolin, Anastasia Antsiferova. [doi]
• KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series AnalysisHanru Bai, Weiyang Ding. [doi]
• How Transformers Learn Structured Data: Insights From Hierarchical FilteringJerome Garnier-Brun, Marc Mézard, Emanuele Moscato, Luca Saglietti. [doi]
• Principled Algorithms for Optimizing Generalized Metrics in Binary ClassificationAnqi Mao, Mehryar Mohri, Yutao Zhong 0002. [doi]
• Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement LearningLaixi Shi, Jingchu Gai, Eric Mazumdar, Yuejie Chi, Adam Wierman. [doi]
• PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field ReconstructionLiMing Shen, Liang Deng, Chongke Bi, Yu Wang, Xinhai Chen, Yueqing Wang, Jie Liu. [doi]
• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax AttentionJianliang He, Xintian Pan, Siyu Chen, Zhuoran Yang. [doi]
• FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision MakingYucen Wang, Rui Yu, Shenghua Wan, Le Gan, De-Chuan Zhan. [doi]
• Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite AttacksYixin Cheng, Hongcheng Guo, Yangming Li, Leonid Sigal. [doi]
• Cooperation of Experts: Fusing Heterogeneous Information with Large MarginShuo Wang, Shunyang Huang, Jinghui Yuan, Zhixiang Shen, Zhao Kang 0001. [doi]
• Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate FactorizationChenbei Lu, Laixi Shi, Zaiwei Chen, Chenye Wu, Adam Wierman. [doi]
• SSHR: More Secure Generative Steganography with High-Quality Revealed Secret ImagesJiannian Wang, Yao Lu 0008, Guangming Lu 0002. [doi]
• SHE: Streaming-media Hashing RetrievalRuitao Pu, Yang Qin, Xiaomin Song, Dezhong Peng, Zhenwen Ren, Yuan Sun 0016. [doi]
• Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle StructuresDongzhe Zheng, Wenjie Mei. [doi]
• Consensus Is All You Get: The Role of Attention in TransformersÁlvaro Rodríguez Abella, João Pedro Silvestre, Paulo Tabuada. [doi]
• Learning-Augmented Hierarchical ClusteringVladimir Braverman, Jon C. Ergun, Chen Wang 0027, Samson Zhou. [doi]
• Self-Consistency Preference OptimizationArchiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu 0014, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason E. Weston, Jane Yu 0001. [doi]
• Model Immunization from a Condition Number PerspectiveAmber Yijia Zheng, Site Bai, Brian Bullins, Raymond A. Yeh. [doi]
• Phase transitions for the existence of unregularized M-estimators in single index modelsTakuya Koriyama, Pierre C. Bellec. [doi]
• Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language ModelsSaketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong 0002, Nael B. Abu-Ghazaleh, Amit Roy-Chowdhury 0001. [doi]
• From Language Models over Tokens to Language Models over CharactersTim Vieira, Benjamin LeBrun, Mario Giulianelli, Juan Luis Gastaldi, Brian DuSell, John Terilla, Timothy J. O'Donnell, Ryan Cotterell. [doi]
• Towards a Unified Framework of Clustering-based Anomaly DetectionZeyu Fang, Ming Gu 0014, Sheng Zhou 0004, Jiawei Chen 0007, Qiaoyu Tan, Haishuai Wang, Jiajun Bu. [doi]
• Rhomboid Tiling for Geometric Graph Deep LearningYipeng Zhang, Longlong Li, Kelin Xia. [doi]
• Vision-Language Model Selection and Reuse for Downstream AdaptationHao-Zhe Tan, Zhi Zhou 0007, Yufeng Li 0008, Lan-Zhe Guo. [doi]
• Global Context-aware Representation Learning for Spatially Resolved TranscriptomicsYunhak Oh, Junseok Lee 0002, Yeongmin Kim, Sangwoo Seo, Namkyeong Lee, Chanyoung Park 0001. [doi]
• RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive LearningYuanhuiyi Lyu, Xu Zheng 0002, Lutao Jiang, Yibo Yan, Xin Zou 0001, Huiyu Zhou 0005, Linfeng Zhang 0001, Xuming Hu. [doi]
• Contextual Optimization Under Model Misspecification: A Tractable and Generalizable ApproachOmar Bennouna, Jiawei Zhang 0007, Saurabh Amin, Asuman E. Ozdaglar. [doi]
• DCBM: Data-Efficient Visual Concept Bottleneck ModelsKatharina Prasse, Patrick Knab, Sascha Marton, Christian Bartelt, Margret Keuper. [doi]
• Improving Multi-Class Calibration through Normalization-Aware Isotonic TechniquesAlon Arad, Saharon Rosset. [doi]
• Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series ModelingTianyu Liu, Kai Sun, Fuchun Sun 0001, Yu Luo, Yuanlong Zhang. [doi]
• Layer by Layer: Uncovering Hidden Representations in Language ModelsOscar Skean, Md Rifat Arefin, Dan Zhao, Niket Patel, Jalal Naghiyev, Yann LeCun, Ravid Shwartz-Ziv. [doi]
• Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot ManipulationShuanghao Bai, Wanqi Zhou, Pengxiang Ding, Wei Zhao, Donglin Wang, Badong Chen. [doi]
• Towards Understanding Parametric Generalized Category Discovery on GraphsBowen Deng 0002, Lele Fu, Jialong Chen, Sheng Huang, Tianchi Liao, Zhang Tao, Chuan Chen 0001. [doi]
• Improving Soft Unification with Knowledge Graph Embedding MethodsXuanming Cui, Chionh Wei Peng, Adriel Kuek, Ser-Nam Lim. [doi]
• KEA: Keeping Exploration Alive by Proactively Coordinating Exploration StrategiesShih-Min Yang, Martin Magnusson 0002, Johannes A. Stork, Todor Stoyanov. [doi]
• Protein Structure Tokenization: Benchmarking and New RecipeXinyu Yuan, Zichen Wang 0002, Marcus D. Collins, Huzefa Rangwala. [doi]
• Learning Safe Strategies for Value Maximizing Buyers in Uniform Price AuctionsNegin Golrezaei, Sourav Sahoo 0001. [doi]
• Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect TheoryMason O. Smith, Wenlong Zhang. [doi]
• Average Certified Radius is a Poor Metric for Randomized SmoothingChenhao Sun, Yuhao Mao, Mark Niklas Müller, Martin T. Vechev. [doi]
• DiffMS: Diffusion Generation of Molecules Conditioned on Mass SpectraMontgomery Bohde, Mrunali Manjrekar, Runzhong Wang, Shuiwang Ji, Connor W. Coley. [doi]
• SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory GenerationYuqi Fan 0003, Zhiyong Cui, Zhenning Li 0001, Yilong Ren, Haiyang Yu 0002. [doi]
• How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit BiasRuiquan Huang, Yingbin Liang, Jing Yang 0002. [doi]
• Investigating the Overlooked Hessian Structure: From CNNs to LLMsQian-Yuan Tang 0001, Yufei Gu, Yunfeng Cai, Mingming Sun 0001, Ping Li 0001, Zhou Xun, Zeke Xie. [doi]
• A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network ParameterizationsAntoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval. [doi]
• Language Models as Implicit Tree SearchZiliang Chen 0001, Zhao-Rong Lai, Yufeng Yang, Liangda Fang, Zhanfu Yang, Liang Lin. [doi]
• Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise CancellationRoie Reshef, Kfir Yehuda Levy. [doi]
• Tracking Most Significant Shifts in Infinite-Armed BanditsJoe Suk, Jung Hun Kim. [doi]
• Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute MappingGuangyi Liu, Suzan Iloglu, Michael Caldara, Joseph W. Durham, Michael M. Zavlanos. [doi]
• KIND: Knowledge Integration and Diversion for Training Decomposable ModelsYucheng Xie, Fu Feng, Ruixiao Shi, Jing Wang 0113, Yong Rui, Xin Geng 0001. [doi]
• Are LLMs Prescient? A Continuous Evaluation using Daily News as the OracleHui Dai, Ryan Teehan, Mengye Ren. [doi]
• Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and InferenceShuqing Luo, Pingzhi Li, Jie Peng 0002, Yang Zhao 0013, Yu Cao, Yu Cheng 0001, Tianlong Chen 0001. [doi]
• Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial OptimizationRobbert Reijnen, Yaoxin Wu, Zaharah Bukhsh, Yingqian Zhang 0001. [doi]
• Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of ExpertsMarta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian, Roberto Bondesan, Alán Aspuru-Guzik, Arnaud Doucet, Rob Brekelmans, Alexander Tong 0001, Kirill Neklyudov. [doi]
• High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context DistributionsRuiyuan Huang, Zengfeng Huang. [doi]
• OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization ModelingHongliang Lu, Zhonglin Xie, Yaoyu Wu, Can Ren, Yuxuan Chen, Zaiwen Wen. [doi]
• Regularized Langevin Dynamics for Combinatorial OptimizationShengyu Feng, Yiming Yang 0002. [doi]
• SPEX: Scaling Feature Interaction Explanations for LLMsJustin Singh Kang, Landon Butler, Abhineet Agarwal, Yigit Efe Erginbas, Ramtin Pedarsani, Bin Yu 0001, Kannan Ramchandran. [doi]
• Positional Encoding meets Persistent Homology on GraphsYogesh Verma, Amauri H. Souza, Vikas K. Garg 0001. [doi]
• Bayesian Active Learning for Bivariate Causal DiscoveryYuxuan Wang 0005, Mingzhou Liu 0001, Xinwei Sun 0001, Wei Wang 0115, Yizhou Wang 0001. [doi]
• Elucidating the Design Space of Multimodal Protein Language ModelsCheng-Yen Hsieh, Xinyou Wang, Daiheng Zhang, Dongyu Xue, Fei Ye, Shujian Huang, Zaixiang Zheng, Quanquan Gu. [doi]
• Improving Compositional Generation with Diffusion Models Using Lift ScoresChenning Yu, Sicun Gao. [doi]
• Extractive Structures Learned in Pretraining Enable Generalization on Finetuned FactsJiahai Feng, Stuart Russell 0001, Jacob Steinhardt. [doi]
• Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task VectorsRunxi Cheng, Feng Xiong, Yongxian Wei, Wanyun Zhu, Chun Yuan. [doi]
• Grokking Beyond the Euclidean Norm of Model ParametersPascal Tikeng Notsawo Jr., Guillaume Dumas, Guillaume Rabusseau. [doi]
• Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial FeedbackQiwei Di, Jiafan He, Quanquan Gu. [doi]
• Distributed Event-Based Learning via ADMMGüner Dilsad Er, Sebastian Trimpe, Michael Muehlebach. [doi]
• On Volume Minimization in Conformal RegressionBatiste Le Bars, Pierre Humbert. [doi]
• CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language ModelsLanyun Zhu, Deyi Ji, Tianrun Chen, Haiyang Wu, De Wen Soh, Jun Liu 0036. [doi]
• Telling Peer Direct Effects from Indirect Effects in Observational Network DataXiaojing Du, Jiuyong Li, Debo Cheng, Lin Liu 0003, Wentao Gao, Xiongren Chen, Ziqi Xu 0001. [doi]
• MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity GuidanceZhixuan Chen, Xing Hu 0010, Dawei Yang, Zukang Xu, Chen Xu, Zhihang Yuan, Sifan Zhou, Jiangyong Yu. [doi]
• Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement LearningAustin A. Nguyen, Anri Gu, Michael P. Wellman. [doi]
• R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-ExpertsZhongyang Li, Ziyue Li, Tianyi Zhou 0001. [doi]
• Relative Error Fair Clustering in the Weak-Strong Oracle ModelVladimir Braverman, Prathamesh Dharangutte, Shaofeng H.-C. Jiang, Hoai An Nguyen, Chen Wang 0027, Yubo Zhang, Samson Zhou. [doi]
• Learning Dynamics in Continual Pre-Training for Large Language ModelsXingjin Wang, Howe Tissue, Lu Wang, Linjing Li, Daniel Dajun Zeng. [doi]
• Embedding Safety into RL: A New Take on Trust Region MethodsNikola Milosevic, Johannes Müller, Nico Scherf. [doi]
• Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and ConvergenceYinbin Han, Meisam Razaviyayn, Renyuan Xu. [doi]
• Hidden No More: Attacking and Defending Private Third-Party LLM InferenceRahul Krishna Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal. [doi]
• Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield PredictionAnkit Ghosh, Gargee Kashyap, Sarthak Mittal, Nupur Jain, Raghavan B. Sunoj, Abir De. [doi]
• Policy Filtration for RLHF to Mitigate Noise in Reward ModelsChuheng Zhang, Wei Shen 0005, Li Zhao 0007, Xuyun Zhang, Xiaolong Xu 0001, Wanchun Dou, Jiang Bian 0002. [doi]
• On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training DynamicsBinghui Li, Yuanzhi Li. [doi]
• Graph4MM: Weaving Multimodal Learning with Structural InformationXuying Ning, Dongqi Fu, Tianxin Wei, Wujiang Xu, Jingrui He. [doi]
• Contradiction Retrieval via Contrastive Learning with SparsityHaike Xu, Zongyu Lin, Kai-Wei Chang, Yizhou Sun, Piotr Indyk. [doi]
• Online Robust Reinforcement Learning Through Monte-Carlo PlanningTuan Dam, Kishan Panaganti, Brahim Driss, Adam Wierman. [doi]
• Sampling Binary Data by Denoising through Score FunctionsFrancis Bach 0001, Saeed Saremi. [doi]
• MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-DesignHaojie Duanmu, Xiuhong Li, Zhihang Yuan, Size Zheng 0001, Jiangfei Duan, Xingcheng Zhang, Dahua Lin. [doi]
• Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language ModelsYinhong Liu, Zhijiang Guo, Tianya Liang, Ehsan Shareghi, Ivan Vulic, Nigel Collier. [doi]
• On Learning Parallel Pancakes with Mostly Uniform WeightsIlias Diakonikolas, Daniel Kane 0001, Sushrut Karmalkar, Jasper C. H. Lee, Thanasis Pittas. [doi]
• Efficient Core-set Selection for Deep Learning Through Squared Loss MinimizationJianting Chen. [doi]
• Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded ActivationsDavide Sartor, Alberto Sinigaglia, Gian Antonio Susto. [doi]
• Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean DatasetsWei Liu 0144, Zhongyu Niu, Lang Gao, Zhiying Deng, Jun Wang 0018, Haozhao Wang, Ruixuan Li 0001. [doi]
• Origin Identification for Text-Guided Image-to-Image Diffusion ModelsWenhao Wang, Yifan Sun 0003, Zongxin Yang, Zhentao Tan, Zhengdong Hu, Yi Yang 0001. [doi]
• Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning AttackTiansheng Huang, Gautam Bhattacharya, Pratik Joshi, Joshua Kimball, Ling Liu 0001. [doi]
• Linearization Turns Neural Operators into Function-Valued Gaussian ProcessesEmilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig. [doi]
• Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridgeRahul Choudhary, Hanbaek Lyu. [doi]
• Efficient Robotic Policy Learning via Latent Space Backward PlanningDongxiu Liu, Haoyi Niu, ZhiHao Wang, Jinliang Zheng, Yinan Zheng, Zhonghong Ou, Jianming Hu, Jianxiong Li, Xianyuan Zhan. [doi]
• The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer trainingMatteo Saponati, Pascal Sager, Pau Vilimelis Aceituno, Thilo Stadelmann, Benjamin F. Grewe. [doi]
• A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative ModelsShivam Kumar, Yun Yang, Lizhen Lin. [doi]
• Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentChenghao Fan, Zhenyi Lu, Sichen Liu, Chengfeng Gu, Xiaoye Qu, Wei Wei 0002, Yu Cheng 0001. [doi]
• Online Pre-Training for Offline-to-Online Reinforcement LearningYongjae Shin, Jeonghye Kim, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngsoo Jang, Geon-hyeong Kim, Jongseong Chae, Youngchul Sung, Kanghoon Lee, Woohyung Lim. [doi]
• Combinatorial Reinforcement Learning with Preference FeedbackJoongkyu Lee, Min-hwan Oh. [doi]
• A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised LearningYaxin Hou, Yuheng Jia. [doi]
• Approximation to Smooth Functions by Low-Rank Swish NetworksZimeng Li, Hongjun Li, Jingyuan Wang, Ke Tang. [doi]
• TeLoGraF: Temporal Logic Planning via Graph-encoded Flow MatchingYue Meng, Chuchu Fan. [doi]
• RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache CompressionPayman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov. [doi]
• Diffusion Sampling Correction via Approximately 10 ParametersGuangyi Wang, Wei Peng 0009, Lijiang Li, Wenyu Chen, Yuren Cai, Song-Zhi Su. [doi]
• Objective drives the consistency of representational similarity across datasetsLaure Ciernik, Lorenz Linhardt, Marco Morik, Jonas Dippel, Simon Kornblith, Lukas Muttenthaler. [doi]
• Interaction-Aware Gaussian Weighting for Clustered Federated LearningAlessandro Licciardi, Davide Leo, Eros Fanì, Barbara Caputo, Marco Ciccone. [doi]
• Faster Approximation Algorithms for k-Center via Data ReductionArnold Filtser, Shaofeng H.-C. Jiang, Yi Li 0002, Anurag Murty Naredla, Ioannis Psarros, Qiaoyuan Yang, Qin Zhang 0001. [doi]
• Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement LearningLong Ma, Fangwei Zhong, Yizhou Wang 0001. [doi]
• Armijo Line-search Can Make (Stochastic) Gradient Descent Provably FasterSharan Vaswani, Reza Babanezhad Harikandeh. [doi]
• SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial TranscriptomicsQingtian Zhu, Yumin Zheng, Yuling Sang, Yifan Zhan, Ziyan Zhu, Jun Ding, Yinqiang Zheng. [doi]
• Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance FunctionsAleksandr Kolomeitsev, Anh Huy Phan 0001. [doi]
• Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge GraphsJaejun Lee 0001, Joyce Jiyoung Whang. [doi]
• Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View CurationJunlin Han, Jianyuan Wang, Andrea Vedaldi, Philip Torr 0001, Filippos Kokkinos. [doi]
• LETS Forecast: Learning Embedology for Time Series ForecastingAbrar Majeedi, Viswanatha Reddy Gajjala, Satya Sai Srinath Namburi GNVV, Nada Magdi Elkordi, Yin Li 0003. [doi]
• Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label ClassificationJie Wen 0001, Yadong Liu, Zhanyan Tang, Yuting He, Yulong Chen, Mu Li 0005, Chengliang Liu 0003. [doi]
• Latent Mamba Operator for Partial Differential EquationsKarn Tiwari, Niladri Dutta, N. M. Anoop Krishnan, Prathosh A. P.. [doi]
• Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action ModelsLucy Xiaoyang Shi, Brian Ichter, Michael Robert Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Driess, Lachy Groom, Sergey Levine, Chelsea Finn. [doi]
• A Unified View on Learning Unnormalized Distributions via Noise-Contrastive EstimationJongha Jon Ryu, Abhin Shah, Gregory W. Wornell. [doi]
• Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging DataSayed Mohammad Hosseini, Maryam Shanechi. [doi]
• Understanding Model Ensemble in Transferable Adversarial AttackWei Yao 0017, Zeliang Zhang 0001, Huayi Tang, Yong Liu 0018. [doi]
• An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN ArchitecturesThibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard, Thomas Massena, Mathieu Serrurier. [doi]
• Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed DataZhe Zhao 0008, Haibin Wen, Pengkun Wang 0001, Shuang Wang, Zhenkun Wang 0001, Qingfu Zhang 0001, Yang Wang 0015. [doi]
• Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMsRavi Ghadia, Avinash Kumar 0008, Gaurav Jain, Prashant J. Nair, Poulami Das 0005. [doi]
• From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?Zhanke Zhou, Xiao Feng 0003, Zhaocheng Zhu, Jiangchao Yao, Sanmi Koyejo, Bo Han 0003. [doi]
• VideoRoPE: What Makes for Good Video Rotary Position Embedding?Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Pan Zhang 0001, Yuhang Cao, Jian Tong, Haodong Duan, Qipeng Guo, Jiaqi Wang 0003, Xipeng Qiu, Dahua Lin. [doi]
• Perception in ReflectionYana Wei, Liang Zhao, Kangheng Lin, En Yu, Yuang Peng, Runpei Dong, Jianjian Sun, Haoran Wei, Zheng Ge, Xiangyu Zhang 0005, Vishal M. Patel. [doi]
• Where is the Truth? The Risk of Getting Confounded in a Continual WorldFlorian Peter Busch, Roshni Ramanna Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt. [doi]
• Optimizing Social Network Interventions via Hypergradient-Based Recommender System DesignMarino Kühne, Panagiotis D. Grontas, Giulia De Pasquale, Giuseppe Belgioioso, Florian Dörfler, John Lygeros. [doi]
• TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular DataElias Chaibub Neto. [doi]
• Hierarchical Equivariant Policy via Frame TransferHaibo Zhao, Dian Wang 0001, Yizhe Zhu, Xupeng Zhu, Owen Lewis Howell, Linfeng Zhao, Yaoyao Qian, Robin Walters 0001, Robert Platt 0001. [doi]
• A Closer Look at Backdoor Attacks on CLIPShuo He 0001, Zhifang Zhang, Feng Liu 0003, Roy Ka-Wei Lee, Bo An 0001, Lei Feng 0006. [doi]
• OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial DistillationYaoxuan Feng, Wenchao Chen, Yuxin Li 0003, Bo Chen 0001, Yubiao Wang, Zixuan Zhao, Hongwei Liu 0001, Mingyuan Zhou. [doi]
• Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal RepresentationsAditya Taparia, Som Sagar, Ransalu Senanayake. [doi]
• Generation from Noisy ExamplesAnanth Raman, Vinod Raman. [doi]
• Unnatural Languages Are Not Bugs but Features for LLMsKeyu Duan, Yiran Zhao 0006, Zhili Feng, Jinjie Ni, Tianyu Pang, Qian Liu 0012, Tianle Cai, Longxu Dou, Kenji Kawaguchi, Anirudh Goyal, J. Zico Kolter, Michael Qizhe Shieh. [doi]
• Deep Electromagnetic Structure Design Under Limited Evaluation BudgetsShijian Zheng, Fangxiao Jin, Shuhai Zhang, Quan Xue, Mingkui Tan. [doi]
• Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing LossBo-Han Lai, Pin-Han Huang, Bo-Han Kung, Shang-Tse Chen. [doi]
• CRANE: Reasoning with constrained LLM generationDebangshu Banerjee 0001, Tarun Suresh, Shubham Ugare, Sasa Misailovic, Gagandeep Singh 0001. [doi]
• Compositional Risk MinimizationDivyat Mahajan, Mohammad Pezeshki, Charles Arnal, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent. [doi]
• LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-IdentificationYiding Lu, Mouxing Yang, Dezhong Peng, Peng Hu 0002, Yijie Lin 0001, Xi Peng 0001. [doi]
• Adversarial Inception Backdoor Attacks against Reinforcement LearningEthan Rathbun, Alina Oprea, Christopher Amato. [doi]
• Scalable Sobolev IPM for Probability Measures on a GraphTam Le, Truyen Nguyen, Hideitsu Hino, Kenji Fukumizu. [doi]
• MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference AlignmentTianZe Wang, Dongnan Gui, Yifan Hu, Shuhang Lin, Linjun Zhang. [doi]
• Beyond One-Hot Labels: Semantic Mixing for Model CalibrationHaoyang Luo, Linwei Tao, Minjing Dong, Chang Xu 0002. [doi]
• A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous SystemsManan Tayal, Aditya Singh, Shishir Kolathaya, Somil Bansal. [doi]
• Multimodal Medical Code TokenizerXiaorui Su 0001, Shvat Messica, Yepeng Huang, Ruth Johnson, Lukas Fesser, Shanghua Gao, Faryad Sahneh, Marinka Zitnik. [doi]
• FedBEns: One-Shot Federated Learning based on Bayesian EnsembleJacopo Talpini, Marco Savi, Giovanni Neglia. [doi]
• Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear ObservationsZhengming Chen 0002, Yewei Xia, Feng Xie 0002, Jie Qiao, Zhifeng Hao, Ruichu Cai, Kun Zhang 0001. [doi]
• Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal PerspectiveLele Fu, Bowen Deng 0002, Sheng Huang, Tianchi Liao, Shirui Pan, Chuan Chen 0001. [doi]
• Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic DimensionYijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei. [doi]
• Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble MethodsYifan Hao 0002, Xingyuan Pan, Hanning Zhang, Chenlu Ye, Rui Pan 0002, Tong Zhang 0001. [doi]
• Unifying Specialized Visual Encoders for Video Language ModelsJihoon Chung, Tyler Zhu, Max Gonzalez Saez-Diez, Juan Carlos Niebles, Honglu Zhou, Olga Russakovsky. [doi]
• Test-time Correlation AlignmentLinjing You, Jiabao Lu, Xiayuan Huang. [doi]
• Zero-Inflated BanditsHaoyu Wei, Runzhe Wan, Lei Shi, Rui Song 0006. [doi]
• Adaptive Exploration for Multi-Reward Multi-Policy EvaluationAlessio Russo, Aldo Pacchiano. [doi]
• Sampling from Binary Quadratic Distributions via Stochastic LocalizationChenguang Wang, Kaiyuan Cui, Weichen Zhao, Tianshu Yu 0001. [doi]
• On the Duality between Gradient Transformations and AdaptersLucas Torroba Hennigen, Hunter Lang, Han Guo, Yoon Kim. [doi]
• Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash EquilibriumRunyu Lu, Yuanheng Zhu, Dongbin Zhao. [doi]
• Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language ModelingHaebin Shin, Lei Ji 0001, Xiao Liu, Yeyun Gong. [doi]
• Graph Neural Network Generalization With Gaussian Mixture Model Based AugmentationYassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine Mohamed Aboussalah, Michalis Vazirgiannis. [doi]
• Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive QueryingSonglin Zhai, Yuan Meng, Yongrui Chen 0002, Yiwei Wang, Guilin Qi. [doi]
• Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision MakingXu Wan 0001, Wenyue Xu, Chao Yang, Mingyang Sun. [doi]
• Predicting the Susceptibility of Examples to Catastrophic ForgettingGuy Hacohen, Tinne Tuytelaars. [doi]
• Learning multivariate Gaussians with imperfect adviceArnab Bhattacharyya 0001, Davin Choo, Philips George John, Themis Gouleakis. [doi]
• Plan-and-Act: Improving Planning of Agents for Long-Horizon TasksLutfi Eren Erdogan, Nicholas Lee, Sehoon Kim 0001, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami. [doi]
• Reinforced Lifelong Editing for Language ModelsZherui Li 0001, Houcheng Jiang, Hao Chen, Baolong Bi, Zhenhong Zhou, Fei Sun, Junfeng Fang, Xiang Wang 0010. [doi]
• Curse of High Dimensionality Issue in Transformer for Long Context ModelingShuhai Zhang, Zeng You, Yaofo Chen, Zhiquan Wen, Qianyue Wang, Zhijie Qiu, Yuanqing Li 0001, Mingkui Tan. [doi]
• ROPO: Robust Preference Optimization for Large Language ModelsXize Liang, Chao Chen 0026, Shuang Qiu, Jie Wang 0005, Yue Wu, Zhihang Fu, Hanzhu Chen, Feng Wu 0001, Jieping Ye. [doi]
• Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure MathematicsHerman Chau, Helen Jenne, Davis Brown, Jesse He, Mark Raugas, Sara C. Billey, Henry Kvinge. [doi]
• Privacy Attacks on Image AutoRegressive ModelsAntoni Kowalczuk, Jan Dubinski, Franziska Boenisch, Adam Dziedzic. [doi]
• SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference LearningTianjian Li, Daniel Khashabi. [doi]
• Homophily Enhanced Graph Domain AdaptationRuiyi Fang, Bingheng Li, Jingyu Zhao, Ruizhi Pu, Qiuhao Zeng, Gezheng Xu, Charles Ling 0001, Boyu Wang 0004. [doi]
• On the Convergence of Continuous Single-timescale Actor-criticXuyang Chen, Lin Zhao. [doi]
• Probabilistic Factorial Experimental Design for Combinatorial InterventionsDivya Shyamal, Jiaqi Zhang, Caroline Uhler. [doi]
• Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot SegmentationJintao Tong, Yixiong Zou, Guangyao Chen, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive SearchMaohao Shen, Guangtao Zeng, Zhenting Qi, Zhang-Wei Hong, Zhenfang Chen, Wei Lu, Gregory W. Wornell, Subhro Das, David Daniel Cox, Chuang Gan 0001. [doi]
• The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data ContaminationYifan Sun 0010, Han Wang 0019, Dongbai Li, Gang Wang 0011, Huan Zhang 0001. [doi]
• Robust and Conjugate Spatio-Temporal Gaussian ProcessesWilliam Laplante, Matías Altamirano, Andrew B. Duncan, Jeremias Knoblauch, François-Xavier Briol. [doi]
• Fairness Overfitting in Machine Learning: An Information-Theoretic PerspectiveFiras Laakom, Haobo Chen, Jürgen Schmidhuber, Yuheng Bu. [doi]
• Are Sparse Autoencoders Useful? A Case Study in Sparse ProbingSubhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan, Max Tegmark, Neel Nanda. [doi]
• Reflection-Bench: Evaluating Epistemic Agency in Large Language ModelsLingyu Li, Yixu Wang, Haiquan Zhao 0002, Shuqi Kong, Yan Teng 0002, Chunbo Li, Yingchun Wang. [doi]
• MCU: An Evaluation Framework for Open-Ended Game AgentsXinyue Zheng, Haowei Lin, Kaichen He, Zihao Wang, Qiang Fu 0016, Haobo Fu, Zilong Zheng, Yitao Liang. [doi]
• Instruct2See: Learning to Remove Any Obstructions Across DistributionsJunhang Li, Yu Guo 0008, Chuhua Xian, Shengfeng He. [doi]
• One Wave To Explain Them All: A Unifying Perspective On Feature AttributionGabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh. [doi]
• PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and PlanningAngel Villar-Corrales, Sven Behnke. [doi]
• Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport PlanJaemoo Choi, Jaewoong Choi, Dohyun Kwon 0002. [doi]
• Neural Event-Triggered Control with Optimal SchedulingLuan Yang, Jingdong Zhang, Qunxi Zhu, Wei Lin. [doi]
• Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot GeneralizationYang Shen 0006, Xiu-Shen Wei, Yifan Sun 0003, Yuxin Song, Tao Yuan, Jian Jin, He-Yang Xu, Yazhou Yao, Errui Ding. [doi]
• Contrastive Localized Language-Image Pre-TrainingHong-You Chen, Zhengfeng Lai, Haotian Zhang 0005, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang 0002, Yinfei Yang, Zhe Gan. [doi]
• Towards Robustness and Explainability of Automatic Algorithm SelectionXingyu Wu, Jibin Wu, Yu Zhou 0045, Liang Feng 0001, Kc Tan. [doi]
• AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive ModellingAlexander Capstick, Rahul G. Krishnan, Payam M. Barnaghi. [doi]
• EditLord: Learning Code Transformation Rules for Code EditingWeichen Li, Albert Jan, Baishakhi Ray, Junfeng Yang, Chengzhi Mao, Kexin Pei. [doi]
• Accelerating Large Language Model Reasoning via Speculative SearchZhihai Wang, Jie Wang 0005, Jilai Pan, Xilin Xia, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Feng Wu 0001. [doi]
• A Recipe for Causal Graph Regression: Confounding Effects RevisitedYujia Yin, Tianyi Qu, Zihao Wang, Yifan Chen. [doi]
• Unifews: You Need Fewer Operations for Efficient Graph Neural NetworksNingyi Liao, Zihao Yu, Ruixiao Zeng, Siqiang Luo. [doi]
• Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language ModelsMingi Jung, Saehyung Lee, Eunji Kim 0002, Sungroh Yoon. [doi]
• RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like ReasoningJason Chan, Robert J. Gaizauskas, Zhixue Zhao. [doi]
• Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSLHarit Vishwakarma, Yi Chen, Satya Sai Srinath Namburi GNVV, Sui Jiet Tay, Ramya Korlakai Vinayak, Frederic Sala. [doi]
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution BehaviorsJing Huang 0014, Junyi Tao, Thomas Icard, Diyi Yang, Christopher Potts. [doi]
• AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality AssessmentYuqin Cao, Xiongkuo Min, Yixuan Gao, Wei Sun 0029, Guangtao Zhai. [doi]
• M2PDE: Compositional Generative Multiphysics and Multi-component PDE SimulationTao Zhang 0102, Zhenhai Liu, Feipeng Qi, Yongjun Jiao, Tailin Wu. [doi]
• Pre-training Auto-regressive Robotic Models with 4D RepresentationsDantong Niu, Yuvan Sharma, Haoru Xue, Giscard Biamby, Junyi Zhang 0004, Ziteng Ji, Trevor Darrell, Roei Herzig. [doi]
• Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update TimeGramoz Goranci, Peter Kiss, Neel Patel, Martin P. Seybold, Eva Szilagyi, Da-Wei Zheng. [doi]
• rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep ThinkingXinyu Guan, Li Lyna Zhang, YiFei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang 0024, Mao Yang 0004. [doi]
• BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and ActivationLian Liu, Xiandong Zhao, Guanchen Li, Dong Li 0025, Mengdi Wang 0004, Yinhe Han 0001, Xiaowei Li 0001, Ying Wang 0001. [doi]
• Stochastic Online Conformal Prediction with Semi-Bandit FeedbackHaosen Ge, Hamsa Bastani, Osbert Bastani. [doi]
• Nonparametric Teaching for Graph Property LearnersChen Zhang, Weixin Bu, Zeyi Ren, Zhengwu Liu, Yik-Chung Wu, Ngai Wong 0001. [doi]
• Resolving Lexical Bias in Model EditingHammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad 0001. [doi]
• Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard ProblemsMikolaj Malkinski, Szymon Pawlonka, Jacek Mandziuk. [doi]
• Random Registers for Cross-Domain Few-Shot LearningShuai Yi, Yixiong Zou, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in DrivingYiheng Li, Cunxin Fan, Chongjian Ge, Seth Z. Zhao, Chenran Li, Chenfeng Xu, Huaxiu Yao, Masayoshi Tomizuka, Bolei Zhou, Chen Tang 0001, Mingyu Ding, Wei Zhan. [doi]
• SafeArena: Evaluating the Safety of Autonomous Web AgentsAda Defne Tur, Nicholas Meade, Xing Han Lù, Alejandra Zambrano, Arkil Patel, Esin Durmus, Spandana Gella, Karolina Stanczak, Siva Reddy. [doi]
• Task Generalization with Autoregressive Compositional Structure: Can Learning from D Tasks Generalize to DT Tasks?Amirhesam Abedsoltan, Huaqing Zhang 0005, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin. [doi]
• Learning Adversarial MDPs with Stochastic Hard ConstraintsFrancesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi 0001, Nicola Gatti 0001. [doi]
• Learning to Steer Learners in GamesYizhou Zhang, Yian Ma, Eric Mazumdar. [doi]
• Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing FlowsGabriele Visentin, Patrick Cheridito. [doi]
• Flat-LoRA: Low-Rank Adaptation over a Flat Loss LandscapeTao Li, Zhengbao He, Yujun Li, Yasheng Wang, Lifeng Shang, Xiaolin Huang. [doi]
• CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and AcquisitionZebin Wang, Menghan Lin, Bolin Shen, Ken Anderson, Molei Liu, Tianxi Cai, Yushun Dong. [doi]
• SelfCite: Self-Supervised Alignment for Context Attribution in Large Language ModelsYung-Sung Chuang, Benjamin Cohen-Wang, Zejiang Shen 0001, Zhaofeng Wu, Hu Xu 0001, Xi Victoria Lin, James R. Glass, Shang-wen Li 0001, Wen-tau Yih. [doi]
• CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic GraphsZhiqiang Wang, Xiaoyi Wang, Jianqing Liang. [doi]
• Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative ExpertsLan Li 0001, Da-Wei Zhou 0001, Han-Jia Ye, De-Chuan Zhan. [doi]
• Learning Adaptive Lighting via Channel-Aware GuidanceQirui Yang, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Bo Li 0026, Huanjing Yue, Jingyu Yang 0002. [doi]
• Continuous Visual Autoregressive Generation via Score MaximizationChenze Shao, Fandong Meng, Jie Zhou 0016. [doi]
• Learning Curves of Stochastic Gradient Descent in Kernel RegressionHaihan Zhang, Weicheng Lin, Yuanshi Liu, Cong Fang 0001. [doi]
• A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional OptimizationBokun Wang, Tianbao Yang. [doi]
• MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech RecognitionSungnyun Kim, Kangwook Jang, Sangmin Bae, Sungwoo Cho, Se-Young Yun. [doi]
• TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity TreeYu-Yang Qian 0001, Yuan-Ze Xu, Zhen-yu Zhang, Peng Zhao 0006, Zhi-Hua Zhou. [doi]
• VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video ModelsHaojian Huang, Haodong Chen, Shengqiong Wu, Meng Luo 0002, JinLan Fu, Xinya Du, Hanwang Zhang, Hao Fei 0001. [doi]
• Improving Reward Model Generalization from Adversarial Process Enhanced PreferencesZhilong Zhang, Tian Xu 0003, Xinghao Du, Xingchen Cao, Yihao Sun, Yang Yu 0001. [doi]
• Feasible Action Search for Bandit Linear Programs via Thompson SamplingAditya Gangrade, Aldo Pacchiano, Clayton Scott, Venkatesh Saligrama. [doi]
• Emergence in non-neural models: grokking modular arithmetic via average gradient outer productNeil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin. [doi]
• Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN DiscriminatorKaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu 0001, Jun Zhu 0001, Qinsheng Zhang. [doi]
• TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable InferenceJack Min Ong, Matthew Di Ferrante, Aaron Pazdera, Ryan Garner, Sami Jaghouar, Manveer Basra, Max Ryabinin, Johannes Hagemann. [doi]
• The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety DirectionsWenbo Pan, Zhichao Liu, Qiguang Chen, Xiangyang Zhou, Haining Yu, Xiaohua Jia. [doi]
• Inverse Flow and Consistency ModelsYuchen Zhang, Jian Zhou. [doi]
• On the Importance of Gaussianizing RepresentationsDaniel Eftekhari, Vardan Papyan. [doi]
• Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE SolversHang Zhou, Yuezhou Ma, Haixu Wu, Haowen Wang, Mingsheng Long. [doi]
• Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature SpacesAmirhossein Roknilamouki, Arnob Ghosh, Ming Shi 0003, Fatemeh Nourzad, Eylem Ekici, Ness B. Shroff. [doi]
• Parametric Scaling Law of Tuning Bias in Conformal PredictionHao Zeng 0005, Kangdao Liu, Bingyi Jing, Hongxin Wei. [doi]
• Diversified Flow Matching with Translation IdentifiabilitySagar Shrestha, Xiao Fu 0001. [doi]
• Strategic A/B testing via Maximum Probability-driven Two-armed BanditYu Zhang, Shanshan Zhao, Bokui Wan, Jinjuan Wang, Xiaodong Yan. [doi]
• Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated LearningMengmeng Chen, Xiaohu Wu, Qiqi Liu, Tiantian He 0001, Yew-Soon Ong, Yaochu Jin, Qicheng Lao, Han Yu 0001. [doi]
• When to Forget? Complexity Trade-offs in Machine UnlearningMartin Van Waerebeke, Marco Lorenzi, Giovanni Neglia, Kevin Scaman. [doi]
• Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device LearningLe-Trung Nguyen, Aël Quélennec, Van Tam Nguyen, Enzo Tartaglione. [doi]
• Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time AlignmentAudrey Huang, Adam Block, Qinghua Liu, Nan Jiang 0008, Akshay Krishnamurthy, Dylan J. Foster. [doi]
• StealthInk: A Multi-bit and Stealthy Watermark for Large Language ModelsYa Jiang, Chuxiong Wu, Massieh Kordi Boroujeny, Brian L. Mark, Kai Zeng 0001. [doi]
• Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational InferenceJunbin Liu, Farzan Farnia, Wing-Kin Ma. [doi]
• Broadband Ground Motion Synthesis by Diffusion Model with Minimal ConditionJaeheun Jung, Jaehyuk Lee, Chang-Hae Jung, Hanyoung Kim, Bosung Jung, Donghun Lee. [doi]
• On the Power of Learning-Augmented Search TreesJingbang Chen, Xinyuan Cao, Alicia Stepin, Li Chen. [doi]
• A Selective Learning Method for Temporal Graph Continual LearningHanmo Liu, Shimin Di, Haoyang Li 0002, Xun Jian 0001, Yue Wang 0012, Lei Chen 0002. [doi]
• Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein DistancesJie Wang 0049, March Boedihardjo, Yao Xie 0002. [doi]
• A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex OptimizationKunjie Ren, Luo Luo. [doi]
• Geometric Contact Flows: Contactomorphisms for Dynamics and ControlAndrea Testa, Søren Hauberg, Tamim Asfour, Leonel Rozo. [doi]
• How to Synthesize Text Data without Model Collapse?Xuekai Zhu, Daixuan Cheng, Hengli Li, Kaiyan Zhang, Ermo Hua, Xingtai Lv, Ning Ding 0002, Zhouhan Lin, Zilong Zheng, Bowen Zhou 0002. [doi]
• Random Policy Evaluation Uncovers Policies of Generative Flow NetworksHaoran He, Emmanuel Bengio, Qingpeng Cai 0001, Ling Pan. [doi]
• LLM Alignment as Retriever Optimization: An Information Retrieval PerspectiveBowen Jin, Jinsung Yoon, Zhen Qin 0001, Ziqi Wang 0003, Wei Xiong 0015, Yu Meng 0001, Jiawei Han 0001, Sercan Ö. Arik. [doi]
• A General Graph Spectral Wavelet Convolution via Chebyshev Order DecompositionNian Liu 0001, Xiaoxin He, Thomas Laurent 0001, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson. [doi]
• Dynamical phases of short-term memory mechanisms in RNNsBariscan Kurtkaya, Fatih Dinc, Mert Yüksekgönül, Marta Blanco-Pozo, Ege Çirakman, Mark J. Schnitzer, Yucel Yemez, Hidenori Tanaka, Peng Yuan, Nina Miolane. [doi]
• LEMoN: Label Error Detection using Multimodal NeighborsHaoran Zhang 0003, Aparna Balagopalan, Nassim Oufattole, Hyewon Jeong, Yan Wu, Jiacheng Zhu, Marzyeh Ghassemi. [doi]
• Adapting to Evolving Adversaries with Regularized Continual Robust TrainingSihui Dai, Christian Cianfarani, Vikash Sehwag, Prateek Mittal, Arjun Nitin Bhagoji. [doi]
• Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token PredictionShu-Wen Yang, Byeonggeun Kim, Kuan-Po Huang, Qingming Tang, Huy Phan, Bo-Ru Lu, Harshavardhan Sundar, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, Chao Wang. [doi]
• MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future KnowledgeYue Dai 0005, Liang Liu, Xulong Tang, Youtao Zhang, Jun Yang 0002. [doi]
• Pixel-level Certified Explanations via Randomized SmoothingAlaa Anani, Tobias Lorenz 0002, Mario Fritz, Bernt Schiele. [doi]
• Diffusion Counterfactual Generation with Semantic AbductionRajat Rasal, Avinash Kori, Fabio De Sousa Ribeiro, Tian Xia, Ben Glocker. [doi]
• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and GuaranteesYannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. [doi]
• Not All Wrong is Bad: Using Adversarial Examples for UnlearningAli Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran. [doi]
• Hgformer: Hyperbolic Graph Transformer for Collaborative FilteringXin Yang, Xingrun Li, Heng Chang, Jinze Yang, Xihong Yang, Shengyu Tao, Maiko Shigeno, Ningkang Chang, Junfeng Wang 0009, Dawei Yin 0001, Erxue Min. [doi]
• TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain AdaptationJaeho Kim, Seulki Lee. [doi]
• UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and InteractionShravan Nayak, Xiangru Jian, Kevin Qinghong Lin, Juan A. Rodríguez, Montek Kalsi, Nicolas Chapados, M. Tamer Özsu, Aishwarya Agrawal, David Vázquez 0001, Christopher Pal, Perouz Taslakian, Spandana Gella, Sai Rajeswar. [doi]
• History-Guided Video DiffusionKiwhan Song, Boyuan Chen 0003, Max Simchowitz, Yilun Du, Russ Tedrake, Vincent Sitzmann. [doi]
• Adaptive Partitioning Schemes for Optimistic OptimizationRaja Sunkara, Ardhendu Tripathy. [doi]
• Rethinking Point Cloud Data Augmentation: Topologically Consistent DeformationJian Bi, Qianliang Wu, Xiang Li 0041, Shuo Chen 0003, Jianjun Qian, Lei Luo 0001, Jian Yang 0003. [doi]
• Controlling Large Language Model with Latent ActionChengxing Jia, Ziniu Li, Pengyuan Wang, Yi-Chen Li 0001, Zhenyu Hou, Yuxiao Dong, Yang Yu 0001. [doi]
• Quantum Optimization via Gradient-Based Hamiltonian DescentJiaqi Leng 0001, Bin Shi. [doi]
• Ensemble Learned Bloom Filters: Two Oracles are Better than OneMing Lin, Lin Chen 0002. [doi]
• Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow NetworksKeyue Qiu, Yuxuan Song, Jie Yu, Hongbo Ma, Ziyao Cao, Zhilong Zhang, Yushuai Wu, Mingyue Zheng, Hao Zhou 0012, Wei-Ying Ma. [doi]
• The Value of Prediction in Identifying the Worst-OffUnai Fischer Abaigar, Christoph Kern 0001, Juan Carlos Perdomo. [doi]
• Weak-to-Strong Jailbreaking on Large Language ModelsXuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li 0005, Yu-Xiang Wang 0003, William Yang Wang. [doi]
• Explicit Discovery of Nonlinear Symmetries from Dynamic DataLexiang Hu, Yikang Li, Zhouchen Lin. [doi]
• Doubly Robust Fusion of Many Treatments for Policy LearningKe Zhu, Jianing Chu, Ilya Lipkovich, Wenyu Ye, Shu Yang. [doi]
• Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving RegularizationZiyu Gong, Jim Lim, David I. Inouye. [doi]
• UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language ModelsXin Xu, Qiyun Xu, Tong Xiao, Tianhao Chen, Yuchen Yan, Jiaxin Zhang, Shizhe Diao, Can Yang, Yang Wang 0020. [doi]
• PDUDT: Provable Decentralized Unlearning under Dynamic TopologiesJing Qiao, Yu Liu 0085, Zengzhe Chen, Mingyi Li, Yuan Yuan 0014, Xiao Zhang 0015, Dongxiao Yu. [doi]
• ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask DatasetYilin Wang, Peixuan Lei, Jie Song, Yuzhe Hao, Tao Chen, Yuxuan Zhang, Lei Jia, Yuanxiang Li, Zhongyu Wei. [doi]
• Determining Layer-wise Sparsity for Large Language Models Through a Theoretical PerspectiveWeizhong Huang, Yuxin Zhang 0002, Xiawu Zheng, Fei Chao 0001, Rongrong Ji. [doi]
• any4: Learned 4-bit Numeric Representation for LLMsMostafa Elhoushi, Jeff Johnson. [doi]
• Fast Large Language Model Collaborative Decoding via SpeculationJiale Fu, Yuchu Jiang, JunKai Chen, Jiaming Fan, Xin Geng 0001, Xu Yang 0021. [doi]
• PENCIL: Long Thoughts with Short MemoryChenxiao Yang, Nathan Srebro, David McAllester, Zhiyuan Li 0005. [doi]
• Equivalence is All: A Unified View for Self-supervised Graph LearningYejiang Wang, Yuhai Zhao, Zhengkui Wang, Ling Li, Jiapu Wang, Fangting Li, Miaomiao Huang, Shirui Pan, Xingwei Wang 0001. [doi]
• Observation Interference in Partially Observable Assistance GamesScott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell 0001. [doi]
• STAMP Your Content: Proving Dataset Membership via Watermarked RephrasingsSaksham Rastogi, Pratyush Maini, Danish Pruthi. [doi]
• Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM CompressionPeijie Dong, Zhenheng Tang, Xiang Liu 0001, Lujun Li 0001, Xiaowen Chu 0001, Bo Li 0001. [doi]
• ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory ImputationTianci Bu, Le Zhou, Wenchuan Yang, Jianhong Mou, Kang Yang, Suoyi Tan, Feng Yao, Jingyuan Wang, Xin Lu 0002. [doi]
• Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed DensitySubhodh Kotekal. [doi]
• Heavy-Tailed Linear Bandits: Huber Regression with One-Pass UpdateJing Wang 0241, Yu-Jie Zhang, Peng Zhao 0006, Zhi-Hua Zhou. [doi]
• The Limits of Predicting Agents from BehaviourAlexis Bellot, Jonathan Richens, Tom Everitt. [doi]
• MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image SegmentationJiawen Wang, Yinda Chen, Xiaoyu Liu 0006, Che Liu, Dong Liu 0002, Jianqing Gao, Zhiwei Xiong. [doi]
• Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy TailsJindong Tong, Hongcheng Liu, Johannes O. Royset. [doi]
• Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and DivergenceZhaowei Chen, Borui Zhao, Yuchen Ge, Yuhao Chen, Renjie Song, Jiajun Liang. [doi]
• OW-VAP: Visual Attribute Parsing for Open World Object DetectionXing Xi, Xing Fu, Weiqiang Wang 0002, Ronghua Luo. [doi]
• The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement LearningJiashun Liu, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan. [doi]
• Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic AgentsEric Frankel, Kshitij Kulkarni, Dmitriy Drusvyatskiy, Sewoong Oh, Lillian J. Ratliff. [doi]
• Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation modelsKonstantin Donhauser, Kristina Ulicna, Gemma E. Moran, Aditya Ravuri, Kian Kenyon-Dean, Cian Eastwood, Jason S. Hartford. [doi]
• (How) Can Transformers Predict Pseudo-Random Numbers?Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He, Maissam Barkeshli. [doi]
• Dataflow-Guided Neuro-Symbolic Language Models for Type InferenceGe Li 0001, Yao Wan 0001, Hongyu Zhang 0002, Zhou Zhao 0001, Wenbin Jiang 0001, Xuanhua Shi, Hai Jin 0001, Zheng Wang 0001. [doi]
• A Variational Perspective on Generative Protein Fitness OptimizationLea Bogensperger, Dominik Narnhofer, Ahmed Allam, Konrad Schindler, Michael Krauthammer. [doi]
• MixMin: Finding Data Mixtures via Convex MinimizationAnvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris J. Maddison. [doi]
• GPEN: Global Position Encoding Network for Enhanced Subgraph Representation LearningNannan Wu, Yuming Huang, Yiming Zhao, Jie Chen, Wenjun Wang 0002. [doi]
• Wasserstein Flow Matching: Generative Modeling Over Families of DistributionsDoron Haviv, Aram-Alexandre Pooladian, Dana Pe'er, Brandon Amos. [doi]
• DAMA: Data- and Model-aware Alignment of Multi-modal LLMsJinda Lu, Junkang Wu, Jinghan Li, Xiaojun Jia, Shuo Wang 0008, Yifan Zhang 0004, Junfeng Fang, Xiang Wang 0010, Xiangnan He 0001. [doi]
• Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?Konrad Mundinger, Max Zimmer, Aldo Kiem, Christoph Spiegel 0002, Sebastian Pokutta. [doi]
• MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active LearningPeter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K. Gilson, Rose Yu. [doi]
• The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite GraphMinghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari. [doi]
• Convergence of Policy Mirror Descent Beyond Compatible Function ApproximationUri Sherman, Tomer Koren, Yishay Mansour. [doi]
• GaussMark: A Practical Approach for Structural Watermarking of Language ModelsAdam Block, Alexander Rakhlin, Ayush Sekhari. [doi]
• O-MAPL: Offline Multi-agent Preference LearningThe Viet Bui, Tien Anh Mai, Thanh Hong Nguyen. [doi]
• PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect PredictionAaron Wenteler, Martina Occhetta, Nikhil Branson, Victor Curean, Magdalena Huebner, William Dee, William Connell, Siu Pui Chung, Alex Hawkins-Hooker, Yasha Ektefaie, César Miguel Valdez Córdova, Amaya Gallagher-Syed. [doi]
• How Much Can We Forget about Data Contamination?Sebastian Bordt, Suraj Srinivas, Valentyn Boreiko, Ulrike von Luxburg. [doi]
• Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference OptimizationEmiliano Penaloza, Tianyue H. Zhang, Laurent Charlin, Mateo Espinosa Zarlenga. [doi]
• Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered ApproachChenyin Gao, Peter B. Gilbert, Larry Han. [doi]
• Measuring Variable Importance in Heterogeneous Treatment Effects with ConfidenceJoseph Paillard, Angel David Reyero Lobo, Vitaliy Kolodyazhniy, Bertrand Thirion, Denis-Alexander Engemann. [doi]
• Deep Streaming View ClusteringHonglin Yuan, Xingfeng Li 0004, Jian Dai 0002, Xiaojian You, Yuan Sun 0016, Zhenwen Ren. [doi]
• Universal Length Generalization with Turing ProgramsKaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach. [doi]
• Feature Importance Metrics in the Presence of Missing DataHenrik von Kleist, Joshua Wendland, Ilya Shpitser, Carsten Marr. [doi]
• MATS: An Audio Language Model under Text-only SupervisionWen Wang 0022, Ruibing Hou, Hong Chang 0001, Shiguang Shan, Xilin Chen 0001. [doi]
• Target Concrete Score Matching: A Holistic Framework for Discrete DiffusionRuixiang Zhang, Shuangfei Zhai, Yizhe Zhang 0002, James Thornton, Zijing Ou, Joshua M. Susskind, Navdeep Jaitly. [doi]
• Continuous-Time Analysis of Heavy Ball Momentum in Min-Max GamesYi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang 0036, Volkan Cevher. [doi]
• ExtPose: Robust and Coherent Pose Estimation by Extending ViTsRongyu Chen, Li'an Zhuo, Linlin Yang, Qi Wang, Liefeng Bo, Bang Zhang, Angela Yao. [doi]
• Robust Sparsification via SensitivityChansophea Wathanak In, Yi Li 0002, David P. Woodruff, Xuan Wu 0002. [doi]
• Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative ModelsMehmet Yigit Balik, Maksim Sinelnikov, Priscilla Ong, Harri Lähdesmäki. [doi]
• HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model TrainingGeon Woo Kim, Junbo Li, Shashidhar Gandham, Omar Baldonado, Adithya Gangidi, Pavan Balaji, Zhangyang Wang, Aditya Akella. [doi]
• KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold NetworksQuan Zhou, Changhua Pei, Fei Sun 0001, Jing Han, Zhengwei Gao, Haiming Zhang 0002, Gaogang Xie, Dan Pei, Jianhui Li. [doi]
• The Relationship Between No-Regret Learning and Online Conformal PredictionRamya Ramalingam, Shayan Kiyani, Aaron Roth 0001. [doi]
• Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language ModelsYangxu Liao, Wenke Huang 0003, Guancheng Wan, Jian Liang 0003, Bin Yang 0026, Mang Ye. [doi]
• Efficiently Serving Large Multimodal Models Using EPD DisaggregationGursimran Singh, Xinglu Wang, Yifan Hu, Timothy Tin Long Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang 0004, Zhenan Fan. [doi]
• On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial RobustnessJunyi Chai 0004, Taeuk Jang, Jing Gao 0004, Xiaoqian Wang 0001. [doi]
• One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional DiscrepancyJiacheng Zhang, Benjamin I. P. Rubinstein, Jingfeng Zhang, Feng Liu. [doi]
• Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-SpeechTaesoo Kim, Jinju Kim, Dongchan Kim, Jong Hwan Ko, Gyeong-Moon Park. [doi]
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View SynthesisSunghwan Hong, Jaewoo Jung, Heeseong Shin, Jisang Han, Jiaolong Yang, Chong Luo 0001, Seungryong Kim. [doi]
• Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?Jinyang Li 0003, Nan Huo, Yan Gao, Jiayi Shi, Yingxiu Zhao, Ge Qu, Bowen Qin, Yurong Wu, Xiaodong Li 0009, Chenhao Ma 0001, Jian-Guang Lou, Reynold Cheng. [doi]
• Explaining, Fast and Slow: Abstraction and Refinement of Provable ExplanationsShahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner, Matthias Althoff, Guy Katz. [doi]
• Mechanisms of Projective Composition of Diffusion ModelsArwen Bradley, Preetum Nakkiran, David Berthelot, James Thornton, Joshua M. Susskind. [doi]
• RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning EvaluationXinnuo Xu, Rachel Lawrence, Kshitij Dubey, Atharva Pandey, Risa Ueno, Fabian Falck, Aditya V. Nori, Rahul Sharma 0001, Amit Sharma 0007, Javier González 0002. [doi]
• Scaling Inference-Efficient Language ModelsSong Bian 0002, Minghao Yan, Shivaram Venkataraman. [doi]
• ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in RoboticsLetian Chen, Nina Marie Moorman, Matthew Craig Gombolay. [doi]
• Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger EquationKevin Han Huang, Ni Zhan 0001, Elif Ertekin, Peter Orbanz, Ryan P. Adams. [doi]
• Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic SegmentationRui Sun 0006, Huayu Mai, Wangkai Li, Yujia Chen, Naisong Luo, Yuan Wang 0064, Tianzhu Zhang 0001. [doi]
• Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face RecognitionShuai Yuan 0009, Hongwei Li 0001, Rui Zhang 0003, Hangcheng Cao, Wenbo Jiang 0001, Tao Ni 0003, Wenshu Fan, Qingchuan Zhao, Guowen Xu. [doi]
• Reward-Guided Prompt Evolving in Reinforcement Learning for LLMsZiyu Ye, Rishabh Agarwal, Tianqi Liu 0002, Rishabh Joshi, Sarmishta Velury, Quoc V. Le, Qijun Tan, Yuan Liu. [doi]
• Pruning for GNNs: Lower Complexity with Comparable ExpressivenessDun Ma, Jianguo Chen, Wenguo Yang, Suixiang Gao, Shengminjie Chen. [doi]
• A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential EquationsJunwei Su, Chuan Wu 0001. [doi]
• Training Dynamics of In-Context Learning in Linear AttentionYedi Zhang, Aaditya K. Singh, Peter E. Latham, Andrew M. Saxe. [doi]
• From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic HarmsJessica Dai, Paula Gradu, Inioluwa Deborah Raji, Benjamin Recht. [doi]
• An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic PerspectiveXinyue Chen 0004, Jinfeng Peng, Yuhao Li, Xiaorong Pu, Yang Yang 0002, Yazhou Ren 0001. [doi]
• Learning with Exact Invariances in Polynomial TimeAshkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka, Patrick Jaillet. [doi]
• Zero-Shot Generalization of GNNs over Distinct Attribute DomainsYangyi Shen, Jincheng Zhou, Beatrice Bevilacqua, Joshua Robinson 0001, Charilaos I. Kanatsoulis, Jure Leskovec, Bruno Ribeiro 0001. [doi]
• Robust ML Auditing using Prior KnowledgeJade Garcia Bourrée, Augustin Godinot, Sayan Biswas, Anne-Marie Kermarrec, Erwan Le Merrer, Gilles Trédan, Martijn de Vos, Milos Vujasinovic. [doi]
• CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive PerspectiveJiayu Liu 0001, Zhenya Huang, Wei Dai, Cheng Cheng, Jinze Wu, Jing Sha, Song Li, Qi Liu 0003, Shijin Wang 0001, Enhong Chen. [doi]
• Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical ReasoningRina Bao, Shilong Dong, Zhenfang Chen, Sheng He, Ellen Grant, Yangming Ou. [doi]
• TS-SNN: Temporal Shift Module for Spiking Neural NetworksKairong Yu, Tianqing Zhang, Qi Xu 0008, Gang Pan 0001, Hongwei Wang 0001. [doi]
• Shortcut-connected Expert Parallelism for Accelerating Mixture of ExpertsWeilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim 0001, Jiayi Huang 0001. [doi]
• The Double-Ellipsoid Geometry of CLIPMeir Yossef Levi, Guy Gilboa. [doi]
• Constant Stepsize Local GD for Logistic Regression: Acceleration by InstabilityMichael Crawshaw, Blake Woodworth, Mingrui Liu. [doi]
• FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearchVirginia Aglietti, Ira Ktena, Jessica Schrouff, Eleni Sgouritsa, Francisco J. R. Ruiz, Alan Malek, Alexis Bellot, Silvia Chiappa. [doi]
• A Sub-Problem Quantum Alternating Operator Ansatz for Correlation ClusteringLucas Fabian Naumann, Jannik Irmai, Bjoern Andres. [doi]
• Latent Diffusion Planning for Imitation LearningAmber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn. [doi]
• MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and EfficiencyDongzhi Jiang, Renrui Zhang, Ziyu Guo, Yanwei Li, Yu Qi, Xinyan Chen 0001, Liuhui Wang, Jianhan Jin, Claire Guo, Shen Yan, Bo Zhang 0069, Chaoyou Fu, Peng Gao 0007, Hongsheng Li 0001. [doi]
• Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental DesignMarcel Hedman, Desi R. Ivanova, Cong Guan, Tom Rainforth. [doi]
• Cross-Modal Alignment via Variational Copula ModellingFeng Wu, Tsai Hor Chan, Fuying Wang, Guosheng Yin, Lequan Yu. [doi]
• Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNNTalal Widatalla, Richard W. Shuai, Brian Hie, Possu Huang. [doi]
• FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic PotentialsSeung Yul Lee, Hojoon Kim, Yutack Park, Dawoon Jeong, Seungwu Han, Yeonhong Park, Jae W. Lee. [doi]
• Consensus Based Stochastic Optimal ControlLiyao Lyu, Jingrun Chen. [doi]
• Dimension-Free Adaptive Subgradient Methods with Frequent DirectionsSifan Yang, Yuanyu Wan, Peijia Li, Yibo Wang 0005, Xiao Zhang, Zhewei Wei, Lijun Zhang 0005. [doi]
• Design Considerations in Offline Preference-based RLAlekh Agarwal, Christoph Dann, Teodor Vanislavov Marinov. [doi]
• Mastering Board Games by External and Internal Planning with Language ModelsJohn Schultz, Jakub Adámek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada A. Lewis, Anian Ruoss, Tom Zahavy, Petar Velickovic, Laurel Prince, Satinder Singh 0001, Eric Malmi, Nenad Tomasev. [doi]
• Survival Analysis via Density EstimationHiroki Yanagisawa, Shunta Akiyama. [doi]
• Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaosChristian Pedersen, Laure Zanna, Joan Bruna. [doi]
• Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian ProcessesSidhanth Holalkere, David Bindel, Silvia Sellán, Alexander Terenin. [doi]
• Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language ModelsShuoyuan Wang, Yixuan Li 0001, Hongxin Wei. [doi]
• Tensorized Multi-View Multi-Label Classification via Laplace Tensor RankQiyu Zhong, Yi Shan, Haobo Wang 0001, Zhen Yang 0004, Gengyu Lyu. [doi]
• Discrepancy Minimization in Input-Sparsity TimeYichuan Deng 0002, Xiaoyu Li, Zhao Song 0002, Omri Weinstein. [doi]
• Sable: a Performant, Efficient and Scalable Sequence Model for MARLOmayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Simon du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Juan Claude Formanek, Liam Clark, Arnu Pretorius. [doi]
• Gradient Boosting Reinforcement LearningBenjamin Fuhrer, Chen Tessler, Gal Dalal. [doi]
• Vintix: Action Model via In-Context Reinforcement LearningAndrei Polubarov, Nikita Lyubaykin, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin, Vladislav Kurenkov. [doi]
• Unlocking the Power of SAM 2 for Few-Shot SegmentationQianxiong Xu, Lanyun Zhu, Xuanyi Liu, Guosheng Lin, Cheng Long 0001, Ziyue Li 0002, Rui Zhao 0001. [doi]
• FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-IdentificationZhen Sun, Lei Tan, Yunhang Shen, Chengmao Cai, Xing Sun 0001, Pingyang Dai, Liujuan Cao, Rongrong Ji. [doi]
• GrokFormer: Graph Fourier Kolmogorov-Arnold TransformersGuoguoAi, Guansong Pang, Hezhe Qiao, Yuan Gao, Hui Yan. [doi]
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty AgentsJen-tse Huang 0001, Jiaxu Zhou, Tailin Jin, Xuhui Zhou, Zixi Chen, Wenxuan Wang 0001, Youliang Yuan, Michael R. Lyu, Maarten Sap. [doi]
• HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal TransportYanbei Liu, Chongxu Wang, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang 0017. [doi]
• Sounding that Object: Interactive Object-Aware Image to Audio GenerationTingle Li, Baihe Huang, Xiaobin Zhuang, Dongya Jia, Jiawei Chen, Yuping Wang 0005, Zhuo Chen 0006, Gopala Anumanchipalli, Yuxuan Wang 0002. [doi]
• Learning to Stop: Deep Learning for Mean Field Optimal StoppingLorenzo Magnino, Yuchen Zhu, Mathieu Laurière. [doi]
• Cape: Context-Aware Prompt Perturbation Mechanism with Differential PrivacyHaoqi Wu, Wei Dai, Li Wang, Qiang Yan. [doi]
• Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement LearningLang Feng 0002, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu 0001, Ming Yan 0008, Fei Huang 0002, Bo An 0001. [doi]
• Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman AlgorithmsDetian Zhang, Chengqiang Zhang, Yanghui Rao, Li Qing, Chunjiang Zhu. [doi]
• unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary ReasoningYafei Yang, Zihui Zhang, Bo Yang 0027. [doi]
• From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMsAng Cao, Sergio Arnaud, Oleksandr Maksymets, Jianing Yang, Ayush Jain, Ada Martin, Vincent-Pierre Berges, Paul McVay, Ruslan Partsey, Aravind Rajeswaran, Franziska Meier, Justin Johnson 0001, Jeong-Joon Park, Alexander Sax. [doi]
• PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete DiffusionSophia Tang, Yinuo Zhang, Pranam Chatterjee. [doi]
• Towards characterizing the value of edge embeddings in Graph Neural NetworksDhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu 0001, Ankur Moitra, Andrej Risteski. [doi]
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual RepresentationsYucheng Hu, Yanjiang Guo, Pengchao Wang, Xiaoyu Chen, Yen-Jen Wang, Jianke Zhang, Koushil Sreenath, Chaochao Lu, Jianyu Chen 0002. [doi]
• Hyperband-based Bayesian Optimization for Black-box Prompt SelectionLennart Schneider, Martin Wistuba, Aaron Klein, Jacek Golebiowski, Giovanni Zappella, Felice Antonio Merra. [doi]
• Overtrained Language Models Are Harder to Fine-TuneJacob Mitchell Springer, Sachin Goyal, Kaiyue Wen, Tanishq Kumar, Xiang Yue, Sadhika Malladi, Graham Neubig, Aditi Raghunathan. [doi]
• Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian ProcessesWeihan Li, Yule Wang, Chengrui Li, Anqi Wu. [doi]
• Detecting Strategic Deception with Linear ProbesNicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim, Marius Hobbhahn. [doi]
• Approximately Correct Label Distribution LearningWeiwei Li 0001, Haitao Wu, Yunan Lu 0002, Xiuyi Jia. [doi]
• Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall CapacityNingyuan Teresa Huang, Miguel Sarabia, Abhinav Moudgil, Pau Rodríguez, Luca Zappella, Federico Danieli. [doi]
• Positional Attention: Expressivity and Learnability of Algorithmic ComputationArtur Back de Luca, George Giapitzakis, Shenghao Yang 0002, Petar Velickovic, Kimon Fountoulakis. [doi]
• MetricEmbedding: Accelerate Metric Nearness by Tropical Inner ProductMuyang Cao, Jiajun Yu, Xin Du 0002, Gang Pan 0001, Wei Wang 0011. [doi]
• The Price of Linear Time: Error Analysis of Structured Kernel InterpolationAlexander Moreno, Justin Xiao, Jonathan Mei. [doi]
• MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation ModelsMahir Labib Dihan, Md Tanvir Hassan, Md Tanvir Parvez, Md Hasebul Hasan, Md Almash Alam, Muhammad Aamir Cheema, Mohammed Eunus Ali, Md. Rizwan Parvez. [doi]
• Efficient Federated Incomplete Multi-View ClusteringSuyuan Liu, Hao Yu 0017, Hao Tan, Ke Liang 0006, Siwei Wang 0001, Shengju Yu, En Zhu, Xinwang Liu 0002. [doi]
• Geometric Generative Modeling with Noise-Conditioned Graph NetworksPeter Pao-Huang, Mitchell Black 0002, Xiaojie Qiu. [doi]
• Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM DetectionZhipeng Wei, Yuqi Liu, N. Benjamin Erichson. [doi]
• LineFlow: A Framework to Learn Active Control of Production LinesKai Müller, Martin Wenzel, Tobias Windisch. [doi]
• PAC-Bayes Analysis for Recalibration in ClassificationMasahiro Fujisawa, Futoshi Futami. [doi]
• Massive Values in Self-Attention Modules are the Key to Contextual Knowledge UnderstandingMingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui Liu 0001, Yongfeng Zhang 0003. [doi]
• Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models StrongerQi Yang 0015, Chenghao Zhang 0003, Lubin Fan, Kun Ding, Jieping Ye, Shiming Xiang. [doi]
• On Mitigating Affinity Bias through Bandits with Evolving Biased FeedbackMatthew Faw, Constantine Caramanis, Jessica Hoffmann. [doi]
• Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From DataKrzysztof Kacprzyk, Julianna Piskorz, Mihaela van der Schaar. [doi]
• Improved Algorithm for Deep Active Learning under Imbalance via Optimal SeparationShyam Nuggehalli, Jifan Zhang, Lalit K. Jain, Robert D. Nowak. [doi]
• Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning AbilitiesSreyan Ghosh, Zhifeng Kong, Sonal Kumar, S. Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro. [doi]
• Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction UncertaintyYeseul Cho, Baekrok Shin, Changmin Kang, Chulhee Yun. [doi]
• What makes an Ensemble (Un) Interpretable?Shahaf Bassan, Guy Amir, Meirav Zehavi, Guy Katz. [doi]
• Simple Randomized Rounding for Max-Min Eigenvalue AugmentationJourdain B. Lamperski, Haeseong Yang, Oleg A. Prokopyev. [doi]
• Tensor Decomposition Based Memory-Efficient Incremental LearningYuhang Li, GuoXu Zhou, Zhenhao Huang, Xinqi Chen, Yuning Qiu, Qibin Zhao. [doi]
• Learnware Specification via Dual AlignmentWei Chen 0141, Junxiang Mao, Xiaozheng Wang, Min-Ling Zhang. [doi]
• MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch TrainingYang Luo, Zangwei Zheng, Ziheng Qin, Zirui Zhu, Yong Liu 0020, Yang You 0001. [doi]
• RelGNN: Composite Message Passing for Relational Deep LearningTianlang Chen, Charilaos I. Kanatsoulis, Jure Leskovec. [doi]
• Improving the Scaling Laws of Synthetic Data with Deliberate PracticeReyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano. [doi]
• Optimal Decision Tree Pruning Revisited: Algorithms and ComplexityJuha Harviainen, Frank Sommer, Manuel Sorge, Stefan Szeider. [doi]
• SlimLLM: Accurate Structured Pruning for Large Language ModelsJialong Guo, Xinghao Chen 0001, Yehui Tang, Yunhe Wang 0001. [doi]
• Provable and Practical Online Learning Rate Adaptation with Hypergradient DescentYa-Chi Chu, Wenzhi Gao, Yinyu Ye 0001, Madeleine Udell. [doi]
• IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion ModelingKuan-Po Huang, Shu-Wen Yang, Huy Phan, Bo-Ru Lu, Byeonggeun Kim, Sashank Macha, Qingming Tang, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, Chao Wang. [doi]
• Learning Representations of Instruments for Partial Identification of Treatment EffectsJonas Schweisthal, Dennis Frauen, Maresa Schröder, Konstantin Hess, Niki Kilbertus, Stefan Feuerriegel. [doi]
• Jacobian Sparse Autoencoders: Sparsify Computations, Not Just ActivationsLucy Farnik, Tim Lawson, Conor Houghton, Laurence Aitchison. [doi]
• Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling LawsXiyuan Wei, Ming Lin, Fanjiang Ye, Fengguang Song, Liangliang Cao, My T. Thai, Tianbao Yang. [doi]
• When Maximum Entropy Misleads Policy OptimizationRuipeng Zhang, Ya-Chien Chang, Sicun Gao. [doi]
• Peri-LN: Revisiting Normalization Layer in the Transformer ArchitectureJeonghoon Kim, Byeongchan Lee 0001, Cheonbok Park, Yeontaek Oh, Beomjun Kim, Taehwan Yoo, Seongjin Shin, Dongyoon Han, Jinwoo Shin, Kang Min Yoo. [doi]
• Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant EvaluationSadegh Mahdavi, Muchen Li, Kaiwen Liu, Christos Thrampoulidis, Leonid Sigal, Renjie Liao. [doi]
• FlowAR: Scale-wise Autoregressive Image Generation Meets Flow MatchingSucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Alan L. Yuille, Liang-Chieh Chen. [doi]
• Preference learning made easy: Everything should be understood through win rateLily H. Zhang, Rajesh Ranganath. [doi]
• PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive SamplingAvery Ma, Yangchen Pan, Amir Massoud Farahmand. [doi]
• Language Models over Canonical Byte-Pair EncodingsTim Vieira, Tianyu Liu 0004, Clemente Pasti, Yahya Emara, Brian DuSell, Benjamin LeBrun, Mario Giulianelli, Juan Luis Gastaldi, Timothy J. O'Donnell, Ryan Cotterell. [doi]
• Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset SelectionZhijing Wan, Zhixiang Wang 0001, Zheng Wang 0007, Xin Xu 0007, Shin'ichi Satoh 0001. [doi]
• Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement LearningAnna Soligo, Pietro Ferraro, David Boyle 0001. [doi]
• Chaos Meets Attention: Transformers for Large-Scale Dynamical PredictionYi He, Yiming Yang, Xiaoyuan Cheng, Hai Wang, Xiao Xue, Boli Chen, Yukun Hu. [doi]
• Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian PlannerChunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee, Nakul Agarwal, Sean Dae Houlihan, Soroush Vosoughi, Shao-Yuan Lo. [doi]
• Feature out! Let Raw Image as Your Condition for Blind Face RestorationXinmin Qiu, Gege Chen, Bonan Li, Congying Han, Tiande Guo, Zicheng Zhang. [doi]
• Distributionally Robust Active Learning for Gaussian Process RegressionShion Takeno, Yoshito Okura, Yu Inatsu, Tatsuya Aoyama, Tomonari Tanaka, Satoshi Akahane, Hiroyuki Hanada, Noriaki Hashimoto, Taro Murayama, Hanju Lee, Shinya Kojima, Ichiro Takeuchi. [doi]
• Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial JacobianThomas Paniagua, Chinmay Savadikar, Tianfu Wu 0001. [doi]
• Self-Bootstrapping for Versatile Test-Time AdaptationShuaicheng Niu, Guohao Chen, Peilin Zhao, Tianyi Wang 0006, Pengcheng Wu, Zhiqi Shen 0001. [doi]
• Hypo3D: Exploring Hypothetical Reasoning in 3DYe Mao, Weixun Luo, Junpeng Jing, Anlan Qiu, Krystian Mikolajczyk. [doi]
• MM-RLHF: The Next Step Forward in Multimodal LLM AlignmentYifan Zhang 0004, Tao Yu, Haochen Tian 0001, Chaoyou Fu, Peiyan Li, Jianshu Zeng, Wulin Xie, Yang Shi 0009, Huanyu Zhang, Junkang Wu, Xue Wang 0010, Yibo Hu, Bin Wen, Tingting Gao, Zhang Zhang 0001, Fan Yang 0094, Di Zhang 0026, Liang Wang 0001, Rong Jin 0001. [doi]
• FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic IntelligenceYichen Li 0006, Yuying Wang, Haozhao Wang, Yining Qi, Tianzhe Xiao, Ruixuan Li 0001. [doi]
• Implicit degree bias in the link prediction taskRachith Aiyappa, Xin Wang, Munjung Kim, Ozgur Can Seckin, Yong-Yeol Ahn, Sadamori Kojaku. [doi]
• Scalable Model Merging with Progressive Layer-wise DistillationJing Xu 0027, Jiazheng Li 0015, Jingzhao Zhang. [doi]
• Inductive Gradient Adjustment for Spectral Bias in Implicit Neural RepresentationsKexuan Shi, Hai Chen, Leheng Zhang, Shuhang Gu. [doi]
• Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of PerspectiveDaniel Franzen, Jan Disselhoff, David Hartmann. [doi]
• Provable In-Context Vector Arithmetic via Retrieving Task ConceptsDake Bu, Wei Huang 0034, Andi Han, Atsushi Nitanda, Qingfu Zhang 0001, Hau-San Wong, Taiji Suzuki. [doi]
• Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term PlanningYuhui Wang 0004, Qingyuan Wu, Dylan R. Ashley, Francesco Faccio, Weida Li, Chao Huang 0015, Jürgen Schmidhuber. [doi]
• MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard PerturbationsKaixuan Huang, Jiacheng Guo, Zihao Li, Xiang Ji, Jiawei Ge 0003, Wenzhe Li, Yingqing Guo, Tianle Cai, Hui Yuan 0002, Runzhe Wang, Yue Wu, Ming Yin 0003, Shange Tang, Yangsibo Huang, Chi Jin 0001, Xinyun Chen, Chiyuan Zhang, Mengdi Wang 0001. [doi]
• Instruction-Following Pruning for Large Language ModelsBairu Hou, Qibin Chen, Jianyu Wang, Guoli Yin, Chong Wang, Nan Du, Ruoming Pang, Shiyu Chang, Tao Lei. [doi]
• Knowledge Swapping via Learning and UnlearningMingyu Xing, Lechao Cheng, Shengeng Tang, Yaxiong Wang, Zhun Zhong, Meng Wang 0001. [doi]
• FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient EstimationSrijith Nair, Michael Lin, Peizhong Ju, Amirreza Talebi, Elizabeth Serena Bentley, Jia Liu 0002. [doi]
• Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight AveragingJunkang Liu, Yuanyuan Liu 0001, Fanhua Shang, Hongying Liu 0001, Jin Liu, Wei Feng 0005. [doi]
• Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with TransformersRoman Abramov, Felix Steinbauer, Gjergji Kasneci. [doi]
• TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series RepresentationDaoyu Wang, Mingyue Cheng, Zhiding Liu, Qi Liu 0003. [doi]
• Learning Parametric Distributions from Samples and PreferencesMarc Jourdan, Gizem Yüce, Nicolas Flammarion. [doi]
• WyckoffDiff - A Generative Diffusion Model for Crystal SymmetryFilip Ekström Kelvinius, Oskar B. Andersson, Abhijith S. Parackal, Dong Qian, Rickard Armiento, Fredrik Lindsten. [doi]
• Underestimated Privacy Risks for Minority Populations in Large Language Model UnlearningRongzhe Wei, Mufei Li, Mohsen Ghassemi, Eleonora Kreacic, Yifan Li, Xiang Yue, Bo Li 0026, Vamsi K. Potluru, Pan Li 0005, Eli Chien. [doi]
• Weak-to-Strong Generalization Even in Random Feature Networks, ProvablyMarko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li 0005, Nathan Srebro. [doi]
• Visual Autoregressive Modeling for Image Super-ResolutionYunpeng Qu, Kun Yuan 0003, Jinhua Hao, Kai Zhao 0011, Qizhi Xie, Ming Sun 0008, Chao Zhou 0003. [doi]
• A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy DataCailong Hua, Sivaraman Rajaganapathy, Rebecca A. Slick, Joseph Vavra, Joseph M. Muretta, James M. Ervasti, Murti V. Salapaka. [doi]
• An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception CapabilityDaiqing Wu, Dongbao Yang, Sicheng Zhao, Can Ma, Yu Zhou 0015. [doi]
• RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned PriorChing Hua Lee, Chouchang Yang, Jaejin Cho, Yashas Malur Saidutta, Rakshith Sharma Srinivasa, Yilin Shen, Hongxia Jin. [doi]
• Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation ClassesJesse He, Helen Jenne, Herman Chau, Davis Brown, Mark Raugas, Sara C. Billey, Henry Kvinge. [doi]
• Cost-efficient Collaboration between On-device and Cloud Language ModelsAvanika Narayan, Dan Biderman, Sabri Eyuboglu, Avner May, Scott W. Linderman, James Zou 0001, Christopher Ré. [doi]
• MedXpertQA: Benchmarking Expert-Level Medical Reasoning and UnderstandingYuxin Zuo, Shang Qu, Yifei Li, Zhang-Ren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding 0002, Bowen Zhou 0002. [doi]
• Leveraging Model Guidance to Extract Training Data from Personalized Diffusion ModelsXiaoyu Wu, Jiaru Zhang, Steven Wu 0001. [doi]
• FrameBridge: Improving Image-to-Video Generation with Bridge ModelsYuji Wang, Zehua Chen, Xiaoyu Chen, Yixiang Wei, Jun Zhu 0001, Jianfei Chen 0001. [doi]
• Optimal Algorithm for Max-Min Fair BanditZilong Wang 0010, Zhiyao Zhang, Shuai Li 0010. [doi]
• Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition ConstraintsQixin Zhang 0001, Wei Huang, Can Jin, Puning Zhao, Yao Shu, Li Shen 0008, Dacheng Tao. [doi]
• CoSER: Coordinating LLM-Based Persona Simulation of Established RolesXintao Wang 0001, Heng Wang, Yifei Zhang, Xinfeng Yuan, Rui Xu 0026, Jen-tse Huang 0001, Siyu Yuan, Haoran Guo, Jiangjie Chen, Shuchang Zhou 0003, Wei Wang 0009, Yanghua Xiao. [doi]
• Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian LensJihwan Jeong, Xiaoyu Wang, Jingmin Wang, Scott Sanner, Pascal Poupart. [doi]
• Confounder-Free Continual Learning via Recursive Feature NormalizationYash Shah, Camila González, Mohammad Hasan Abbasi, Qingyu Zhao, Kilian M. Pohl, Ehsan Adeli 0001. [doi]
• End-to-End Learning Framework for Solving Non-Markovian Optimal ControlXiaole Zhang, Peiyu Zhang 0002, Xiongye Xiao, Shixuan Li, Vasileios Tzoumas, Vijay Gupta, Paul Bogdan. [doi]
• Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms?Yaolong Yu, Fan Yao 0002, Sinno Jialin Pan. [doi]
• Compositional Generalization via Forced Rendering of Disentangled LatentsQiyao Liang, Daoyuan Qian, Liu Ziyin 0001, Ila R. Fiete. [doi]
• A Simple Model of Inference Scaling LawsNoam Itzhak Levi. [doi]
• Learning Progress Driven Multi-Agent CurriculumWenshuai Zhao, Zhiyuan Li, Joni Pajarinen. [doi]
• Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix RecoveryParis Giampouras, HanQin Cai, René Vidal. [doi]
• Revisiting Differentially Private Algorithms for Decentralized Online LearningXiaoyu Wang, Wenhao Yang, Chang Yao 0001, Mingli Song, Yuanyu Wan. [doi]
• The Jailbreak Tax: How Useful are Your Jailbreak Outputs?Kristina Nikolic, Luze Sun, Jie Zhang 0107, Florian Tramèr. [doi]
• Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse AgentsShayan Kiyani, George J. Pappas, Aaron Roth 0001, Hamed Hassani. [doi]
• Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision TransformerYilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang 0018, Li Shen 0008, Xueqian Wang 0001, Dacheng Tao. [doi]
• Identifying and Understanding Cross-Class Features in Adversarial TrainingZeming Wei, Steven Y. Guo, Yisen Wang 0001. [doi]
• Offline Opponent Modeling with Truncated Q-driven Instant Policy RefinementYuheng Jing, Kai Li 0022, Bingyun Liu, Ziwen Zhang, Haobo Fu, Qiang Fu 0016, Junliang Xing, Jian Cheng 0001. [doi]
• What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuningZuchao Li, Yonghua Hei, Qiwei Li 0002, Lefei Zhang, Ping Wang 0028, Hai Zhao 0001, Baoyuan Qi, Liu Guoming. [doi]
• Fluctuations of the largest eigenvalues of transformed spiked Wigner matricesAro Lee, Ji Oon Lee. [doi]
• Avoiding Leakage Poisoning: Concept Interventions Under Distribution ShiftsMateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik. [doi]
• Spatial Reasoning with Denoising ModelsChristopher Wewer, Bartlomiej Pogodzinski, Bernt Schiele, Jan Eric Lenssen. [doi]
• FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow FieldsGwanhyeong Koo, Sunjae Yoon, Younghwan Lee, Ji Woo Hong, Chang D. Yoo. [doi]
• From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and ReasoningJinyu Wang, Jingjing Fu, Rui Wang 0028, Lei Song 0001, Jiang Bian 0002. [doi]
• Approximate Differential Privacy of the ℓ2 MechanismMatthew Joseph, Alex Kulesza, Alexander Yu. [doi]
• Thinking LLMs: General Instruction Following with Thought GenerationTianhao Wu 0002, Janice Lan, Weizhe Yuan, Jiantao Jiao, Jason E. Weston, Sainbayar Sukhbaatar. [doi]
• False Coverage Proportion Control for Conformal PredictionAlexandre Blain, Bertrand Thirion, Pierre Neuvial. [doi]
• Heterogeneous Sufficient Dimension Reduction and Subspace ClusteringLei Yan, Xin Zhang, Qing Mai. [doi]
• PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff DropChenyu Li, Oscar Michel, Xichen Pan, Sainan Liu, Mike Roberts, Saining Xie. [doi]
• Isolated Causal Effects of Natural LanguageVictoria Lin 0001, Louis-Philippe Morency, Eli Ben-Michael. [doi]
• Learning with Selectively Labeled Data from Multiple Decision-makersJian Chen, Zhehao Li, Xiaojie Mao. [doi]
• A First-order Generative Bilevel Optimization Framework for Diffusion ModelsQuan Xiao, Hui Yuan 0002, A. F. M. Saif, Gaowen Liu, Ramana Rao Kompella, Mengdi Wang 0001, Tianyi Chen. [doi]
• Should Decision-Makers Reveal Classifiers in Online Strategic Classification?Han Shao, Shuo Xie, Kunhe Yang. [doi]
• Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target RecognitionChong Zhang, Peng Zhang, Mengke Li 0001. [doi]
• Enabling Optimal Decisions in Rehearsal Learning under CARE ConditionWen-Bo Du 0002, Hao-Yi Lei, Lue Tao, Tian-Zuo Wang, Zhi-Hua Zhou. [doi]
• The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal TransportChenrui Wang, Yixuan Qiu. [doi]
• Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric GamesJiawei Ge 0003, Yuanhao Wang 0001, Wenzhe Li, Chi Jin 0001. [doi]
• CLOVER: Cross-Layer Orthogonal Vectors PruningFanxu Meng, Pingzhi Tang, Fan Jiang, Muhan Zhang. [doi]
• Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local MeasurementsManwen Liao, Yan Zhu, Weitian Zhang, Yuxiang Yang. [doi]
• Softmax is not Enough (for Sharp Size Generalisation)Petar Velickovic, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu. [doi]
• NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent KernelGabriel Thompson, Kai Yue, Chau-Wai Wong, Huaiyu Dai. [doi]
• BiMark: Unbiased Multilayer Watermarking for Large Language ModelsXiaoyan Feng, He Zhang 0012, Yanjun Zhang, Leo Yu Zhang, Shirui Pan. [doi]
• Floating-Point Neural Networks Can Represent Almost All Floating-Point FunctionsGeonho Hwang, Yeachan Park, Wonyeol Lee 0001, Sejun Park. [doi]
• Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between SamplesXize Liang, Lin Yang 0009, Jie Wang 0005, Yiyang Lu, Runyu Wu, Hanzhu Chen, Jianye Hao. [doi]
• ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference OptimizationHee Suk Yoon, Eunseop Yoon, Mark A. Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo. [doi]
• Scaffold with Stochastic Gradients: New Analysis with Linear Speed-UpPaul Mangold, Alain Oliviero Durmus, Aymeric Dieuleveut, Eric Moulines. [doi]
• RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector QuantizationChen Xu, Yuxuan Yue, Zukang Xu, Xing Hu 0010, Jiangyong Yu, Zhixuan Chen, Sifan Zhou, Zhihang Yuan, Dawei Yang. [doi]
• Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder PerspectiveSeungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal 0001. [doi]
• An Error Analysis of Flow Matching for Deep Generative ModelingZhengyu Zhou, Weiwei Liu 0003. [doi]
• Stay-Positive: A Case for Ignoring Real Image Features in Fake Image DetectionAnirudh Sundara Rajan, Yong Jae Lee. [doi]
• Efficiently Access Diffusion Fisher: Within the Outer Product Span SpaceFangyikang Wang, Hubery Yin, Shaobin Zhuang, Huminhao Zhu, Yinan Li, Lei Qian, Chao Zhang 0029, Hanbin Zhao, Hui Qian 0001, Chen Li 0031. [doi]
• Optimal and Practical Batched Linear Bandit AlgorithmSanghoon Yu, Min-hwan Oh. [doi]
• No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural NetworksAttila Szász, Balázs Bánhelyi, Márk Jelasity. [doi]
• Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?Simon Park 0002, Abhishek Panigrahi, Yun Cheng, Dingli Yu, Anirudh Goyal, Sanjeev Arora. [doi]
• DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMsJongwoo Ko, Tianyi Chen, Sungnyun Kim, Tianyu Ding, Luming Liang, Ilya Zharkov, Se-Young Yun. [doi]
• Sample Efficient Demonstration Selection for In-Context LearningKiran Purohit, Venktesh V, Sourangshu Bhattacharya, Avishek Anand. [doi]
• The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward ModelsZichao Li, Xueru Wen, Jie Lou, Yuqiu Ji, Yaojie Lu 0001, Xianpei Han, Debing Zhang, Le Sun 0001. [doi]
• Cover learning for large-scale topology representationLuis Scoccola, Uzu Lim, Heather A. Harrington. [doi]
• Direct Motion Models for Assessing Generated VideosKelsey R. Allen, Carl Doersch, Guangyao Zhou, Mohammed Suhail, Danny Driess, Ignacio Rocco, Yulia Rubanova, Thomas Kipf, Mehdi S. M. Sajjadi, Kevin Patrick Murphy, João Carreira 0001, Sjoerd van Steenkiste. [doi]
• Diffusion-based Adversarial Purification from the Perspective of the Frequency DomainGaozheng Pei, Ke Ma 0001, Yingfei Sun, Qianqian Xu 0001, Qingming Huang. [doi]
• Probably Approximately Global Robustness CertificationPeter Blohm, Patrick Indri, Thomas Gärtner 0001, Sagar Malhotra. [doi]
• CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation ModelsWei Dai 0013, Peilin Chen, Malinda Lu, Daniel Li, Haowen Wei, Hejie Cui, Paul Pu Liang. [doi]
• Disparate Conditional Prediction in Multiclass ClassifiersSivan Sabato, Eran Treister, Elad Yom-Tov. [doi]
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV CacheRishabh Tiwari, Haocheng Xi, Aditya Tomar, Coleman Richard Charles Hooper, Sehoon Kim 0001, Maxwell Horton, Mahyar Najibi, Michael W. Mahoney, Kurt Keutzer, Amir Gholami. [doi]
• Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field RegimeDiyuan Wu, Marco Mondelli. [doi]
• SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point CloudsAli Bahri, Moslem Yazdanpanah, Sahar Dastani, Mehrdad Noori, Gustavo Adolfo Vargas Hakim, David Osowiechi, Farzad Beizaee, Ismail Ben Ayed, Christian Desrosiers. [doi]
• Multi-Objective Causal Bayesian OptimizationShriya Bhatija, Paul-David Joshua Zuercher, Jakob Thumm, Thomas Bohné. [doi]
• Counterfactual Effect Decomposition in Multi-Agent Sequential Decision MakingStelios Triantafyllou, Aleksa Sukovic, Yasaman Zolfimoselo, Goran Radanovic. [doi]
• Transformative or Conservative? Conservation laws for ResNets and TransformersSibylle Marcotte, Rémi Gribonval, Gabriel Peyré. [doi]
• On the Training Convergence of Transformers for In-Context Classification of Gaussian MixturesWei Shen, Ruida Zhou, Jing Yang 0002, Cong Shen 0001. [doi]
• FDGen: A Fairness-Aware Graph Generation ModelZichong Wang, Wenbin Zhang. [doi]
• Robust Autonomy Emerges from Self-PlayMarco Francis Cusumano-Towner, David Hafner, Alexander Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor W. Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun. [doi]
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceYuan Zhang 0020, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng, Tao Huang 0020, Kuan Cheng, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang. [doi]
• How Do Large Language Monkeys Get Their Power (Laws)?Rylan Schaeffer, Joshua Kazdan, John Hughes, Jordan Juravsky, Sara Price, Aengus Lynch, Erik Jones, Robert Kirk, Azalia Mirhoseini, Sanmi Koyejo. [doi]
• Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement LearningMehrdad Moghimi, Hyejin Ku. [doi]
• The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial ConditionsGül Sena Altintas, Devin Kwok, Colin Raffel, David Rolnick. [doi]
• Persistent Topological Features in Large Language ModelsYuri Gardinazzi, Karthik Viswanathan, Giada Panerai, Alessio Ansuini, Alberto Cazzaniga, Matteo Biagetti. [doi]
• TabICL: A Tabular Foundation Model for In-Context Learning on Large DataJingang Qu, David Holzmüller, Gaël Varoquaux, Marine Le Morvan. [doi]
• Textural or Textual: How Vision-Language Models Read Text in ImagesHanzhang Wang, Qingyuan Ma. [doi]
• Stable Offline Value Function Learning with Bisimulation-based RepresentationsBrahma S. Pavse, Yudong Chen 0001, Qiaomin Xie, Josiah P. Hanna. [doi]
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-VerificationHyunseok Lee, Seunghyuk Oh, Jaehyung Kim 0001, Jinwoo Shin, Jihoon Tack. [doi]
• TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel OptimizationSongtao Lu. [doi]
• Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful ContributionAlex Clinton, Yiding Chen, Jerry Zhu, Kirthevasan Kandasamy. [doi]
• Local Pan-privacy for Federated AnalyticsVitaly Feldman, Audra McMillan, Guy N. Rothblum, Kunal Talwar. [doi]
• Graph-Assisted Stitching for Offline Hierarchical Reinforcement LearningSeungho Baek, Tae-Geon Park, Jongchan Park, Seungjun Oh, Yusung Kim 0001. [doi]
• The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model InferenceZeyu Yang, Wesley Armour. [doi]
• Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank AdaptationZhan Zhuang, Xiequn Wang, Wei Li, Yulong Zhang 0005, Qiushi Huang, Shuhao Chen, Xuehao Wang, Yanbin Wei, Yuhe Nie, Kede Ma, Yu Zhang 0006, Ying Wei 0001. [doi]
• ResearchTown: Simulator of Human Research CommunityHaofei Yu, Zhaochen Hong, Zirui Cheng, Kunlun Zhu, Keyang Xuan, Jinwei Yao, Tao Feng, Jiaxuan You. [doi]
• BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion ModelingHao Li 0074, Yu-Hao Huang 0002, Chang Xu 0008, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian 0002. [doi]
• Learning Extrapolative Sequence Transformations from Markov ChainsSophia Hager, Aleem Khan, Andrew Wang, Nicholas Andrews. [doi]
• From Logits to Hierarchies: Hierarchical Clustering made SimpleEmanuele Palumbo, Moritz Vandenhirtz, Alain Ryser, Imant Daunhawer, Julia E. Vogt. [doi]
• Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based CentralityJoshua Southern, Yam Eitan, Guy Bar-Shalom, Michael M. Bronstein, Haggai Maron, Fabrizio Frasca. [doi]
• Efficient Generative Modeling with Residual Vector Quantization-Based TokensJaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho. [doi]
• Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit AnalysisXu Wang 0033, Yan Hu, Wenyu Du, Reynold Cheng, Benyou Wang, Difan Zou. [doi]
• Nonparametric Identification of Latent ConceptsYujia Zheng 0001, Shaoan Xie, Kun Zhang 0001. [doi]
• Flexible and Efficient Grammar-Constrained DecodingKanghee Park, Timothy Zhou, Loris D'Antoni. [doi]
• Exploring Criteria of Loss Reweighting to Enhance LLM UnlearningPuning Yang, Qizhou Wang, Zhuo Huang, Tongliang Liu, Chengqi Zhang, Bo Han 0003. [doi]
• Density Ratio Estimation with Conditional Probability PathsHanlin Yu, Arto Klami, Aapo Hyvärinen, Anna Korba, Omar Chehab. [doi]
• Multiaccuracy and Multicalibration via Proxy GroupsBeepul Bharti, Mary Versa Clemens-Sewall, Paul H. Yi, Jeremias Sulam. [doi]
• Gradient-based Explanations for Deep Learning Survival ModelsSophie Hanna Langbein, Niklas Koenen, Marvin N. Wright. [doi]
• Enhancing Statistical Validity and Power in Hybrid Controlled Trials: A Randomization Inference Approach with Conformal Selective BorrowingKe Zhu, Shu Yang, Xiaofei Wang. [doi]
• HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series ForecastingBoyuan Li, Yicheng Luo, Zhen Liu 0023, Junhao Zheng, Jianming Lv, Qianli Ma 0001. [doi]
• Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated LearningHui Zeng, Wenke Huang 0003, Tongqing Zhou,