Table of Contents

• Bridging Expressivity and Scalability with Adaptive Unitary SSMsArjun Karuvally, Franz Nowak, T. Anderson Keller 0001, Carmen Amo Alonso, Terrence J. Sejnowski, Hava T. Siegelmann. [doi]
• Diffusion Transformers as Open-World Spatiotemporal Foundation ModelsYuan Yuan 0032, Chonghua Han, Jingtao Ding, Guozhen Zhang 0001, Depeng Jin, Yong Li 0008. [doi]
• CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep LearningNingyuan Teresa Huang, Richard Stiskalek, Jun-Young Lee, Adrian E. Bayer, Charles C. Margossian, Christian Kragh Jespersen, Lucia A. Perez, Lawrence K. Saul, Francisco Villaescusa-Navarro. [doi]
• Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data CurriculumWenquan Lu, Jiaqi Zhang, Hugues Van Assel, Randall Balestriero. [doi]
• Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental LimitsZiyi Zhang, Yorie Nakahira, Guannan Qu. [doi]
• PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware MechanismsYifei Xia, Shuchen Weng, Siqi Yang, Jingqi Liu, Chengxuan Zhu, Minggui Teng, Zijian Jia, Han Jiang, Boxin Shi. [doi]
• TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMsYunheng Li, Jing Cheng, Shaoyong Jia, Hangyi Kuang, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng. [doi]
• Discovering Symbolic Partial Differential Equation by Abductive LearningEn-Hao Gao, Cunjing Ge, Yuan Jiang 0001, Zhi-Hua Zhou. [doi]
• Trained Mamba Emulates Online Gradient Descent in In-Context Linear RegressionJiarui Jiang, Wei Huang 0034, Miao Zhang 0022, Taiji Suzuki, Liqiang Nie. [doi]
• Sparse Polyak: an adaptive step size rule for high-dimensional M-estimationTianqi Qiao, Marie Maros. [doi]
• Discovering Compositional Hallucinations in LVLMsSibei Yang, Ge Zheng, Jiajin Tang, Jiaye Qian, Hanzhuo Huang, Cheng Shi 0001. [doi]
• Put CASH on Bandits: A Max K-Armed Problem for Automated Machine LearningAmir Rezaei Balef, Claire Vernade, Katharina Eggensperger. [doi]
• PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMsJaewon Chu, Seunghun Lee 0001, Hyunwoo J. Kim. [doi]
• Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative ModelsJiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen, Ge Liu. [doi]
• A Temporal Difference Method for Stochastic Continuous DynamicsHaruki Settai, Naoya Takeishi, Takehisa Yairi. [doi]
• Convergence Theorems for Entropy-Regularized and Distributional Reinforcement LearningYash Jhaveri, Harley Wiltzer, Patrick Shafto, Marc G. Bellemare, David Meger. [doi]
• AdaSPEC: Selective Knowledge Distillation for Efficient Speculative DecodersYuezhou Hu, Jiaxin Guo, Xinyu Feng, Tuo Zhao. [doi]
• Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature TransformationNanxu Gong, Zijun Li, Sixun Dong, Haoyue Bai 0002, Wangyang Ying, Xinyuan Wang 0011, Yanjie Fu. [doi]
• COME: Adding Scene-Centric Forecasting Control to Occupancy World ModelYining Shi 0002, Kun Jiang 0002, Qiang Meng, Ke Wang 0021, Jiabao Wang, Wenchao Sun, Tuopu Wen, Mengmeng Yang 0001, Diange Yang. [doi]
• ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAGYikuan Hu, Jifeng Zhu, Lanrui Tang, Chen Huang 0006. [doi]
• Learning-Augmented Facility Location Mechanisms for Envy RatioHaris Aziz 0001, Yuhang Guo 0003, Alexander Lam, Houyu Zhou. [doi]
• A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth ApproximationQichao Cao, Shangzhi Zeng, Jin Zhang. [doi]
• p-Regularized Objectives Yield the Sparsest ReLU Neural NetworksJulia B. Nakhleh, Robert D. Nowak. [doi]
• Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-TuningArian Raje, Baris Askin, Divyansh Jhunjhunwala, Gauri Joshi. [doi]
• ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research CodeTianyu Hua, Harper Hua, Violet Xiang, Benjamin Klieger, Sang T. Truong, Weixin Liang, Fan-Yun Sun, Nick Haber. [doi]
• Semantic Surgery: Zero-Shot Concept Erasure in Diffusion ModelsLexiang Xiong, Chengyu Liu, Jingwen Ye, Yan Liu, Yuecong Xu. [doi]
• HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge RepresentationHaoran Luo 0001, Haihong E, Guanting Chen 0004, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng 0015, Zemin Kuang, Meina Song, Yifan Zhu 0001, Anh Tuan Luu. [doi]
• Correlated Low-Rank Adaptation for ConvNetsWu Ran, Weijia Zhang, Shuyang Pang, Qi Zhu, Jinfan Liu, Jingsheng Liu, Xin Cao, Qiang Li, Yichao Yan, Chao Ma. [doi]
• Understanding Adam Requires Better Rotation Dependent AssumptionsTianyue H. Zhang, Lucas Maes, Alan Milligan, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret. [doi]
• GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait predictionEya Cherif, Arthur Ouaknine, Luke A. Brown, Phuong D. Dao, Kyle R. Kovach, Bing Lu, Daniel Mederer, Hannes Feilhauer, Teja Kattenborn, David Rolnick. [doi]
• YEAST: Yet Another Sequential TestAlexey Kurennoy, Majed Dodin, Tural Gurbanov, Ana Peleteiro-Ramallo. [doi]
• Simple and Efficient Heterogeneous Temporal Graph Neural NetworkYili Wang 0005, Tairan Huang, Changlong He, Qiutong Li, Jianliang Gao. [doi]
• Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy DualityMincheol Park, Heeji Won, Won Woo Ro, Suhyun Kim 0001. [doi]
• Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person RetrievalDelong Liu, Haiwen Li, Zhaohui Hou, Zhicheng Zhao 0001, Fei Su, Yuan Dong. [doi]
• SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real TransferYarden As, Chengrui Qu, Benjamin Unger, DongHo Kang, Max van der Hart, Laixi Shi, Stelian Coros, Adam Wierman, Andreas Krause 0001. [doi]
• k Decoding for Language ModelsGeorgy Noarov, Soham Mallick, Tao Wang, Sunay Joshi, Yan Sun, Yangxinyu Xie, Mengxin Yu, Edgar Dobriban. [doi]
• HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate ClassJames V. Roggeveen, Erik Y. Wang, David Ettel, Will Flintoft, Peter Donets, Raglan Ward, Ahmed Roman, Anton Marius Graf, Siddharth Dandavate, Ava Williamson, Felix Yeung, Kacper K. Migacz, Yijun Wang, Egemen Bostan, Duy-Thuc Nguyen, Zhe He, Marc L. Descoteaux, Anne Mykland, Shida Liu, Jorge García Ponce, Luke Zhu, Yuyang Chen, Ekaterina S. Ivshina, Miguel Fernandez, Minjae Kim, Kennan Gumbs, Matthew Scott Tan, Russell Yang, Mai-Hoang, David Brown, Isabella A. Silveira, Lavon Sykes, Arjun Nageswaran, William Fredenberg, Yiming Chen, Lucas Martin, Yixing Tang, Kelly Werker Smith, Hongyu Liao, Logan G. Wilson, Alexander Dazhen Cai, Lucy S. Nathwani, Nickholas Gutierrez, Andrea Elizabeth Biju, Michael P. Brenner. [doi]
• Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMsWanyun Cui, Mingwei Xu. [doi]
• Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RLSongjun Tu, Jiahao Lin, Qichao Zhang, Xiangyu Tian, Linjing Li, Xiangyuan Lan, Dongbin Zhao. [doi]
• GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture PreservationYi Dong, Yuxi Wang, Xianhui Lin, Wenqi Ouyang, Zhiqi Shen 0001, Peiran Ren, Ruoxi Fan, Rynson W. H. Lau. [doi]
• What Data Enables Optimal Decisions? An Exact Characterization for Linear OptimizationOmar Bennouna, Amine Bennouna, Saurabh Amin, Asuman Ozdaglar. [doi]
• Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied AgentsZhizhen Zhang, Lei Zhu 0002, Zhen Fang 0001, Zi Huang, Yadan Luo. [doi]
• Hybrid-Balance GFlowNet for Solving Vehicle Routing ProblemsNi Zhang, Zhiguang Cao. [doi]
• A faster training algorithm for regression trees with linear leaves, and an analysis of its complexityKuat Gazizov, Miguel Á. Carreira-Perpiñán. [doi]
• Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein BarycentresSamuel Howard, Peter Potaptchik, George Deligiannidis. [doi]
• True Impact of Cascade Length in Contextual Cascading BanditsHyun-Jun Choi, Joongkyu Lee, Min-hwan Oh. [doi]
• Tensor Product Attention Is All You NeedYifan Zhang 0029, Yifeng Liu 0004, Huizhuo Yuan, Zhen Qin, Yang Yuan 0010, Quanquan Gu, Andrew C. Yao. [doi]
• SpecReason: Fast and Accurate Inference-Time Compute via Speculative ReasoningRui Pan 0003, Yinwei Dai, Zhihao Zhang 0001, Gabriele Oliaro, Zhihao Jia, Ravi Netravali. [doi]
• LLM Unlearning via Neural Activation RedirectionWilliam F. Shen, Xinchi Qiu, Meghdad Kurmanji, Alex Iacob, Lorenzo Sani, Yihong Chen, Nicola Cancedda, Nicholas D. Lane. [doi]
• Boosting Generative Image Modeling via Joint Image-Feature SynthesisTheodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou, Spyridon Gidaris, Nikos Komodakis. [doi]
• A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at RandomBinh H. Ho, Long Nguyen Chi, TrungTin Nguyen, Van-Ha Hoang, Thanh Binh Nguyen, Chris Drovandi. [doi]
• PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion TransformersYuchen Lin 0006, Chenguo Lin, Panwang Pan, Honglei Yan, Yiqiang Feng, Yadong Mu, Katerina Fragkiadaki. [doi]
• Bisecle: Binding and Separation in Continual Learning for Video Language UnderstandingYue Tan, Xiaoqian Hu, Hao Xue 0001, Celso de Melo, Flora D. Salim. [doi]
• Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement LearningZhe Hu, Jing Li 0049, Zhongzhu Pu, Hou Pong Chan, Yu Yin 0001. [doi]
• AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchEdan Toledo, Karen Hambardzumyan, Martin Josifoski, Rishi Hazra, Nicolas Mario Baldwin, Alexis Audran-Reiss, Michael Kuchnik, Despoina Magka, Minqi Jiang, Alisia Maria Lupidi, Andrei Lupu, Roberta Raileanu, Tatiana Shavrina, Kelvin Niu, Jean-Christophe Gagnon-Audet, Michael Shvartsman, Shagun Sodhani, Alexander H. Miller, Abhishek Charnalia, Derek Dunfield, Carole-Jean Wu, Pontus Lars Erik Saito Stenetorp, Nicola Cancedda, Jakob N. Foerster, Yoram Bachrach. [doi]
• OmniGaze: Reward-inspired Generalizable Gaze Estimation in the WildHongyu Qu, Jianan Wei, Xiangbo Shu, Yazhou Yao, Wenguan Wang, Jinhui Tang 0001. [doi]
• Multiscale guidance of protein structure prediction with heterogeneous cryo-EM dataRishwanth Raghu, Axel Levy, Gordon Wetzstein, Ellen D. Zhong. [doi]
• Enhancing LLM Planning for Robotics Manipulation through Hierarchical Procedural Knowledge GraphsJiacong Zhou, Jiaxu Miao, Xianyun Wang, Jun Yu 0002. [doi]
• Let Them Talk: Audio-Driven Multi-Person Conversational Video GenerationZhe Kong, Feng Gao, Yong Zhang 0034, Zhuoliang Kang, Xiaoming Wei, Xunliang Cai, Guanying Chen, Wenhan Luo. [doi]
• Solving Inequality Proofs with Large Language ModelsJiayi Sheng, Luna Lyu, Jikai Jin, Tanglin Xia, Alex Gu, James Y. Zou, Pan Lu. [doi]
• Preference Learning with Response Time: Robust Losses and GuaranteesAyush Sawarni, Sahasrajit Sarmasarkar, Vasilis Syrgkanis. [doi]
• Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge IntegrationWenju Sun, Qingyong Li, Wen Wang 0019, Yang Liu, Yangliao Geng, Boyang Li 0001. [doi]
• Distilling LLM Agent into Small Models with Retrieval and Code ToolsMinki Kang, Jongwon Jeong, Seanie Lee, Jaewoong Cho, Sung Ju Hwang. [doi]
• Establishing Best Practices in Building Rigorous Agentic BenchmarksYuxuan Zhu 0003, Tengjun Jin, Yada Pruksachatkun, Andy Zhang, Shu Liu, Sasha Cui, Sayash Kapoor, Shayne Longpre, Kevin Meng, Rebecca Weiss, Fazl Barez, Rahul Gupta 0001, Jwala Dhamala, Jacob Merizian, Mario Giulianelli, Harry Coppock, Cozmin Ududec, Antony Kellermann, Jasjeet S. Sekhon, Jacob Steinhardt, Sarah Schwettmann, Arvind Narayanan, Matei A. Zaharia, Ion Stoica, Percy Liang, Daniel Kang 0001. [doi]
• Multi-Modal Interactive Agent Layer for Few-Shot Universal Cross-Domain Retrieval and BeyondKaixiang Chen, Pengfei Fang, Hui Xue. [doi]
• Unlocking hidden biomolecular conformational landscapes in diffusion models at inference timeDaniel D. Richman, Jessica Karaguesian, Carl-Mikael Suomivuori, Ron O. Dror. [doi]
• ComPO: Preference Alignment via Comparison OraclesPeter Chen, Xi Chen, Wotao Yin, Tianyi Lin. [doi]
• InstanceAssemble: Layout-Aware Image Generation via Instance Assembling AttentionQiang Xiang, Shuang Sun, Binglei Li, Dejia Song, Huaxia Li, Yibo Chen, Xu Tang 0007, Yao Hu 0002, Junping Zhang. [doi]
• Training Language Models to Generate Quality Code with Program Analysis FeedbackFeng Yao, Zilong Wang 0002, Liyuan Liu, Junxia Cui, Li Zhong, Xiaohan Fu, Haohui Mai, Viswanathan Krishnan, Jianfeng Gao 0001, Jingbo Shang. [doi]
• MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow GenerationKerui Ren, Jiayang Bai, Linning Xu, Lihan Jiang, Jiangmiao Pang, Mulin Yu, Bo Dai 0002. [doi]
• DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS ChannelAlan J. X. Guo, Sihan Sun, Xiang Wei, Mengyi Wei, Xin Chen. [doi]
• Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction FollowingVivek Myers, Bill Zheng 0001, Anca D. Dragan, Kuan Fang, Sergey Levine. [doi]
• Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human CorrectionsXiaomeng Xu, Yifan Hou, Zeyi Liu, Shuran Song. [doi]
• ST$^2$360D: Spatial-to-Temporal Consistency for Training-free 360 Monocular Depth EstimationZidong Cao, Jinjing Zhu, Hao Ai, Lutao Jiang, Yuanhuiyi Lyu, Hui Xiong 0001. [doi]
• On the Surprising Effectiveness of Large Learning Rates under Standard Width ScalingMoritz Haas, Sebastian Bordt, Ulrike von Luxburg, Leena Chennuru Vankadara. [doi]
• Policy Optimized Text-to-Image Pipeline DesignUri Gadot, Rinon Gal, Yftah Ziser, Gal Chechik, Shie Mannor. [doi]
• On the Edge of Memorization in Diffusion ModelsSam Buchanan, Druv Pai, Yi Ma 0001, Valentin De Bortoli. [doi]
• Bandit Guided Submodular Curriculum for Adaptive Subset SelectionPrateek Chanda, Prayas Agrawal, Saral Sureka, Lokesh Reddy Polu, Atharv Kshirsagar, Ganesh Ramakrishnan. [doi]
• SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language ModelsYibo Wang 0005, Guangda Huzhang, Qingguo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang 0005. [doi]
• Logical Expressiveness of Graph Neural Networks with Hierarchical Node IndividualizationArie Soeteman, Balder ten Cate. [doi]
• Distributional Training Data Attribution: What do Influence Functions Sample?Bruno Kacper Mlodozeniec, Isaac Reid, Sam Power, David Krueger 0001, Murat A. Erdogdu, Richard E. Turner, Roger Baker Grosse. [doi]
• LuxDiT: Lighting Estimation with Video Diffusion TransformerRuofan Liang, Kai He, Zan Gojcic, Igor Gilitschenski, Sanja Fidler, Nandita Vijaykumar, Zian Wang. [doi]
• Differentially Private Quantiles with Smaller ErrorJacob Imola, Fabrizio Boninsegna, Hannah Keller, Anders Aamand, Amrita Roy Chowdhury 0001, Rasmus Pagh. [doi]
• Learning Parameterized Skills from DemonstrationsVedant Gupta, Haotian Fu, Calvin Luo, Yiding Jiang, George Konidaris 0001. [doi]
• Causal Explanation-Guided Learning for Organ AllocationAlessandro Marchese, Jeroen Berrevoets, Sam Verboven. [doi]
• DISCO: Disentangled Communication Steering for Large Language ModelsMax Torop, Aria Masoomi, Masih Eskandar, Jennifer G. Dy. [doi]
• Bigram Subnetworks: Mapping to Next Tokens in Transformer Language ModelsTyler A. Chang, Benjamin Bergen 0001. [doi]
• EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event RepresentationSheng Wu, Lin Jin, Hui Feng 0001, Bo Hu 0002. [doi]
• Causal Sufficiency and Necessity Improves Chain-of-Thought ReasoningXiangning Yu 0001, Zhuohan Wang, Linyi Yang, Haoxuan Li 0001, Anjie Liu, Xiao Xue 0001, Jun Wang 0012, Mengyue Yang. [doi]
• Beyond Random: Automatic Inner-loop Optimization in Dataset DistillationMuquan Li, Hang Gou, Dongyang Zhang 0001, Shuang Liang 0002, Xiurui Xie, Deqiang Ouyang, Ke Qin. [doi]
• Multi-Class Support Vector Machine with Differential PrivacyJinseong Park 0001, Yujin Choi, Jaewook Lee 0001. [doi]
• CG-SSL: Concept-Guided Self-Supervised LearningSara Atito 0001, Josef Kittler, Imran Razzak, Muhammad Awais 0001. [doi]
• OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic SegmentationBowen Yin, Jiao-Long Cao, Xuying Zhang, Yuming Chen, Ming-Ming Cheng, Qibin Hou. [doi]
• Free-Lunch Color-Texture Disentanglement for Stylized Image GenerationJiang Qin, Alexandra Gomez-Villa, Senmao Li, Shiqi Yang 0002, Yaxing Wang, Kai Wang 0060, Joost van de Weijer 0001. [doi]
• Alias-Free ViT: Fractional Shift Invariance via Linear AttentionHagay Michaeli, Daniel Soudry. [doi]
• Contrastive Representations for Temporal ReasoningAlicja Ziarko, Michal Bortkiewicz, Michal Zawalski, Benjamin Eysenbach, Piotr Milos. [doi]
• GlobalTomo: A global dataset for physics-ML seismic wavefield modeling and FWIShiqian Li, Zhi Li, Zhancun Mu, Shiji Xin, Zhixiang Dai, Kuangdai Leng, Rita Zhang, Xiaodong Song, Yixin Zhu 0001. [doi]
• Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular OptimizationYiran Yang, Rui Chen. [doi]
• An Ellipsoid Algorithm for Online Convex OptimizationZakaria Mhammedi. [doi]
• Memory Mosaics at scaleJianyu Zhang, Léon Bottou. [doi]
• VeriThinker: Learning to Verify Makes Reasoning Model EfficientZigeng Chen, Xinyin Ma, Gongfan Fang, Ruonan Yu, Xinchao Wang. [doi]
• Practical do-Shapley Explanations with Estimand-Agnostic Causal InferenceÁlvaro Parafita, Tomas Garriga, Axel Brando, Francisco J. Cazorla. [doi]
• SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World ModelsSen Wang, Jingyi Tian, Le Wang 0003, Zhimin Liao, Jiayi Li, Huaiyi Dong, Kun Xia, Sanping Zhou, Wei Tang 0016, Gang Hua 0001. [doi]
• Improving the Straight-Through Estimator with Zeroth-Order InformationNingfeng Yang, Tor M. Aamodt. [doi]
• RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language ModelsChenxu Niu, Jie M. Zhang, Yanbing Liu 0007, Yunpeng Li 0006, Jinta Weng, Yue Hu 0002. [doi]
• OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic GeodataOussema Dhaouadi, Riccardo Marin, Johannes Meier, Jacques Kaiser, Daniel Cremers. [doi]
• Improving Decision Trees through the Lens of Parameterized Local SearchJuha Harviainen, Frank Sommer, Manuel Sorge. [doi]
• Learning Shared Representations from Unpaired DataAmitai Yacobi, Nir Ben-Ari, Ronen Talmon, Uri Shaham 0001. [doi]
• RLZero: Direct Policy Inference from Language Without In-Domain SupervisionHarshit Sikchi, Siddhant Agarwal, Pranaya Jajoo, Samyak Parajuli, Caleb Chuck, Max Rudolph, Peter Stone 0001, Amy Zhang 0001, Scott Niekum. [doi]
• With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide YouFabian Gröger, Shuo Wen, Huyen Le, Maria Brbic. [doi]
• Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual LearningViet Anh Khoa Tran, Emre Neftci, Willem Wybo. [doi]
• Not All Data are Good Labels: On the Self-supervised Labeling for Time Series ForecastingYuxuan Yang 0005, Dalin Zhang 0001, Yuxuan Liang, Hua Lu 0001, Gang Chen 0001, Huan Li 0003. [doi]
• Identifying Macro Causal Effects in C-DMGs over DMGsSimon Ferreira, Charles K. Assaad. [doi]
• Unlocking Dataset Distillation with Diffusion ModelsBrian B. Moser, Federico Raue, Sebastian Palacio, Stanislav Frolov, Andreas Dengel 0001. [doi]
• SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMsJinhong Deng, Wen Li 0001, Joey Tianyi Zhou, Yang He 0002. [doi]
• Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-GeneratorPeiwen Yuan, Yiwei Li, Shaoxiong Feng, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li 0001. [doi]
• Siegel Neural NetworksXuan Son Nguyen, Aymeric Histace, Nistor Grozavu. [doi]
• CaMiT: A Time-Aware Car Model Dataset for Classification and GenerationFrédéric Lin, Biruk Abere Ambaw, Adrian Popescu 0001, Hejer Ammar, Romaric Audigier, Hervé Le Borgne. [doi]
• Simultaneous Modeling of Protein Conformation and Dynamics via AutoregressionYuning Shen, Lihao Wang, Huizhuo Yuan, Yan Wang, Bangji Yang, Quanquan Gu. [doi]
• Factorio Learning EnvironmentJack Hopkins, Mart Bakler, Akbir Khan. [doi]
• Grounded Reinforcement Learning for Visual ReasoningGabriel Sarch, Snigdha Saha, Naitik Khandelwal, Ayush Jain, Michael J. Tarr, Aviral Kumar, Katerina Fragkiadaki. [doi]
• Plug-and-play Feature Causality Decomposition for Multimodal Representation LearningYe Liu, Zihan Ji, Hongmin Cai. [doi]
• Aligning Transformers with Continuous Feedback via Energy Rank AlignmentShriram Chennakesavalu, Frank Hu, Sebastian Ibarraran, Grant M. Rotskoff. [doi]
• Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function ApproximationToshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo. [doi]
• FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text TrainingXinxin You, Qixin Sun, Chenwei Yan, Xiao Zhang 0001, Chen Ning, Xiangling Fu, Si Liu, Guoping Hu, Shijin Wang 0001, Ji Wu 0002, Xien Liu. [doi]
• Quantum Visual Fields with Neural Amplitude EncodingShuteng Wang, Christian Theobalt, Vladislav Golyanik. [doi]
• Do Language Models Use Their Depth Efficiently?Róbert Csordás, Christopher D. Manning, Christopher Potts. [doi]
• Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online ApproachHaitong Ma, Haoran Yu, Haobo Fu, Shuai Li. [doi]
• HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-locationTing Sun 0004, Penghan Wang, Fan Lai 0001. [doi]
• Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse EnvironmentWeiming Zhang, Dingwen Xiao, Aobotao Dai, Yexin Liu, Tianbo Pan, Shiqi Wen, Lei Chen 0002, Lin Wang 0040. [doi]
• RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image GenerationBoyuan Cao, Jiaxin Ye, Yujie Wei 0001, Hongming Shan. [doi]
• Approximate Gradient Coding for Distributed Learning with Heterogeneous StragglersHeekang Song, Wan Choi 0001. [doi]
• Enhancing Infrared Vision: Progressive Prompt Fusion Network and BenchmarkJinyuan Liu 0001, Zihang Chen, Zhu Liu 0004, Zhiying Jiang, Long Ma 0002, Xin Fan 0001, Risheng Liu. [doi]
• Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame ProjectionsBerken Utku Demirel, Christian Holz 0001. [doi]
• AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language ModelsJiaxi Cheng, Yuliang Xu, Shoupeng Wang, Tao Ma, Yuchen He, Jinghe Zhang, Sihang Cai, Jiawei Zhen, Jingyi Jia, Yao Wan 0001, Yan Xia 0006, Zhou Zhao 0001. [doi]
• A Unified Solution to Video Fusion: From Multi-Frame Learning to BenchmarkingZixiang Zhao, Haowen Bai, Bingxin Ke, Yukun Cui, Lilun Deng, Yulun Zhang 0001, Kai Zhang 0008, Konrad Schindler. [doi]
• CoFFT: Chain of Foresight-Focus Thought for Visual Language ModelsXinyu Zhang 0021, Yuxuan Dong, Lingling Zhang 0005, Chengyou Jia, Zhuohang Dang, Basura Fernando, Jun Liu 0036, Mike Zheng Shou. [doi]
• PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QALanlan Ji, Dominic Seyler, Gunkirat Kaur, Manjunath Hegde, Koustuv Dasgupta, Bing Xiang. [doi]
• Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation DataKaiyuan Eric Chen, Shuangyu Xie, Zehan Ma, Pannag Sanketi, Ken Goldberg. [doi]
• Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept SpaceZhen Zhang, Xuehai He, Weixiang Yan, Ao Shen, Chenyang Zhao, Xin Wang 0061. [doi]
• TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and IncidentsXiaochuan Gou, Ziyue Li 0002, Tian Lan, Junpeng Lin, Zhishuai Li, Bingyu Zhao, Chen Zhang 0007, Di Wang 0015, Xiangliang Zhang 0001. [doi]
• How Benchmark Prediction from Fewer Data Misses the MarkGuanhua Zhang, Florian E. Dorner, Moritz Hardt. [doi]
• On Reasoning Strength Planning in Large Reasoning ModelsLeheng Sheng, An Zhang 0003, Zijian Wu 0003, Weixiang Zhao, Changshuo Shen, Yi Zhang 0001, Xiang Wang 0010, Tat-Seng Chua. [doi]
• TabArena: A Living Benchmark for Machine Learning on Tabular DataNick Erickson, Lennart Purucker, Andrej Tschalzev, David Holzmüller, Prateek Mutalik Desai, David Salinas, Frank Hutter. [doi]
• Generative Graph Pattern MachineZehong Wang, Zheyuan Zhang 0008, Tianyi Ma, Chuxu Zhang, Yanfang Ye 0001. [doi]
• Small Singular Values Matter: A Random Matrix Analysis of Transformer ModelsMax Staats, Matthias Thamm, Bernd Rosenow. [doi]
• Enhancing Bioactivity Prediction via Spatial Emptiness Representation of Protein-ligand Complex and Union of Multiple PocketsZhiyuan Zhou, Yueming Yin, Yiming Yang, Yuguang Mu, Hoi-Yeung Li, Adams Wai-Kin Kong. [doi]
• OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link PredictionJuntong Wang, Xiyuan Wang, Muhan Zhang. [doi]
• AugGen: Synthetic Augmentation using Diffusion Models Can Improve RecognitionParsa Rahimi, Damien Teney, Sébastien Marcel. [doi]
• Towards General Continuous Memory for Vision-Language ModelsWenyi Wu, Zixuan Song, Kun Zhou 0002, Yifei Shao, Zhiting Hu, Biwei Huang. [doi]
• Accelerated Distance-adaptive Methods for Hölder Smooth and Convex OptimizationYijin Ren, Haifeng Xu, Qi Deng. [doi]
• A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing DetectionGaku Morio, Harri Rowlands, Dominik Stammbach, Christopher D. Manning, Peter Henderson 0002. [doi]
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual EditingXiangyu Zhao, Peiyuan Zhang, Kexian Tang, Xiaorong Zhu, Hao Li 0069, Wenhao Chai, Zicheng Zhang, Renqiu Xia, Guangtao Zhai, Junchi Yan, Hua Yang 0001, Xue Yang 0005, Haodong Duan. [doi]
• CORAL: Disentangling Latent Representations in Long-Tailed DiffusionEsther Rodriguez, Monica Welfert, Samuel McDowell, Nathan Stromberg, Julian Antolin Camarena, Lalitha Sankar. [doi]
• Atom of Thoughts for Markov LLM Test-Time ScalingFengwei Teng, Quan Shi, Zhaoyang Yu 0004, Jiayi Zhang 0017, Yuyu Luo, Chenglin Wu 0001, Zhijiang Guo. [doi]
• Differentially Private Gomory-Hu TreesAnders Aamand, Justin Y. Chen, Mina Dalirrooyfard, Slobodan Mitrovic, Yuriy Nevmyvaka, Sandeep Silwal, Yinzhan Xu. [doi]
• MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal AssistantsZeyu Zhang 0007, Quanyu Dai, Luyu Chen, Zeren Jiang, Rui Li 0086, Jieming Zhu, Xu Chen 0017, Yi Xie, Zhenhua Dong, Ji-Rong Wen. [doi]
• STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC HistopathologyBarathi Subramanian, Rathinaraja Jeyaraj, Mitchell Nevin Peterson, Terry Guo, Nigam H. Shah, Curtis Langlotz, Andrew Y. Ng, Jeanne Shen. [doi]
• Interactive Anomaly Detection for Articulated Objects via Motion AnticipationAnkan Bhunia, Changjian Li 0001, Hakan Bilen. [doi]
• Omni-Mol: Multitask Molecular Model for Any-to-any ModalitiesChengxin Hu, Hao Li, Yihe Yuan, Zezheng Song, Chenyang Zhao, Haixin Wang 0003. [doi]
• Flow-Based Policy for Online Reinforcement LearningLei Lyu, Yunfei Li, Yu Luo, Fuchun Sun 0001, Tao Kong, Jiafeng Xu, Xiao Ma. [doi]
• How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer ModelHee bin Yoo, Sungyoon Lee, Cheongjae Jang, Dong-Sig Han, Jaein Kim 0004, SeungHyeon Lim, Byoung-Tak Zhang. [doi]
• Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability DisproportionQing-Yuan Jiang, Longfei Huang, Yang Yang 0074. [doi]
• 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene ReconstructionMaria Taktasheva, Lily Goli, Alessandro Fiorini, Zhen Li, Daniel Rebain, Andrea Tagliasacchi. [doi]
• Where Does It Exist from the Low-Altitude: Spatial Aerial Video GroundingYang Zhan 0007, Yuan Yuan 0001. [doi]
• Constrained Discrete DiffusionMichael Cardei, Jacob K. Christopher, Bhavya Kailkhura, Tom Hartvigsen, Ferdinando Fioretto. [doi]
• Learning to Zoom with Anatomical Relations for Medical Structure DetectionBin Pu, Liwen Wang 0002, Xingbo Dong, Xingguo Lv, Zhe Jin 0001. [doi]
• Sparse Gaussian Processes: Structured Approximations and Power-EP RevisitedThang D. Bui, Michalis K. Titsias. [doi]
• Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clusteringClément Yvernes, Emilie Devijver, Adèle H. Ribeiro, Marianne Clausel, Éric Gaussier. [doi]
• Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flowsLeslie Hwang. [doi]
• Vocabulary In-Context Learning in Transformers: Benefits of Positional EncodingQian Ma, Ruoxiang Xu, Yongqiang Cai. [doi]
• PyraMotion: Attentional Pyramid-Structured Motion Integration for Co-Speech 3D Gesture SynthesisZhizhuo Yin, Yuk Hang Tsui, Pan Hui 0001. [doi]
• An Adaptive Algorithm for Bilevel Optimization on Riemannian ManifoldsXu Shi, Rufeng Xiao, Rujun Jiang. [doi]
• Balanced Token Pruning: Accelerating Vision Language Models Beyond Local OptimizationKaiyuan Li, Xiaoyue Chen, Chen Gao 0001, Yong Li 0008, Xinlei Chen. [doi]
• World Models as Reference Trajectories for Rapid Motor AdaptationCarlos Stein Brito, Daniel McNamee. [doi]
• Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its PreconditionerRuna Eschenhagen, Aaron Defazio, Tsung-Hsien Lee, Richard E. Turner, Hao-Jun Michael Shi. [doi]
• Connecting Neural Models Latent Geometries with Relative Geodesic RepresentationsHanlin Yu, Berfin Inal, Georgios Arvanitidis, Søren Hauberg, Francesco Locatello, Marco Fumero. [doi]
• SPARTAN: A Sparse Transformer World Model Attending to What MattersAnson Lei, Bernhard Schölkopf, Ingmar Posner. [doi]
• MOSDT: Self-Distillation-Based Decision Transformer for Multi-Agent Offline Safe Reinforcement LearningYuchen Xia, Yunjian Xu. [doi]
• Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language ModelsYimu Wang, Mozhgan Nasr Azadani, Sean Sedwards, Krzysztof Czarnecki 0001. [doi]
• TSENOR: Highly-Efficient Algorithm for Finding Transposable N: M Sparse MasksXiang Meng 0004, Mehdi Makni, Rahul Mazumder. [doi]
• Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile EstimatorsImon Banerjee, Sayak Chakrabarty. [doi]
• Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and ImproveYuanzhe Liu 0001, Ryan Deng, Tim Kaler, Xuhao Chen 0001, Charles E. Leiserson, Yao Ma, Jie Chen 0007. [doi]
• CoT Information: Improved Sample Complexity under Chain-of-Thought SupervisionAwni Altabaa, Omar Montasser, John D. Lafferty. [doi]
• CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural RenderingZhengqing Wang, Yuefan Wu, Jiacheng Chen, Fuyang Zhang, Yasutaka Furukawa. [doi]
• Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution OptimizationGuanchen Li, Yixing Xu, Zeping Li, Ji Liu, Xuanwu Yin, Dong Li, Emad Barsoum. [doi]
• Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video SpecialistsBojia Zi, Penghui Ruan, Marco Chen, Xianbiao Qi, Shaozhe Hao, Shihao Zhao, Youze Huang, Bin Liang 0004, Rong Xiao 0003, Kam-Fai Wong. [doi]
• Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment BenchmarkingChanglun Li, Yao Shi, Chen Wang, Qiqi Duan, Runke Ruan, Weijie Huang, Haonan Long, Lijun Huang, Nan Tang 0001, Yuyu Luo. [doi]
• CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene GenerationLi Liang 0006, Bo Miao, Xinyu Wang, Naveed Akhtar, Jordan Vice, Ajmal Mian. [doi]
• Sparta Alignment: Collectively Aligning Multiple Language Models through CombatYuru Jiang, Wenxuan Ding 0001, Shangbin Feng, Greg Durrett, Yulia Tsvetkov. [doi]
• Smoothed Agnostic Learning of Halfspaces over the HypercubeYiwen Kou, Raghu Meka. [doi]
• Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You NeedKecheng Chen, Pingping Zhang, Hui Liu 0036, Jie Liu 0044, Yibing Liu, Jiaxin Huang, Shiqi Wang 0001, Hong Yan 0001, Haoliang Li. [doi]
• AgMMU: A Comprehensive Agricultural Multimodal Understanding BenchmarkAruna Gauba, Irene Pi, Yunze Man, Ziqi Pang, Vikram S. Adve, Yu-Xiong Wang. [doi]
• EyeBench: Predictive Modeling from Eye Movements in ReadingOmer Shubi, David Robert Reich, Keren Gruteke Klein, Yuval Angel, Paul Prasse, Lena A. Jäger, Yevgeni Berzak. [doi]
• Conservative classifiers do consistently well with improving agents: characterizing statistical and online learningDravyansh Sharma, Alec Sun. [doi]
• Soft-consensual Federated Learning for Data Heterogeneity via Multiple PathsSheng Huang, Lele Fu, Fanghua Ye 0001, Tianchi Liao, Bowen Deng 0002, Chuanfu Zhang, Chuan Chen 0001. [doi]
• Geometric Algorithms for Neural Combinatorial Optimization with ConstraintsNikolaos Karalias, Akbar Rafiey, Yifei Xu, Zhishang Luo, Behrooz Tahmasebi, Connie Jiang, Stefanie Jegelka. [doi]
• Consensus-Robust Transfer Attacks via Parameter and Representation PerturbationsShixin Li 0001, Zewei Li, Xiaojing Ma 0002, Xiaofan Bai, Pingyi Hu, Dongmei Zhang 0001, Bin Zhu 0008. [doi]
• Individual Fairness In Strategic ClassificationZhiqun Zuo, Mohammad Mahdi Khalili. [doi]
• VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object DetectionWuyang Li, Zhu Yu, Alexandre Alahi. [doi]
• Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential PrivacyBogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Jamie Hayes, Borja Balle, Flávio P. Calmon, Jean Louis Raisaro. [doi]
• On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order OptimizationShaocong Ma, Heng Huang 0001. [doi]
• Reading Recognition in the WildCharig Yang, Samiul Alam, Shakhrul Iman Siam, Michael J. Proulx, Lambert Mathias, Kiran K. Somasundaram, Luis Pesqueira, James Fort, Sheroze Sheriffdeen, Omkar M. Parkhi, Carl Yuheng Ren, Mi Zhang 0002, Yuning Chai, Richard A. Newcombe, Hyo Jin Kim 0004. [doi]
• RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task SolvingHuacan Wang, Ziyi Ni, Shuo Zhang, Shuo Lu, Sen Hu 0005, Ziyang He, Chen Hu, Jiaye Lin, Yifu Guo, Yuntao Du 0001, Pin Lyu. [doi]
• OverLayBench: A Benchmark for Layout-to-Image Generation with Dense OverlapsBingnan Li, Chen-Yu Wang, Haiyang Xu 0002, Xiang Zhang 0015, Ethan Armand, Divyansh Srivastava, Xiaojun Shan, Zeyuan Chen, Jianwen Xie, Zhuowen Tu. [doi]
• Stable Matching with Ties: Approximation Ratios and LearningShiyun Lin, Simon Mauras, Nadav Merlis, Vianney Perchet. [doi]
• CHiQPM: Calibrated Hierarchical Interpretable Image ClassificationThomas Norrenbrock, Timo Kaiser, Sovan Biswas, Neslihan Kose, Ramesh Manuvinakurike, Bodo Rosenhahn. [doi]
• DeltaFlow: An Efficient Multi-frame Scene Flow Estimation MethodQingwen Zhang, Xiaomeng Zhu, Yushan Zhang, Yixi Cai, Olov Andersson, Patric Jensfelt. [doi]
• Statistical inference for Linear Stochastic Approximation with Markovian NoiseSergey Samsonov, Marina Sheshukova, Eric Moulines, Alexey Naumov. [doi]
• Information Theoretic Learning for Diffusion Models with Warm StartYirong Shen, Lu Gan 0002, Cong Ling 0001. [doi]
• Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range TasksAli Hariri, Alvaro Arroyo, Alessio Gravina, Moshe Eliasof, Carola-Bibiane Schönlieb, Davide Bacciu, Xiaowen Dong 0001, Kamyar Azizzadenesheli, Pierre Vandergheynst. [doi]
• A CLT for Polynomial GNNs on Community-Based GraphsLuciano Vinas, Arash A. Amini. [doi]
• DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMsRuokai Yin, Yuhang Li 0001, Donghyun Lee 0002, Priyadarshini Panda. [doi]
• Causal Discovery and Inference through Next-Token PredictionEivinas Butkus, Nikolaus Kriegeskorte. [doi]
• Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of DecodersJames Oldfield 0001, Shawn Im, Sharon Li 0001, Mihalis A. Nicolaou, Ioannis Patras, Grigorios Chrysos 0002. [doi]
• STACI: Spatio-Temporal Aleatoric Conformal InferenceBrandon R. Feng, David K. Park, Xihaier Luo, Arantxa Urdangarin, Shinjae Yoo, Brian J. Reich. [doi]
• A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image WatermarksMucong Ding, Bang An 0001, Tahseen Rabbani, Chenghao Deng, Anirudh Satheesh, Souradip Chakraborty, Mehrdad Saberi, Yuxin Wen, Kyle Sang, Aakriti Agrawal, Xuandong Zhao, Mo Zhou, Mary-Anne Hartley, Lei Li 0005, Yu-Xiang Wang 0003, Vishal M. Patel, Soheil Feizi, Tom Goldstein, Furong Huang. [doi]
• TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR PerceptionRunjian Chen, Hyoungseob Park, Bo Zhang 0069, Wenqi Shao, Ping Luo 0002, Alex Wong 0001. [doi]
• Deployment Efficient Reward-Free Exploration with Linear Function ApproximationZihan Zhang, Yuxin Chen 0002, Jason D. Lee, Simon S. Du, Lin F. Yang, Ruosong Wang. [doi]
• Vision Transformers with Self-Distilled RegistersZipeng Yan, Yinjie Chen, Chong Zhou, Bo Dai 0002, Andrew Luo 0001. [doi]
• Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative ModelsSima Noorani, Shayan Kiyani, George J. Pappas, Hamed Hassani. [doi]
• DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian NetworksWentao Wu, Shiyuan He, Jianhua Guo. [doi]
• High-Dimensional Calibration from Swap RegretMaxwell Fishelson, Noah Golowich, Mehryar Mohri, Jon Schneider. [doi]
• DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented GenerationJiashuo Sun, Xianrui Zhong, Sizhe Zhou, Jiawei Han 0001. [doi]
• The Computational Advantage of Depth in Learning High-Dimensional Hierarchical TargetsYatin Dandi, Luca Pesce, Lenka Zdeborová, Florent Krzakala. [doi]
• Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language TranslationEdward Fish, Richard Bowden. [doi]
• Attribution-Driven Adaptive Token Pruning for TransformersYaoyao Yan, Hui Yu 0010, Weizhi Xu 0001. [doi]
• DeepHalo: A Neural Choice Model with Controllable Context EffectsShuhan Zhang, Zhi Wang, Rui Gao 0001, Shuang Li 0002. [doi]
• Constrained Best Arm IdentificationTyron Lardy, Christina Katsimerou, Wouter M. Koolen. [doi]
• Fairness-Regularized Online Optimization with Switching CostsPengfei Li 0008, Yuelin Han, Adam Wierman, Shaolei Ren. [doi]
• Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented AugmentationRiccardo Corvi, Davide Cozzolino, Ekta Prashnani, Shalini De Mello, Koki Nagano, Luisa Verdoliva. [doi]
• Advancing Machine-Generated Text Detection from an Easy to Hard Supervision PerspectiveChenwang Wu, Yiu-ming Cheung, Bo Han 0003, Defu Lian. [doi]
• Enhancing Interpretability in Deep Reinforcement Learning through Semantic ClusteringLiang Zhang, Justin Lieffers, Adarsh Pyarelal. [doi]
• Revisiting Glorot Initialization for Long-Range Linear RecurrencesNoga Bar, Mariia Seleznova, Yotam Alexander, Gitta Kutyniok, Raja Giryes. [doi]
• Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form GamesFivos Kalogiannis, Gabriele Farina. [doi]
• Meta-learning how to Share Credit among Macro-ActionsIonel-Alexandru Hosu, Traian Rebedea, Razvan Pascanu. [doi]
• One Head to Rule Them All: Amplifying LVLM Safety through a Single Critical Attention HeadJunhao Xia, Haotian Zhu, Shuchao Pang, Zhigang Lu 0001, Bing Li 0002, Yongbin Zhou, Minhui Xue 0001. [doi]
• G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural NetworksAlireza Aghasi, Nicholas F. Marshall, Saeid Pourmand, Wyatt D. Whiting. [doi]
• Low-Rank Head Avatar Personalization with RegistersSai Tanmay Reddy Chakkera, Aggelina Chatziagapi, Md. Moniruzzaman, Chen-Ping Yu, Yi-Hsuan Tsai, Dimitris Samaras. [doi]
• Avoiding exp(R) scaling in RLHF through Preference-based ExplorationMingyu Chen 0012, Yiding Chen, Wen Sun, Xuezhou Zhang. [doi]
• Inverse Optimization Latent Variable Models for Learning Costs Applied to Route ProblemsAlan A. Lahoud, Erik Schaffernicht, Johannes Andreas Stork. [doi]
• VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction, Characterization and RecognitionRahul Moorthy Mahesh, Jun-Jee Chao, Volkan Isler. [doi]
• AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion ModelsSeunghoon Lee, Jeongwoo Choi, Byunggwan Son, Jaehyeon Moon, Jeimin Jeon, Bumsub Ham. [doi]
• Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMindQingmei Li, Yang Zhang, Zurong Mai, Yuhang Chen, Shuohong Lou, Henglian Huang, Jiarui Zhang 0008, Zhiwei Zhang, Yibin Wen, Weijia Li, Haohuan Fu, Jianxi Huang, Juepeng Zheng. [doi]
• Covering Multiple Objectives with a Small Set of Solutions Using Bayesian OptimizationNatalie Maus, Kyurae Kim, Yimeng Zeng, Haydn Thomas Jones, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Jacob R. Gardner. [doi]
• mmWalk: Towards Multi-modal Multi-view Walking AssistanceKedi Ying, Ruiping Liu 0001, Chongyan Chen, Mingzhe Tao, Hao Shi 0004, Kailun Yang 0001, Jiaming Zhang 0001, Rainer Stiefelhagen. [doi]
• The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and MitigationHaoyu Wang, Wei Dai, Jiawei Zhang, Jialun Ma, Mingyi Huang, Yuguo Yu. [doi]
• Unveiling Extraneous Sampling Bias with Data Missing-Not-At-RandomChunyuan Zheng 0001, Haocheng Yang, Haoxuan Li 0001, Mengyue Yang. [doi]
• PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL TranslationWei Zhou 0053, Guoliang Li 0001, Haoyu Wang, Yuxing Han 0002, Xufei Wu, Fan Wu 0006, Xuanhe Zhou. [doi]
• Efficient Multimodal Dataset Distillation via Generative ModelsZhenghao Zhao, Haoxuan Wang 0002, Junyi Wu 0002, Yuzhang Shang, Gaowen Liu, Yan Yan 0002. [doi]
• Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream TasksHeasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana. [doi]
• Explaining and Mitigating Crosslingual Tokenizer InequitiesCatherine Arnett, Tyler A. Chang, Stella Biderman, Benjamin Bergen 0001. [doi]
• FoGE: Fock Space inspired encoding for graph promptingTakis Chytas, Rudrasis Chakraborty, Vikas Singh. [doi]
• Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel RefillingQilong Guo, Tianjing Zhang, Zhiyuan Ma, Hui Ji 0002. [doi]
• SAM2Flow: Interactive Optical Flow Estimation with Dual Memory for in vivo Microcirculation AnalysisLuojie Huang, Ryan Zhang, Marisa Morakis, Michaela Taylor-Williams, Gregory N. McKay, Nicholas J. Durr. [doi]
• Lorentz Local Canonicalization: How to make any Network Lorentz-EquivariantJonas Spinner, Luigi Favaro, Peter Lippmann, Sebastian Pitz, Gerrit Gerhartz, Tilman Plehn, Fred A. Hamprecht. [doi]
• RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-NetZhenyi Lin, Xiaofan Ming, Qilong Wang 0001, Dongwei Ren, Wangmeng Zuo, Qinghua Hu. [doi]
• Faster Algorithms for Structured John Ellipsoid ComputationYang Cao 0020, Xiaoyu Li 0001, Zhao Song 0002, Xin Yang 0017, Tianyi Zhou 0011. [doi]
• HoPE: Hybrid of Position Embedding for Long Context Vision-Language ModelsHaoran Li, Yingjie Qin, Baoyuan Ou, Lai Xu, Ruiwen Xu. [doi]
• Perception-R1: Pioneering Perception Policy with Reinforcement LearningEn Yu, Kangheng Lin, Liang Zhao, Jisheng Yin, Yana Wei, Yuang Peng, Haoran Wei, Jianjian Sun, Chunrui Han, Zheng Ge, Xiangyu Zhang 0005, Daxin Jiang, Jingyu Wang 0001, Wenbing Tao. [doi]
• Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training DataFelix Koehler, Nils Thuerey. [doi]
• Provably Efficient Online RLHF with One-Pass Reward ModelingLong-Fei Li, Yu-Yang Qian 0001, Peng Zhao 0006, Zhi-Hua Zhou. [doi]
• Dimension-free Score Matching and Time Bootstrapping for Diffusion ModelsSyamantak Kumar, Dheeraj Nagaraj, Purnamrita Sarkar. [doi]
• CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered ScenesJiyao Zhang, Zhiyuan Ma, Tianhao Wu 0001, Zeyuan Chen, Hao Dong 0003. [doi]
• Diffusion on Demand: Selective Caching and Modulation for Efficient GenerationHee Min Choi, Hyoa Kang, Dokwan Oh, Nam Ik Cho. [doi]
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained OptimizationGang Li 0048, Ming Lin 0002, Tomer Galanti, Zhengzhong Tu, Tianbao Yang. [doi]
• Video-R1: Reinforcing Video Reasoning in MLLMsKaituo Feng, Kaixiong Gong, BoHao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Junfei Wu, Xiaoying Zhang, Benyou Wang, Xiangyu Yue 0001. [doi]
• SHAP Meets Tensor Networks: Provably Tractable Explanations with ParallelismReda Marzouk, Shahaf Bassan, Guy Katz. [doi]
• Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video ReconstructionJiacong Chen, Qingyu Mao, Youneng Bao, Xiandong Meng, Fanyang Meng, Ronggang Wang, Yongsheng Liang 0001. [doi]
• Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural NetworksKiJung Yoon. [doi]
• SeerAttention: Self-distilled Attention Gating for Efficient Long-context PrefillingYizhao Gao 0002, Zhichen Zeng 0002, Dayou Du, Shijie Cao, Peiyuan Zhou, Jiaxing Qi, Junjie Lai, Hayden K. H. So, Ting Cao 0003, Fan Yang 0024, Mao Yang 0004. [doi]
• Kinaema: a recurrent sequence model for memory and pose in motionMert Bülent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf 0001. [doi]
• OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech SynthesisRun Luo, Ting-En Lin, Haonan Zhang 0003, Yuchuan Wu, Xiong Liu, Yongbin Li 0001, Longze Chen, Jiaming Li 0004, Lei Zhang 0201, Xiaobo Xia, Hamid Alinejad-Rokny, Fei Huang 0002, Min Yang 0007. [doi]
• Checklists Are Better Than Reward Models For Aligning Language ModelsVijay Viswanathan 0002, Yanchao Sun, Xiang Kong, Meng Cao, Graham Neubig, Sherry Wu. [doi]
• MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined AnnotationsWenxiang Guo, Changhao Pan, Zhiyuan Zhu, Xintong Hu, Yu Zhang 0126, Li Tang, Rui Yang, Han Wang 0019, Zongbao Zhang, Yuhan Wang, Yixuan Chen, Hankun Xu, Ke Xu, Pengfei Fan, ZheTao Chen, Yanhao Yu, Qiange Huang, Fei Wu 0001, Zhou Zhao 0001. [doi]
• Let LRMs Break Free from Overthinking via Self-Braking TuningHaoran Zhao, Yuchen Yan, Yongliang Shen 0001, Haolei Xu, Wenqi Zhang 0001, Kaitao Song, Jian Shao 0001, Weiming Lu 0001, Jun Xiao 0001, Yueting Zhuang. [doi]
• DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity PredictionYupu Zhang 0001, Zelin Xu 0001, Tingsong Xiao, Gustavo de M. Seabra, Yanjun Li 0005, Chenglong Li, Zhe Jiang 0001. [doi]
• D-VST: Diffusion Transformer for Pathology-Correct Tone-Controllable Cross-Dye Virtual Staining of Whole Slide ImagesShurong Yang, Dong Wei 0004, Yihuang Hu, Qiong Peng, Hong Liu, Yawen Huang, Xian Wu 0001, Yefeng Zheng 0001, Liansheng Wang 0002. [doi]
• CoT Red-Handed: Stress Testing Chain-of-Thought MonitoringBenjamin Arnav, Pablo Bernabeu-Perez, Nathan Helm-Burger, Timothy H. Kostolansky, Hannes Whittingham, Mary Phuong. [doi]
• Channel Simulation and Distributed Compression with Ensemble Rejection SamplingBuu Phan, Ashish Khisti. [doi]
• Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal DatasetsJi Xia, Yizi Zhang, Shuqi Wang, Genevera I. Allen, Liam Paninski, Cole L. Hurwitz, Kenneth D. Miller. [doi]
• ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-SearchZeyu Shen, Basileal Imana, Tong Wu, Chong Xiang 0001, Prateek Mittal, Aleksandra Korolova. [doi]
• BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered EditingJinsu Kim, Yunhun Nam, Minseon Kim, Sangpil Kim, Jongheon Jeong. [doi]
• MixAT: Combining Continuous and Discrete Adversarial Training for LLMsCsaba Dékány, Stefan Balauca, Dimitar I. Dimitrov, Robin Staab, Martin T. Vechev. [doi]
• Compositional Neural Network Verification via Assume-Guarantee ReasoningHai Duong, David Shriver, ThanhVu Nguyen, Matthew Dwyer 0001. [doi]
• LBMKGC: Large Model-Driven Balanced Multimodal Knowledge Graph CompletionYuan Guo, Qian Ma 0003, Hui Li 0014, Qiao Ning, Furui Zhan, Yu Gu 0002, Ge Yu 0001, Shikai Guo. [doi]
• Once Upon an Input: Reasoning via Per-Instance Program SynthesisAdam Stein, Neelay Velingker, Mayur Naik, Eric Wong 0001. [doi]
• Adaptive Stochastic Coefficients for Accelerating Diffusion SamplingRuoyu Wang, Beier Zhu, Junzhi Li, Liangyu Yuan, Chi Zhang 0007. [doi]
• CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & SparsificationWei Li, Renshan Zhang, Rui Shao 0001, Jie He, Liqiang Nie. [doi]
• Red-Teaming Text-to-Image Systems by Rule-based Preference ModelingYichuan Cao, Yibo Miao, Xiao-Shan Gao, Yinpeng Dong. [doi]
• UniTok: a Unified Tokenizer for Visual Generation and UnderstandingChuofan Ma, Yi Jiang 0009, Junfeng Wu, Jihan Yang, Xin Yu 0004, Zehuan Yuan, Bingyue Peng, Xiaojuan Qi 0001. [doi]
• Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty QuantificationZeqi Ye, Minshuo Chen. [doi]
• Scaling can lead to compositional generalizationFlorian Redhardt, Yassir Akram, Simon Schug. [doi]
• Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration TimeQiang Fu, Andre Wibisono. [doi]
• Demystifying Spectral Feature Learning for Instrumental Variable RegressionDimitri Meunier, Antoine Moulin, Jakub Wornbard, Vladimir Kostic, Arthur Gretton. [doi]
• SimWorld: An Open-ended Simulator for Agents in Physical and Social WorldsXiaokang Ye, Jiawei Ren, Yan Zhuang, Xuhong He, Yiming Liang, Yiqing Yang, Mrinaal Dogra, Xianrui Zhong, Eric Liu, Kevin Benavente, Rajiv Mandya Nagaraju, Dhruv Vivek Sharma, Ziqiao Ma 0001, Tianmin Shu, Zhiting Hu, Lianhui Qin. [doi]
• Linear Transformers Implicitly Discover Unified Numerical AlgorithmsPatrick Lutz, Aditya Gangrade, Hadi Daneshmand, Venkatesh Saligrama. [doi]
• AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property EstimationXinbiao Wang, Yuxuan Du, Zihan Lou, Yang Qian, Kaining Zhang, Yong Luo 0002, Bo Du 0001, Dacheng Tao. [doi]
• Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial InferenceFrank Shih, Zhenghao Jiang, Faming Liang. [doi]
• TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer NetworksItzik Waizman, Yakov Gusakov, Itay Benou, Tammy Riklin-Raviv. [doi]
• VisionThink: Smart and Efficient Vision Language Model via Reinforcement LearningSenqiao Yang, Junyi Li, Xin Lai, Jinming Wu, Wei Li 0159, Zejun Ma 0001, Bei Yu 0001, Hengshuang Zhao, Jiaya Jia. [doi]
• For Better or for Worse, Transformers Seek Patterns for MemorizationMadhur Panwar, Gail Weiss, Navin Goyal, Antoine Bosselut. [doi]
• Compositional Discrete Latent Code for High Fidelity, Productive Diffusion ModelsSamuel Lavoie, Michael Noukhovitch, Aaron C. Courville. [doi]
• CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEsJan Hagnberger, Daniel Musekamp, Mathias Niepert. [doi]
• NeurIPS should lead scientific consensus on AI policyRishi Bommasani. [doi]
• Depth-Width Tradeoffs for Transformers on Graph TasksGilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson. [doi]
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM InferenceXiang Liu 0001, Zhenheng Tang, Peijie Dong, ZeYu Li, Yue Liu, Bo Li 0001, Xuming Hu, Xiaowen Chu 0001. [doi]
• Accurate and Efficient Low-Rank Model Merging in Core SpaceAniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartlomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer 0001. [doi]
• Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon LayersZeyuan Allen Zhu. [doi]
• FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis NetworkFangtong Sun, Congyu Li, Ke Yang, Yuchen Pan, Hanwen Yu, Xichuan Zhang, Yiying Li. [doi]
• Beyond Scores: Proximal Diffusion ModelsZhenghan Fang, Mateo Díaz, Sam Buchanan, Jeremias Sulam. [doi]
• Autoencoding Random ForestsBinh Duc Vu, Jan Kapar, Marvin N. Wright, David S. Watson. [doi]
• Incentivizing LLMs to Self-Verify Their AnswersFuxiang Zhang, Jiacheng Xu, Chaojie Wang 0001, Ce Cui, Yang Liu 0084, Bo An 0001. [doi]
• FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video DiffusionAkide Liu, Zeyu Zhang 0006, Zhexin Li, Xuehai Bai, Yuanjie Xing, Yizeng Han, Jiasheng Tang, Jichao Wu, Mingyang Yang, Weihua Chen, Jiahao He, Yuanyu He, Fan Wang 0019, Reza Haffari, Bohan Zhuang. [doi]
• UniGist: Towards General and Hardware-aligned Sequence-level Long Context CompressionChenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Tianqing Fang, Hongming Zhang 0009, Haitao Mi, Dong Yu 0001, Zhicheng Dou. [doi]
• Solver-Informed RL: Grounding Large Language Models for Authentic Optimization ModelingYitian Chen 0003, Jingfan Xia, Siyu Shao, Dongdong Ge, Yinyu Ye 0001. [doi]
• COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement LearningJules Sintes, Ana Busic. [doi]
• More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning ModelsZhongxing Xu, Chengzhi Liu, QingYue Wei, Juncheng Wu, James Y. Zou, Xin Wang 0061, Yuyin Zhou, Sheng Liu. [doi]
• Additive Models Explained: A Computational Complexity ApproachShahaf Bassan, Michal Moshkovitz, Guy Katz. [doi]
• OmniSync: Towards Universal Lip Synchronization via Diffusion TransformersZiqiao Peng, Jiwen Liu, Haoxian Zhang, Xiaoqiang Liu, Songlin Tang, Pengfei Wan 0001, Di Zhang 0026, Hongyan Liu 0002, Jun He 0008. [doi]
• Self-Supervised Learning of Graph Representations for Network Intrusion DetectionLorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van Tam Nguyen. [doi]
• Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic ControlMing Cheng, Hao Chen 0062, Zhiqing Li, Jia Wang, Senzhang Wang. [doi]
• SPFL: Sequential updates with Parallel aggregation for Enhanced Federated Learning under Category and Domain ShiftsHaoyuan Liang, Shilei Cao 0005, Guowen Li, ZhiYu Ye, Haohuan Fu, Juepeng Zheng. [doi]
• Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture DistributionsJhanvi Garg, Krishnakumar Balasubramanian 0002, Quan Zhou. [doi]
• Codifying Character Logic in Role-PlayingLetian Peng, Jingbo Shang. [doi]
• Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial InferenceYuhong Luo, Austin Hoag, Xintong Wang, Philip S. Thomas, Przemyslaw A. Grabowicz. [doi]
• PID-controlled Langevin Dynamics for Faster Sampling of Generative ModelsHongyi Chen, Jianhai Shu, Jingtao Ding, Yong Li, Xiao-Ping (Steven) Zhang. [doi]
• Synergistic Tensor and Pipeline ParallelismMengshi Qi, Jiaxuan Peng 0001, Jie M. Zhang, Juan Zhu, Yong Li, Huadong Ma. [doi]
• It's Hard to Be Normal: The Impact of Noise on Structure-agnostic EstimationJikai Jin, Lester Mackey, Vasilis Syrgkanis. [doi]
• Direct Fisher Score Estimation for Likelihood MaximizationSherman Khoo, Yakun Wang, Song Liu, Mark Beaumont. [doi]
• Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and IntegrationJunyu Zhang, Lizhong Ding 0003, Minghong Zhang, Ye Yuan 0001, Xingcan Li, Pengqi Li, Tihang Xi, Guoren Wang, Changsheng Li. [doi]
• Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language ModelsTaha Entesari, Arman Hatami, Rinat Khaziev, Anil Ramakrishna, Mahyar Fazlyab. [doi]
• JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial TranscriptomicsYuanchuan Guo, Jun Liu, Huimin Cheng, Ying Ma. [doi]
• Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision TransformerRuiqi Xue, Ziqian Zhang, Lihe Li, Cong Guan, Lei Yuan 0005, Yang Yu 0001. [doi]
• The Complexity of Correlated Equilibria in Generalized GamesMartino Bernasconi, Matteo Castiglioni, Andrea Celli, Gabriele Farina. [doi]
• Geometry of Decision Making in Language ModelsAbhinav Joshi, Divyanshu Bhatt, Ashutosh Modi. [doi]
• Inference-Time Personalized Alignment with a Few User Preference QueriesVictor-Alexandru Padurean, Parameswaran Kamalaruban, Nachiket Kotalwar, Alkis Gotovos, Adish Singla. [doi]
• SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series ClassificationZenan Ying, Zhi Zheng 0008, Huijun Hou, Tong Xu 0001, Qi Liu 0003, Jinke Wang, Wei Chen 0156. [doi]
• Gains: Fine-grained Federated Domain Adaptation in Open SetZhengyi Zhong, Wenzheng Jiang, Weidong Bao 0001, Ji Wang 0002, Qi (Cheems) Wang, Guanbo Wang, Yongheng Deng, Ju Ren 0001. [doi]
• Enhancing CLIP Robustness via Cross-Modality AlignmentXingyu Zhu, Beier Zhu, Shuo Wang 0008, Kesen Zhao, Hanwang Zhang. [doi]
• On the Sample Complexity Bounds of Bilevel Reinforcement LearningMudit Gaur, Utsav Singh, Amrit Singh Bedi, Raghu Pasupathy, Vaneet Aggarwal. [doi]
• ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of DataXiaoyang Liu, Kangjie Bao, Jiashuo Zhang, Yunqi Liu, Yu Chen, Yuntian Liu, Yang Jiao, Tao Luo. [doi]
• LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context InstructionsChaochen Gao, Xing Wu 0002, Zijia Lin, Debing Zhang, Songlin Hu 0001. [doi]
• LiveStar: Live Streaming Assistant for Real-World Online Video UnderstandingZhenyu Yang 0009, Kairui Zhang, Yuhang Hu, Bing Wang, Shengsheng Qian, Bin Wen, Fan Yang 0094, Tingting Gao, Weiming Dong, Changsheng Xu. [doi]
• Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language ModelsYasha Ektefaie, Andrew Shen, Lavik Jain, Maha R. Farhat, Marinka Zitnik. [doi]
• Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual DisentanglementLinyang He, Tianjun Zhong, Richard J. Antonello, Gavin Mischler, Micah Goldblum, Nima Mesgarani. [doi]
• Fixed-Point RNNs: Interpolating from Diagonal to DenseSajad Movahedi, Felix Sarnthein, Nicola Muca Cirone, Antonio Orvieto. [doi]
• MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM InferenceDonghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari. [doi]
• Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and ScalingNan Sun, Luyu Yuan, Han Fang 0004, Yuxing Lu, Hefei Ling, Sijing Xie, Chengxin Zhao. [doi]
• OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance FieldsLisa Weijler, Sebastian Koch, Fabio Poiesi, Timo Ropinski, Pedro Hermosilla. [doi]
• Scaling Speculative Decoding with Lookahead ReasoningYichao Fu, Rui Ge 0008, Zelei Shao, Zhijie Deng, Hao Zhang 0025. [doi]
• LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor AttacksDi Jin 0001, Yuxiang Zhang, Bingdao Feng, Xiaobao Wang, Dongxiao He, Zhen Wang 0004. [doi]
• Rethinking Joint Maximum Mean Discrepancy for Visual Domain AdaptationWei Wang 0335, Haifeng Xia, Chao Huang 0008, Zhengming Ding, Cong Wang 0018, Haojie Li, Xiaochun Cao. [doi]
• pLSTM: parallelizable Linear Source Transition Mark networksKorbinian Pöppel, Richard Freinschlag, Thomas Schmied, Wei Lin 0019, Sepp Hochreiter. [doi]
• Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-AttentionMumin Jia, Jairo Diaz Rodriguez. [doi]
• Reverse Diffusion Sequential Monte Carlo SamplersLuhuan Wu, Yi Han, Christian Andersson Naesseth, John P. Cunningham. [doi]
• Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta CompressionXiaohui Wang, Peng Ye 0006, Chenyu Huang 0001, Shenghe Zheng, Bo Zhang 0069, Lei Bai 0001, Wanli Ouyang, Tao Chen 0003. [doi]
• ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic BridgeCuong Dao, The Hung Tran, Phi-Le Nguyen, Truong Thao Nguyen, Nghia Hoang. [doi]
• Robust Estimation Under Heterogeneous Corruption RatesSyomantak Chaudhuri, Jerry Li, Thomas A. Courtade. [doi]
• SpatialReasoner: Towards Explicit and Generalizable 3D Spatial ReasoningWufei Ma, Yu-Cheng Chou, Qihao Liu, Xingrui Wang, Celso de Melo, Jianwen Xie, Alan L. Yuille. [doi]
• UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site KnowledgeChenao Li, Shuo Yan, Enyan Dai. [doi]
• OpenGU: A Comprehensive Benchmark for Graph UnlearningBowen Fan, Yuming Ai, Xunkai Li, Zhilin Guo 0003, Lei Zhu, Guang Zeng 0001, Rong-Hua Li 0001, Guoren Wang. [doi]
• Clustering via Hedonic Games: New Concepts and AlgorithmsGergely Csáji, Alexander Gundert, Jörg Rothe, Ildikó Schlotter. [doi]
• AgentAuditor: Human-level Safety and Security Evaluation for LLM AgentsHanjun Luo, Shenyu Dai, Chiming Ni, Xinfeng Li, Guibin Zhang, Kun Wang 0056, Tongliang Liu, Hanan Salam. [doi]
• Sequential Multi-Agent Dynamic Algorithm ConfigurationChen Lu, Ke Xue 0001, Lei Yuan 0005, Yao Wang, Yaoyuan Wang, Sheng Fu, Chao Qian 0001. [doi]
• Formal Models of Active Learning from Contrastive ExamplesFarnam Mansouri, Hans Simon 0001, Adish Singla, Yuxin Chen 0001, Sandra Zilles. [doi]
• Understanding Softmax Attention Layers: Exact Mean-Field Analysis on a Toy ProblemElvis Dohmatob. [doi]
• AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft ContrastsDenizhan Kara, Tomoyoshi Kimura, Jinyang Li 0004, Bowen He, Yizhuo Chen, Yigong Hu, Hongjue Zhao, Shengzhong Liu, Tarek F. Abdelzaher. [doi]
• Wavelet Canonical Coherence for Nonstationary SignalsHaibo Wu, Marina I. Knight, Keiland W. Cooper, Norbert Fortin, Hernando Ombao. [doi]
• Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RLXingyu Chen, Shihao Ma, Runsheng Lin, Jiecong Lin, Bo Wang. [doi]
• Anchored Diffusion Language ModelLitu Rout, Constantine Caramanis, Sanjay Shakkottai. [doi]
• SpecMER: Fast Protein Generation with K-mer Guided Speculative DecodingThomas Walton, Darin Tsui, Aryan Musharaf, Amirali Aghazadeh. [doi]
• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual ReprogrammingZhen Zhang 0023, Bingsheng He. [doi]
• FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language ModelsXuan Liu 0009, Siru Ouyang, Xianrui Zhong, Jiawei Han 0001, Huimin Zhao 0007. [doi]
• The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean LabelsYonatan Slutzky, Yotam Alexander, Noam Razin, Nadav Cohen 0001. [doi]
• Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language ModelDongki Kim, Wonbin Lee, Sung Ju Hwang. [doi]
• Fairness-aware Bayes Optimal Functional ClassificationXiaoyu Hu, Gengyu Xue, Zhenhua Lin, Yi Yu. [doi]
• Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion TrajectoryHanru Bai, Weiyang Ding, Difan Zou. [doi]
• UltraLED: Learning to See Everything in Ultra-High Dynamic Range ScenesYuang Meng, Xin Jin 0005, Lina Lei, Chun-Le Guo, Chongyi Li. [doi]
• V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel SimulationHanyue Lou, Jinxiu Liang, Minggui Teng, Yi Wang, Boxin Shi. [doi]
• RESAnything: Attribute Prompting for Arbitrary Referring SegmentationRuiqi Wang, Hao Helen Zhang. [doi]
• Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed DataChen Shu, Hongjun Xu, Ruichi Zhang, Mengke Li 0001, Yonggang Zhang 0003, Yang Lu 0009, Bo Han 0003, Yiu-ming Cheung, Hanzi Wang. [doi]
• UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality DatasetChen Zhao 0002, En Ci, Yunzhe Xu, Tiehan Fan, Shanyan Guan, Yanhao Ge, Jian Yang 0003, Ying Tai. [doi]
• SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and SegmentationRey Koki, Michael McCabe, Dhruv Kedar, Josh Myers-Dean, Annabel Wade, Jebb Q. Stewart, Christina Kumler-Bonfanti, Jed Brown. [doi]
• Spectral Conditioning of Attention Improves Transformer PerformanceHemanth Saratchandran, Simon Lucey. [doi]
• Measuring what Matters: Construct Validity in Large Language Model BenchmarksAndrew M. Bean 0001, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner, Harry Mayne, Jan Batzner, Negar Foroutan Eghlidi, Chris Schmitz, Karolina Korgul, Hunar Batra, Oishi Deb, Emma Beharry, Cornelius Emde, Thomas Foster, Anna Gausen, María Grandury, Sophia Simeng Han, Valentin Hofmann, Lujain Ibrahim, Hazel Kim, Hannah Rose Kirk, Fangru Lin, Gabrielle K. Liu, Lennart Luettgau, Jabez Magomere, Jonathan Rystrøm, Anna Sotnikova, Yushi Yang, Yilun Zhao 0001, Adel Bibi, Antoine Bosselut, Ronald Clark, Arman Cohan, Jakob N. Foerster, Yarin Gal, Scott A. Hale, Inioluwa Deborah Raji, Christopher Summerfield, Philip H. S. Torr, Cozmin Ududec, Luc Rocher, Adam Mahdi. [doi]
• Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime SafetySiyuan Xu, Minghui Zhu. [doi]
• A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity GuaranteesYuhao Zhou, Jintao Xu, Bingrui Li, Chenglong Bao, Chao Ding, Jun Zhu 0001. [doi]
• Mean-Field Sampling for Cooperative Multi-Agent Reinforcement LearningEmile Anand, Ishani Karmarkar, Guannan Qu. [doi]
• Problem-Parameter-Free Decentralized Bilevel OptimizationZhiwei Zhai, Wenjing Yan, Ying Jun Zhang. [doi]
• OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative GeneralizationYiyou Sun, Shawn Hu, Georgia Zhou, Ken Zheng, Hanna Hajishirzi, Nouha Dziri, Dawn Song. [doi]
• Robust Distortion-Free Watermark for Autoregressive Audio Generation ModelsYihan Wu, Georgios Milis, Ruibo Chen, Heng Huang 0001. [doi]
• Learning Gradient Boosted Decision Trees with Algorithmic RecourseKentaro Kanamori, Ken Kobayashi, Takuya Takagi. [doi]
• AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving ScenariosYunhao Hou, Bochao Zou, Min Zhang, Ran Chen, Shangdong Yang, Yanmei Zhang, Junbao Zhuo, Siheng Chen, Jiansheng Chen 0001, Huimin Ma 0001. [doi]
• In-Context Learning Strategies Emerge RationallyDaniel Wurgaft, Ekdeep Singh Lubana, Core Francisco Park, Hidenori Tanaka, Gautam Reddy, Noah D. Goodman. [doi]
• Minimal Semantic Sufficiency Meets Unsupervised Domain GeneralizationTan Pan, Kaiyu Guo, Dongli Xu, Zhaorui Tan, Chen Jiang 0006, Deshu Chen, Xin Guo 0010, Brian C. Lovell, Limei Han, Yuan Cheng, Mahsa Baktashmotlagh. [doi]
• Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single ImageJunkun Chen, Aayush Bansal, Minh Vo, Yu-Xiong Wang. [doi]
• Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic ClassificationXinpeng Lv, Yunxin Mao, Haoxuan Li 0001, Ke Liang 0006, Jinxuan Yang, Wanrong Huang, Haoang Chi, Huan Chen, Long Lan, Yuanlong Chen, Wenjing Yang 0002, Haotian Wang 0001. [doi]
• Improving Model-Based Reinforcement Learning by Converging to Flatter MinimaShrinivas Ramasubramanian, Benjamin Freed, Alexandre Capone, Jeff G. Schneider. [doi]
• State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video UnderstandingJiahuan Zhou, Kai Zhu, Zhenyu Cui, Zichen Liu, Xu Zou 0002, Gang Hua 0001. [doi]
• Do Neural Networks Need Gradient Descent to Generalize? A Theoretical StudyYotam Alexander, Yonatan Slutzky, Yuval Ran-Milo, Nadav Cohen 0001. [doi]
• A Multi-Task Benchmark for Abusive Language Detection in Low-Resource SettingsFitsum Gaim, Hoyun Song, Huije Lee, Changgeon Ko, Eui Jun Hwang, Jong C. Park. [doi]
• Towards Unsupervised Domain Bridging via Image Degradation in Semantic SegmentationWangkai Li, Rui Sun 0006, Huayu Mai, Tianzhu Zhang 0001. [doi]
• MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPOYicheng Xiao, Lin Song 0002, Yukang Chen, Yingmin Luo, Yuxin Chen, Yukang Gan, Wei Huang 0042, Xiu Li 0001, Xiaojuan Qi 0001, Ying Shan. [doi]
• Physics-Driven Spatiotemporal Modeling for AI-Generated Video DetectionShuhai Zhang, Zihao Lian, Jiahao Yang, Daiyuan Li, Guoxuan Pang, Feng Liu 0003, Bo Han 0003, Shutao Li 0001, Mingkui Tan. [doi]
• Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation FactorMaryam Aliakbarpour, Zhan Shi, Ria Stevens, Vincent X. Wang. [doi]
• Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual GradientsYuxing Lu, Gecheng Fu, Wei Wu, Xukai Zhao, Sin Yee Goi, Jinzhuo Wang. [doi]
• To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-TuningMing Li, Jike Zhong, Shitian Zhao, Yuxiang Lai, Haoquan Zhang, Wang Bill Zhu, Kaipeng Zhang. [doi]
• Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional AsymptoticsSean McGrath, Debarghya Mukherjee, Rajarshi Mukherjee, Zixiao Jolene Wang. [doi]
• Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language ModelsHaoyu Wang 0004, Peihao Wang, Mufei Li, Shikun Liu, Siqi Miao 0001, Zhangyang (Atlas) Wang, Pan Li 0005. [doi]
• Superposition Yields Robust Neural ScalingYizhou Liu 0001, Ziming Liu 0001, Jeff Gore. [doi]
• Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial RepresentationsYujia Zhang 0003, Xiaoyang Wu 0002, Yixing Lao, Chengyao Wang, Zhuotao Tian, Naiyan Wang, Hengshuang Zhao. [doi]
• Neural Mutual Information Estimation with Vector CopulasYanzhi Chen, Zijing Ou, Adrian Weller, Michael U. Gutmann. [doi]
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem ComplexityParshin Shojaee, Iman Mirzadeh, Keivan Alizadeh-Vahid, Maxwell Horton, Samy Bengio, Mehrdad Farajtabar. [doi]
• Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online DataQijia He, Minghan Wang, Xutong Liu 0002, Zhiyong Wang, Fang Kong 0002. [doi]
• Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMsMasahiro Kaneko, Timothy Baldwin. [doi]
• Continual Release Moment Estimation with Differential PrivacyNikita P. Kalinin, Jalaj Upadhyay, Christoph H. Lampert. [doi]
• UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and DomainsDuo Wang, Yuan Zuo, Guangyue Lu, Junjie Wu 0002. [doi]
• Faster Fixed-Point Methods for Multichain MDPsMatthew Zurek, Yudong Chen. [doi]
• GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New InsightsShengbo Gong, Juntong Ni, Noveen Sachdeva, Carl Yang 0001, Wei Jin 0009. [doi]
• From Programs to Poses: Factored Real-World Scene Generation via Learned Program LibrariesJoy Hsu, Emily Jin, Jiajun Wu 0001, Niloy J. Mitra. [doi]
• InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model FusionYuanyi Wang, Zhaoyi Yan, Yiming Zhang, Qi Zhou, Yanggan Gu, Fei Wu 0001, Hongxia Yang. [doi]
• JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching AgentYunlong Lin, Zixu Lin, Kunjie Lin, Jinbin Bai, Panwang Pan, Chenxin Li, Haoyu Chen 0003, Zhongdao Wang, Xinghao Ding, Wenbo Li 0002, Shuicheng Yan. [doi]
• Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch MiningRaghuveer Thirukovalluru, Rui Meng, Ye Liu 0006, Karthikeyan K, Mingyi Su, Ping Nie, Semih Yavuz, Yingbo Zhou 0002, Wenhu Chen, Bhuwan Dhingra. [doi]
• Learning to Rank for In-Context Example RetrievalYuwen Ji, Luodan Zhang, Ambyer Han, Haoran Que, Lei Shi, Chao Wang, Yue Zhang. [doi]
• Embodied Cognition Augmented End2End Autonomous DrivingLing Niu, Xiaoji Zheng, Han Wang, Ziyuan Yang 0005, Chen Zheng, Bokui Chen, Jiangtao Gong. [doi]
• Private Statistical Estimation via TruncationManolis Zampetakis, Felix Zhou 0002. [doi]
• Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image SynthesisHengyuan Cao, Yutong Feng, Biao Gong, Yijing Tian, Yunhong Lu, Chuang Liu, Bin Wang. [doi]
• CarbonGlobe: A Global-Scale, Multi-Decade Dataset and Benchmark for Carbon Forecasting in Forest EcosystemsZhiHao Wang, Lei Ma, George C. Hurtt, Xiaowei Jia, Yanhua Li, Ruohan Li, Zhili Li, Shuo Xu 0002, Yiqun Xie. [doi]
• Ultrametric Cluster Hierarchies: I Want 'em All!Andrew Draganov, Pascal Weber 0001, Rasmus Skibdahl Melanchton Jørgensen, Anna Beer 0001, Claudia Plant, Ira Assent. [doi]
• Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in HistopathologySaghir Alfasly, Wataru Uegami, Md. Enamul Hoq, Ghazal Alabtah, Hamid R. Tizhoosh. [doi]
• Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural FieldsWeiyi Xue, Fan Lu 0001, Yunwei Zhu, Zehan Zheng, Sanqing Qu, Jiangtong Li, Ya Wu, Haiyun Wei, Guang Chen 0001. [doi]
• ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single ModelJialong Zuo, Yongtai Deng, Mengdan Tan, Rui Jin, Dongyue Wu, Nong Sang, Liang Pan, Changxin Gao. [doi]
• WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View InpaintingKaitao Huang, Yan Yan 0001, Jing-Hao Xue, Hanzi Wang. [doi]
• IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse RenderingHengyu Liu 0007, Chenxin Li, Zhengxin Li, Yipeng Wu, Wuyang Li, Zhiqin Yang, Zhenyuan Zhang 0001, Yunlong Lin, Sirui Han, Brandon Y. Feng. [doi]
• Multipole Attention for Efficient Long Context ReasoningColeman Hooper, Sebastian Zhao, Luca Manolache, Sehoon Kim 0001, Michael W. Mahoney, Sophia Shao, Kurt Keutzer, Amir Gholami. [doi]
• MobileODE: An Extra Lightweight NetworkLe Yu, Jun Wu, Bo Gou, Xiangde Min, Lei Zhang 0005, Zhang Yi 0001, Tao He 0016. [doi]
• LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language ModelsYihao Liu, Xinqi Lyu, Dong Wang 0042, Yanjie Li 0006, Bin Xiao 0001. [doi]
• Improving planning and MBRL with temporally-extended actionsPalash Chatterjee, Roni Khardon. [doi]
• Efficient RAW Image Deblurring with Adaptive Frequency ModulationWenlong Jiao, Binglong Li, Wei Shang 0001, Ping Wang 0072, Dongwei Ren. [doi]
• Majority of the Bests: Improving Best-of-N via BootstrappingAmin Rakhsha, Kanika Madan, Tianyu Zhang 0003, Amir Massoud Farahmand, Amir Khasahmadi. [doi]
• Efficient Speech Language Modeling via Energy Distance in Continuous Latent SpaceZhengrui Ma, Yang Feng 0004, Chenze Shao, Fandong Meng, Jie Zhou 0016, Min Zhang 0005. [doi]
• Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUsGuoliang He, Youhe Jiang, Wencong Xiao, Kaihua Jiang, Shuguang Wang, Jun Wang 0039, Zixian Du, Zhuo Jiang, Xinlei Zhang, Binhang Yuan, Eiko Yoneki. [doi]
• Reinforcement Learning Teachers of Test Time ScalingEdoardo Cetin, Tianyu Zhao 0001, Yujin Tang. [doi]
• Dynamic Diameter in High-Dimensions against Adaptive Adversary and BeyondKiarash Banihashem, Jeff Giliberti, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh. [doi]
• VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DRShenghui Chen, Po-han Li, Sandeep Chinchali, Ufuk Topcu. [doi]
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-ConditioningChen Chen, Majid Abdolshah, Violetta Shevchenko, Hongdong Li, Chang Xu, Pulak Purkait. [doi]
• Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural NetsYuandong Tian. [doi]
• SparseMVC: Probing Cross-view Sparsity Variations for Multi-view ClusteringRuimeng Liu, Xin Zou 0001, Chang Tang, Xiao Zheng, Xingchen Hu 0001, Kun Sun 0002, Xinwang Liu 0002. [doi]
• Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series PredictionYuanpei Gao, Qi Yan, Yan Leng, Renjie Liao 0001. [doi]
• Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive OperatorShuchang Zhang, Yaoyun Zeng, Kangkang Deng, Hongxia Wang. [doi]
• Efficient Randomized Experiments Using Foundation ModelsPiersilvio De Bartolomeis, Javier Abad, Guanbo Wang, Konstantin Donhauser, Raymond M. Duch, Fanny Yang, Issa J. Dahabreh. [doi]
• Self-supervised Learning of Echocardiographic Video Representations via Online Cluster DistillationDivyanshu Mishra, Mohammadreza Salehi, Pramit Saha, Olga Patey, Aris T. Papageorghiou, Yuki Asano 0001, J. Alison Noble. [doi]
• SEMPO: Lightweight Foundation Models for Time Series ForecastingHui He, Kun Yi 0001, Yuanchi Ma, Qi Zhang 0020, Zhendong Niu, Guansong Pang. [doi]
• Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image ClassificationSimone Azeglio, Olivier Marre, Peter Neri, Ulisse Ferrari. [doi]
• Distances for Markov chains from sample streamsSergio Calo, Anders Jonsson 0001, Gergely Neu, Ludovic Schwartz, Javier Segovia Aguas. [doi]
• Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept GeometrySai Sumedh R. Hindupur, Ekdeep Singh Lubana, Thomas Fel, Demba Ba 0001. [doi]
• dKV-Cache: The Cache for Diffusion Language ModelsXinyin Ma, Runpeng Yu, Gongfan Fang, Xinchao Wang. [doi]
• Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR SpectraZiyu Xiong, Yichi Zhang, Foyez Alauddin, Chu Xin Cheng, Joon Soo An, Mohammad R. Seyedsayamdost, Ellen D. Zhong. [doi]
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning EngineeringRushi Qiang, Yuchen Zhuang, Yinghao Li, Dingu Sagar V. K, Rongzhi Zhang, Changhao Li, Ian Wong, Sherry Yang 0001, Percy Liang, Chao Zhang 0014, Bo Dai 0001. [doi]
• LOPT: Learning Optimal Pigovian Tax in Sequential Social DilemmasYun Hua, Shang Gao, Wenhao Li 0001, Haosheng Chen, Bo Jin 0003, Xiangfeng Wang 0001, Jun Luo, Hongyuan Zha. [doi]
• Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous DrivingYi Huang, Zhan Qu, Lihui Jiang, Bingbing Liu, Hongbo Zhang. [doi]
• Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D TokensZijian Dong 0001, Ruilin Li 0001, Joanna Su Xian Chong, Niousha Dehestani, Yinghui Teng, Yi Lin, Zhizhou Li, Yichi Zhang, Yapei Xie, Leon Qi Rong Ooi, B. T. Thomas Yeo, Juan Helen Zhou. [doi]
• Introducing FOReCAst: The Future Outcome Reasoning and Confidence Assessment BenchmarkZhangdie Yuan, Zifeng Ding, Andreas Vlachos 0001. [doi]
• Simple and Effective Specialized Representations for Fair ClassifiersAlberto Sinigaglia, Davide Sartor, Marina Ceccon, Gian Antonio Susto. [doi]
• Memory Injection Attacks on LLM Agents via Query-Only InteractionShen Dong, Shaochen Xu, Pengfei He, Yige Li, Jiliang Tang, Tianming Liu 0001, Hui Liu 0031, Zhen Xiang. [doi]
• Distributionally Robust Feature SelectionMaitreyi Swaroop, Tamar Krishnamurti, Bryan Wilder. [doi]
• Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human FeedbackWei Shen, Guanlin Liu, Yu Yue, Ruofei Zhu, Qingping Yang, Chao Xin, Lin Yan. [doi]
• Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold StartFuyang Liu, Jiaqi Xu, Xiaowei Hu 0001. [doi]
• Scalable Best-of-N Selection for Large Language Models via Self-CertaintyZhewei Kang, Xuandong Zhao, Dawn Song. [doi]
• Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry AdaptiveTyler Farghly, Peter Potaptchik, Samuel Howard, George Deligiannidis, Jakiw Pidstrigach. [doi]
• Diversity-Aware Policy Optimization for Large Language Model ReasoningJian Yao, Ran Cheng 0004, Xingyu Wu, Jibin Wu, Kc Tan. [doi]
• Factor Decorrelation Enhanced Data Removal from Deep Predictive ModelsWenhao Yang, Lin Li 0001, Xiaohui Tao 0001, Kaize Shi. [doi]
• SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM HallucinationsBuyun Liang 0001, Liangzu Peng, Jinqi Luo, Darshan Thaker, Kwan Ho Ryan Chan, René Vidal. [doi]
• WorldMem: Long-term Consistent World Simulation with MemoryZeqi Xiao, Yushi Lan, Yifan Zhou 0001, Wenqi Ouyang, Shuai Yang 0001, Yanhong Zeng, Xingang Pan. [doi]
• The Parameterized Complexity of Computing the VC-DimensionFlorent Foucaud, Harmender Gahlawat, Fionn Mc Inerney, Prafullkumar Tale. [doi]
• Improving Progressive Generation with Decomposable Flow MatchingMoayed Haji Ali, Willi Menapace, Ivan Skorokhodov, Arpit Sahni, Sergey Tulyakov, Vicente Ordonez, Aliaksandr Siarohin. [doi]
• Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the ConstraintsJayanta Mandi, Marianne Defresne, Senne Berden, Tias Guns. [doi]
• FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question AnsweringLiangyu Zhong, Fabio Rosenthal, Joachim Sicking, Fabian Hüger, Thorsten Bagdonat, Hanno Gottschalk, Leo Schwinn. [doi]
• RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human MobilityHaoyu He, Haozheng Luo, Yan Chen, Qi (Cheems) Wang. [doi]
• Accelerating Feature Conformal Prediction via Taylor ApproximationZihao Tang 0001, Boyuan Wang, Chuan Wen, Jiaye Teng. [doi]
• Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learningNic Fishman, Gokul Gowri, Peng Yin, Jonathan Gootenberg, Omar Abudayyeh. [doi]
• Understanding and Enhancing Mask-Based Pretraining towards Universal RepresentationsMingze Dong, Leda Wang, Yuval Kluger. [doi]
• RLVR-World: Training World Models with Reinforcement LearningJialong Wu 0001, Shaofeng Yin, Ningya Feng, Mingsheng Long. [doi]
• Generalization vs Specialization under Concept ShiftAlex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn. [doi]
• Local Learning for Covariate Selection in Nonparametric Causal Effect Estimation with Latent VariablesZheng Li, Xichen Guo, Feng Xie 0002, Yan Zeng 0002, Hao Helen Zhang, Zhi Geng. [doi]
• Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path PlanningMinglu Zhao, Dehong Xu, Deqian Kong, Wenhao Zhang 0002, Ying Nian Wu. [doi]
• Collective Bargaining in the Information Economy Can Address AI-Driven Power ConcentrationNicholas Vincent, Matthew Prewitt, Hanlin Li 0001. [doi]
• Overcoming Challenges of Long-Horizon Prediction in Driving World ModelsArian Mousakhan, Sudhanshu Mittal, Silvio Galesso, Karim Farid, Thomas Brox. [doi]
• Guided Diffusion Sampling on Function Spaces with Applications to PDEsJiachen Yao, Abbas Mammadov, Julius Berner, Gavin Kerrigan, Jong Chul Ye, Kamyar Azizzadenesheli, Animashree Anandkumar. [doi]
• DINGO: Constrained Inference for Diffusion LLMsTarun Suresh, Debangshu Banerjee 0001, Shubham Ugare, Sasa Misailovic, Gagandeep Singh 0001. [doi]
• VT-FSL: Bridging Vision and Text with LLMs for Few-Shot LearningWenhao Li, Qiangchang Wang, Xianjing Meng, Zhibin Wu, Yilong Yin. [doi]
• Watermarking Autoregressive Image GenerationNikola Jovanovic 0001, Ismail Labiad, Tomás Soucek, Martin T. Vechev, Pierre Fernandez. [doi]
• Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic ActivationsAlexandru Craciun 0001, Debarghya Ghoshdastidar. [doi]
• Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMsJinzhe Liu, Junshu Sun, Shufan Shen, Chenxue Yang, Shuhui Wang. [doi]
• GLSim: Detecting Object Hallucinations in LVLMs via Global-Local SimilaritySeongheon Park, Sharon Li 0001. [doi]
• Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion GamesAndreas Kontogiannis, Vasilis Pollatos, Gabriele Farina, Panayotis Mertikopoulos, Ioannis Panageas. [doi]
• A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and MaskingGal Fadlon, Idan Arbiv, Nimrod Berman, Omri Azencot. [doi]
• Rao-Blackwellised Reparameterisation GradientsKevin H. Lam, Thang Bui, George Deligiannidis, Yee Whye Teh. [doi]
• ConnectomeBench: Can LLMs proofread the connectome?Jeff Brown, Andrew Kirjner, Annika Vivekananthan, Edward S. Boyden. [doi]
• Connectome-Based Modelling Reveals Orientation Maps in the Drosophila Optic LobeJia Nuo Liew, Shenghan Lin, Bowen Chen, Wei Zhang, Xiaowei Zhu, Xiaolin Hu. [doi]
• Cosmos: Compressed and Smooth Latent Space for Text Diffusion ModelingViacheslav Meshchaninov, Egor Chimbulatov, Alexander Shabalin, Aleksandr Abramov, Dmitry P. Vetrov. [doi]
• On Group Sufficiency Under Label BiasHaoran Zhang 0003, Olawale Salaudeen, Marzyeh Ghassemi. [doi]
• Zero-Shot Trajectory Planning for Signal Temporal Logic TasksRuijia Liu, Ancheng Hou, Xiao Yu 0002, Xiang Yin 0003. [doi]
• Auditing Meta-Cognitive Hallucinations in Reasoning Large Language ModelsHaolang Lu, Yilian Liu, Jingxin Xu, Guoshun Nan, Yuanlong Yu 0002, Zhican Chen, Kun Wang 0056. [doi]
• ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement LearningZeyuan Liu, Zhihe Yang, Jiawei Xu, Rui Yang, Jiafei Lyu, Baoxiang Wang 0001, Yunjian Xu, Xiu Li 0001. [doi]
• Linearly Constrained Diffusion Implicit ModelsVivek Jayaram, Ira Kemelmacher-Shlizerman, Steven M. Seitz, John Thickstun. [doi]
• Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical GuaranteesChenguang Duan, Yuling Jiao, Huazhen Lin, Wensen Ma, Jerry Zhijian Yang. [doi]
• Isotropic Noise in Stochastic and Quantum Convex OptimizationAnnie Marsden, Liam O'Carroll, Aaron Sidford, Chenyi Zhang 0003. [doi]
• The Temporal Graph of Bitcoin TransactionsVahid Jalili. [doi]
• CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech GenerationKi-Joong Kwon, Jun Ho So, Sang-Hoon Lee. [doi]
• Instance-Level Composed Image RetrievalBill Psomas, George Retsinas, Nikos Efthymiadis, Panagiotis Paraskevas Filntisis, Yannis Avrithis, Petros Maragos, Ondrej Chum, Giorgos Tolias. [doi]
• PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial OptimizationFederico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park 0002, Kyuree Ahn, Changhyun Kwon 0001, Lin Xie, Jinkyoo Park. [doi]
• GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object DetectionJiaming Li 0010, Zhijia Liang, Weikai Chen 0001, Lin Ma 0002, Guanbin Li. [doi]
• OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory GenerationRaktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami. [doi]
• Beyond Components: Singular Vector-Based Interpretability of Transformer CircuitsAreeb Ahmad, Abhinav Joshi, Ashutosh Modi. [doi]
• HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid NormalizationZhijian Zhuo 0001, Yutao Zeng, Ya Wang 0002, Sijun Zhang, Xiaoqing Li, Jian Yang, Xun Zhou, Jinwen Ma. [doi]
• Spatially-aware Weights Tokenization for NeRF-Language ModelsAndrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti, Samuele Salti, Luigi di Stefano. [doi]
• Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm ShiftEunsu Baek, Keondo Park, JeongGil Ko, Min-hwan Oh, Taesik Gong, Hyung-Sin Kim. [doi]
• Preference-Based Dynamic Ranking Structure RecognitionNan Lu, Jian Shi, Xinyu Tian. [doi]
• Discovering Data Structures: Nearest Neighbor Search and BeyondOmar Salemohamed, Laurent Charlin, Shivam Garg 0001, Vatsal Sharan, Gregory Valiant. [doi]
• High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Predictionseongsu Kim, Nayoung Kim, Dongwoo Kim, Sungsoo Ahn. [doi]
• FaCT: Faithful Concept Traces for Explaining Neural Network DecisionsAmin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele. [doi]
• Pause Tokens Strictly Increase the Expressivity of Constant-Depth TransformersCharles London, Varun Kanade. [doi]
• Purest Quantum State IdentificationYingqi Yu, Honglin Chen, Jun Wu, Wei Xie 0028, Xiangyang Li 0001. [doi]
• Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-AutoformalizationQi Liu, Xinhao Zheng, Renqiu Xia, Qinxiang Cao, Junchi Yan. [doi]
• CoUn: Empowering Machine Unlearning via Contrastive LearningYasser H. Khalil, Mehdi Setayesh, Hongliang Li. [doi]
• Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial OptimizationYang Li 0197, Lvda Chen, Haonan Wang, Runzhong Wang, Junchi Yan. [doi]
• Counterfactual Identifiability via Dynamic Optimal TransportFabio De Sousa Ribeiro, Ainkaran Santhirasekaram, Ben Glocker. [doi]
• OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image ModelsZiheng Cheng, Yixiao Huang 0004, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei. [doi]
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and MetricsVineeth Dorna, Anmol Mekala, Wenlong Zhao 0001, Andrew McCallum, Zico Kolter, Zachary C. Lipton, Pratyush Maini. [doi]
• Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task ConditioningWenjun Huang 0001, Ziteng Cui, Yinqiang Zheng, Yirui He, Tatsuya Harada, Mohsen Imani. [doi]
• GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant AdaptersWanjia Zhao, Jiaqi Han, Siyi Gu, Mingjian Jiang, James Y. Zou, Stefano Ermon. [doi]
• Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM AlignmentSamuel Yeh, Sharon Li 0001. [doi]
• Enhancing 3D Reconstruction for Dynamic ScenesJisang Han, Honggyu An, Jaewoo Jung, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim. [doi]
• Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet InequalityJunyan Liu, Ziyun Chen, Kun Wang, Haipeng Luo, Lillian J. Ratliff. [doi]
• Dense Metric Depth Estimation via Event-based Differential Focus Volume PromptingBoyu Li, Peiqi Duan 0002, Zhaojun Huang, Xinyu Zhou, Yifei Xia, Boxin Shi. [doi]
• A Closer Look at Graph Transformers: Cross-Aggregation and BeyondJiaming Zhuo, Ziyi Ma, Yintong Lu, Yuwei Liu, Kun Fu, Di Jin 0001, Chuan Wang 0002, Wenning Wu, Zhen Wang 0004, Xiaochun Cao, Liang Yang 0002. [doi]
• Efficient Training-Free Online Routing for High-Volume Multi-LLM ServingFangzhou Wu, Sandeep Silwal. [doi]
• Reward-oriented Causal Representation LearningZirui Yan, Emre Acartürk, Ali Tajer. [doi]
• Are Large Language Models Sensitive to the Motives Behind Communication?Addison J. Wu, Ryan Liu 0001, Kerem Oktar, Theodore R. Sumers, Tom Griffiths 0001. [doi]
• TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language ModelsMaya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz. [doi]
• Probing Neural Combinatorial Optimization ModelsZhiqin Zhang 0001, Yining Ma 0001, Zhiguang Cao, Hoong Chuin Lau. [doi]
• Harnessing the Universal Geometry of EmbeddingsRishi D. Jha, Collin Zhang, Vitaly Shmatikov, John X. Morris. [doi]
• Value-Guided KV Compression for LLMs via Approximated CUR DecompositionAyan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty 0002. [doi]
• ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy DataYifeng Jiao, Yuchen Liu, Yu Zhang, Xin Guo 0010, Yushuai Wu, Chen Jiang 0006, Jiyang Li, Hongwei Zhang, Limei Han, Xin Gao 0001, Yuan Qi 0001, Yuan Cheng. [doi]
• RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment ApproximationZixun Wang, Ben Dai. [doi]
• MLLM-ISU: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models based Intrusion Scene UnderstandingFujun Han, Peng Ye 0006. [doi]
• Reasoning Planning for Language ModelsNgoc-Bao Nguyen, Trung Hieu Nguyen, Ruifeng She, Xiaojin Fu, Viet Anh Nguyen. [doi]
• Counterfactual Implicit Feedback ModelingChuan Zhou 0013, Lina Yao 0001, Haoxuan Li 0001, Mingming Gong. [doi]
• RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented GenerationXingliang Wang, Zemin Liu, Junxiao Han, ShuiGuang Deng. [doi]
• ToF-IP: Time-of-Flight Enhanced Sparse Inertial Poser for Real-time Human Motion CaptureYuan Yao, Shifan Jiang, Yangqing Hou, Chengxu Zuo, Xinrui Chen, Shihui Guo, Yipeng Qin. [doi]
• Online Strategic Classification With Noise and Partial FeedbackTianrun Zhao, Xiaojie Mao, Yong Liang. [doi]
• Improving Video Generation with Human FeedbackJie Liu 0047, Gongye Liu, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Menghan Xia, Xintao Wang 0002, Xiaohong Liu 0001, Fei Yang, Pengfei Wan 0001, Di Zhang 0026, Kun Gai, Yujiu Yang 0001, Wanli Ouyang. [doi]
• AutoJudge: Judge Decoding Without Manual AnnotationRoman Garipov, Fedor Velikonivtsev, Ivan Ermakov, Ruslan Svirschevski, Vage Egiazarian, Max Ryabinin. [doi]
• Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsIlgee Hong, Changlong Yu, Liang Qiu, Weixiang Yan, Zhenghao Xu, Haoming Jiang, Qingru Zhang, Qin Lu, Xin Liu, Chao Zhang 0014, Tuo Zhao. [doi]
• A Token is Worth over 1, 000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneJitai Hao, Qiang Huang, Hao Liu, Xinyan Xiao, Zhaochun Ren, Jun Yu 0002. [doi]
• Conditional Diffusion Anomaly Modeling on GraphsChunyu Wei, Haozhe Lin, Yueguo Chen, Yunhai Wang. [doi]
• Targeted Maximum Likelihood Learning: An Optimization PerspectiveDiyang Li, Kyra Gan. [doi]
• Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy EvaluationFeichen Gan, Youcun Lu, Yingying Zhang, Yukun Liu. [doi]
• Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language ModelsChantal Shaib, Vinith M. Suriyakumar, Byron C. Wallace, Marzyeh Ghassemi. [doi]
• Generating Full-field Evolution of Physical Dynamics from Irregular Sparse ObservationsPanqi Chen, Yifan Sun, Lei Cheng 0003, Yang Yang, Weichang Li, Yang Liu 0278, Weiqing Liu, Jiang Bian 0002, Shikai Fang. [doi]
• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement LearningSiyan Zhao, Devaansh Gupta, Qinqing Zheng, Aditya Grover. [doi]
• Interactive and Hybrid Imitation Learning: Provably Beating Behavior CloningYichen Li, Chicheng Zhang. [doi]
• GPO: Learning from Critical Steps to Improve LLM ReasoningJiahao Yu 0001, Zelei Cheng, Xian Wu 0007, Xinyu Xing 0001. [doi]
• Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain GeneralizationFuyuan Cao, Shichang Qiao, Kui Yu, Jiye Liang. [doi]
• Exploring the Translation Mechanism of Large Language ModelsHongbin Zhang, Kehai Chen, Xuefeng Bai 0001, Xiucheng Li, Yang Xiang 0003, Min Zhang 0005. [doi]
• TreeGen: A Bayesian Generative Model for HierarchiesMarcel Kollovieh, Nils Fleischmann, Filippo Guerranti, Bertrand Charpentier, Stephan Günnemann. [doi]
• More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion ModelsHongkai Lin, Dingkang Liang, Mingyang Du, Xin Zhou 0013, Xiang Bai. [doi]
• A Sustainable AI Economy Needs Data Deals That Work for GeneratorsRuoxi Jia 0001, Luis Oala, Wenjie Xiong 0001, Suqin Ge, Jiachen (Tianhao) Wang, Feiyang Kang, Dawn Song. [doi]
• Disentangling misreporting from genuine adaptation in strategic settings: a causal approachDylan Zapzalka, Trenton Chang, Lindsay A. Warrenburg, Sae-Hwan Park, Daniel K. Shenfeld, Ravi B. Parikh, Jenna Wiens, Maggie Makar. [doi]
• Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced DistortionsRazaib Tariq, Minji Heo, Shahroz Tariq, Simon S. Woo. [doi]
• Federated Multi-armed Bandits with Efficient Bit-Level CommunicationsHaoran Zhang, Yang Xu, Xuchuang Wang, Hao-Xu Chen, Hao Qiu, Lin F. Yang, Yang Gao. [doi]
• Contrastive Self-Supervised Learning As Neural Manifold PackingGuanming Zhang, David J. Heeger, Stefano Martiniani. [doi]
• FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow PropagationYutong Feng, Xu Liu 0014, Yutong Xia, Yuxuan Liang 0002. [doi]
• Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical SystemsMinchan Jeong, Jongha Ryu, Se-Young Yun, Gregory W. Wornell. [doi]
• Tight Generalization Bounds for Large-Margin HalfspacesKasper Green Larsen, Natascha Schalburg. [doi]
• Broken Tokens? Your Language Model can Secretly Handle Non-Canonical TokenizationsBrian Siyuan Zheng, Alisa Liu, Orevaoghene Ahia, Jonathan Hayase, Yejin Choi 0001, Noah A. Smith. [doi]
• SPOT-Trip: Dual-Preference Driven Out-of-Town Trip RecommendationYinghui Liu, Hao Miao, Guojiang Shen, Yan Zhao, Xiangjie Kong 0001, Ivan Lee 0001. [doi]
• On Efficiency-Effectiveness Trade-off of Diffusion-based RecommendersWenyu Mao, Jiancan Wu, Guoqing Hu, Zhengyi Yang 0007, Wei Ji 0008, Xiang Wang 0010. [doi]
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level ComputationSangmin Bae, Yujin Kim, Reza Bayat, Sungnyun Kim, Jiyoun Ha, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron C. Courville, Se-Young Yun. [doi]
• Decomposing stimulus-specific sensory neural information via diffusion modelsSteeve Laquitaine, Simone Azeglio, Carlo Paris, Ulisse Ferrari, Matthew Chalk. [doi]
• Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers PoolJiangtong Li, Dongyi Liu, Kun Zhu 0036, Dawei Cheng, Changjun Jiang 0002. [doi]
• CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow MatchingLeying Zhang, Yao Qian, Xiaofei Wang 0009, Manthan Thakker, Dongmei Wang, Jianwei Yu 0001, Haibin Wu, Yuxuan Hu 0003, Jinyu Li 0001, Yanmin Qian, Sheng Zhao 0002. [doi]
• CF-VLM: CounterFactual Vision-Language Fine-tuningJusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang 0100, Keze Wang. [doi]
• Multi-Agent Reinforcement Learning with Communication-Constrained PriorsGuang Yang 0066, Tianpei Yang, Jingwen Qiao, Yanqing Wu, Jing Huo, Xingguo Chen, Yang Gao 0001. [doi]
• BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and ConstraintsLyle Regenwetter, Yazan Abu Obaideh, Fabien Chiotti, Ioanna Lykourentzou, Faez Ahmed. [doi]
• Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control PoliciesVipul Sharma, Wesley Suttle, S. Sivaranjani. [doi]
• On the Relation between Rectified Flows and Optimal TransportJohannes Hertrich, Antonin Chambolle, Julie Delon. [doi]
• Detecting Data Deviations in Electronic Health RecordsKaiping Zheng, Horng Ruey Chua, Beng Chin Ooi. [doi]
• Tight Lower Bounds and Improved Convergence in Performative PredictionPedram Khorsandi, Rushil Gupta, Mehrnaz Mofakhami, Simon Lacoste-Julien, Gauthier Gidel. [doi]
• MoRIC: A Modular Region-based Implicit Codec for Image CompressionGen Li, Haotian Wu, Deniz Gündüz. [doi]
• Mixture-of-Experts Meets In-Context Reinforcement LearningWenhao Wu, Fuhong Liu, Haoru Li, Zican Hu, Daoyi Dong, Chunlin Chen 0001, Zhi Wang 0001. [doi]
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion ModelingYanchen Luo, Zhiyuan Liu 0001, Yi Zhao, Sihang Li 0002, Hengxing Cai, Kenji Kawaguchi, Tat-Seng Chua, Yang Zhang 0094, Xiang Wang 0010. [doi]
• Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex DataHarsh Poonia, Felix Divo, Kristian Kersting, Devendra Singh Dhami. [doi]
• Class conditional conformal prediction for multiple inputs by p-value aggregationJean-Baptiste Fermanian, Mohamed Hebiri, Joseph Salmon. [doi]
• GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream GenerationYuchen Li, Chaoran Feng 0001, Zhenyu Tang 0004, Kaiyuan Deng, Wangbo Yu, Yonghong Tian 0001, Li Yuan 0007. [doi]
• MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition QueryWei Chow, Yuan Gao, Linfeng Li, Xian Wang, Qi Xu, Hang Song, Lingdong Kong, Ran Zhou, Yi Zeng, Yidong Cai, Botian Jiang, Shilin Xu 0001, Jiajun Zhang, Minghui Qiu, Xiangtai Li, Tianshu Yang, Siliang Tang, Juncheng Li 0006. [doi]
• QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code TranslationChangxin Ke, Rui Zhang 0040, Shuo Wang, Li Ding, Guangli Li, Yuanbo Wen 0001, Shuoming Zhang, Ruiyuan Xu, Jin Qin, Jiaming Guo, Chenxi Wang 0005, Ling Li, Qi Guo 0001, Yunji Chen. [doi]
• Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug RecommendationWenjie Du 0003, Xuqiang Li, Jinke Feng, Shuai Zhang, Wen Zhang, Yang Wang 0015. [doi]
• Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-TrainingReza Shirkavand, Peiran Yu, Qi He, Heng Huang 0001. [doi]
• Self-alignment of Large Video Language Models with Refined Regularized Preference OptimizationPritam Sarkar, Ali Etemad. [doi]
• KAIROS: Scalable Model-Agnostic Data ValuationJiongli Zhu, Parjanya Prashant, Alex Cloninger, Babak Salimi. [doi]
• Coresets for Clustering Under Stochastic NoiseLingxiao Huang, Zhize Li 0001, Nisheeth K. Vishnoi, Runkai Yang, Haoyu Zhao. [doi]
• Discovering Latent Graphs with GFlowNets for Diverse Conditional Image GenerationBailey Trang Nguyen, Parham Saremi, Alan Q. Wang 0001, Fangrui Huang, Zahra Tehraninasab, Amar Kumar, Tal Arbel, Fei-Fei Li 0001, Ehsan Adeli 0001. [doi]
• Video World Models with Long-term Spatial MemoryTong Wu, Shuai Yang 0001, Ryan Po, Yinghao Xu 0001, Ziwei Liu 0002, Dahua Lin, Gordon Wetzstein. [doi]
• OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time ScalesTung Nguyen, Tuan Pham, Troy Arcomano, Rao Kotamarthi, Ian T. Foster, Sandeep Madireddy, Aditya Grover. [doi]
• Look-Ahead Reasoning on Learning PlatformsHaiqing Zhu, Tijana Zrnic, Celestine Mendler-Dünner. [doi]
• Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language modelsNicolas Le Roux, Marc G. Bellemare, Jonathan Lebensold, Arnaud Bergeron, Joshua Greaves, Alexandre Fréchette, Carolyne Pelletier, Eric Thibodeau-Laufer, Sándor Tóth, Sam Work. [doi]
• Transition Matching: Scalable and Flexible Generative ModelingNeta Shaul, Uriel Singer, Itai Gat, Yaron Lipman. [doi]
• SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic ReasoningYiting Wang, Wanghao Ye, Ping Guo 0007, Yexiao He, Ziyao Wang, Bowei Tian, Shwai He, Guoheng Sun, Zheyu Shen, Sihan Chen, Ankur Srivastava 0001, Qingfu Zhang 0001, Gang Qu 0001, Ang Li 0005. [doi]
• π-RealizabilityShayan Karimi, Xiaoqi Tan. [doi]
• Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion PredictionWenbo Shang 0001, Zihan Feng 0001, Yajun Yang, Xin Huang 0001. [doi]
• FlowDAS: A Stochastic Interpolant-based Framework for Data AssimilationSiyi Chen, Yixuan Jia, Qing Qu 0001, He Sun 0010, Jeffrey A. Fessler. [doi]
• Frame In-N-Out: Unbounded Controllable Image-to-Video GenerationBoyang Wang, Xuweiyi Chen, Matheus Gadelha, Zezhou Cheng. [doi]
• MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts SystemsYinsicheng Jiang, Yao Fu 0013, Yeqi Huang, Ping Nie, Zhan Lu, Leyang Xue, Congjie He, Man-Kit Sit, Jilong Xue, Li Dong, Ziming Miao, Dayou Du, Tairan Xu, Kai Zou, Edoardo Maria Ponti, Luo Mai. [doi]
• Vector Quantization in the Brain: Grid-like Codes in World ModelsXiangyuan Peng, Xingsi Dong, Si Wu 0001. [doi]
• Neighbor-aware Contrastive Disambiguation for Cross-Modal Hashing with Redundant AnnotationsChao Su 0003, Likang Peng, Yuan Sun 0016, Dezhong Peng, Xi Peng 0001, Xu Wang 0028. [doi]
• PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers InferenceJiarui Fang, Jinzhe Pan, Aoyu Li, Xibo Sun, Jiannan Wang. [doi]
• On the Expressive Power of Mixture-of-Experts for Structured Complex TasksMingze Wang, Weinan E. [doi]
• Position: Biology is the Challenge Physics-Informed ML Needs to EvolveJulien Martinelli. [doi]
• Incentivizing Time-Aware Fairness in Data SharingJiangwei Chen 0001, Kieu Thao Nguyen Pham, Rachael Hwee Ling Sim, Arun Verma, Zhaoxuan Wu, Chuan-Sheng Foo, Bryan Kian Hsiang Low. [doi]
• PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time SeriesXinghong Chen, Weilin Wu, Kunping Yang, Guannan Chen. [doi]
• Functional Virtual Adversarial Training for Semi-Supervised Time Series ClassificationQingyi Pan, Yicheng Li. [doi]
• Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale AlignmentChen Liu, Wenfang Yao, Kejing Yin, William K. Cheung 0001, Jing Qin. [doi]
• Guarantees for Alternating Least Squares in Overparameterized Tensor DecompositionsDionysis Arvanitakis, Vaidehi Srinivas, Aravindan Vijayaraghavan. [doi]
• Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMsFangrui Zhu, Hanhui Wang, Yiming Xie, Jing Gu, Tianye Ding, Jianwei Yang, Huaizu Jiang. [doi]
• A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable InputBar Mahpud, Or Sheffet. [doi]
• Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPsXiangcheng Zhang, Yige Hong, Weina Wang 0001. [doi]
• From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training DynamicsZheng-An Chen, Tao Luo 0012. [doi]
• Prior-Guided Diffusion Planning for Offline Reinforcement LearningDonghyeon Ki, Junhyeok Oh, Seong-Woong Shim, Byung-Jun Lee 0001. [doi]
• Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal ActivationsDa Ma, Gonghu Shang, Zhi Chen 0006, Libo Qin 0001, Yijie Luo, Hongshen Xu, Lei Pan, Shuai Fan 0005, Kai Yu 0004, Lu Chen 0002. [doi]
• AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu 0001, Samuel K. Ainsworth, Dominik Krupke, Patrick Kidger, Touqir Sajed, Bartolomeo Stellato, Jisun Park 0003, Nathanael Bosch, Eli Meril, Albert Steppi, Arman Zharmagambetov, Fangzhao Zhang, David Pérez-Piñeiro, Alberto Mercurio, Ni Zhan 0002, Talor Abramovich, Kilian Lieret, Hanlin Zhang, Shirley Huang, Matthias Bethge, Ofir Press. [doi]
• Optimize the Unseen - Fast NeRF Cleanup with Free Space PriorLeo Segre, Shai Avidan. [doi]
• OpenBox: Annotate Any Bounding Boxes in 3DIn-Jae Lee, Mungyeom Kim, Kwonyoung Ryu, Pierre Musacchio, Jaesik Park. [doi]
• OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization DataYiren Song, Cheng Liu, Mike Zheng Shou. [doi]
• Learning Spatial-Aware Manipulation OrderingYuxiang Yan, Zhiyuan Zhou, Xin Gao, Guanghao Li 0001, Shenglin Li, Jiaqi Chen, Qunyan Pu, Jian Pu. [doi]
• Cue3D: Quantifying the Role of Image Cues in Single-Image 3D GenerationXiang Li, Zirui Wang, Zixuan Huang 0001, James M. Rehg. [doi]
• The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias OptimizationYihua Zhang, Changsheng Wang, Yiwei Chen, Chongyu Fan, Jinghan Jia, Sijia Liu 0001. [doi]
• Color Conditional Generation with Sliced Wasserstein GuidanceAlexander Lobashev, Maria A. Larchenko, Dmitry Guskov. [doi]
• Optimal Estimation of the Best Mean in Multi-Armed BanditsTakayuki Osogami, Junya Honda, Junpei Komiyama. [doi]
• Estimating Model Performance Under Covariate Shift Without LabelsJakub Bialek, Juhani Kivimäki, Wojtek Kuberski, Nikolaos Perrakis. [doi]
• Flow-GRPO: Training Flow Matching Models via Online RLJie Liu 0047, Gongye Liu, Jiajun Liang, Yangguang Li 0001, Jiaheng Liu, Xintao Wang 0002, Pengfei Wan 0001, Di Zhang 0026, Wanli Ouyang. [doi]
• Policy Compatible Skill Incremental Learning via Lazy Learning InterfaceDaehee Lee 0001, DongSu Lee, TaeYoon Kwack, Wonje Choi 0003, Honguk Woo. [doi]
• Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal TransportTaoran Zheng, Yan Yang 0007, Xing Li 0027, Xiang Gu 0005, Jian Sun 0009, ZongBen Xu. [doi]
• Composing Linear Layers from IrreduciblesTravis Pence, Daisuke Yamada, Vikas Singh. [doi]
• Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem SolvingXinji Mai, Haotian Xu, Xing W, Weinong Wang, Yingying Zhang, Wenqiang Zhang. [doi]
• Rectified CFG++ for Flow Based ModelsShreshth Saini, Shashank Gupta, Alan Bovik. [doi]
• Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?Junchi Yu, Yujie Liu, Jindong Gu, Philip H. S. Torr, Dongzhan Zhou. [doi]
• Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative SearchHaoran Sun, Yankai Jiang 0003, Wenjie Lou, Yujie Zhang, Wenjie Li, Lilong Wang, Mianxin Liu, Lei Liu 0029, Xiaosong Wang 0001. [doi]
• Linear Attention for Efficient Bidirectional Sequence ModelingArshia Afzal, Elías Abad-Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher. [doi]
• Preventing Shortcuts in Adapter Training via Providing the ShortcutsAnujraaj Goyal, Guocheng Qian, Huseyin Coskun, Aarush Gupta, Himmy Tam, Daniil Ostashev, Ju Hu, Dhritiman Sagar, Sergey Tulyakov, Kfir Aberman, Kuan-Chieh Wang. [doi]
• MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data CurationZhenwen Liang, Linfeng Song, Yang Li, Tao Yang 0033, Haitao Mi, Dong Yu 0001. [doi]
• When Models Don't Collapse: On the Consistency of Iterative MLEDaniel Barzilai, Ohad Shamir. [doi]
• IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task EstimationHanting Yan, Pan Mu, Shiqi Zhang 0009, Yuchao Zhu, Jinglin Zhang, Cong Bai. [doi]
• Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur CuesChinmay Talegaonkar, Nikhil Gandudi Suresh, Zachary Novack, Yash Belhe, Priyanka Nagasamudra, Nicholas Antipa. [doi]
• Forecasting in Offline Reinforcement Learning for Non-stationary EnvironmentsSuzan Ece Ada, Georg Martius, Emre Ugur, Erhan Oztop. [doi]
• 1000+ FPS 4D Gaussian Splatting for Dynamic Scene RenderingYuheng Yuan, Qiuhong Shen, Xingyi Yang, Xinchao Wang. [doi]
• A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly AnalysisDongheng Lin, Mengxue Qu, Kunyang Han, Jianbo Jiao, Xiaojie Jin 0004, Yunchao Wei. [doi]
• SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore MechanismBeitao Chen, Xinyu Lyu, Shengming Yuan, Jingkuan Song, Hengtao Shen, Lianli Gao. [doi]
• Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit FeedbackShinji Ito, Kevin G. Jamieson, Haipeng Luo, Arnab Maiti, Taira Tsuchiya. [doi]
• DataSIR: A Benchmark Dataset for Sensitive Information RecognitionFan Mo, Bo Liu, Yuan Fan, Kun Qin, Yizhou Zhao, Jinhe Zhou, Jia Sun, Jinfei Liu, Kui Ren 0001. [doi]
• GeRaF: Neural Geometry Reconstruction from Radio Frequency SignalsJiachen Lu, Hailan Shanbhag, Haitham Al-Hassanieh. [doi]
• Conformal Risk Training: End-to-End Optimization of Conformal Risk ControlChristopher Yeh, Nicolas Christianson, Adam Wierman, Yisong Yue. [doi]
• Enhancing Visual Prompting through Expanded Transformation Space and Overfitting MitigationShohei Enomoto. [doi]
• Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link PredictionJialin Zhao 0004, Alessandro Muscoloni, Umberto Michieli, Yingtao Zhang, Carlo Vittorio Cannistraci. [doi]
• MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model FrameworkQirui Mi, Mengyue Yang, Xiangning Yu 0001, Zhiyu Zhao, Cheng Deng 0001, Bo An 0001, Haifeng Zhang 0002, Xu Chen 0017, Jun Wang 0012. [doi]
• Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior SamplingShayan Mohajer Hamidi, Ben Liang 0001, En-Hui Yang. [doi]
• RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep StereoJueun Ko, Hyewon Park, Hyesong Choi, Dongbo Min. [doi]
• AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution PredictionNiklas Freymuth, Tobias Würth, Nicolas Schreiber, Balázs Gyenes, Andreas Boltres, Johannes Mitsch, Aleksandar Taranovic, Tai Hoang, Philipp Dahlinger, Philipp Becker, Luise Kärger, Gerhard Neumann. [doi]
• Prompt Tuning Transformers for Data MemorizationHaiyu Wang, Yuanyuan Lin. [doi]
• 2: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation LearningTangwen Qian, Junhe Li, Yile Chen 0001, Gao Cong, Zezhi Shao, Jun Zhang, Tao Sun 0011, Fei Wang 0014, Yongjun Xu 0001. [doi]
• Entropy-Calibrated Label Distribution LearningYunan Lu 0002, Bowen Xue, Xiuyi Jia, Lei Yang. [doi]
• Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based ModelsZitao Yang, Amin Ullah, Shuai Li, Fuxin Li, Jun Li. [doi]
• Streaming Stochastic Submodular Maximization with On-Demand User RequestsHonglian Wang, Sijing Tu, Lutz Oettershagen, Aristides Gionis. [doi]
• MaNGO - Adaptable Graph Network Simulators via Meta-LearningPhilipp Dahlinger, Tai Hoang, Denis Blessing, Niklas Freymuth, Gerhard Neumann. [doi]
• Gemstones: A Model Suite for Multi-Faceted Scaling LawsSean McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein. [doi]
• BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation LearningHongyi Zhou, Weiran Liao, Xi Huang, Yucheng Tang, Fabian Otto, Xiaogang Jia, Xinkai Jiang, Simon Hilber, Ge Li, Qian Wang, Ömer Erdinç Yagmurlu, Nils Blank, Moritz Reuss, Rudolf Lioutikov. [doi]
• VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron ChunkingKichang Yang, Seonjun Kim, Minjae Kim 0001, Nairan Zhang, Chi Zhang, Youngki Lee 0001. [doi]
• Attention Sinks: A 'Catch, Tag, Release' Mechanism for EmbeddingsStephen Zhang, Mustafa Khan, Vardan Papyan. [doi]
• Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via GrokkingTing Han, Linara Adilova, Henning Petzka, Jens Kleesiek, Michael Kamp. [doi]
• UGoDIT: Unsupervised Group Deep Image Prior Via Transferable WeightsShijun Liang 0001, Ismail Alkhouri, Siddhant Gautam, Qing Qu 0001, Saiprasad Ravishankar. [doi]
• CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action ModelDapeng Zhang, Fei Shen, Rui Zhao, Yinda Chen, Peng Zhi, Chenyang Li, Rui Zhou 0005, Qingguo Zhou. [doi]
• BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based OptimizationTonghan Wang 0001, Yanchen Jiang, David C. Parkes. [doi]
• Matchings Under Biased and Correlated EvaluationsAmit Kumar 0001, Nisheeth K. Vishnoi. [doi]
• SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language ModelsYe Sun 0004, Hao Helen Zhang, Henghui Ding, Tiehua Zhang, Xingjun Ma, Yu-Gang Jiang 0001. [doi]
• Bilevel Network Learning via Hierarchically Structured SparsityJiayi Fan, Jingyuan Yang, Shuangge Ma, MengYun Wu. [doi]
• I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media InteractionsShuhong Liu, Lin Gu 0003, Ziteng Cui, Xuangeng Chu, Tatsuya Harada. [doi]
• 3DOT: Texture Transfer for 3DGS Objects from a Single Reference ImageXiao Cao, Beibei Lin, Bo Wang 0019, Zhiyong Huang, Robby T. Tan. [doi]
• Learning to Steer: Input-dependent Steering for Multimodal LLMsJayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, Matthieu Cord. [doi]
• Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and VideosWeifeng Lin, Xinyu Wei, Ruichuan An, Tianhe Ren, Tingwei Chen, Renrui Zhang, Ziyu Guo, Wentao Zhang 0001, Lei Zhang 0006, Hongsheng Li 0001. [doi]
• Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential FeaturesKaichen Xu, Yihang Du, Mianpeng Liu, Zimu Yu, Xiaobo Sun. [doi]
• GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence DesignHanqun Cao, Haosen Shi 0003, Chenyu Wang, Sinno Jialin Pan, Pheng-Ann Heng. [doi]
• C-NAV: Towards Self-Evolving Continual Object Navigation in Open WorldMingming Yu, Fei Zhu 0004, Wenzhuo Liu, Yirong Yang, Qunbo Wang, Wenjun Wu, Jing Liu 0001. [doi]
• Activation-Informed Merging of Large Language ModelsAmin Heyrani Nobari, Kaveh Alimohammadi, Ali ArjomandBigdeli, Akash Srivastava, Faez Ahmed, Navid Azizan. [doi]
• Training a Scientific Reasoning Model for ChemistrySiddharth Narayanan, James D. Braza, Ryan-Rhys Griffiths, Albert Bou, Geemi P. Wellawatte, Mayk Caldas Ramos, Ludovico Mitchener, Michael Pieler, Samuel G. Rodriques, Andrew D. White. [doi]
• Evaluating Program Semantics Reasoning with Type Inference in System $F$Yifeng He, Luning Yang, Christopher Castro Gaw Gonzalo, Hao Chen. [doi]
• The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed TextNikhil Kandpal, Brian Lester, Colin A. Raffel, Sebastian Majstorovic, Stella Biderman, Baber Abbasi, Luca Soldaini, Enrico Shippole, A. Feder Cooper, Aviya Skowron, Shayne Longpre, Lintang Sutawika, Alon Albalak, Zhenlin Xu, Guilherme Penedo, Loubna Ben Allal, Elie Bakouch, John David Pressman, Honglu Fan, Dashiell Stander, Guangyu Song, Aaron Gokaslan, John Kirchenbauer, Tom Goldstein, Brian R. Bartoldson, Bhavya Kailkhura, Tyler Murray. [doi]
• LLM Meeting Decision Trees on Tabular DataHangting Ye, Jinmeng Li, He Zhao 0001, Dandan Guo, Yi Chang 0001. [doi]
• <tt>BetaConform</tt>: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior TransferHuaizhi Qu, Inyoung Choi, Zhen Tan 0001, Song Wang 0013, Sukwon Yun, Qi Long, Faizan Siddiqui 0001, Kwonjoon Lee, Tianlong Chen 0001. [doi]
• A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer LearningQingyue Zhang 0003, Haohao Fu, Guanbo Huang, Yaoyuan Liang, Chang Chu, Tianren Peng, Yanru Wu, Qi Li 0002, Yang Li, Shao-Lun Huang. [doi]
• On the Convergence of Single-Timescale Actor-CriticNavdeep Kumar, Priyank Agrawal, Giorgia Ramponi, Kfir Y. Levy, Shie Mannor. [doi]
• Structure Matters: Dynamic Policy GradientSara Klein, Xiangyuan Zhang, Tamer Basar, Simon Weissmann, Leif Döring. [doi]
• The third pillar of causal analysis? A measurement perspective on causal representationsDingling Yao, Shimeng Huang, Riccardo Cadei, Kun Zhang 0001, Francesco Locatello. [doi]
• Neural Thermodynamics: Entropic Forces in Deep and Universal Representation LearningLiu Ziyin 0001, Yizhou Xu, Isaac L. Chuang. [doi]
• Sequential Monte Carlo for Policy Optimization in Continuous POMDPsHany Abdulsamad, Sahel Mohammad Iqbal, Simo Särkkä. [doi]
• Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job SchedulingInguk Choi, Woo Jin Shin, Sang-Hyun Cho, Hyun-jung Kim. [doi]
• Data-Free Model Extraction for Black-box Recommender Systems via Graph ConvolutionsZeyu Wang 0011, Yidan Song, Shihao Qin, Shanqing Yu, Yujin Huang, Qi Xuan 0001, Xin Zheng 0008. [doi]
• TwinMarket: A Scalable Behavioral and Social Simulation for Financial MarketsYuzhe Yang 0002, Yifei Zhang, Minghao Wu, Kaidi Zhang, Yunmiao Zhang, Honghai Yu, Yan Hu, Benyou Wang. [doi]
• SWE-bench Goes Live!Linghao Zhang, Shilin He, Chaoyun Zhang, Yu Kang 0006, Bowen Li 0002, Chengxing Xie, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang 0001. [doi]
• Learning Human-Object Interaction as GroupsJiajun Hong, Jianan Wei, Wenguan Wang. [doi]
• ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type NeighborhoodsMichal Kmicikiewicz, Vincent Fortuin, Ewa Szczurek. [doi]
• Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement LearningEzgi Korkmaz. [doi]
• Learning from A Single Markovian Trajectory: Optimality and Variance ReductionZhenyu Sun, Ermin Wei. [doi]
• Online Learning of Pure States is as Hard as Mixed StatesMaxime Meyer, Soumik Adhikary, Naixu Guo, Patrick Rebentrost. [doi]
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised CompensationXiaoqi Zhao 0003, Youwei Pang, Chenyang Yu, Lihe Zhang, Huchuan Lu, Shijian Lu, Georges El Fakhri, Xiaofeng Liu 0001. [doi]
• LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert SpaceZhangyu Wang, Zeping Liu, Jielu Zhang, Zhongliang Zhou, Qian Cao, Nemin Wu, Lan Mu, Yang Song, Yiqun Xie, Ni Lao, Gengchen Mai. [doi]
• Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CTJiaheng Zhou, Wei Fang 0005, Luyuan Xie, Yanfeng Zhou, Lianyan Xu, Minfeng Xu, Ge Yang 0002, YuXing Tang. [doi]
• Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic EstimatorsLucas Berry, David Meger. [doi]
• Can LLMs Outshine Conventional Recommenders? A Comparative EvaluationQijiong Liu, Jieming Zhu, Lu Fan, Kun Wang 0042, Hengchang Hu, Wei Guo 0006, Yong Liu 0018, Xiao-Ming Wu 0003. [doi]
• Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through TrainingYoussef Mansour, Reinhard Heckel. [doi]
• Collaborative and Confidential Junction Trees for Hybrid Bayesian NetworksRoberto Gheda, Abele Malan, Thiago S. Guzella, Carlo Lancia, Robert Birke, Lydia Y. Chen. [doi]
• LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data CentersAvisek Naug, Antonio Guillen-Perez, Vineet Kumar, Scott Greenwood, Wesley Brewer, Sahand Ghorbanpour, Ashwin Ramesh Babu, Vineet Gundecha, Ricardo Luna Gutierrez 0001, Soumyendu Sarkar. [doi]
• ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming ContestsShiyi Xu, Yiwen Hu, Yingqian Min, Zhipeng Chen 0001, Xin Zhao 0018, Ji-Rong Wen. [doi]
• Emergent Risk Awareness in Rational Agents under Resource ConstraintsDaniel Jarne Ornia, Nicholas Bishop, Joel Dyer, Wei-chen Lee, Anisoara Calinescu, J. Doyne Farmer, Michael J. Wooldridge. [doi]
• Autoregressive Motion Generation with Gaussian Mixture-Guided Latent SamplingLinnan Tu, Lingwei Meng, Zongyi Li, Hefei Ling, Shijuan Huang. [doi]
• Adaptive Fission: Post-training Encoding for Low-latency Spike Neural NetworksYizhou Jiang, Feng Chen 0007, Yihan Li, Yuqian Liu, Haichuan Gao, Tianren Zhang, Ying Fang. [doi]
• Can Large Language Models Master Complex Card Games?Wei Wang 0074, Fuqing Bie, Junzhe Chen 0001, Dan Zhang, Shiyu Huang 0001, Evgeny Kharlamov, Jie Tang 0001. [doi]
• Personalized Subgraph Federated Learning with Differentiable Auxiliary ProjectionsWei Zhuo 0006, Zhaohuan Zhan, Han Yu 0001. [doi]
• Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive LawsLin Guo, Xiaoqing Luo, Wei Xie, Zhancheng Zhang, Hui Li 0037, Rui Wang 0050, Zhenhua Feng 0001, Xiaoning Song. [doi]
• One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-ResolutionYujing Sun, Lingchen Sun, Shuaizheng Liu, Rongyuan Wu, Zhengqiang Zhang, Lei Zhang 0006. [doi]
• Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous ThoughtHanlin Zhu, Shibo Hao, Zhiting Hu, Jiantao Jiao, Stuart J. Russell, Yuandong Tian. [doi]
• TAPVid-360: Tracking Any Point in 360 from Narrow Field of View VideoFinlay G. C. Hudson, James A. D. Gardner, William Smith 0002. [doi]
• Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory AlternativesSarah H. Cen, Salil Goyal, Zaynah Javed, Ananya Karthik, Percy Liang, Daniel E. Ho. [doi]
• HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous SynapsesZhichao Deng, Zhikun Liu, Junxue Wang, Shengqian Chen, Xiang Wei, Qiang Yu. [doi]
• Unified Reinforcement and Imitation Learning for Vision-Language ModelsByung kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang, Yueh-Hua Wu. [doi]
• MuSLR: Multimodal Symbolic Logical ReasoningJundong Xu, Hao Fei 0001, Yuhui Zhang, Liangming Pan, Qijun Huang, Qian Liu 0012, Preslav Nakov, Min-Yen Kan, William Yang Wang, Mong-Li Lee, Wynne Hsu. [doi]
• Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional GeneralizationMatthew S. Bull, Po-Chen Kuo, Andrew L. Smith, Michael A. Buice. [doi]
• Differentiable Decision Tree via "ReLU+Argmin" ReformulationQiangqiang Mao, Jiayang Ren, Yixiu Wang, Chenxuanyin Zou, Jingjing Zheng, Yankai Cao. [doi]
• SafeVid: Toward Safety Aligned Video Large Multimodal ModelsYixu Wang, Jiaxin Song, Yifeng Gao 0002, Xin Wang 0119, Yang Yao, Yan Teng 0002, Xingjun Ma, Yingchun Wang 0004, Yu-Gang Jiang 0001. [doi]
• 2Prompt: Class-aware Client Knowledge Interaction for Federated Continual LearningKunlun Xu, Yibo Feng, Jiangmeng Li, Yongsheng Qi, Jiahuan Zhou. [doi]
• UMoE: Unifying Attention and FFN with Shared ExpertsYuanhang Yang, Chaozheng Wang, Jing Li. [doi]
• Optimal community detection in dense bipartite graphsJulien Chhor, Parker Knight. [doi]
• CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive ProgrammingHan Deng, Yuan Meng, Shixiang Tang, Wanli Ouyang, Xinzhu Ma. [doi]
• Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation DelaysSongchen Fu, Siang Chen, Shaojing Zhao, Letian Bai, Hong Liang, Ta Li, YongHong Yan. [doi]
• Sum Estimation under Personalized Local Differential PrivacyDajun Sun, Wei Dong 0007, Yuan Qiu 0002, Ke Yi 0001, Graham Cormode. [doi]
• Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMsXudong Li, Mengdan Zhang, Peixian Chen, Xiawu Zheng, Yan Zhang 0109, Jingyuan Zheng, Yunhang Shen, Ke Li 0015, Chaoyou Fu, Xing Sun 0001, Rongrong Ji. [doi]
• Sinusoidal Initialization, Time for a New StartAlberto Fernández-Hernández, José I. Mestre, Manuel F. Dolz, José Duato, Enrique S. Quintana-Ortí. [doi]
• Pay Attention to Small WeightsChao Zhou, Tom Jacobs, Advait Gadhikar, Rebekka Burkholz. [doi]
• Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object DetectionGongzhe Li, Linwei Qiu, Peibei Cao, Fengying Xie, Xiangyang Ji, Qilin Sun 0001. [doi]
• SpiderSolver: A Geometry-Aware Transformer for Solving PDEs on Complex GeometriesKai Qi, Fan Wang, Zhewen Dong, Jian Sun 0009. [doi]
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language ModelsYonggan Fu, Xin Dong 0009, Shizhe Diao, Matthijs Van Keirsbilck, Hanrong Ye, Wonmin Byeon, Yashaswi Karnati, Lucas Liebenwein, Maksim Khadkevich, Alexander Keller 0001, Jan Kautz, Yingyan (Celine) Lin, Pavlo Molchanov 0001. [doi]
• From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature LearningJunsoo Oh, Jerry Song, Chulhee Yun. [doi]
• Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and GroundingYanglin Feng, Hongyuan Zhu 0002, Dezhong Peng, Xi Peng 0001, Xiaomin Song, Peng Hu 0002. [doi]
• From Experts to a Generalist: Toward General Whole-Body Control for Humanoid RobotsYuxuan Wang, Ming Yang, Gang Ding, Yu Zhang, Weishuai Zeng, Xinrun Xu, Haobin Jiang, Zongqing Lu 0002. [doi]
• GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS FusionJiayi Tian, Haiduo Huang, Tian Xia 0008, Wenzhe Zhao, Pengju Ren. [doi]
• Building 3D Representations and Generating Motions From a Single Image via Video-GenerationWeiming Zhi, Ziyong Ma, Tianyi Zhang 0014, Matthew Johnson-Roberson. [doi]
• LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference OptimizationZhenpeng Huang, Jiaqi Li, Zihan Jia, Xinhao Li 0004, Desen Meng, Lingxue Song, Xi Chen, Liang Li, Limin Wang 0002. [doi]
• SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit TokensYinhan He, Wendy Zheng, Yaochen Zhu, Zaiyi Zheng, Lin Su, Sriram Vasudevan, Qi Guo, Liangjie Hong, Jundong Li. [doi]
• Improving LLM General Preference Alignment via Optimistic Online Mirror DescentYuheng Zhang, Dian Yu 0001, Tao Ge 0001, Linfeng Song, Zhichen Zeng 0001, Haitao Mi, Nan Jiang 0008, Dong Yu 0001. [doi]
• Memorization in Graph Neural NetworksAdarsh Jamadandi, Jing Xu 0028, Adam Dziedzic, Franziska Boenisch. [doi]
• MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search DirectionsLam Ngo, Huong Ha 0001, Jeffrey Chan, Hongyu Zhang 0002. [doi]
• AmorLIP: Efficient Language-Image Pretraining via AmortizationHaotian Sun, Yitong Li, Yuchen Zhuang, Niao He, Hanjun Dai, Bo Dai 0001. [doi]
• STAR: Spatial-Temporal Tracklet Matching for Multi-Object TrackingXuewei Bai, Yongcai Wang, Deying Li 0001, Haodi Ping, Chunxu Li. [doi]
• Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video UnderstandingXiaoqian Shen, Wenxuan Zhang 0003, Jun Chen 0021, Mohamed Elhoseiny 0001. [doi]
• Show-o2: Improved Native Unified Multimodal ModelsJinheng Xie, Zhenheng Yang, Mike Zheng Shou. [doi]
• Functional data analysis for multivariate distributions through Wasserstein slicingHan Chen, Hans-Georg Müller. [doi]
• Multi-SWE-bench: A Multilingual Benchmark for Issue ResolvingDaoguang Zan, Zhirong Huang, Wei Liu, Hanwu Chen, Shulin Xin, Linhao Zhang, Qi Liu, Aoyan Li, Lu Chen, Xiaojian Zhong, Siyao Liu, Yongsheng Xiao, Liangqiang Chen, Yuyu Zhang, Jing Su, Tianyu Liu, Rui Long, Ming Ding, Liang Xiang. [doi]
• How Memory in Optimization Algorithms Implicitly Modifies the LossMatias D. Cattaneo, Boris Shigida. [doi]
• ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel LearningChau Pham 0001, Juan C. Caicedo, Bryan A. Plummer. [doi]
• DesignX: Human-Competitive Algorithm Designer for Black-Box OptimizationHongshu Guo, Zeyuan Ma, Yining Ma 0001, Xinglin Zhang 0001, Wei-neng Chen, Yue-jiao Gong. [doi]
• WKV-sharing embraced random shuffle RWKV high-order modeling for pan-sharpeningMan Zhou 0003, Xuanhua He, Danfeng Hong, Bo Huang 0001. [doi]
• DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and ResponseJunjue Wang, Weihao Xuan, Heli Qi, Zhihao Liu, Kunyi Liu, Yuhan Wu, Hongruixuan Chen, Jian Song 0010, Junshi Xia, Zhuo Zheng, Naoto Yokoya. [doi]
• Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference OptimizationJingfeng Guo, Jian Liu 0036, Jinnan Chen, Shiwei Mao, Changrong Hu, Puhua Jiang, Junlin Yu, Jing Xu, Qi Liu, Lixin Xu, Zhuo Chen, Chunchao Guo. [doi]
• Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent IntelligenceYining Hong, Rui Sun 0011, Bingxuan Li, Xingcheng Yao, Maxine Wu, Alexander Chien, Da Yin, Ying Nian Wu, Zhecan James Wang, Kai-Wei Chang 0001. [doi]
• End-to-End Vision Tokenizer TuningWenxuan Wang 0002, Fan Zhang, Yufeng Cui, Haiwen Diao, Zhuoyan Luo, Huchuan Lu, Jing Liu 0001, Xinlong Wang. [doi]
• Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language ModelsMatvei Popov, Peter Robicheaux, Anish Madan, Isaac Robinson, Joseph Nelson, Deva Ramanan, Neehar Peri. [doi]
• Scaling Up Parameter Generation: A Recurrent Diffusion ApproachKai Wang 0036, Dongwen Tang, Wangbo Zhao, Konstantin Schürholt, Zhangyang (Atlas) Wang, Yang You 0001. [doi]
• Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image AnalysisNeeraj Kumar, Chad Vanderbilt. [doi]
• Unbiased Sliced Wasserstein Kernels for High-Quality Audio CaptioningManh Luong, Khai Nguyen, Dinh Phung 0001, Reza Haffari, Lizhen Qu. [doi]
• PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical EnvironmentsWeijie Zhou, Xuantang Xiong, Yi Peng, Manli Tao, Chaoyang Zhao, Honghui Dong, Ming Tang 0001, Jinqiao Wang. [doi]
• CAMILA: Context-Aware Masking for Image Editing with Language AlignmentHyunseung Kim, Chiho Choi, Srikanth Malla, Sai Prahladh Padmanabhan, Saurabh Bagchi, Joon Hee Choi. [doi]
• LithoSim: A Large, Holistic Lithography Simulation Benchmark for AI-Driven Semiconductor ManufacturingHongquan He, Zhen Wang, Jingya Wang 0001, Tao Wu, Xuming He 0001, Bei Yu 0001, Jingyi Yu 0001, Hao Geng. [doi]
• Performative Validity of Recourse ExplanationsGunnar König, Hidde Fokkema, Timo Freiesleben, Celestine Mendler-Dünner, Ulrike von Luxburg. [doi]
• Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order AccelerationYifeng Yu, Lu Yu. [doi]
• What's in Common? Multimodal Models Hallucinate When Reasoning Across ScenesCandace Ross, Florian Bordes, Adina Williams, Polina Kirichenko, Mark Ibrahim. [doi]
• A Differential and Pointwise Control Approach to Reinforcement LearningMinh H. Nguyen, Chandrajit Bajaj. [doi]
• VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language ModelZuwei Long, Yunhang Shen, Chaoyou Fu, Heting Gao, Lijiang Li, Peixian Chen, Mengdan Zhang, Hang Shao, Jian Li 0062, Jinlong Peng, Haoyu Cao 0001, Ke Li 0015, Rongrong Ji, Xing Sun 0001. [doi]
• Robust and Diverse Multi-Agent Learning via Rational Policy GradientNiklas Lauffer, Ameesh Shah, Micah Carroll, Sanjit A. Seshia, Stuart J. Russell, Michael Dennis 0001. [doi]
• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)Tianyi Zhang 0011, Mohsen Hariri, Shaochen (Henry) Zhong, Vipin Chaudhary, Yang Sui 0001, Xia Hu 0001, Anshumali Shrivastava. [doi]
• Where Graph Meets Heterogeneity: Multi-View Collaborative Graph ExpertsZhihao Wu 0003, Jinyu Cai, Yunhe Zhang 0001, Jielong Lu, Zhaoliang Chen, Shuman Zhuang, Haishuai Wang. [doi]
• Neural B-frame Video Compression with Bi-directional Reference HarmonizationYuxi Liu, Dengchao Jin, Shuai Huo, Jiawen Gu, Chao Zhou, Huihui Bai, Ming Lu 0003, Zhan Ma 0001. [doi]
• Scalable Exploration via Ensemble++Yingru Li, Jiawei Xu, Baoxiang Wang 0001, Zhi-Quan Tom Luo. [doi]
• Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language ModelsHanze Guo, Jing Yao 0003, Xiao Zhou 0005, Xiaoyuan Yi, Xing Xie 0001. [doi]
• FastJAM: a Fast Joint Alignment Model for ImagesOmri Hirsch, Ron Shapira Weber, Shira Ifergane, Oren Freifeld. [doi]
• FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language ModelsPukang Ye, Junwei Luo, Jiachen Shen, Saipan Zhou, Shangmin Dou, Zhenfu Cao, Hanzhe Yao, Xiaolei Dong, Yunbo Yang. [doi]
• DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair ParadigmXiaowei Zhu, Yubing Ren, Fang Fang 0009, Qingfeng Tan, Shi Wang 0002, Yanan Cao 0001. [doi]
• PLD: A Choice-Theoretic List-Wise Knowledge DistillationEjafa Bassam, Dawei Zhu, Kaigui Bian. [doi]
• Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal EvaluatorsJongwoo Ko, Sungnyun Kim, Sungwoo Cho, Se-Young Yun. [doi]
• Generalizable Domain Adaptation for Sim-and-Real Policy Co-TrainingShuo Cheng, Liqian Ma, Zhenyang Chen, Ajay Mandlekar, Caelan Reed Garrett, Danfei Xu. [doi]
• CRRL: Learning Channel-invariant Neural Representations for High-performance Cross-day DecodingXianhan Tan, Binli Luo, Yu Qi, Yueming Wang 0001. [doi]
• Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?Josu Eguiluz Castañeira, Axel Brando, Migle Laukyte, Marc Serra-Vidal. [doi]
• Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable SolversNima Hosseini Dashtbayaz, Hesam Salehipour, Adrian Butscher, Nigel Morris. [doi]
• CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code AssistanceMyeongSoo Kim, Shweta Garg 0001, Baishakhi Ray, Varun Kumar, Anoop Deoras. [doi]
• Understanding Data Influence in Reinforcement FinetuningHaoru Tan, Xiuzhe Wu, Sitong Wu, Shaofeng Zhang, Yanfeng Chen, Xingwu Sun, Jeanne Shen, Xiaojuan Qi 0001. [doi]
• Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-ThoughtZihui Cheng, Qiguang Chen, Xiao Xu 0005, Jiaqi Wang 0012, Weiyun Wang, Hao Fei 0003, Yidong Wang 0003, Alex Jinpeng Wang, Zhi Chen 0006, Wanxiang Che, Libo Qin 0001. [doi]
• LLM Query Scheduling with Prefix Reuse and Latency ConstraintsGregory Dexter, Shao Tang, Ata Fatahi Baarzi, Qingquan Song, Tejas Dharamsi, Aman Gupta. [doi]
• Robust Sampling for Active Statistical InferencePuheng Li, Tijana Zrnic, Emmanuel J. Candès. [doi]
• Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D ReconstructionJiahao Ma, Lei Wang 0108, Miaomiao Liu 0001, David Ahmedt-Aristizabal, Chuong Nguyen. [doi]
• Natural Gradient VI: Guarantees for Non-Conjugate ModelsFangyuan Sun, Ilyas Fatkhullin, Niao He. [doi]
• On the rankability of visual embeddingsAnkit Sonthalia, Arnas Uselis, Seong Joon Oh. [doi]
• Robust learning of halfspaces under log-concave marginalsJane Lange, Arsen Vasilyan. [doi]
• Revisiting Orbital Minimization Method for Neural Operator DecompositionJongha Ryu, Samuel Zhou, Gregory W. Wornell. [doi]
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video HaystacksSanjoy Chowdhury, Mohamed Elmoghany, Yohan Abeysinghe, Junjie Fei, Sayan Nag, Salman H. Khan 0001, Mohamed Elhoseiny 0001, Dinesh Manocha. [doi]
• Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time ScalingHao Mark Chen, Guanxi Lu, Yasuyuki Okoshi, Zhiwen Mo, Masato Motomura, Hongxiang Fan. [doi]
• Towards Robust Parameter-Efficient Fine-Tuning for Federated LearningXiuwen Fang, Mang Ye. [doi]
• NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy DataHaolong Qian, Xianliang Yang, Ling Zhang, Lei Song, Jiang Bian 0002, Chun Yuan 0003. [doi]
• ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D ModelingShuyuan Zhang, Chenhan Jiang, ZuoOu Li, Jiankang deng. [doi]
• Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain PerspectiveJorge (Zhoujun) Cheng, Shibo Hao, Tianyang Liu 0003, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Nilabjo Dey, Yonghao Zhuang 0001, Yuheng Zha, Yi Gu 0002, Kun Zhou 0002, Yuqi Wang, Yuan Li, Richard Fan, Jianshu She, Chengqian Gao, Abulhair Saparov, Taylor W. Killian, Haonan Li 0002, Mikhail Yurochkin, Eric P. Xing, Zhengzhong Liu 0001, Zhiting Hu. [doi]
• HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic RelationsShuaicheng Zhang, Haohui Wang, Junhong Lin 0004, Xiaojie Guo 0002, Yada Zhu, Si Zhang, Dongqi Fu, Dawei Zhou 0003. [doi]
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-TuningRiccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause 0001. [doi]
• Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image GenerationJiesong Liu, Xipeng Shen. [doi]
• Enhanced Self-Distillation Framework for Efficient Spiking Neural Network TrainingXiaochen Zhao, Chengting Yu, Kairong Yu, Lei Liu, Aili Wang 0002. [doi]
• CMoB: Modality Valuation via Causal Effect for Balanced Multimodal LearningJun Wang 0012, Fuyuan Cao, Zhixin Xue, Xingwang Zhao 0001, Jiye Liang. [doi]
• Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation LearningYuxuan Zhou 0002, Xien Liu, Xiao Zhang 0001, Chen Ning, Shijin Wang 0001, Guoping Hu, Ji Wu 0002. [doi]
• Selective Omniprediction and Fair AbstentionSílvia Casacuberta, Varun Kanade. [doi]
• BlurDM: A Blur Diffusion Model for Image DeblurringJin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng, Min-Hung Chen, Chia-Wen Lin, Yen-Yu Lin. [doi]
• Understanding Prompt Tuning and In-Context Learning via Meta-LearningTim Genewein, Kevin Li, Jordi Grau-Moya, Anian Ruoss, Laurent Orseau, Marcus Hutter. [doi]
• Streaming Federated Learning with Markovian DataKhiem Huynh, Malcolm Egan, Giovanni Neglia, Jean-Marie Gorce. [doi]
• Leveraging robust optimization for llm alignment under distribution shiftsMingye Zhu, Yi Liu 0148, Zheren Fu, Yongdong Zhang 0001, Zhendong Mao 0001. [doi]
• Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-DistillersYongqi Ding, Lin Zuo, Mengmeng Jing, Kunshan Yang, Pei He, Tonglan Xie. [doi]
• Words That Unite The World: A Unified Framework for Deciphering Central Bank CommunicationsAgam Shah, Siddhant Sukhani, Huzaifa Pardawala, Saketh Budideti, Riya Bhadani, Rudra Gopal, Siddhartha Somani, Rutwik Routu, Michael Galarnyk, Soungmin Lee, Arnav Hiray, Akshar Ravichandran, Eric Kim, Pranav Aluru, Joshua Zhang, Sebastian Jaskowski, Veer Guda, Meghaj Tarte, Liqin Ye, Spencer Gosden, Rachel Yuh, Sloka Chava, Sahasra Chava, Dylan Patrick Kelly, Aiden Chiang, Harsit Mittal, Sudheer Chava. [doi]
• SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image SegmentationZhenjie Mao, Yuhuan Yang, Chaofan Ma, Dongsheng Jiang, Jiangchao Yao, Ya Zhang 0002, Yanfeng Wang 0001. [doi]
• MLEP: Multi-granularity Local Entropy Patterns for Generalized AI-generated Image DetectionLin Yuan 0002, Xiaowan Li, Yan Zhang 0108, Jiawei Zhang 0011, Hongbo Li, Xinbo Gao 0001. [doi]
• ARM: Adaptive Reasoning ModelSiye Wu, Jian Xie, Yikai Zhang 0004, Aili Chen, Kai Zhang 0033, Yu Su 0001, Yanghua Xiao. [doi]
• MisoDICE: Multi-Agent Imitation from Mixed-Quality DemonstrationsThe Viet Bui, Tien Anh Mai, Thanh Hong Nguyen. [doi]
• MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image ReasoningYuxuan Luo, Ryan Yuan, Junwen Chen, Haonan Cai, Ziyi Yue, Yuwei Yang, Fatima Zohra Daha, Ji Li, Zhouhui Lian. [doi]
• Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled DataXingyu Ren, Pengwei Liu, PengKai Wang, Guanyu Chen, QinXin Wu, Dong Ni 0002. [doi]
• Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental LimitsFan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie. [doi]
• LLM-PySC2: Starcraft II learning environment for Large Language ModelsZongyuan Li, Yanan Ni, Runnan Qi, Chang Lu, Lumin Jiang, Xiaojie Xu, Xiangbei Liu 0001, Pengfei Li, Yunzheng Guo, Zhe Ma, HuanYu Li, Hui Wu, Xian Guo, Kuihua Huang, Xuebo Zhang 0003. [doi]
• ChemPile: A 250 GB Diverse and Curated Dataset for Chemical Foundation ModelsAdrian Mirza, Nawaf Alampara, Martiño Ríos-García, Mohamed Abdelalim, Jack Butler, Bethany Connolly, Tunca Dogan, Marianna Nezhurina, Bünyamin Sen, Santosh Tirunagari, Mark Worrall, Adamo Young, Philippe Schwaller, Michael Pieler, Kevin Maik Jablonka. [doi]
• Many LLMs Are More Utilitarian Than OneAnita Keshmirian, Razan Baltaji, Babak Hemmatian, Hadi Asghari, Lav R. Varshney. [doi]
• Whose Instructions Count? Resolving Preference Bias in Instruction Fine-TuningJiayu Zhang, Changbang Li, Yinan Peng, Weihao Luo, Peilai Yu, Xuan Zhang. [doi]
• One Sample is Enough to Make Conformal Prediction RobustSoroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski. [doi]
• Exploring Tradeoffs through Mode Connectivity for Multi-Task LearningZhipeng Zhou, Ziqiao Meng, Pengcheng Wu, Peilin Zhao, Chunyan Miao. [doi]
• Normalized Attention Guidance: Universal Negative Guidance for Diffusion ModelsDar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe Song. [doi]
• Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular ObjectivesQixin Zhang 0001, Yan Sun, Can Jin, Xikun Zhang 0007, Yao Shu, Puning Zhao, Li Shen 0008, Dacheng Tao. [doi]
• CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion ModelsShristi Das Biswas, Arani Roy, Kaushik Roy 0001. [doi]
• Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural NetworksLongde Huang, Oleksandr Balabanov, Hampus Linander, Mats Granath, Daniel Persson, Jan E. Gerken. [doi]
• Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two PerspectivesGeng Zhang, Jiangrong Shen, Kaizhong Zheng, Liangjun Chen, Badong Chen. [doi]
• Bridging Human and LLM Judgments: Understanding and Narrowing the GapFelipe Maia Polo, Xinhe Wang, Mikhail Yurochkin, Gongjun Xu, Moulinath Banerjee, Yuekai Sun. [doi]
• Implicit Modeling for Transferability Estimation of Vision Foundation ModelsYaoyan Zheng, Huiqun Wang, Nan Zhou, Di Huang 0001. [doi]
• VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion TransformersQinkai Xu, Yijin Liu, Yang Chen, Lin F. Yang, Li Erran Li, Yuxiang Fu. [doi]
• AGI-Elo: How Far Are We From Mastering A Task?Shuo Sun, Yimin Zhao, Christina E. Lee, Jiawei Sun 0006, Chengran Yuan, Zefan Huang, Dongen Li, Justin KW Yeoh, Alok Prakash, Tom Malone 0001, Marcelo H. Ang Jr.. [doi]
• Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep AllocationWoojin Kim, Jaeyoung Do. [doi]
• Deep Continuous-Time State-Space Models for Marked Event SequencesYuxin Chang, Alex Boyd, Cao (Danica) Xiao, Taha A. Kass-Hout, Parminder Bhatia, Padhraic Smyth, Andrew Warrington. [doi]
• MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning ResearchHui Chen, Miao Xiong, Yujie Lu, Wei Han, Ailin Deng, Yufei He, Jiaying Wu, Yibo Li, Yue Liu 0008, Bryan Hooi. [doi]
• EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and RetrievalZebin Yang, Sunjian Zheng, Tong Xie, Tianshi Xu, Bo Yu 0014, Fan Wang 0021, Jie Tang 0003, Shaoshan Liu, Meng Li. [doi]
• Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer MemoryYuqi Wu, Wenzhao Zheng, Jie Zhou 0001, Jiwen Lu. [doi]
• PermLLM: Learnable Channel Permutation for N: M Sparse Large Language ModelsLancheng Zou, Shuo Yin, Zehua Pei, Tsung-Yi Ho, Farzan Farnia, Bei Yu 0001. [doi]
• Detecting Generated Images by Fitting Natural Image DistributionsYonggang Zhang 0003, Jun Nie, Xinmei Tian 0001, Mingming Gong, Kun Zhang 0001, Bo Han 0003. [doi]
• NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data ConstraintsChangyao Tian, Hao Li 0069, Gen Luo, Xizhou Zhu, Weijie Su 0002, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li 0001, Jifeng Dai. [doi]
• MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM InferenceWenxuan Zeng, Ye Dong, Jinjin Zhou, Jin Tan, Lei Wang 0251, Tao Wei 0002, Runsheng Wang, Meng Li 0004. [doi]
• Sparse Autoencoders Learn Monosemantic Features in Vision-Language ModelsMateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge J. Belongie, Zeynep Akata. [doi]
• Video Perception Models for 3D Scene SynthesisRui Huang 0012, Guangyao Zhai, Zuria Bauer, Marc Pollefeys, Federico Tombari, Leonidas J. Guibas, Gao Huang 0001, Francis Engelmann. [doi]
• Mellow: a small audio language model for reasoningSoham Deshmukh, Satvik Dixit, Rita Singh, Bhiksha Raj. [doi]
• MixPrompt: Efficient Mixed Prompting for Multimodal Semantic SegmentationZhiwei Hao 0001, Zhongyu Xiao, Jianyuan Guo, Li Shen 0008, Yong Luo 0002, Han Hu 0003, Dan Zeng 0001. [doi]
• Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time MarkersDaniel D'Souza, Julia Kreutzer, Adrien Morisot, Ahmet Üstün, Sara Hooker. [doi]
• Copresheaf Topological Neural Networks: A Generalized Deep Learning FrameworkMustafa Hajij, Lennart Bastian, Sarah Osentoski, Hardik Kabaria, John L. Davenport, Sheik Dawood, Balaji Cherukuri, Joseph G. Kocheemoolayil, Nastaran Shahmansouri, Adrian Lew, Theodore Papamarkou, Tolga Birdal. [doi]
• Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive PoliciesJing Wang 0112, Weiting Peng, Jing Tang, Zeyu Gong, Xihua Wang, Bo Tao 0001, Li Cheng. [doi]
• GLNCD: Graph-Level Novel Category DiscoveryBowen Deng 0002, Lele Fu, Sheng Huang, Tianchi Liao, Jialong Chen, Tao Zhang 0096, Chuan Chen 0001. [doi]
• Generalizing Verifiable Instruction FollowingValentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert 0001, Hanna Hajishirzi. [doi]
• FrameShield: Adversarially Robust Video Anomaly DetectionMojtaba Nafez, Mobina Poulaei, Nikan Vasei, Bardia Soltani Moakhar, Mohammad Sabokrou, Mohammad Hossein Rohban. [doi]
• SimpleStrat: Diversifying Language Model Generation with StratificationJustin Wong, Yury Orlovskiy, Alexander Shypula, Michael Luo, Sanjit A. Seshia, Joseph E. Gonzalez. [doi]
• Jacobian-Based Interpretation of Nonlinear Neural Encoding ModelXiaohui Gao, Haoran Yang, Yue Cheng, Mengfei Zuo, Yiheng Liu, Peiyang Li. [doi]
• RvLLM: LLM Runtime Verification with Domain KnowledgeYedi Zhang, Sun Yi Emma, Annabelle Lee Jia En, Jin Song Dong 0001. [doi]
• Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity GuaranteesSourav Ganguly, Kishan Panaganti, Arnob Ghosh, Adam Wierman. [doi]
• The Price of Opportunity Fairness in Matroid Allocation ProblemsRémi Castera, Felipe Garrido-Lucero, Patrick Loiseau, Simon Mauras, Mathieu Molina, Vianney Perchet. [doi]
• Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video GenerationHao Helen Zhang, Chun-Han Yao, Simon Donné, Narendra Ahuja, Varun Jampani. [doi]
• CAT: Circular-Convolutional Attention for Sub-Quadratic TransformersYoshihiro Yamada. [doi]
• BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural NetworksSen Bai, Chunqi Yang, Xin Bai 0004, Xin Zhang, Zhengang Jiang. [doi]
• Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-trainingShizhe Diao, Yu Yang, Yonggan Fu, Xin Dong 0009, Dan Su 0003, Markus Kliegl, Zijia Chen, Peter Belcak, Yoshi Suhara, Hongxu Yin, Mostofa Patwary, Yingyan (Celine) Lin, Jan Kautz, Pavlo Molchanov 0001. [doi]
• Lattice Boltzmann Model for Learning Real-World Pixel DynamicityGuangze Zheng 0001, Shijie Lin, Haobo Zuo, Si Si, Ming-Shan Wang, Changhong Fu 0001, Jia Pan 0001. [doi]
• EquiTabPFN: A Target-Permutation Equivariant Prior Fitted NetworkMichael Arbel, David Salinas, Frank Hutter. [doi]
• SubTrack++ : Gradient Subspace Tracking for Scalable LLM TrainingSahar Rajabi, Nayeema Nonta, Sirisha Rambhatla. [doi]
• Doubly-Robust Estimation of Counterfactual Policy Mean EmbeddingsHoussam Zenati, Bariscan Bozkurt, Arthur Gretton. [doi]
• GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual ReasoningJusheng Zhang, Yijia Fan, Wenjun Lin, Ruiqi Chen, Haoyi Jiang, Wenhao Chai, Jian Wang, Keze Wang. [doi]
• Near-Optimal Sample Complexity for Online Constrained MDPsChang Liu, Yunfan Li, Lin F. Yang. [doi]
• Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and ReasoningYang Li, Aming Wu, Zihao Zhang, Yahong Han. [doi]
• MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage ScenesJing Zhang 0037, Ruiheng Zhang 0001, Zhe Cao 0001, Kaizheng Chen. [doi]
• PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth ObservationChong Tang 0006, Joseph Powell, Dirk Koch, Robert Mullins 0001, Alex S. Weddell, Jagmohan Chauhan. [doi]
• Distributional Adversarial Attacks and Training in Deep HedgingGuangyi He, Tobias Sutter, Lukas Gonon. [doi]
• Estimating Hitting Times Locally at ScaleThemistoklis Haris, Fabian Spaeh, Spyridon Konstantinos Dragazis, Charalampos E. Tsourakakis. [doi]
• Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio RegularizationSunay Joshi, Shayan Kiyani, George J. Pappas, Edgar Dobriban, Hamed Hassani. [doi]
• Exploring Structural Degradation in Dense Representations for Self-supervised LearningSiran Dai, Qianqian Xu 0001, Peisong Wen, Yang Liu 0350, Qingming Huang. [doi]
• CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi SensingGuozhen Zhu, Yuqian Hu, Weihang Gao, Wei-Hsiang Wang, Beibei Wang 0001, K. J. Ray Liu. [doi]
• Ascent Fails to ForgetIoannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi, Volkan Cevher. [doi]
• LaViDa: A Large Diffusion Language Model for Multimodal UnderstandingShufan Li, Konstantinos Kallidromitis, Hritik Bansal, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Jason Kuen, Zhe Lin, Kai-Wei Chang 0001, Aditya Grover. [doi]
• AI-Generated Video Detection via Perceptual StraighteningChristian Internò, Robert Geirhos, Markus Olhofer, Sunny Liu, Barbara Hammer, David A. Klindt. [doi]
• A Signed Graph Approach to Understanding and Mitigating OversmoothingJiaqi Wang, Xinyi Wu, James Cheng, Yifei Wang. [doi]
• Cyclic Counterfactuals under Shift-Scale InterventionsSaptarshi Saha, Dhruv Vansraj Rathore, Utpal Garain. [doi]
• Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal ModelsXiwen Wei, Mustafa Munir, Radu Marculescu. [doi]
• Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness DegreesFu Luo, Yaoxin Wu, Zhi Zheng 0009, Zhenkun Wang 0001. [doi]
• GVPO: Group Variance Policy Optimization for Large Language Model Post-TrainingKaichen Zhang, Yuzhong Hong, Junwei Bao 0001, Hongfei Jiang, Yang Song 0021, Dingqian Hong, Hui Xiong 0001. [doi]
• Better Training Data Attribution via Better Inverse Hessian-Vector ProductsAndrew Wang, Elisa Nguyen, Runshi Yang, Juhan Bae, Sheila A. McIlraith, Roger Baker Grosse. [doi]
• Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation DecodersQiming Hu, Linlong Fan, Yiyan Luo, Yuhang Yu, Xiaojie Guo 0001, Qingnan Fan. [doi]
• Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View ClusteringYiming Wang 0007, Qun Li 0002, Dongxia Chang, Jie Wen 0001, Hua Dai 0003, Fu Xiao 0001, Yao Zhao 0001. [doi]
• SAS: Simulated Attention ScoreChuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Peihao Wang, Jing Xiong, Liliang Ren, Hao Cheng 0002, Janardhan Kulkarni, Yelong Shen, Zhangyang (Atlas) Wang, Mac Schwager, Anderson Schneider, Xiaodong Liu, Jianfeng Gao 0001. [doi]
• Leveraging Conditional Dependence for Efficient World Model DenoisingShaowei Zhang 0001, Jiahan Cao, Dian Cheng, Xunlan Zhou, Shenghua Wan, Le Gan, De-Chuan Zhan. [doi]
• Learning Simple Interpolants for Linear Integer ArithmeticMinchao Wu, Naoki Kobayashi 0001. [doi]
• Neurosymbolic Diffusion ModelsEmile van Krieken, Pasquale Minervini, Edoardo Maria Ponti, Antonio Vergari. [doi]
• No Experts, No Problem: Avoidance Learning from Bad DemonstrationsHuy Hoang, Tien Mai, Pradeep Varakantham. [doi]
• Token-Level Self-Play with Importance-Aware Guidance for Large Language ModelsTue Le, Hoang Tran Vuong, Quyen Tran, Linh Van Ngo 0001, Mehrtash Harandi, Trung Le 0001. [doi]
• Metropolis-Hastings Sampling for 3D Gaussian ReconstructionHyunjin Kim, Haebeom Jung, Jaesik Park. [doi]
• Do different prompting methods yield a common task representation in language models?Guy Davidson, Todd M. Gureckis, Brenden M. Lake, Adina Williams. [doi]
• Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOChengzhuo Tong, Ziyu Guo, Renrui Zhang, Wenyu Shan, Xinyu Wei, Zhenghao Xing, Hongsheng Li 0001, Pheng-Ann Heng. [doi]
• Compositional Monte Carlo Tree Diffusion for Extendable PlanningJaesik Yoon, Hyeonseo Cho, Sungjin Ahn. [doi]
• MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient BackpropagationChu Xu, Xinke Jiang, Rihong Qiu, Jiaran Gao, Junfeng Zhao 0001. [doi]
• Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion GamesRunyu Lu, Peng Zhang 0127, Ruochuan Shi, Yuanheng Zhu, Dongbin Zhao, Yang Liu 0066, Dong Wang 0004, Cesare Alippi. [doi]
• ELDET: Early-Learning Distillation with Noisy Labels for Object DetectionDongmin Choi, Sangbin Lee, EungGu Yun 0001, Jonghyuk Baek, Frank C. Park 0001. [doi]
• Deep learning for continuous-time stochastic control with jumpsPatrick Cheridito, Jean-Loup Dupret, Donatien Hainaut. [doi]
• Bootstrap Off-policy with World ModelGuojian Zhan, Likun Wang, Xiangteng Zhang, Jiaxin Gao 0002, Masayoshi Tomizuka, Shengbo Eben Li. [doi]
• Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language ModelsShenglong Zhou 0002, Manjiang Yin, Leiyu Sun, Shicai Yang, Di Xie, Jiang Zhu. [doi]
• Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian FrameworkThomson Yen, Andrew Siah, Haozhe Chen, C. Guetta, Tianyi Peng, Hongseok Namkoong. [doi]
• LexiCon: a Benchmark for Planning under Temporal Constraints in Natural LanguagePeriklis Mantenoglou, Rishi Hazra, Pedro Zuidberg Dos Martires, Luc De Raedt. [doi]
• UniViT: Unifying Image and Video Understanding in One Vision EncoderFeilong Tang, Xiang An, Haolin Yang, Yin Xie, Kaicheng Yang 0002, Ming Hu, Zheng Cheng, Xingyu Zhou, Zimin Ran, Imran Razzak, Ziyong Feng, Behzad Bozorgtabar, Jiankang deng, ZongYuan Ge. [doi]
• Understanding and Rectifying Safety Perception Distortion in VLMsXiaohan Zou, Jian Kang, George Kesidis, Lu Lin 0001. [doi]
• Let the LLM Stick to Its Strengths: Learning to Route Economical LLMYi-Kai Zhang, Shiyin Lu, Qingguo Chen, Weihua Luo, De-Chuan Zhan, Han-Jia Ye. [doi]
• p-Matchoid Constraints and Fully Dynamic SettingKiarash Banihashem, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh. [doi]
• VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video GenerationWenhao Wang, Yi Yang. [doi]
• Revitalizing SVD for Global Covariance Pooling: Halley's Method to Overcome Over-FlatteningJiawei Gu, Ziyue Qiao, Xinming Li, Zechao Li. [doi]
• MixSignGraph: A Sign Sequence is Worth Mixed Graphs of NodesShiwei Gan, Yafeng Yin 0002, Zhiwei Jiang 0001, Lei Xie 0004, Sanglu Lu, Hongkai Wen 0001. [doi]
• Revising and Falsifying Sparse Autoencoder Feature ExplanationsGeorge Ma, Samuel Pfrommer, Somayeh Sojoudi. [doi]
• SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model CheckingRishabh Agrawal, Kaushik T. Ranade, Aja Khanal, Kalyan S. Basu, Apurva Narayan. [doi]
• Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement LearningAlex Su, Haozhe Wang 0002, Weiming Ren, Fangzhen Lin, Wenhu Chen. [doi]
• Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility MatrixZhuonan Zheng, Yuanchen Bei, Zhiyao Zhou, Sheng Zhou 0004, Yao Ma 0001, Ming Gu 0014, Hongjia Xu, Jiawei Chen 0007, Jiajun Bu. [doi]
• LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language ModelsHao Sun, Huailiang Peng, Qiong Dai, Xu Bai, Yanan Cao 0001. [doi]
• MONITRS: Multimodal Observations of Natural Incidents Through Remote SensingShreelekha Revankar, Utkarsh Mall, Cheng Perng Phoo, Kavita Bala, Bharath Hariharan. [doi]
• Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical OperationsHao Li 0073, He Cao, Bin Feng, Daniel Shao, Robert Tang, Zhiyuan Yan 0002, Yonghong Tian 0001, Li Yuan, Yu Li. [doi]
• DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic ManipulationJingyi Tian, Le Wang 0003, Sanping Zhou, Sen Wang, Jiayi Li, Gang Hua 0001. [doi]
• Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM PretrainingHaochen Zhang, Junze Yin, Guanchu Wang, Zirui Liu 0001, Lin F. Yang, Tianyi Zhang 0011, Anshumali Shrivastava, Vladimir Braverman. [doi]
• DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-ResolutionRongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li 0014, Lei Zhang 0006. [doi]
• Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and MoreJinwoo Lim, Suhyun Kim, Soo-Mook Moon. [doi]
• Influence Guided Context Selection for Effective Retrieval-Augmented GenerationJiale Deng, Yanyan Shen, Ziyuan Pei, Youmin Chen, Linpeng Huang. [doi]
• Quantitative convergence of trained neural networks to Gaussian processesAndrea Agazzi, Eloy Mósig García, Dario Trevisan. [doi]
• Computational Efficiency under Covariate Shift in Kernel Ridge RegressionAndrea Della Vecchia, Arnaud Mavakala Watusadisi, Ernesto De Vito, Lorenzo Rosasco. [doi]
• Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum CircuitsMd Mobasshir Arshed Naved, Wenbo Xie, Wojciech Szpankowski, Ananth Grama. [doi]
• PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector QuantizationHonglin Li 0001, Zhongyi Shui, YunLong Zhang, Chenglu Zhu, Lin Yang 0002. [doi]
• Angles Don't Lie: Unlocking Training‑Efficient RL Through the Model's Own SignalsQinsi Wang, JingHan Ke, Hancheng Ye, Yueqian Lin, Yuzhe Fu, Jianyi Zhang, Kurt Keutzer, Chenfeng Xu, Yiran Chen 0001. [doi]
• Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied LearningWei Huang, Jianshu Zhang, Leiyu Wang, Heyue Li, Luoyi Fan, Yichen Zhu, Nanyang Ye 0001, Qinying Gu. [doi]
• Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial ImputationZhangqi Jiang, Tingjin Luo, Xu Yang, Xinyan Liang. [doi]
• Continuous Concepts Removal in Text-to-image Diffusion ModelsTingxu Han, Weisong Sun, Yanrong Hu, Chunrong Fang, Yonglong Zhang, ShiQing Ma, Tao Zheng 0005, Zhenyu Chen 0001, Zhenting Wang. [doi]
• ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real WorldWeixiang Yan, Haitian Liu, Tengxiao Wu, Qian Chen 0003, Wen Wang 0001, Haoyuan Chai, Jiayi Wang. [doi]
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion ModelsLuca Eyring, Shyamgopal Karthik, Alexey Dosovitskiy, Nataniel Ruiz, Zeynep Akata. [doi]
• Searching Latent Program SpacesMatthew Macfarlane, Clément Bonnet. [doi]
• Does Stochastic Gradient really succeed for bandits?Dorian Baudry, Emmeran Johnson, Simon Vary, Ciara Pike-Burke, Patrick Rebeschini. [doi]
• KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing ModelsYongliang Wu, Zonghui Li, Xinting Hu, Xinyu Ye, Xianfang Zeng, Gang Yu, Wenbo Zhu, Bernt Schiele, Ming-Hsuan Yang 0001, Xu Yang 0004. [doi]
• PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in EndoscopyRuyu Liu, Lin Wang, Mingming Zhou, Jianhua Zhang 0002, Haoyu Zhang, Xiufeng Liu 0001, Xu Cheng 0003, Sixian Chan 0001, Yanbin Shen, Sheng Dai, YuPing Yan, Yaochu Jin, Lingjuan Lyu. [doi]
• SteerConf: Steering LLMs for Confidence ElicitationZiang Zhou, Tianyuan Jin, Jieming Shi 0001, Qing Li 0001. [doi]
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical DiagnosisHaolin Li 0001, Tianjie Dai, Zhe Chen 0024, Siyuan Du, Jiangchao Yao, Ya Zhang 0002, Yanfeng Wang 0001. [doi]
• From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical ImagingDmitry Lvov, Ilya Pershin. [doi]
• MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time SeriesPayal Mohapatra, Yueyuan Sui, Akash Pandey, Stephen Xia, Qi Zhu 0002. [doi]
• TransferBench: Benchmarking Ensemble-based Black-box Transfer AttacksFabio Brau, Maura Pintor, Antonio Emanuele Cinà, Raffaele Mura, Luca Scionis, Luca Oneto, Fabio Roli, Battista Biggio. [doi]
• Quantifying Elicitation of Latent Capabilities in Language ModelsElizabeth Donoway, Hailey Joren, Arushi Somani, Henry Sleight, Julian Michael, Michael R. DeWeese, John Schulman, Ethan Perez, Fabien Roger, Jan Leike. [doi]
• Discrete Diffusion Models: Novel Analysis and New Sampler GuaranteesYuchen Liang, Yingbin Liang, Lifeng Lai, Ness Shroff. [doi]
• WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-LocalizationJiahao Wen, Hang Yu 0006, Zhedong Zheng. [doi]
• GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic AlgorithmsNoah Krever, Jakub Cerný, Moïse Blanchard, Christian Kroer. [doi]
• Optimizing Anytime Reasoning via Budget Relative Policy OptimizationPenghui Qi, Zichen Liu, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin. [doi]
• Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled StreamsDonghao Sun, Xi Wang, Xu Yang 0019, Kun Wei, Cheng Deng 0002. [doi]
• RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguardsJingnan Zheng, Xiangtian Ji, Yijun Lu, Chenhang Cui, Weixiang Zhao, Gelei Deng, Zhenkai Liang, An Zhang 0003, Tat-Seng Chua. [doi]
• FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language ModelsYan Gao 0016, Massimo Roberto Scamarcia, Javier Fernández-Marqués, Mohammad Naseri, Chong Shen Ng, Dimitris Stripelis, Zexi Li 0001, Tao Shen 0002, Jiamu Bai, Daoyuan Chen, Zikai Zhang 0003, Rui Hu 0005, Inseo Song, KangYoon Lee, Hong Jia, Ting Dang, Junyan Wang, Zheyuan Liu 0002, Daniel J. Beutel, Lingjuan Lyu, Nicholas D. Lane. [doi]
• Efficient Adaptive Federated OptimizationSu-Hyeong Lee, Sidharth Sharma, Manzil Zaheer, Tian Li 0005. [doi]
• Efficient Multi-modal Large Language Models via Progressive Consistency DistillationZichen Wen, Shaobo Wang 0001, Yufa Zhou 0001, Junyuan Zhang, Qintong Zhang, Yifeng Gao 0003, Zhaorun Chen, Bin Wang 0065, Weijia Li, Conghui He, Linfeng Zhang 0001. [doi]
• DermaCon-IN: A Multiconcept-Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI ResearchShanawaj S. Madarkar, Mahajabeen Madarkar, Madhumitha Venkatesh, Teli Prakash, Konda Reddy Mopuri, Vinaykumar MV, KVL Sathwika, Adarsh Kasturi, Gandla Dilip Raj, Padharthi Supranitha, Harsh Udai. [doi]
• Concept Incongruence: An Exploration of Time and Death in Role PlayingXiaoyan Bai, Ike Peng, Aditya Singh, Chenhao Tan. [doi]
• From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language ModelsCharles W. J. Pugh, Paulina G. Nuñez-Valencia, Mafalda Dias, Jonathan Frazer. [doi]
• HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message PassingJohann Flemming Gloy, Simon Olsson. [doi]
• Constrained Posterior Sampling: Time Series Generation with Hard ConstraintsSai Shankar Narasimhan, Shubhankar Agarwal, Litu Rout, Sanjay Shakkottai, Sandeep Chinchali. [doi]
• Learning Intractable Multimodal Policies with Reparameterization and Diversity RegularizationZiqi Wang 0011, Jiashun Liu, Ling Pan. [doi]
• Keeping an Eye on LLM Unlearning: The Hidden Risk and RemedyJie Ren 0019, Zhenwei Dai, Xianfeng Tang, Yue Xing 0002, Shenglai Zeng, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He 0002, Charu Aggarwal 0001, Hui Liu 0003. [doi]
• Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm DiscoveryQinglong Hu, Qingfu Zhang 0001. [doi]
• FAN: Fourier Analysis NetworksYihong Dong, Ge Li 0001, Yongding Tao, Xue Jiang, Kechi Zhang, Jia Li 0012, Jinliang Deng, Jing Su, Jun Zhang, Jingjing Xu. [doi]
• Delta Attention: Fast and Accurate Sparse Attention Inference by Delta CorrectionJeffrey Willette, Heejun Lee, Sung Ju Hwang. [doi]
• MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and ThoroughlyZhaowei Wang 0003, Wenhao Yu 0002, Xiyu Ren, Jipeng Zhang, Yu Zhao 0043, Rohit Saxena, Liang Cheng, Ginny Y. Wong, Simon See, Pasquale Minervini, Yangqiu Song, Mark Steedman. [doi]
• Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning ModelsJunyi Li 0001, Hwee Tou Ng. [doi]
• Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and InferenceDenis Blessing, Julius Berner, Lorenz Richter, Carles Domingo-Enrich, Yuanqi Du, Arash Vahdat, Gerhard Neumann. [doi]
• Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention NetworksLuca Arnaboldi 0002, Bruno Loureiro, Ludovic Stephan, Florent Krzakala, Lenka Zdeborová. [doi]
• CPO: Condition Preference Optimization for Controllable Image GenerationZonglin Lyu, Ming Li 0010, Xinxin Liu, Chen Chen 0001. [doi]
• Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / FailureAleksandrs Slivkins, Yunzong Xu, Shiliang Zuo. [doi]
• BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object NavigationZibo Zhou, Yue Hu 0011, Lingkai Zhang, Zonglin Li, Siheng Chen. [doi]
• Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English VarietiesJiyoung Lee, Seungho Kim, Jieun Han, Jun Min Lee, Kitaek Kim, Alice Oh, Edward Choi 0003. [doi]
• Gymnasium: A Standard Interface for Reinforcement Learning EnvironmentsMark Towers, Ariel Kwiatkowski, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, Arjun KG, Rodrigo Perez-Vicente, J. K. Terry 0001, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G. Younis. [doi]
• VaMP: Variational Multi-Modal Prompt Learning for Vision-Language ModelsSilin Cheng, Kai Han 0001. [doi]
• State Size Independent Statistical Error Bound for Discrete Diffusion ModelsShintaro Wakasugi, Taiji Suzuki. [doi]
• WorldWeaver: Generating Long-Horizon Video Worlds via Rich PerceptionZhiheng Liu, Xueqing Deng, Shoufa Chen, Angtian Wang, Qiushan Guo, Mingfei Han 0003, Zeyue Xue, Mengzhao Chen, Ping Luo 0002, Linjie Yang. [doi]
• Robust Equilibria in Continuous Games: From Strategic to Dynamic RobustnessKyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose H. Blanchet. [doi]
• Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human BrainJingmin An, Yilong Song, Ruolin Yang 0006, Nai Ding, Lingxi Lu, Yuxuan Wang, Wei Wang, Chu Zhuang, Qian Wang, Fang Fang. [doi]
• Adjusted Count Quantification Learning on GraphsClemens Damke, Eyke Hüllermeier. [doi]
• HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM ReasoningZhi Jing 0004, Siyuan Yang, Jicong Ao, Ting Xiao 0002, Yu-Gang Jiang 0001, Chenjia Bai. [doi]
• egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world TasksMatthias Jammot, Björn Braun, Paul Streli, Rafael Wampfler, Christian Holz 0001. [doi]
• STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language ModelYuang Qi, Na Zhao 0009, Qiyi Yao, BenLong Wu, Weiming Zhang 0001, Nenghai Yu, Kejiang Chen. [doi]
• How Particle System Theory Enhances Hypergraph Message PassingYixuan Ma, Kai Yi, Pietro Lió, Shi Jin, Yuguang Wang 0001. [doi]
• Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction DetectionDongkeun Kim, Minsu Cho, Suha Kwak. [doi]
• DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation PlatformPeizhi Niu, Yu-Hsiang Wang, Vishal Rana, Chetan Rupakheti, Abhishek Pandey, Olgica Milenkovic. [doi]
• The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum GamesIoannis Anagnostides, Ioannis Panageas, Tuomas Sandholm, Jingming Yan. [doi]
• Some Optimizers are More Equal: Understanding the Role of Optimizers in Group FairnessMojtaba Kolahdouzi, Hatice Gunes, Ali Etemad. [doi]
• MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image RecoveryHainuo Wang, Qiming Hu, Xiaojie Guo 0001. [doi]
• ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion GenerationXiaomeng Yang, Lei Lu, Qihui Fan, Changdi Yang, Juyi Lin, Yanzhi Wang 0001, Xuan Zhang, Shangqian Gao. [doi]
• ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail PredictionJiabao Lei, Kewei Shi, Zhihao Liang 0002, Kui Jia. [doi]
• Cancer Survival Analysis via Zero-shot Tumor Microenvironment Segmentation on Low-resolution Whole Slide Pathology ImagesJiao Tang, Wei Shao 0005, Daoqiang Zhang. [doi]
• From Sequence to Structure: Uncovering Substructure Reasoning in TransformersXinnan Dai, Kai Yang, Jay Revolinsky, Kai Guo 0003, Aoran Wang, Bohang Zhang, Jiliang Tang. [doi]
• FastVID: Dynamic Density Pruning for Fast Video Large Language ModelsLeqi Shen, Guoqiang Gong, Tao He, Yifeng Zhang, Pengzhang Liu, Sicheng Zhao, Guiguang Ding. [doi]
• REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion TrainingZiqiao Wang, Wangbo Zhao, Yuhao Zhou 0004, Zekai Li, Zhiyuan Liang, Mingjia Shi, Xuanlei Zhao, Pengfei Zhou, Kaipeng Zhang, Zhangyang (Atlas) Wang, Kai Wang 0036, Yang You 0001. [doi]
• Preference Optimization on Pareto Sets: On a Theory of Multi-Objective OptimizationAbhishek Roy, Geelon So, Yian Ma. [doi]
• YOLOv12: Attention-Centric Real-Time Object DetectorsYunjie Tian, Qixiang Ye, David S. Doermann. [doi]
• Fully Autonomous Neuromorphic Navigation and Dynamic Obstacle AvoidanceXiaochen Shang, Pengwei Luo, Xinning Wang, Jiayue Zhao, Huilin Ge, Bo Dong 0004, Xin Yang 0011. [doi]
• Redefining Experts: Interpretable Decomposition of Language Models for Toxicity MitigationZuhair Hasan Shaik, Abdullah Mazhar, Aseem Srivastava, Md. Shad Akhtar. [doi]
• Representation Consistency for Accurate and Coherent LLM Answer AggregationJunqi Jiang, Tom Bewley, Salim I. Amoukou, Francesco Leofante, Antonio Rago 0001, Saumitra Mishra, Francesca Toni. [doi]
• The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert ModelSohini Saha, Mezisashe Ojuba, Leslie M. Collins, Boyla Mainsah. [doi]
• Revisiting Frank-Wolfe for Structured Nonconvex OptimizationHoomaan Maskan, Yikun Hou, Suvrit Sra, Alp Yurtsever. [doi]
• Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse ProblemsDeliang Wei, Peng Chen 0045, Haobo Xu, Jiale Yao, Fang Li 0004, Tieyong Zeng. [doi]
• Chain-of-Action: Trajectory Autoregressive Modeling for Robotic ManipulationWenbo Zhang 0009, Tianrun Hu, Hanbo Zhang, Yanyuan Qiao, Yuchu Qin, Yang Li 0184, Jiajun Liu 0004, Tao Kong, Lingqiao Liu, Xiao Ma. [doi]
• ReDit: Reward Dithering for Improved LLM Policy OptimizationChenxing Wei, Jiarui Yu, Ying He 0006, Hande Dong, Yao Shu, Fei Richard Yu. [doi]
• Learning Expandable and Adaptable Representations for Continual LearningRuilong Yu, Mingyan Liu, Fei Ye 0004, Adrian G. Bors, Rongyao Hu, Jingling Sun, Shijie Zhou 0002. [doi]
• Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow ReasoningHao Chen 0193, Jiaming Liu 0003, Chenyang Gu, Zhuoyang Liu, Renrui Zhang, Xiaoqi Li 0020, Xiao He, Yandong Guo, Chi-Wing Fu, Shanghang Zhang, Pheng-Ann Heng. [doi]
• Causal Climate Emulation with Bayesian FilteringSebastian Hickman, Ilija Trajkovic, Julia Kaltenborn, Francis Pelletier, Alex Archibald, Yaniv Gurwicz, Peer Nowack, David Rolnick, Julien Boussard. [doi]
• Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier RegularizationWeiming Liu 0005, Xinting Liao, Jun Dan, Fan Wang 0020, Hua Yu 0006, Junhao Dong 0001, Shunjie Dong, Lianyong Qi, Yew-Soon Ong. [doi]
• Beyond Modality Collapse: Representation Blending for Multimodal Dataset DistillationXin Zhang 0092, Ziruo Zhang, Jiawei Du, Zuozhu Liu, Joey Tianyi Zhou. [doi]
• CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide designZiyi Yang 0011, Hanyuan Xie, Yinjun Jia, Xiangzhe Kong, Jiqing Zheng, Ziting Zhang, Yang Liu 0003, Lei Liu 0049, Yanyan Lan. [doi]
• SentinelKilnDB: A Large-Scale Dataset and Benchmark for OBB Brick Kiln Detection in South Asia Using Satellite ImageryRishabh Mondal, Jeet Parab, Heer Kubadia, Shataxi Dubey, Shardul Junagade, Zeel B. Patel, Nipun Batra 0001. [doi]
• EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned LearningYuhan Liu 0021, Linghui Fu, Zhen Yang 0004, Hao Chen 0034, Youfu Li 0001, Yongjian Deng. [doi]
• DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real TransferWentao Xu, Huiqiao Fu, Haoyu Dong, Zhehao Zhou, Chunlin Chen 0001. [doi]
• Depth-Bounds for Neural Networks via the Braid ArrangementMoritz Grillo, Christoph Hertrich, Georg Loho. [doi]
• PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled PriorsYimeng Chen, Piotr Piekos, Mateusz Ostaszewski, Firas Laakom, Jürgen Schmidhuber. [doi]
• LoRA vs Full Fine-tuning: An Illusion of EquivalenceReece Shuttleworth, Jacob Andreas, Antonio Torralba 0001, Pratyusha Sharma. [doi]
• Learning long range dependencies through time reversal symmetry breakingGuillaume Pourcel, Maxence Ernoult. [doi]
• Multimodal 3D Genome Pre-trainingMinghao Yang, Pengteng Li, Yan Liang, Qianyi Cai, Zhihang Zheng, Shichen Zhang, Pengfei Zhang 0005, Zhi-an Huang, Hui Xiong 0001. [doi]
• MokA: Multimodal Low-Rank Adaptation for MLLMsYake Wei, Yu Miao, Dongzhan Zhou, Di Hu 0001. [doi]
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeZihan Qiu, Zekun Wang, Bo Zheng 0007, Zeyu Huang, Kaiyue Wen, Songlin Yang, Rui Men, Le Yu, Fei Huang, Suozhi Huang, Dayiheng Liu, Jingren Zhou 0001, Junyang Lin. [doi]
• Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You ThinkGe Wu, Shen Zhang, Ruijing Shi, Shanghua Gao, Zhenyuan Chen, Lei Wang 0118, Zhaowei Chen, Hongcheng Gao, Yao Tang, Jian Yang 0003, Ming-Ming Cheng, Xiang Li 0041. [doi]
• Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without InterventionsHidde Fokkema, Tim van Erven, Sara Magliacane. [doi]
• Non-Stationary Lipschitz BanditsNicolas Nguyen, Solenne Gaucher, Claire Vernade. [doi]
• PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation AnalysisYan Wu, Esther Wershof, Sebastian M. Schmon, Marcel Nassar, Blazej Osinski, Ridvan Eksi, Zichao Yan, Rory Stark, Kun Zhang, Thore Graepel. [doi]
• Resource-Constrained Federated Continual Learning: What Does Matter?Yichen Li 0006, Yuying Wang, Jiahua Dong 0001, Haozhao Wang, Yining Qi, Rui Zhang 0003, Ruixuan Li 0001. [doi]
• FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion RecognitionPragya Singh, Ankush Gupta, Somay Jalan, Mohan Kumar, Pushpendra Singh 0001. [doi]
• Latent Mixture of Symmetries for Sample-Efficient Dynamic LearningHaoran Li 0005, Chenhan Xiao, Muhao Guo, Yang Weng. [doi]
• Subgraph Federated Learning via Spectral MethodsJavad Aliakbari, Johan Östman, Ashkan Panahi, Alexandre Graell i Amat. [doi]
• VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic PlayZelai Xu, Ruize Zhang 0001, Chao Yu 0005, Huining Yuan 0002, Xiangmin Yi, Shilong Ji, Chuqi Wang, Wenhao Tang, Feng Gao, Wenbo Ding 0001, Xinlei Chen, Yu Wang 0002. [doi]
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial OptimizationYu Wang, Yang Li, Junchi Yan, Yi Chang. [doi]
• Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate SchedulesBinghui Li, Fengling Chen, Zixun Huang, Lean Wang, Lei Wu. [doi]
• HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained ModelsHan Liu 0008, Jiaqi Li, Zhi Xu 0008, Xiaotong Zhang 0003, Xiaoming Xu 0003, Fenglong Ma, Yuanman Li, Hong Yu 0005. [doi]
• DISCO: DISCrete nOise for Conditional Control in Text-to-Image Diffusion ModelsLongquan Dai, Ming Wu, Dejiao Xue, He Wang, Jinhui Tang 0001. [doi]
• Angular Constraint Embedding via SpherePair Loss for Constrained ClusteringShaojie Zhang, Ke Chen. [doi]
• Approximation theory for 1-Lipschitz ResNetsDavide Murari, Takashi Furuya, Carola-Bibiane Schönlieb. [doi]
• NEP: Autoregressive Image Editing via Next Editing Token PredictionHuimin Wu 0001, Xiaojian (Shawn) Ma, Haozhe Zhao, Yanpeng Zhao, Qing Li 0003. [doi]
• Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning SystemsMarcos Negre Saura, Richard Allmendinger 0001, Wei Pan 0004, Theodore Papamarkou. [doi]
• Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable PuzzlesJiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Jiaze Chen, Xuefeng Li, Qiying Yu, Hao Zhou 0012, Mingxuan Wang. [doi]
• Risk-Averse Total-Reward Reinforcement LearningXihong Su, Jia Lin Hau, Gersi Doko, Kishan Panaganti, Marek Petrik. [doi]
• FRN: Fractal-Based Recursive Spectral Reconstruction NetworkGe Meng, Zhongnan Cai, Ruizhe Chen, Jingyan Tu, Yingying Wang 0005, Yue Huang 0001, Xinghao Ding. [doi]
• Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video GenerationAgneet Chatterjee, Rahim Entezari, Maksym Zhuravinskyi, Maksim Lapin, Reshinth Adithyan, Amit Raj, Chitta Baral, Yezhou Yang, Varun Jampani. [doi]
• Find your Needle: Small Object Image Retrieval via Multi-Object Attention OptimizationMichael Green, Matan Levy, Issar Tzachor, Dvir Samuel, Nir Darshan, Rami Ben-Ari. [doi]
• SONAR: Long-Range Graph Propagation Through Information WavesAlessandro Trenta, Alessio Gravina, Davide Bacciu. [doi]
• Non-rectangular Robust MDPs with Normed Uncertainty SetsNavdeep Kumar, Adarsh Gupta, Maxence Mohamed Elfatihi, Giorgia Ramponi, Kfir Y. Levy, Shie Mannor. [doi]
• Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic ApproachWoohyeon Byeon, Giseung Park, Jongseong Chae, Amir Leshem, Youngchul Sung. [doi]
• SPMDM: Enhancing Masked Diffusion Models through Simplifying Sampling PathYichen Zhu, Weiyu Chen, James Kwok 0001, Zhou Zhao 0001. [doi]
• Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?Xi Chen, Kaituo Feng, Changsheng Li, Xunhao Lai, Xiangyu Yue 0001, Ye Yuan 0001, Guoren Wang. [doi]
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video GenerationAriel Shaulov, Itay Hazan 0001, Lior Wolf, Hila Chefer. [doi]
• Towards Pre-trained Graph Condensation via Optimal TransportYeyu Yan, Shuai Zheng 0005, Wenjun Hui, Xiangkai Zhu, Dong Chen 0043, Zhenfeng Zhu, Yao Zhao 0001, Kunlun He. [doi]
• Metric Automata Theory: A Unifying Theory of RNNsAdam Dankowiakowski, Alessandro Ronca. [doi]
• Towards Provable Emergence of In-Context Reinforcement LearningJiuqi Wang, Rohan Chandra, Shangtong Zhang. [doi]
• On the Emergence of Linear Analogies in Word EmbeddingsDaniel J. Korchinski, Dhruva Karkada, Yasaman Bahri, Matthieu Wyart. [doi]
• G-Memory: Tracing Hierarchical Memory for Multi-Agent SystemsGuibin Zhang, Muxin Fu, Kun Wang 0056, Frank Wan, Miao Yu, Shuicheng Yan. [doi]
• Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for ReasoningJie Cheng 0009, Gang Xiong 0001, Ruixi Qiao, Lijun Li, Chao Guo 0006, Junle Wang, Yisheng Lv, Fei-Yue Wang 0001. [doi]
• Gaussian Processes for Shuffled RegressionMasahiro Kohjima. [doi]
• Forging Time Series with Language: A Large Language Model Approach to Synthetic Data GenerationCécile Rousseau, Tobia Boschi, Giandomenico Cornacchia, Dhaval Salwala, Alessandra Pascale, Juan Bernabé-Moreno. [doi]
• Scaling Physical Reasoning with the PHYSICS DatasetShenghe Zheng, QianJia Cheng, Junchi Yao, Mengsong Wu, Haonan He, Ning Ding 0002, Yu Cheng 0001, Shuyue Hu, Lei Bai 0001, Dongzhan Zhou, Ganqu Cui, Peng Ye 0006. [doi]
• AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language ModelsXinyi Wang, Xun Yang 0001, Yanlong Xu, Yuchen Wu, Zhen Li 0026, Na Zhao 0004. [doi]
• Effects of Dropout on Performance in Long-range Graph Learning TasksJasraj Singh, Keyue Jiang, Brooks Paige, Laura Toni. [doi]
• Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot DemonstrationsZican Dong, Han Peng, Peiyu Liu 0002, Xin Zhao 0018, Dong Wu, Feng Xiao, Zhifeng Wang. [doi]
• Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural NetworksYi Xiao 0003, Qiangqiang Yuan, Kui Jiang, Wenke Huang 0003, Qiang Zhang 0011, Tingting Zheng, Chia-Wen Lin, Liangpei Zhang 0001. [doi]
• Elastic Robust Unlearning of Specific Knowledge in Large Language ModelsYize Sui, Jing Ren, Wenjing Yang 0002, Ruochun Jin, Liyang Xu, Xiyao Liu, J. Wang. [doi]
• GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation ScalingTianhao Chen, Xin Xu 0001, Zijing Liu, Pengxiang Li, Xinyuan Song 0002, Ajay Jaiswal, Fan Zhang, Jishan Hu, Yang Wang 0020, Hao Chen 0103, Shizhe Diao, Shiwei Liu 0003, Yu Li, Lu Yin 0006, Can Yang 0002. [doi]
• Cost-Aware Contrastive Routing for LLMsReza Shirkavand, Shangqian Gao, Peiran Yu, Heng Huang 0001. [doi]
• Generative Trajectory Stitching through Diffusion CompositionYunhao Luo 0001, Utkarsh A. Mishra, Yilun Du, Danfei Xu. [doi]
• Model-Informed Flows for Bayesian InferenceJoohwan Ko, Justin Domke. [doi]
• A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant ModelsYuqing Xie 0006, Tess E. Smidt. [doi]
• A Minimalistic Unified Framework for Incremental Learning across Image Restoration TasksXiaoxuan Gong, Jie Ma. [doi]
• AliO: Output Alignment Matters in Long-Term Time Series ForecastingKwangryeol Park, Jaeho Kim, Seulki Lee 0002. [doi]
• Vision Function Layer in Multimodal LLMsCheng Shi, Yizhou Yu, Sibei Yang. [doi]
• Shape it Up! Restoring LLM Safety during FinetuningShengyun Peng, Pin-Yu Chen, Jianfeng Chi, Seongmin Lee 0007, Duen Horng Chau. [doi]
• Convergent Functions, Divergent FormsHyeonseong Jeon, Ainaz Eftekhar, Aaron Walsman, Kuo-Hao Zeng, Ali Farhadi, Ranjay Krishna. [doi]
• Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming ReformulationWen-Bo Du 0002, Tian Qin, Tian-Zuo Wang, Zhi-Hua Zhou. [doi]
• Valid Selection among Conformal SetsMahmoud Hegazy, Liviu Aolaritei, Michael I. Jordan, Aymeric Dieuleveut. [doi]
• Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss LandscapesJumin Han, Jun-Hui Kim, Seong-Whan Lee. [doi]
• Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connectedYingtao Zhang, Diego Cerretti, Jialin Zhao 0004, Wenjing Wu, Ziheng Liao, Umberto Michieli, Carlo Vittorio Cannistraci. [doi]
• Time Series Generation Under Data Scarcity: A Unified Generative Modeling ApproachTal Gonen, Itai Pemper, Ilan Naiman, Nimrod Berman, Omri Azencot. [doi]
• SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety FactsYueh-Han Chen, Guy Davidson, Brenden M. Lake. [doi]
• Rethinking PCA Through DualityJan Quan, Johan A. K. Suykens, Panagiotis Patrinos. [doi]
• CALM: Culturally Self-Aware Language ModelsLingzhi Shen, Xiaohao Cai, Yunfei Long, Imran Razzak, Guanming Chen, Shoaib Jameel. [doi]
• The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT ImprovementsBingchen Zhao, Despoina Magka, Minqi Jiang, Xian Li 0003, Roberta Raileanu, Tatiana Shavrina, Jean-Christophe Gagnon-Audet, Kelvin Niu, Shagun Sodhani, Michael Shvartsman, Andrei Lupu, Alisia Maria Lupidi, Karen Hambardzumyan, Martin Josifoski, Edan Toledo, Thomas Foster, Lucia Cipolina-Kun, Derek Dunfield, Abhishek Charnalia, Alexander H. Miller, Oisin Mac Aodha, Jakob Foerster, Yoram Bachrach. [doi]
• On the Stability and Generalization of Meta-Learning: the Impact of Inner-LevelsWenjun Ding, Jingling Liu, Lixing Chen, Xiu Su, Tao Sun, Fan Wu, Zhe Qu. [doi]
• Salient Concept-Aware Generative Data AugmentationTianchen Zhao, Xuanbai Chen, Zhihua Li, Jun Fang, Dongsheng An, Xiang Xu, Zhuowen Tu, Yifan Xing. [doi]
• Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and AlgorithmXuefeng Zhu 0003, Tianyang Xu 0001, Yifan Pan, Jinjie Gu, Xi Li 0001, Jiwen Lu, Xiaojun Wu 0001, Josef Kittler. [doi]
• Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)Zhenjie Yang 0001, Xiaosong Jia, Qifeng Li, Xue Yang 0005, Maoqing Yao, Junchi Yan. [doi]
• HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the WildValentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann, Leonidas J. Guibas. [doi]
• Fast MRI for All: Bridging Access Gaps by Training without Raw DataYasar Utku Alçalar, Merve Gülle, Mehmet Akçakaya. [doi]
• Enhanced Expert Merging for Mixture-of-Experts in Graph Foundation ModelsLei Liu 0072, Xingyu Xia, Qianqian Xie, Ben Liu 0002, Wenjie Xu, Min Peng 0002. [doi]
• Preference-Guided Diffusion for Multi-Objective Offline OptimizationYashas Annadani, Syrine Belakaria, Stefano Ermon, Stefan Bauer, Barbara Engelhardt. [doi]
• LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow TransformersYusuf Dalva, Hidir Yesiltepe, Pinar Yanardag. [doi]
• Boosting the Uniqueness of Neural Networks Fingerprints with Informative TriggersZhuomeng Zhang, Fangqi Li 0001, Hanyi Wang, Shi-Lin Wang. [doi]
• Predictable Scale (Part II) - Farseer: A Refined Scaling Law in LLMsHouyi Li, Wenzhen Zheng, Qiufeng Wang, Zhenyu Ding, Haoying Wang, Zili Wang, Shijie Xuyang, Ning Ding 0002, Shuigeng Zhou, Xiangyu Zhang 0005, Daxin Jiang. [doi]
• Learning (Approximately) Equivariant Networks via Constrained OptimizationAndrei Manolache, Luiz F. O. Chamon, Mathias Niepert. [doi]
• The Impact of Coreset Selection on Spurious Correlations and Group RobustnessAmaya Dharmasiri, William Yang, Polina Kirichenko, Lydia T. Liu, Olga Russakovsky. [doi]
• Solving Inverse Problems with FLAIRJulius Erbach, Dominik Narnhofer, Andreas Dombos, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler. [doi]
• Minimizing False-Positive Attributions in Explanations of Non-Linear ModelsAnders Gjølbye, Stefan Haufe, Lars Kai Hansen. [doi]
• Combinatorial Ski Rental Problem: Robust and Learning-Augmented AlgorithmsZiwei Li, Bo Sun, Zhiqiu Zhang, Mohammad Hajiesmaili, Binghan Wu, Lin F. Yang, Yang Gao. [doi]
• Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPsMehran Shakerinava, Siamak Ravanbakhsh, Adam M. Oberman. [doi]
• A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM ReasoningZhi Zhou 0007, Tan Yuhao, Zenan Li, Yuan Yao 0001, Lan-Zhe Guo, Yufeng Li 0008, Xiaoxing Ma. [doi]
• PAC-Bayes Bounds for Multivariate Linear Regression and Linear AutoencodersRuixin Guo, Ruoming Jin, Xinyu Li, Yang Zhou. [doi]
• How Far Are We from Optimal Reasoning Efficiency?Jiaxuan Gao, Shu Yan, Qixin Tan, Lu Yang, Shusheng Xu, Wei Fu, Zhiyu Mei, Kaifeng Lyu, Yi Wu 0013. [doi]
• Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLMXiaoyu Wu, Yifei Pang, Terrance Liu, Steven Z. Wu. [doi]
• Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering PhenomenonTongtong Liang, Dan Qiao 0002, Yu-Xiang Wang 0003, Rahul Parhi. [doi]
• Steering When Necessary: Flexible Steering Large Language Models with BacktrackingZifeng Cheng, Jinwei Gan, Zhiwei Jiang 0001, Cong Wang 0034, Yafeng Yin 0002, Xiang Luo, Yuchen Fu, Qing Gu 0001. [doi]
• Fast Local Search Algorithms for Clustering with Adaptive Sampling and Bandit StrategiesJunyu Huang, Zhen Zhang 0025, Beirong Cui, Jianxin Wang 0001, Qilong Feng. [doi]
• On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel OptimizationJincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari. [doi]
• Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in RecommendationYidong Wu, Siyuan Chen, Binrui Wu, Fan Li 0017, Jiechao Gao. [doi]
• Dataset Distillation for Pre-Trained Self-Supervised Vision ModelsGeorge Cazenavette, Antonio Torralba 0001, Vincent Sitzmann. [doi]
• Improving Energy Natural Gradient Descent through Woodbury, Momentum, and RandomizationAndrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager, Marius Zeinhofer. [doi]
• MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly DetectionShengtian Yang, Yue Feng, Yingshi Liu, Jingrou Zhang, Jie Qin 0004. [doi]
• Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic SegmentationSiyu Chen 0004, Ting Han 0001, Chengzheng Fu, Changshe Zhang, Chaolei Wang, Jinhe Su, Guorong Cai, Meiliu Wu. [doi]
• Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise DependenciesTianxing Man, Yu Bai, Ganyu Wang, Jinjie Fang, Haoran Fang, Bin Gu 0001, Yi Chang 0001. [doi]
• SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged SeniorsYang Chen 0034, Hui Wang 0075, Shiyao Wang, Junyang Chen, Jiabei He 0001, Jiaming Zhou 0001, Xi Yang 0023, Yequan Wang, Yonghua Lin, Yong Qin. [doi]
• Safety Pretraining: Toward the Next Generation of Safe AIPratyush Maini, Sachin Goyal, Dylan Sam, Alexander Robey, Yash Savani, Yiding Jiang, Andy Zou, Matt Fredrikson, Zachary C. Lipton, Zico Kolter. [doi]
• Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than HelpsHaibo Jin, Peiyan Zhang, Man Luo, Haohan Wang. [doi]
• Learning quadratic neural networks in high dimensions: SGD dynamics and scaling lawsGérard Ben Arous, Murat A. Erdogdu, Nuri Mert Vural, Denny Wu. [doi]
• JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation ModelQihao Duan, Bingding Huang, Zhenqiao Song, Irina Lehmann, Lei Gu, Roland Eils, Benjamin Wild. [doi]
• OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial OptimizationHao Yuan 0002, Wenli Ouyang, Changwen Zhang, Congrui Li, Yong Sun. [doi]
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning SegmentationJiaxin Huang, Runnan Chen, Ziwen Li, Zhengqing Gao, Xiao He, Yandong Guo, Mingming Gong, Tongliang Liu. [doi]
• RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step RetrosynthesisRobin Yadav, Qi Yan, Guy Wolf, Joey Bose, Renjie Liao 0001. [doi]
• Sekai: A Video Dataset towards World ExplorationZhen Li 0026, Chuanhao Li 0001, Xiaofeng Mao, Shaoheng Lin, Ming Li 0010, Shitian Zhao, Zhaopan Xu, Xinyue Li 0001, Yukang Feng, Jianwen Sun, Zizhen Li, Fanrui Zhang, Jiaxin Ai, Zhixiang Wang, Yuwei Wu 0001, Tong He 0001, Yunde Jia, Kaipeng Zhang. [doi]
• π-Realizable MDPsAntoine Moulin, Gergely Neu, Luca Viano. [doi]
• IBGS: Image-Based Gaussian SplattingHoang Chuong Nguyen, Wei Mao 0001, José M. Álvarez 0004, Miaomiao Liu 0001. [doi]
• Value Improved Actor Critic AlgorithmsYaniv Oren, Moritz A. Zanger, Pascal R. van der Vaart, Mustafa Mert Çelikok, Wendelin Boehmer, Matthijs T. J. Spaan. [doi]
• Δ Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD GeneralizationLin Zhu, Yifeng Yang, Xinbing Wang, Qinying Gu, Nanyang Ye 0001. [doi]
• NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMsHaeun Lee, Omin Kwon, Yeonhong Park, Jae W. Lee. [doi]
• Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal InferenceHarry Amad, Zhaozhi Qian, Dennis Frauen, Julianna Piskorz, Stefan Feuerriegel, Mihaela van der Schaar. [doi]
• On the Optimality of the Median-of-Means Estimator under Adversarial ContaminationXabier de Juan, Santiago Mazuelas. [doi]
• Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology OptimizationAmin Heyrani Nobari, Lyle Regenwetter, Cyril Picard, Ligong Han, Faez Ahmed. [doi]
• TopER: Topological Embeddings in Graph Representation LearningAstrit Tola, Funmilola Mary Taiwo, Cuneyt Gurcan Akcora, Baris Coskunuzer. [doi]
• MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based DynamicsChangmin Lee, Jihyun Lee, Tae-Kyun Kim 0001. [doi]
• DeltaFormer: Unlock the state space of TransformerMingyu Xu, Tenglong Ao, Jiaao He, Jianqiao Lu, Guang Shi, Mingwu Zheng. [doi]
• Hierarchical Shortest-Path Graph Kernel NetworkJiaxin Wang, Wenxuan Tu, Jieren Cheng. [doi]
• Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video GroundingZaiquan Yang, Yuhao Liu 0001, Gerhard P. Hancke 0002, Rynson W. H. Lau. [doi]
• Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMsInsu Lee, Wooje Park, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim. [doi]
• SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement LearningJiaqi Huang, Zunnan Xu, Jun Zhou, Ting Liu, Yicheng Xiao, Mingwen Ou, Bowen Ji, Xiu Li 0001, Kehong Yuan. [doi]
• Polyline Path Masked Attention for Vision TransformerZhongchen Zhao, Chaodong Xiao, Hui Lin, Qi Xie 0002, Lei Zhang 0006, Deyu Meng. [doi]
• Topology-Aware Conformal Prediction for Stream NetworksJifan Zhang, Fangxin Wang 0003, Zihe Song 0001, Philip S. Yu, Kaize Ding, Shixiang Zhu. [doi]
• Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized TrainingQinglun Li, Yingqi Liu, Miao Zhang 0037, Xiaochun Cao, Quanjun Yin, Li Shen 0008. [doi]
• Sampled Estimators For Softmax Must Be BiasedLi-Chung Lin, Yaxu Liu, Chih-Jen Lin. [doi]
• Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial ApproachChangyeol Lee, Yongho Shin, Hyung-Chan An. [doi]
• Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score DistillationEnshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai 0001, Zinan Lin 0001, Yu Wang 0002. [doi]
• INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction TuningWujian Peng, Lingchen Meng, Yitong Chen, Yiweng Xie, Yang Liu 0003, Tao Gui, Hang Xu 0004, Xipeng Qiu, Zuxuan Wu, Yu-Gang Jiang 0001. [doi]
• Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic SegmentationMehrdad Noori, David Osowiechi, Gustavo Adolfo Vargas Hakim, Ali Bahri, Moslem Yazdanpanah, Sahar Dastani, Farzad Beizaee, Ismail Ben Ayed, Christian Desrosiers. [doi]
• FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM TokensChao Wang 0086, Yixin Song, Jinhui Ye, Chuan Qin 0002, Dazhong Shen, Lingfeng Liu, Xiang Wang, Yanyong Zhang. [doi]
• Network two-sample test for block modelsChung Kyong Nguen, Arash A. Amini, Oscar Hernan Madrid Padilla. [doi]
• Ranking-based Preference Optimization for Diffusion Models from Implicit User FeedbackYi-Lun Wu, Bo-Kai Ruan, Chiang Tseng, Hong-Han Shuai. [doi]
• Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient DescentTong Yang 0007, Yu Huang, Yingbin Liang, Yuejie Chi. [doi]
• TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local CorrespondenceFeng Jiang 0012, Mangal Prakash, Hehuan Ma, Jianyuan Deng, Yuzhi Guo, Amina Mollaysa, Tommaso Mansi, Rui Liao, JunZhou Huang. [doi]
• Vocabulary-Guided Gait RecognitionPanjian Huang, Saihui Hou, Chunshui Cao, Xu Liu 0008, Yongzhen Huang. [doi]
• Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)Ruaridh Mon-Williams, Max Taylor-Davies, Elizabeth Mieczkowski, Natalia Vélez, Neil Bramley, Yanwei Wang, Tom Griffiths 0001, Christopher G. Lucas. [doi]
• Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and SegmentationJianyang Qin, Chaoyang Li, Jinhao Cui, Lingzhi Wang 0001, Zhao Liu, Qing Liao 0001. [doi]
• Scaling RL to Long VideosYukang Chen, Wei Huang 0042, Baifeng Shi, Qinghao Hu 0004, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov 0001, Jan Kautz, Xiaojuan Qi 0001, Sifei Liu, Hongxu Yin, Yao Lu 0006, Song Han 0003. [doi]
• SuperCLIP: CLIP with Simple Classification SupervisionWeiheng Zhao, Zilong Huang, Jiashi Feng, Xinggang Wang. [doi]
• OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed DomainWenzhen Yue, Yong Liu, Hao Wang 0179, Haoxuan Li 0001, Xianghua Ying, Ruohao Guo, Bowei Xing, Ji Shi 0003. [doi]
• Consistent Supervised-Unsupervised Alignment for Generalized Category DiscoveryJizhou Han, Shaokun Wang, Yuhang He 0001, Chenhao Ding, Qiang Wang, Xinyuan Gao, Songlin Dong, Yihong Gong. [doi]
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World KnowledgeWenyao Zhang, Hongsi Liu, Zekun Qi, Yunnan Wang, Xinqiang Yu, Jiazhao Zhang, Runpei Dong, Jiawei He 0002, He Wang 0010, Zhizheng Zhang 0011, Li Yi 0001, Wenjun Zeng 0001, Xin Jin 0014. [doi]
• Learning Relative Gene Expression Trends from Pathology Images in Spatial TranscriptomicsKazuya Nishimura, Haruka Hirose, Ryoma Bise, Kaito Shiku, Yasuhiro Kojima. [doi]
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement LearningSimin Li, Zihao Mao, Hanxiao Li, Zonglei Jing, Zhuohang Bian, Jun Guo 0009, Li Wang 0170, Zhuoran Han, Ruixiao Xu, Xin Yu 0009, Chengdong Ma, Yuqing Ma, Bo An 0001, Yaodong Yang 0001, Weifeng Lv, Xianglong Liu 0001. [doi]
• E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation ModelsJiaheng Dong, Hong Jia, Soumyajit Chatterjee, Abhirup Ghosh, James Bailey, Ting Dang. [doi]
• ReDi: Rectified Discrete FlowJaehoon Yoo, Wonjung Kim, Seunghoon Hong. [doi]
• Compress & Cache: Vision token compression for efficient generation and retrievalAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos. [doi]
• Benchmarking Large Language Models with Integer Sequence Generation TasksDaniel O'Malley, Manish Bhattarai, Nishath Rajiv Ranasinghe, Erick Draayer, Javier E. Santos. [doi]
• K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge DecouplingYongrui Chen 0002, Yi Huang 0017, Yunchang Liu, Shenyu Zhang 0002, Junhao He, Tongtong Wu, Guilin Qi, Tianxing Wu 0001. [doi]
• Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making TasksVishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian. [doi]
• Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language ModelsHao Cheng 0015, Erjia Xiao, Jing Shao, Yichi Wang 0002, Le Yang 0007, Chao Shen 0001, Philip H. S. Torr, Jindong Gu, Renjing Xu. [doi]
• Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model TrainingMinhak Song, Beomhan Baek, Kwangjun Ahn, Chulhee Yun. [doi]
• Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution DetectionIgnacio Meza De la Jara, Cristian Rodriguez Opazo, Damien Teney, Damith Ranasinghe, Ehsan Abbasnejad. [doi]
• FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit DesignAsal Mehradfar, Xuzhe Zhao, Yilun Huang 0006, Emir Ceyani, Yankai Yang, Shihao Han, Hamidreza Aghasi, Salman Avestimehr. [doi]
• NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic LightingAndrea Dunn Beltran, Daniel Rho, Marc Niethammer, Roni Sengupta. [doi]
• Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA ServingXinyu Wang 0062, Jonas M. Kübler, Kailash Budhathoki, Yida Wang 0003, Matthäus Kleindessner. [doi]
• Multimodal Tabular Reasoning with Privileged Structured InformationJun-Peng Jiang, Yu Xia, Hai-Long Sun, Shiyin Lu, Qingguo Chen, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye. [doi]
• scGeneScope: A Treatment-Matched Single Cell Imaging and Transcriptomics Dataset and Benchmark for Treatment Response ModelingJoel Dapello, Marcel Nassar, Ridvan Eksi, Ban Wang, Jules Gagnon-Marchand, Kenneth T. Gao, Akram Baharlouei, Kyra Thrush, Nina Riehs, Amy Peterson, Aniket A. Tolpadi, Abhejit Rajagopal, Henry Miller, Ashley Conard, David Alvarez-Melis, Rory Stark, Simone Bianco 0002, Morgan Levine, Ava Amini, Alex X. Lu, Nicolò Fusi, Ravi Pandya, Valentina Pedoia, Hana El-Samad. [doi]
• Informed Correctors for Discrete Diffusion ModelsYixiu Zhao, Jiaxin Shi, Feng Chen, Shaul Druckmann, Lester Mackey, Scott W. Linderman. [doi]
• The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index ModelsAlex Damian, Jason D. Lee, Joan Bruna. [doi]
• Adaptive Classifier-Free Guidance via Dynamic Low-Confidence MaskingPengxiang Li, Shilin Yan, Jiayin Cai, Renrui Zhang, Ruichuan An, Ziyu Guo, Xiaowei Gao. [doi]
• VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning ArchitectureMaonan Wang, Yirong Chen, Aoyu Pang, Yuxin Cai, Chung Shue Chen, Yuheng Kan, Man-On Pun. [doi]
• Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-ThoughtChao Huang 0008, Benfeng Wang, Wei Wang 0169, Jie Wen 0001, Chengliang Liu 0003, Li Shen 0008, Xiaochun Cao. [doi]
• Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement LearningGhada Sokar, Pablo Samuel Castro. [doi]
• Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuningQitao Tan, Jun Liu 0075, Zheng Zhan 0001, Caiwen Ding, Yanzhi Wang 0001, Xiaolong Ma, Jaewoo Lee, Jin Lu 0001, Geng Yuan. [doi]
• CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMsZhiyuan Ning, Jiawei Shao, Ruge Xu, Xinfei Guo, Jun Zhang, Chi Zhang, Xuelong Li 0001. [doi]
• SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy SupervisionYiyang Gu, Bohan Wu, Qinghua Ran, Rong-Cheng Tu, Xiao Luo 0001, Zhiping Xiao 0001, Wei Ju 0001, Dacheng Tao, Ming Zhang 0004. [doi]
• What do you know? Bayesian knowledge inference for navigating agentsMatthias Schultheis, Jana-Sophie Schönfeld, Constantin A. Rothkopf, Heinz Koeppl. [doi]
• Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree SearchYanbo Wang 0005, Zixiang Xu, Yue Huang 0001, Chujie Gao, Siyuan Wu 0001, Jiayi Ye, Pin-Yu Chen, Xiuying Chen, Xiangliang Zhang 0001. [doi]
• Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoEZhaokun Wang, Jinyu Guo, Jingwen Pu, Lingfeng Chen, Hongli Pu, Jie Ou, Libo Qin 0001, Wenhong Tian. [doi]
• U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise MatchingJunsheng Zhou, Xingyu Shi, Haichuan Song, Yi Fang 0006, Yu-Shen Liu, Zhizhong Han. [doi]
• A Beyond-Worst-Case Analysis of Greedy k-means++Qingyun Chen, Sungjin Im, Benjamin Moseley, Ryan Milstrey, Chenyang Xu 0002, Ruilong Zhang 0001. [doi]
• Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective RolloutsHaizhong Zheng, Yang Zhou, Brian R. Bartoldson, Bhavya Kailkhura, Fan Lai 0001, Jiawei Zhao, Beidi Chen. [doi]
• SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse AutoencodersZhuohao Yu 0001, Xingru Jiang, Weizheng Gu, Yidong Wang 0003, Qingsong Wen, Shikun Zhang, Wei Ye 0004. [doi]
• Towards Identifiability of Hierarchical Temporal Causal Representation LearningZijian Li 0001, Minghao Fu 0002, Junxian Huang 0002, Yifan Shen 0004, Ruichu Cai, Yuewen Sun, Guangyi Chen 0002, Kun Zhang 0001. [doi]
• End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWsXuelin Shen, Haifeng Jiao, Yitong Wang, Yulin He, Wenhan Yang. [doi]
• Safety Depth in Large Language Models: A Markov Chain PerspectiveChing-Chia Kao, Chia-Mu Yu, Chun-Shien Lu, Chu-Song Chen. [doi]
• GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified FlowMengbo Wang 0001, Shourya Verma, Aditya Malusare, Luopin Wang, Yiyang Lu, Vaneet Aggarwal, Mario Sola, Ananth Grama, Nadia Atallah Lanman. [doi]
• Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive StepsizesZaiwei Chen. [doi]
• BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion ModelWeilin Lin, Nanjun Zhou, Yanyun Wang 0003, Jianze Li, Hui Xiong, Li Liu 0036. [doi]
• Meta CLIP 2: A Worldwide Scaling RecipeYung-Sung Chuang, Yang Li, Dong Wang, Ching-feng Yeh, Kehan Lyu, Ramya Raghavendra, Jim Glass 0001, Lifei Huang, Jason E. Weston, Luke Zettlemoyer, Xinlei Chen, Zhuang Liu 0003, Saining Xie, Scott Yih, Shang-wen Li 0001, Hu Xu 0001. [doi]
• Optimizing Retrieval for RAG via Reinforcement LearningJiawei Zhou, Lei Chen. [doi]
• Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language ModelsHongqiong Zhong, Qingyang Teng, Baolin Zheng, Guanlin Chen, Yingshui Tan, Zhendong Liu, Jiaheng Liu, Wenbo Su, Xiaoyong Zhu, Bo Zheng 0007, Kaifu Zhang. [doi]
• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout ReplayYifan Sun 0010, Jingyan Shen, Yibin Wang 0005, Tianyu Chen, Zhendong Wang 0005, Mingyuan Zhou, Huan Zhang 0001. [doi]
• Identifiability of Deep Polynomial Neural NetworksKonstantin Usevich, Ricardo Augusto Borsoi, Clara Dérand, Marianne Clausel. [doi]
• HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous DrivingZhiwen Chen, Hanming Deng, Zhuoren Li, Huanxi Wen, Guizhe Jin, Ran Yu, Bo Leng. [doi]
• TokMan: Tokenize Manhattan Mask Optimization for Inverse LithographyYiwen Wu, Yuyang Chen, Ye Xia, Yao Zhao, Jingya Wang 0001, Xuming He 0001, Hao Geng, Jingyi Yu 0001. [doi]
• Rethinking Losses for Diffusion Bridge SamplersSebastian Sanokowski, Lukas Gruber, Christoph Bartmann, Sepp Hochreiter, Sebastian Lehner. [doi]
• Accelerating Diffusion LLMs via Adaptive Parallel DecodingDaniel Israel, Guy Van den Broeck, Aditya Grover. [doi]
• FEAT: Free energy Estimators with Adaptive TransportYuanqi Du, Jiajun He 0003, Francisco Vargas 0001, Yuanqing Wang, Carla P. Gomes, José Miguel Hernández-Lobato, Eric Vanden-Eijnden. [doi]
• GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse ProjectionPingbang Hu, Joseph Melkonian, Weijing Tang, Han Zhao 0002, Jiaqi Ma 0001. [doi]
• Compress Large Language Models via Collaboration Between Learning and Matrix ApproximationYuesen Liao, Zhiwei Li, Binrui Wu, Zihao Cheng, Su Zhao, Shuai Chen, Weizhong Zhang. [doi]
• Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI AutomationYuyang Wanyan, Xi Zhang, Haiyang Xu 0001, Haowei Liu, Junyang Wang 0001, Jiabo Ye, Yutong Kou, Ming Yan 0008, Fei Huang 0002, Xiaoshan Yang, Weiming Dong, Changsheng Xu. [doi]
• FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech ProcessingShoutao Guo, Shaolei Zhang 0001, Qingkai Fang, Zhengrui Ma, Min Zhang 0005, Yang Feng 0004. [doi]
• VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM AgentsKangrui Wang, Pingyue Zhang, Zihan Wang 0008, Yaning Gao, Linjie Li, Qineng Wang, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu 0001, Fei-Fei Li 0001, Yejin Choi 0001, Manling Li. [doi]
• SpEx: A Spectral Approach to Explainable ClusteringTal Argov, Tal Wagner. [doi]
• EnCompass: Enhancing Agent Programming with Search Over Program Execution PathsZhening Li, Armando Solar-Lezama, Yisong Yue, Stephan Zheng. [doi]
• MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source ExtractionYunkee Chae, Kyogu Lee. [doi]
• Mixture of Inputs: Text Generation Beyond Discrete Token SamplingYufan Zhuang, Liyuan Liu, Chandan Singh, Jingbo Shang, Jianfeng Gao 0001. [doi]
• Scaling Off-Policy Reinforcement Learning with Batch and Weight NormalizationDaniel Palenicek, Florian Vogt, Joe Watson, Jan Peters 0001. [doi]
• Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLPShohei Ohsawa. [doi]
• URB - Urban Routing Benchmark for RL-equipped Connected Autonomous VehiclesAhmet Onur Akman, Anastasia Psarou, Michal Hoffmann, Lukasz Gorczyca, Lukasz Kowalski, Pawel Góra, Grzegorz Jamróz, Rafal Kucharski. [doi]
• InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer InteractionBin Lei, Weitai Kang, Zijian Zhang, Winson Chen, Xi Xie, Shan Zuo, Mimi Xie, Ali Payani, Mingyi Hong 0001, Yan Yan, Caiwen Ding. [doi]
• SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous DrivingHaiming Zhang 0001, Yiyao Zhu, Wending Zhou, Xu Yan 0005, Yingjie Cai, Bingbing Liu, Shuguang Cui, Zhen Li 0026. [doi]
• What Do Latent Action Models Actually Learn?Chuheng Zhang, Tim Pearce, Pushi Zhang, Kaixin Wang, Xiaoyu Chen, Wei Shen 0005, Li Zhao 0007, Jiang Bian 0002. [doi]
• InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic ChartsTianchi Xie, Minzhi Lin, Mengchen Liu, Yilin Ye, Changjian Chen, Shixia Liu. [doi]
• Robust Contextual PricingAnupam Gupta 0001, Guru Guruganesh, Renato Paes Leme, Jon Schneider. [doi]
• GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMsAdvik Raj Basani, Xiao Zhang. [doi]
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven GenerationAbdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem, Peter Wonka. [doi]
• Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural NetworksAnn Huang, Satpreet Harcharan Singh, Flavio Martinelli, Kanaka Rajan. [doi]
• The Boundaries of Fair AI in Medical Image Prognosis: A Causal PerspectiveThai-Hoang Pham, Jiayuan Chen 0003, Seungyeon Lee 0002, Yuanlong Wang, Sayoko Moroi, Xueru Zhang, Ping Zhang 0016. [doi]
• OS-Harm: A Benchmark for Measuring Safety of Computer Use AgentsThomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko. [doi]
• GraphTOP: Graph Topology-Oriented Prompting for Graph Neural NetworksXingbo Fu, Zhenyu Lei 0004, Zihan Chen 0002, Binchi Zhang, Chuxu Zhang, Jundong Li. [doi]
• RelationAdapter: Learning and Transferring Visual Relation with Diffusion TransformersYan Gong, Yiren Song, Yicheng Li 0005, Chenglin Li, Yin Zhang 0006. [doi]
• Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive DecodingDaiqing Qi, Dongliang Guo 0002, Hanzhang Yuan, Handong Zhao, Mengxuan Hu, Lehan Yang, Sheng Li 0001. [doi]
• Learning-Augmented Streaming Algorithms for Correlation ClusteringYinhao Dong, Shan Jiang, Shi Li, Pan Peng 0001. [doi]
• Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schrödinger Bridge EstimationIbuki Maeda, Rentian Yao, Atsushi Nitanda. [doi]
• Universal Video Temporal Grounding with Generative Multi-modal Large Language ModelsZeqian Li, Shangzhe Di, Zhonghua Zhai, Weilin Huang, Yanfeng Wang, Weidi Xie. [doi]
• QiMeng-CodeV-R1: Reasoning-Enhanced Verilog GenerationYaoyu Zhu, Di Huang, Han-Qi Lyu, Xiaoyun Zhang, Chongxiao Li, Wenxuan Shi, Yutong Wu, Jianan Mu, Jinghua Wang, Yang Zhao 0013, Pengwei Jin, Shuyao Cheng, Shengwen Liang, Xishan Zhang, Rui Zhang 0040, Zidong Du, Qi Guo 0001, Xing Hu 0001, Yunji Chen. [doi]
• CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric RewardYandong Guan, Xilin Wang, XiMing Xing, Jing Zhang 0017, Dong Xu 0001, Qian Yu 0002. [doi]
• Semi-Supervised Regression with Heteroscedastic Pseudo-LabelsXueqing Sun, Renzhen Wang, Quanziang Wang, Yichen Wu, Xixi Jia, Deyu Meng. [doi]
• MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure ElucidationYang Han, Pengyu Wang, Kai Yu 0004, Xin Chen, Lu Chen 0002. [doi]
• FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated LearningYunbo Li, Jiaping Gui, Zhihang Deng, Fanchao Meng, Yue Wu 0010. [doi]
• Shaping Sequence Attractor Schema in Recurrent Neural NetworksZhikun Chu, Bo Ho, Xiaolong Zou, Yuanyuan Mi. [doi]
• Panoptic Captioning: An Equivalence Bridge for Image and TextKun-Yu Lin, Hongjun Wang, Weining Ren, Kai Han 0001. [doi]
• Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-ConcordanceQiujiang Jin, Aryan Mokhtari. [doi]
• Quantum Speedups for Minimax Optimization and BeyondChengchang Liu, Zongqi Wan, Jialin Zhang 0001, Xiaoming Sun 0001, John C. S. Lui. [doi]
• Algorithm- and Data-Dependent Generalization Bounds for Diffusion ModelsBenjamin Dupuis, Dario Shariatian, Maxime Haddouche, Alain Durmus, Umut Simsekli. [doi]
• Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and EfficiencyKelvin Kan, Xingjian Li 0005, Benjamin J. Zhang, Tuhin Sahai, Stanley J. Osher, Markos A. Katsoulakis. [doi]
• MR. Video: MapReduce as an Effective Principle for Long Video UnderstandingZiqi Pang, Yu-Xiong Wang. [doi]
• How to Train Your LLM Web Agent: A Statistical DiagnosisDheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Thibault Le Sellier De Chezelles, Megh Thakkar, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Steve (Xue) Liu, Alexandre Drouin, Alexandre Piché, Alexandre Lacoste, Massimo Caccia. [doi]
• Weak-shot Keypoint Estimation via Keyness and Correspondence TransferJunjie Chen 0008, Zeyu Luo, Zezheng Liu, Wenhui Jiang 0001, Li Niu 0002, Yuming Fang 0001. [doi]
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable RefinementYidi Liu, Xueyang Fu, Jie Huang 0017, Jie Xiao 0002, Dong Li 0055, Wenlong Zhang, Lei Bai 0001, Zheng-Jun Zha. [doi]
• SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning ModelsEmil Biju, Shayan Talaei, Zhemin Huang 0001, Mohammadreza Pourreza, Azalia Mirhoseini, Amin Saberi. [doi]
• Stable Gradients for Stable Learning at Scale in Deep Reinforcement LearningRoger Creus Castanyer, Johan S. Obando-Ceron, Lu Li, Pierre-Luc Bacon, Glen Berseth, Aaron C. Courville, Pablo Samuel Castro. [doi]
• Temporal Chain of Thought: Long-Video Understanding by Thinking in FramesAnurag Arnab, Ahmet Iscen, Mathilde Caron, Alireza Fathi, Cordelia Schmid. [doi]
• Entropy Rectifying Guidance for Diffusion and Flow ModelsTariq Berrada, Adriana Romero-Soriano, Michal Drozdzal, Jakob J. Verbeek, Karteek Alahari. [doi]
• PurpCode: Reasoning for Safer Code GenerationJiawei Liu 0004, Nirav Diwan, Zhe Wang, Haoyu Zhai, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Muntasir Wahed, Yinlin Deng, Hadjer Benkraouda, Yuxiang Wei 0003, Lingming Zhang 0001, Ismini Lourentzou, Gang Wang. [doi]
• Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D ScenesJiaxin Huang, Ziwen Li, Hanlue Zhang, Runnan Chen, Zhengqing Gao, Xiao He, Yandong Guo, Wenping Wang 0001, Tongliang Liu, Mingming Gong. [doi]
• Learning to Generate Human-Human-Object Interactions from Textual DescriptionsJeonghyeon Na, Sangwon Baik, Inhee Lee 0003, Junyoung Lee, Hanbyul Joo. [doi]
• Graph Diffusion that can Insert and DeleteMatteo Ninniri, Marco Podda, Davide Bacciu. [doi]
• Precise Diffusion Inversion: Towards Novel Samples and Few-Step ModelsJing Zuo, Luoping Cui, Chuang Zhu, Yonggang Qi. [doi]
• Higher-Order Learning with Graph Neural Networks via Hypergraph EncodingsRaphaël Pellegrin, Lukas Fesser, Melanie Weber 0001. [doi]
• Relieving the Over-Aggregating Effect in Graph TransformersJunshu Sun, Wanxing Chang, Chenxue Yang, Qingming Huang, Shuhui Wang. [doi]
• Absence Bench: Language Models Can't See What's MissingHarvey Yiyun Fu, Aryan Shrivastava, Jared Moore, Peter West, Chenhao Tan, Ari Holtzman. [doi]
• Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust ConstraintsHyungki Im, Wyame Benslimane, Paul Grigas. [doi]
• Geometric Mixture Models for Electrolyte Conductivity PredictionAnyi Li, Jiacheng Cen, Songyou Li, Mingze Li, Yang Yu, Wenbing Huang 0001. [doi]
• Adaptive LoRA Experts Allocation and Selection for Federated Fine-TuningLei Wang 0199, Jieming Bian, Letian Zhang, Jie Xu 0001. [doi]
• Cross-Modal Representational Knowledge Distillation for Enhanced Spike-informed LFP ModelingEray Erturk, Saba Hashemi, Maryam M. Shanechi. [doi]
• PoseCrafter: Extreme Pose Estimation with Hybrid Video SynthesisQing Mao, Tianxin Huang, Yu Zhu 0004, Jinqiu Sun, Yanning Zhang 0001, Gim Hee Lee. [doi]
• NeuralSurv: Deep Survival Analysis with Bayesian Uncertainty QuantificationMélodie Monod, Alessandro Micheli, Samir Bhatt. [doi]
• Feature-aware Modulation for Learning from Temporal Tabular DataHaorun Cai, Han-Jia Ye. [doi]
• Learn2Mix: Training Neural Networks Using Adaptive Data IntegrationShyam Venkatasubramanian, Vahid Tarokh. [doi]
• Seeing the Arrow of Time in Large Multimodal ModelsZihui Xue, Romy Luo, Kristen Grauman. [doi]
• Revealing Multimodal Causality with Large Language ModelsJin Li 0002, Shoujin Wang, Qi Zhang 0020, Feng Liu 0003, Tongliang Liu, Longbing Cao, Shui Yu 0001, Fang Chen 0001. [doi]
• Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-TransportJiawei Huang 0009, Minming Li, Hu Ding 0003. [doi]
• Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is AttainableBicheng Ying, Zhe Li 0083, Haibo Yang 0001. [doi]
• EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character AnimationHaotian Ling, Zequn Chen, Qiuying Chen, Donglin Di, Yongjia Ma, Hao Li 0030, Chen Wei, Zhulin Tao, Xun Yang 0001. [doi]
• Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without SmoothingKangkang Deng, Jiachen Jin, Jiang Hu, Hongxia Wang. [doi]
• Faster Video Diffusion with Trainable Sparse AttentionPeiyuan Zhang, Yongqi Chen, Haofeng Huang, Will Lin, Zhengzhong Liu 0001, Ion Stoica, Eric P. Xing, Hao Zhang 0025. [doi]
• Distillation Robustifies UnlearningBruce W. Lee, Addie Foote, Alex Infanger, Leni Shor, Harish Kamath, Jacob Goldman-Wetzler, Bryce Woodworth, Alex Cloud, Alexander Matt Turner. [doi]
• Irrational Complex Rotations Empower Low-bit OptimizersZhen Tian 0001, Xin Zhao 0018, Ji-Rong Wen. [doi]
• Theoretical Benefit and Limitation of Diffusion Language ModelGuhao Feng, Yihan Geng, Jian Guan 0002, Wei Wu 0014, Liwei Wang 0001, Di He 0001. [doi]
• Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian ManifoldsEmre Sahinoglu, Youbang Sun, Shahin Shahrampour. [doi]
• FlexOLMo: Open Language Models for Flexible Data UseWeijia Shi, Akshita Bhagia, Kevin Farhat, Niklas Muennighoff, Jacob Morrison, Evan Pete Walsh, Dustin Schwenk, Shayne Longpre, Jake Poznanski, Allyson Ettinger, Daogao Liu, Margaret Li, Mike Lewis, Scott Yih, Dirk Groeneveld, Luca Soldaini, Kyle Lo, Noah A. Smith, Luke Zettlemoyer, Pang Wei W. Koh, Hanna Hajishirzi, Ali Farhadi, Sewon Min. [doi]
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMsYuxiang Zhang, Zhengxu Yu, Weihang Pan, Zhongming Jin 0001, Qiang Fu, Deng Cai 0001, Binbin Lin, Jieping Ye. [doi]
• Boundary-to-Region Supervision for Offline Safe Reinforcement LearningHuikang Su, Dengyun Peng, Zifeng Zhuang, Yuhan Liu, Qiguang Chen, Donglin Wang, Qinghe Liu. [doi]
• Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP TasksWentao Deng, Jiahuan Pei, Zhiwei Xu 0005, Zhaochun Ren, Zhumin Chen, Pengjie Ren. [doi]
• QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm DesignRui Yang, Ziruo Wang, Yuntian Gu, Yitao Liang, Tongyang Li. [doi]
• Diffusion-Driven Progressive Target Manipulation for Source-Free Domain AdaptationYuyang Huang, Yabo Chen, Junyu Zhou 0001, Wenrui Dai, Xiaopeng Zhang 0008, Junni Zou, Hongkai Xiong, Qi Tian 0001. [doi]
• Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior ModelingTianyi Tan, Yinan Zheng, Ruiming Liang, Zexu Wang, Kexin Zheng, Jinliang Zheng, Jianxiong Li, Xianyuan Zhan, Jingjing Liu. [doi]
• Human-assisted Robotic Policy Refinement via Action Preference OptimizationWenke Xia, Yichu Yang, Hongtao Wu, Xiao Ma, Tao Kong, Di Hu. [doi]
• HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic SceneJianing Chen 0007, Zehao Li, Yujun Cai, Hao Jiang 0013, Chengxuan Qian, Juyuan Kang, Shuqin Gao, Honglong Zhao, Tianlu Mao, Yucheng Zhang. [doi]
• 2)Bowei Zhu, Shaojie Li, Mingyang Yi, Yong Liu 0018. [doi]
• On Optimal Steering to Achieve Exact FairnessMohit Sharma 0004, Amit Deshpande 0001, Chiranjib Bhattacharyya, Rajiv Ratn Shah. [doi]
• Benign Overfitting in Single-Head AttentionRoey Magen, Shuning Shang, Zhiwei Xu, Spencer Frei, Wei Hu, Gal Vardi. [doi]
• Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a RestorerXuelin Shen, Quan Liu, Jiayin Xu, Wenhan Yang. [doi]
• Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GANWei Huang 0040, Hanchen Wang 0001, Dong Wen 0001, Shaozhen Ma, Wenjie Zhang 0001, Xuemin Lin 0001. [doi]
• COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent SpacePengyi Li 0001, Hongyao Tang, Yifu Yuan, Jianye Hao, Zibin Dong, Yan Zheng 0002. [doi]
• Adversary Aware Optimization for Robust DefenseDaniel Wesego, Pedram Rooshenas. [doi]
• Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality GenerationDogyun Park, Taehoon Lee 0004, Minseok Joo, Hyunwoo J. Kim. [doi]
• Transformers for Mixed-type Event SequencesFelix Draxler, Yang Meng, Kai Nelson, Lukas Laskowski, Yibo Yang, Theofanis Karaletsos, Stephan Mandt. [doi]
• Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes ModelingZhihao Li, Yufei Wang 0006, Heliang Zheng, Yihao Luo, Bihan Wen. [doi]
• Probing Hidden Knowledge Holes in Unlearned LLMsMyeongseob Ko, Hoang Anh Just, Charles Fleming, Ming Jin 0002, Ruoxi Jia 0001. [doi]
• Learning-Augmented Algorithms for $k$-median via Online LearningAnish Hebbar, Rong Ge 0001, Amit Kumar 0001, Debmalya Panigrahi. [doi]
• You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural NetworkYi Li, Zhichun Guo, Guanpeng Li, Bingzhe Li. [doi]
• Learning Robust Spectral Dynamics for Temporal Domain GeneralizationEn Yu, Jie Lu 0001, Xiaoyu Yang, Guangquan Zhang 0001, Zhen Fang 0001. [doi]
• Neighborhood Self-Dissimilarity Attention for Medical Image SegmentationJunren Chen, Rui Chen, Wei Wang 0278, Junlong Cheng, Gang Liang, Lei Zhang 0103, Liangyin Chen. [doi]
• Masked Gated Linear UnitYukito Tajima, Nakamasa Inoue, Yusuke Sekikawa, Ikuro Sato, Rio Yokota. [doi]
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language ModelsHaichao Zhang 0002, Yun Fu 0001. [doi]
• Learning to Integrate Diffusion ODEs by Averaging the DerivativesWenze Liu, Xiangyu Yue 0001. [doi]
• Learning from Interval TargetsRattana Pukdee, Ziqi Ke, Chirag Gupta. [doi]
• Adversarial Locomotion and Motion Imitation for Humanoid Policy LearningJiyuan Shi, Xinzhe Liu, Dewei Wang, Ouyang Lu, Sören Schwertfeger, Chi Zhang 0012, Fuchun Sun, Chenjia Bai, Xuelong Li 0001. [doi]
• Memory by accident: a theory of learning as a byproduct of network stabilizationBasile Confavreux, William Dorrell, Nishil Patel, Andrew M. Saxe. [doi]
• Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive AlignmentXiao-fei, Michail Chatzianastasis, Sarah Almeida Carneiro, Hadi Abdine, Lawrence P. Petalidis, Michalis Vazirgiannis. [doi]
• LabelAny3D: Label Any Object 3D in the WildJin Yao, Radowan Mahmud Redoy, Sebastian G. Elbaum, Matthew Dwyer 0001, Zezhou Cheng. [doi]
• Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal boundsVahan Arsenyan, Elen Vardanyan, Arnak S. Dalalyan. [doi]
• You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep ClusteringHanyang Li, Yuheng Jia, Hui Liu 0032, Junhui Hou. [doi]
• Optimal Graph Clustering without Edge Density SignalsMaximilien Dreveton, Elaine Siyu Liu, Matthias Grossglauser, Patrick Thiran. [doi]
• NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human PosesJing Wen, Alex Schwing 0001, Shenlong Wang. [doi]
• GTPBD: A Fine-Grained Global Terraced Parcel and Boundary DatasetZhiwei Zhang, Zi Ye, Yibin Wen, Shuai Yuan 0005, Haohuan Fu, Jianxi Huang, Juepeng Zheng. [doi]
• StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model TrainingZiming Liu, Shaoyu Wang, Shenggan Cheng, Zhongkai Zhao, Kai Wang 0036, Xuanlei Zhao, James Demmel, Yang You 0001. [doi]
• Scaling Laws For Scalable OversightJoshua Engels, David D. Baek, Subhash Kantamneni, Max Tegmark. [doi]
• UltraVideo: High-Quality UHD Video Dataset with Comprehensive CaptionsZhucun Xue, Jiangning Zhang, Teng Hu, Haoyang He, Yinan Chen, Yuxuan Cai, Yabiao Wang, Chengjie Wang 0001, Yong Li 0008, Xiangtai Li, Dacheng Tao. [doi]
• Towards foundational LiDAR world models with efficient latent flow matchingTianran Liu, Shengwen Zhao, Nicholas Rhinehart. [doi]
• RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid ArthritisSongxiao Yang, Haolin Wang 0007, Yao Fu, Ye Tian, Tamotsu Kamishima, Masayuki Ikebe, Yafei Ou, Masatoshi Okutomi. [doi]
• Mechanistic Interpretability of RNNs emulating Hidden Markov ModelsElia Torre, Michele Viscione, Lucas Pompe, Benjamin F. Grewe, Valerio Mante. [doi]
• RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster EventsZhenyuan Chen, Chenxi Wang, Ningyu Zhang 0001, Feng Zhang. [doi]
• Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language GameRong Ye, Yongxin Zhang, Yikai Zhang, Haoyu Kuang, Peng Sun, Zhongyu Wei. [doi]
• On the Loss of Context Awareness in General Instruction Fine-tuningYihan Wang, Andrew Bai, Nanyun Peng 0001, Cho-Jui Hsieh. [doi]
• RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon TasksMingxuan Yan, Yuping Wang, Zechun Liu, Jiachen Li. [doi]
• Analog Foundation ModelsJulian Büchel, Iason Chalas, Giovanni Acampa, An Chen 0002, Omobayode Fagbohungbe, Hsinyu Tsai, Kaoutar El Maghraoui, Manuel Le Gallo, Abbas Rahimi, Abu Sebastian. [doi]
• Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI SystemsGordon Dai, Yunze Xiao. [doi]
• Discovering Opinion Intervals from Conflicts in Signed GraphsPeter Blohm, Florian Chen, Aristides Gionis, Stefan Neumann 0003. [doi]
• FACE: Faithful Automatic Concept ExtractionDipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi. [doi]
• UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept TokensRuichuan An, Sihan Yang, Renrui Zhang, Zijun Shen, Ming Lu 0002, Gaole Dai, Hao Liang 0017, Ziyu Guo, Shilin Yan, Yulin Luo, Bocheng Zou, Chaoqun Yang, Wentao Zhang 0001. [doi]
• MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task AdaptationShen Yuan, Yin Zheng, Taifeng Wang, Binbin Liu, Hongteng Xu. [doi]
• Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language ModelingWentao Lu, Dong Nie, Pengcheng Xue, Zheng Cui, Piji Li, Daoqiang Zhang, Xuyun Wen. [doi]
• RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time VideoShuhang Xun, Sicheng Tao, Jungang Li, Yibo Shi, Zhixin Lin, Zhanhui Zhu, Yibo Yan, Hanqian Li, Linghao Zhang, Shikang Wang, Yixin Liu, Hanbo Zhang, Ying Ma, Xuming Hu. [doi]
• Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly DetectionJinyu Cai, Yuan Xie, Glynnis Lim, Yifang Yin, Roger Zimmermann, See-Kiong Ng. [doi]
• A Dynamic Learning Strategy for Dempster-Shafer Theory with Applications in Classification and EnhancementLinlin Fan, Xingyu Liu, Mingliang Zhou 0001, Xuekai Wei, Weizhi Xian, Jielu Yan, Weijia Jia 0001. [doi]
• Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature EfficiencyNaoki Nishikawa, Rei Higuchi, Taiji Suzuki. [doi]
• AI Testing Should Account for Sophisticated Strategic BehaviourVojta Kovarik, Eric Olav Chen, Sami Petersen, Alexis Ghersengorin, Vincent Conitzer. [doi]
• FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous TokensYiming Zhong 0001, Yumeng Liu, Chuyang Xiao, Zemin Yang, Youzhuo Wang, Yufei Zhu, Ye Shi 0001, Yujing Sun 0001, Xinge Zhu, Yuexin Ma. [doi]
• GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular UtilityMatthew Fahrbach, Srikumar Ramalingam, Morteza Zadimoghaddam, Sara Ahmadian, Gui Citovsky, Giulia DeSalvo. [doi]
• Recurrent Memory for Online Interdomain Gaussian ProcessesWenlong Chen, Naoki Kiyohara, Harrison Zhu, Jacob Curran-Sebastian, Samir Bhatt, Yingzhen Li. [doi]
• KORGym: A Dynamic Game Platform for LLM Reasoning EvaluationJiajun Shi, Jian Yang 0037, Jiaheng Liu, Xingyuan Bu, Jiangjie Chen, Junting Zhou, Kaijing Ma, Zhoufutu Wen, Bingli Wang, Yancheng He, Liang Song, Hualei Zhu, Shilong Li, Xingjian Wang, Wei Zhang 0021, Ruibin Yuan, Yifan Yao, Wenjun Yang, Yunli Wang, Siyuan Fang, Siyu Yuan, Qianyu He, Robert Tang, Yingshui Tan, Wangchunshu Zhou, Zhao-Xiang Zhang 0001, Zhoujun Li 0001, Wenhao Huang 0001, Ge Zhang 0009. [doi]
• High Resolution UDF Meshing via Iterative NetworksFederico Stella, Nicolas Talabot, Hieu Le 0001, Pascal Fua. [doi]
• Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle SetsRunhan Shi, Letian Chen, Gufeng Yu, Yang Yang. [doi]
• Differentially Private Federated Low Rank Adaptation Beyond Fixed-MatrixMing Wen, Jiaqi Zhu, Yuedong Xu 0001, Yipeng Zhou, Dingding Han. [doi]
• Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language ModelsZhentao He, Can Zhang, Ziheng Wu, Zhenghao Chen, Yufei Zhan, Yifan Li 0009, Zhao Zhang, Xian Wang, Minghui Qiu. [doi]
• LinEAS: End-to-end Learning of Activation Steering with a Distributional LossPau Rodríguez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau. [doi]
• GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K ResolutionFengxiang Wang 0004, Mingshuo Chen, Yueying Li, Di Wang 0023, Haotian Wang 0001, Zonghao Guo, Zefan Wang, Boqi Shan, Long Lan, Yulin Wang 0002, Hongzhen Wang, Wenjing Yang 0002, Bo Du 0001, Jing Zhang 0037. [doi]
• One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMsPengbo Wang, Chaozhuo Li, Chenxu Wang 0001, Liwen Zheng, Litian Zhang, Xi Zhang 0008. [doi]
• Linear Mixture Distributionally Robust Markov Decision ProcessesZhishuai Liu, Pan Xu 0002. [doi]
• FlashBias: Fast Computation of Attention with BiasHaixu Wu, Minghao Guo, Yuezhou Ma, Yuanxu Sun, Jianmin Wang 0001, Wojciech Matusik, Mingsheng Long. [doi]
• Instant4D: 4D Gaussian Splatting in MinutesZhanpeng Luo, Haoxi Ran, Li Lu. [doi]
• Fix False Transparency by Noise Guided SplattingAly El Hakie, Yiren Lu, Yu Yin, Michael Jenkins, Yehe Liu. [doi]
• Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer LearningYuyang Deng, Samory Kpotufe. [doi]
• Decoupled Entropy MinimizationJing Ma, Hanlin Li, Xiang Xiang 0001. [doi]
• HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMsNingning Chen, Weicai Ye, Ying Jiang 0002. [doi]
• Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement LearningKaihang Pan, Yang Wu, Wendong Bu, Kai Shen, Juncheng Li 0006, Yingting Wang, Yunfei Li, Siliang Tang, Jun Xiao 0001, Fei Wu 0001, Hang Zhao, Yueting Zhuang. [doi]
• Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization PerspectiveSifan Wang, Ananyae Kumar Bhartari, Bowen Li, Paris Perdikaris. [doi]
• Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence InstructionYifei Wang, Weimin Bai, Colin Zhang, Debing Zhang, Weijian Luo, He Sun 0010. [doi]
• An Analysis of Causal Effect Estimation using Outcome Invariant Data AugmentationUzair Akbar, Niki Kilbertus, Hao Shen, Krikamol Muandet, Bo Dai 0001. [doi]
• Deep Video Discovery: Agentic Search with Tool Use for Long-form Video UnderstandingXiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li 0001, Bin Li 0012, Houqiang Li, Yan Lu 0001. [doi]
• Simple Distillation for One-Step Diffusion ModelsHuaisheng Zhu, Teng Xiao, Shijie Zhou 0008, Zhimeng Guo, Hangfan Zhang, Siyuan Xu, Vasant G. Honavar. [doi]
• Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variablesYu Gui, Cong Ma 0001, Zongming Ma. [doi]
• Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine LearningFélix Lefebvre, Gaël Varoquaux. [doi]
• Oracle-Efficient Combinatorial Semi-BanditsJung Hun Kim, Milan Vojnovic, Min-hwan Oh. [doi]
• Target Speaker Extraction through Comparing Noisy Positive and Negative Audio EnrollmentsShitong Xu, Yiyuan Yang, Niki Trigoni, Andrew Markham. [doi]
• Learning to Better Search with Language Models via Guided Reinforced Self-TrainingSeungyong Moon, Bumsoo Park, Hyun Oh Song. [doi]
• Towards Principled Unsupervised Multi-Agent Reinforcement LearningRiccardo Zamboni, Mirco Mutti, Marcello Restelli. [doi]
• Mechanism Design via the Interim RelaxationKshipra Bhawalkar, Marios Mertzanidis, Divyarthi Mohan, Alexandros Psomas 0001. [doi]
• Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised LearningXingxing Yang 0002, Jie Chen 0026, Zaifeng Yang. [doi]
• Efficient Utility-Preserving Machine Unlearning with Implicit Gradient SurgeryShiji Zhou, Tianbai Yu, Zhi Zhang, Heng Chang, Xiao Zhou, Dong Wu, Han Zhao 0002. [doi]
• Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video UnderstandingWeiyu Guo, Ziyang Chen, Shaoguang Wang, Jianxiang He, Yijie Xu, Jinhui Ye, Ying Sun 0006, Hui Xiong 0001. [doi]
• Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer InferenceWeizhi Fei, Xueyan Niu 0001, Guoqing Xie, Yingqing Liu, Bo Bai 0001, Wei Han 0004. [doi]
• MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology SegmentationMeilong Xu, Xiaoling Hu 0002, Shahira Abousamra, Chen Li 0045, Chao Chen 0012. [doi]
• Attention on the SphereBoris Bonev, Max Rietmann, Andrea Paris, Alberto Carpentieri, Thorsten Kurth. [doi]
• From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained VideosAnimesh Gupta, Jay Parmar, Ishan Rajendrakumar Dave, Mubarak Shah. [doi]
• Optimized Minimal 3D Gaussian SplattingJoo Chan Lee, Jong Hwan Ko, Eunbyung Park. [doi]
• Transductive Conformal Inference for Full RankingJean-Baptiste Fermanian, Pierre Humbert, Gilles Blanchard. [doi]
• ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective PrimitiveXinhao Luo, Zihan Liu 0002, Yangjie Zhou 0001, Shihan Fang, Ziyu Huang, Yu Feng 0007, Chen Zhang 0001, Shixuan Sun, Zhenzhe Zheng 0001, Jingwen Leng, Minyi Guo. [doi]
• Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain AdaptationJing Wang, Wonho Bae, Jiahong Chen, Wenxu Wang, Junhyug Noh. [doi]
• Scaling Laws for Optimal Data MixturesMustafa Shukor, Louis Béthune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin El-Nouby, Pierre Ablin. [doi]
• Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow ModelsMinghao Yin, Yukang Cao, Kai Han 0001. [doi]
• An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a GraphTam Le, Truyen Nguyen, Hideitsu Hino, Kenji Fukumizu. [doi]
• Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion ModelsWenda Li 0005, Huijie Zhang, Qing Qu 0001. [doi]
• In Search of Adam's Secret SauceAntonio Orvieto, Robert Gower. [doi]
• Private Geometric Median in Nearly-Linear TimeSyamantak Kumar, Daogao Liu, Kevin Tian, Chutong Yang. [doi]
• CheMixHub: Datasets and Benchmarks for Chemical Mixture Property PredictionElla M. Rajaonson, Mahyar Rajabi Kochi, Luis Martin Mejia Mendoza, Seyed Mohamad Moosavi, Benjamín Sánchez-Lengeling. [doi]
• Your Pre-trained LLM is Secretly an Unsupervised Confidence CalibratorBeier Luo, Shuoyuan Wang, Sharon Li 0001, Hongxin Wei. [doi]
• PALQO: Physics-informed model for Accelerating Large-scale Quantum OptimizationYiming Huang, Yajie Hao, Yuxuan Du, Jing Zhou, Xiao Yuan, Xiaoting Wang. [doi]
• Weak-to-Strong Generalization under Distribution ShiftsMyeongho Jeon, Jan Sobotka, Suhwan Choi, Maria Brbic. [doi]
• Go With the Flow: Fast Diffusion for Gaussian Mixture ModelsGeorge Rapakoulias, Ali Reza Pedram, Fengjiao Liu, Lingjiong Zhu, Panagiotis Tsiotras. [doi]
• MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern ModelingJiaming Ma, Binwu Wang, Qihe Huang, Guanjun Wang, Pengkun Wang 0001, Zhengyang Zhou, Yang Wang 0015. [doi]
• Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic BottlenecksSara Cammarota, Matteo Ferrante, Nicola Toschi. [doi]
• WASP: Benchmarking Web Agent Security Against Prompt Injection AttacksIvan Evtimov, Arman Zharmagambetov, Aaron Grattafiori, Chuan Guo 0001, Kamalika Chaudhuri. [doi]
• Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ PruningChaofan Lin, Jiaming Tang, Shuo Yang 0011, Hanshuo Wang, Tian Tang 0001, Boyu Tian, Ion Stoica, Song Han 0003, Mingyu Gao 0001. [doi]
• Zero-Shot Context Generalization in Reinforcement Learning from Few Training ContextsJames Chapman 0007, Kedar Karhadkar, Guido F. Montúfar. [doi]
• UMU-Bench: Closing the Modality Gap in Multimodal Unlearning EvaluationChengye Wang, Yuyuan Li 0001, Xiaohua Feng 0002, Chaochao Chen 0001, Xiaolin Zheng, Jianwei Yin. [doi]
• ML4CFD Competition: Results and Retrospective AnalysisMouadh Yagoubi, David Danan, Milad Leyli-Abadi, Jocelyn Ahmed Mazari, Jean-Patrick Brunet, Abbas Kabalan, Fabien Casenave, Yuxin Ma, Giovanni Catalani, Jean Fesquet, Jacob Helwig, Xuan Zhang, Haiyang Yu 0005, Xavier Bertrand, Frederic Tost, Michael Bauerheim, Joseph Morlier, Shuiwang Ji. [doi]
• Asymmetric Dual-Lens Video DeblurringZeyu Xiao 0002, Xinchao Wang. [doi]
• Neural Atlas Graphs for Dynamic Scene Decomposition and EditingJan Philipp Schneider, Pratik Singh Bisht, Ilya Chugunov, Andreas Kolb 0001, Michael Moeller 0001, Felix Heide. [doi]
• Solving Neural Min-Max Games: The Role of Architecture, Initialization & DynamicsDeep Patel, Emmanouil-Vasileios Vlatakis-Gkaragkounis. [doi]
• Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy ModelYicong Chen, Jiahua Rao, Jiancong Xie, Dahao Xu, Zhen Wang 0004, Yuedong Yang. [doi]
• VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMsShmuel Berman, Jia Deng 0001. [doi]
• ALTo: Adaptive-Length Tokenizer for Autoregressive Mask GenerationLingfeng Wang 0003, Hualing Lin, Senda Chen, Tao Wang, Changxu Cheng, Yangyang Zhong, Dong Zheng, Wuyue Zhao. [doi]
• Conformal Prediction for Causal Effects of Continuous TreatmentsMaresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Valentyn Melnychuk, Stefan Feuerriegel. [doi]
• MergeBench: A Benchmark for Merging Domain-Specialized LLMsYifei He, Siqi Zeng 0001, Yuzheng Hu, Rui Yang 0010, Tong Zhang 0001, Han Zhao 0002. [doi]
• Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix CompressionKyo Kuroki, Yasuyuki Okoshi, Thiem Van Chu, Kazushi Kawamura, Masato Motomura. [doi]
• Differentiable Generalized Sliced Wasserstein PlansLaetitia Chapel, Romain Tavenard, Samuel Vaiter. [doi]
• Safe-Sora: Safe Text-to-Video Generation via Graphical WatermarkingZihan Su, Xuerui Qiu, Hongbin Xu, Tangyu Jiang, Junhao Zhuang, Chun Yuan 0003, Ming Li 0073, Shengfeng He, Fei Richard Yu. [doi]
• Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial AssociationsDavid R. Burt, Renato Berlinghieri, Stephen Bates, Tamara Broderick. [doi]
• Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door InterventionZhen Yang 0010, Ziwei Du, Minghan Zhang, Wei Du, Jie Chen 0025, Fulan Qian, Shu Zhao 0005. [doi]
• DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image EditingZixiang Li, Haoyu Wang, Wei Wang 0108, Chuangchuang Tan, Yunchao Wei, Yao Zhao 0001. [doi]
• Bidirectional Representations Augmented Autoregressive Biological Sequence GenerationXiang Zhang 0028, Jiaqi Wei, Zijie Qiu, Sheng Xu, Zhi Jin, Zhiqiang Gao, Nanqing Dong, Siqi Sun. [doi]
• Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention ReallocationWenbin An, Jiahao Nie 0002, Feng Tian 0002, Haonan Lin, Mingxiang Cai, Yaqiang Wu, Qianying Wang 0002, Xiaoqin Zhang, Shijian Lu. [doi]
• Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion modelsVineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh. [doi]
• TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture searchAkash Kundu, Stefano Mangini. [doi]
• WolBanking77: Wolof Banking Speech Intent Classification DatasetAbdou Karim Kandji, Frédéric Precioso, Cheikh Ba, Samba Ndiaye, Augustin Ndione. [doi]
• Metritocracy: Representative Metrics for Lite BenchmarksAriel D. Procaccia, Ben Schiffer, Serena Wang 0001, Shirley Zhang 0001. [doi]
• Asymptotic theory of SGD with a general learning-rateOr Goldreich, Ziyang Wei, Soham Bonnerjee, Jiaqi Li 0032, Wei Biao Wu. [doi]
• Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language ModelsXinran Wang, Jin Du, Azal Ahmad Khan, Qi Le, Enmao Diao, Jiawei Zhou, Jie Ding 0002, Ali Anwar 0001. [doi]
• MiniMax-Remover: Taming Bad Noise Helps Video Object RemovalBojia Zi, Weixuan Peng, Xianbiao Qi, Jianan Wang, Shihao Zhao, Rong Xiao 0003, Kam-Fai Wong. [doi]
• GeoCAD: Local Geometry-Controllable CAD Generation with Large Language ModelsZhanwei Zhang, Kaiyuan Liu, Junjie Liu 0002, Wenxiao Wang 0001, Binbin Lin, Liang Xie 0003, Chen Shen 0003, Deng Cai 0001. [doi]
• MoleBridge: Synthetic Space Projecting with Discrete Markov BridgesRongchao Zhang, Yu Huang 0004, Yongzhi Cao, Hanpin Wang. [doi]
• Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow VariantsGangda Deng, Hongkuan Zhou, Rajgopal Kannan, Viktor Prasanna 0001. [doi]
• Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference ShiftYi Zhang, Elynn Chen, Yujun Yan. [doi]
• Orientation Matters: Making 3D Generative Models Orientation-AlignedYichong Lu, Yuzhuo Tian, Zijin Jiang, Yikun Zhao, Yuanbo Yang, Hao Ouyang, Haoji Hu, Huimin Yu, Yujun Shen, Yiyi Liao. [doi]
• MaxSup: Overcoming Representation Collapse in Label SmoothingYuxuan Zhou 0004, Heng Li, Zhi-Qi Cheng, Xudong Yan, Yifei Dong 0002, Mario Fritz, Margret Keuper. [doi]
• AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured GaussiansXiyu Zhang 0003, Chong Bao, Yipeng Chen, Hongjia Zhai, Yitong Dong, Hujun Bao, Zhaopeng Cui, Guofeng Zhang 0001. [doi]
• Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary DynamicsLorenzo Magnino, Kai Shao, Zida Wu, Jiacheng Shen, Mathieu Laurière. [doi]
• TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series ForecastingJaebin Lee, Hankook Lee. [doi]
• Uncertainty Estimation by Flexible Evidential Deep LearningTaeseong Yoon, Heeyoung Kim. [doi]
• Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences AlignmentKaixun Jiang, Zhaoyu Chen 0001, Haijing Guo, Jinglun Li, Jiyuan Fu, Pinxue Guo, Hao Tang 0005, Bo Li 0115, Wenqiang Zhang. [doi]
• Beyond Last-Click: An Optimal Mechanism for Ad AttributionNan An, Weian Li, Qi Qi 0003, Changyuan Yu, Liang Zhang. [doi]
• Preference-driven Knowledge Distillation for Few-shot Node ClassificationXing Wei, Chunchun Chen, Rui Fan 0001, Xiaofeng Cao 0002, Sourav Medya, Wei Ye 0001. [doi]
• Enhancing Consistency of Flow-Based Image Editing through Kalman ControlHaozhe Chi, Zhicheng Sun 0001, Yang Jin, Yi Ma, Jing Wang, Yadong Mu. [doi]
• Understanding Bias Terms in Neural RepresentationsWeixiang Zhang, Boxi Li, Shuzhao Xie, Chengwei Ren, Yuan Xue 0013, Zhi Wang 0001. [doi]
• CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency DiscriminationYuena Lin, Hao Wei 0006, Hai-Chun Cai, Bohang Sun, Tao Yang, Zhen Yang 0004, Gengyu Lyu. [doi]
• Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion ModelsQingsong Wang, Zhengchao Wan, Misha Belkin, Yusu Wang. [doi]
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation EditingYisong Xiao, Aishan Liu, Siyuan Liang 0004, Zonghao Ying, Xianglong Liu 0001, Dacheng Tao. [doi]
• SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace ColorizationJunpyo Seo, Hanbin Koo, Jieun Yook, Byung Ro Moon. [doi]
• AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of SoundGijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier. [doi]
• Conformal Linguistic Calibration: Trading-off between Factuality and SpecificityZhengping Jiang, Anqi Liu 0001, Benjamin Van Durme. [doi]
• Discretization-free Multicalibration through Loss Minimization over Tree EnsemblesHongyi Henry Jin, Zijun Ding, Dung Daniel T. Ngo, Zhiwei Steven Wu. [doi]
• MSTAR: Box-free Multi-query Scene Text Retrieval with Attention RecyclingLiang Yin, Xudong Xie, Zhang Li, Xiang Bai, Yuliang Liu. [doi]
• Hamiltonian Neural PDE Solvers through Functional ApproximationAnthony Y. Zhou, Amir Barati Farimani. [doi]
• Two Causally Related Needles in a Video HaystackMiaoyu Li, Qin Chao, Boyang Li 0001. [doi]
• Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal ApproachYuting Huang 0009, Ziquan Fang, ZhiHao Zeng, Lu Chen 0001, Yunjun Gao. [doi]
• PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?Atharva Gundawar, Som Sagar, Ransalu Senanayake. [doi]
• Execution Guided Line-by-Line Code GenerationBoaz Lavon, Shahar Katz, Lior Wolf. [doi]
• A Standardized Benchmark for Multilabel Antimicrobial Peptide ClassificationSebastian Ojeda, Rafael Velasquez, Nicolás Aparicio, Juanita Puentes, Paula Cárdenas, Nicolás Andrade, Gabriel González, Sergio Rincón, Carolina Muñoz-Camargo, Pablo Arbeláez. [doi]
• Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual SparsitySusav Shrestha, Bradley W. Settlemyer, Nikoli Dryden, Narasimha Reddy. [doi]
• Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function SingularityZichen Liu, Wei Zhang 0065, Tiejun Li. [doi]
• Enforcing convex constraints in Graph Neural NetworksAhmed Rashwan, Keith Briggs, Chris J. Budd, Lisa Maria Kreusser. [doi]
• PhySense: Sensor Placement Optimization for Accurate Physics SensingYuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang 0001, Mingsheng Long. [doi]
• Structured Reinforcement Learning for Combinatorial Decision-MakingHeiko Hoppe, Léo Baty, Louis Bouvier, Axel Parmentier, Maximilian Schiffer. [doi]
• Personalized Bayesian Federated Learning with Wasserstein Barycenter AggregationTing Wei, Biao Mei, Junliang Lyu, Renquan Zhang, Feng Zhou, Yifan Sun. [doi]
• AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive ProjectionSaleh Momeni, Changnan Xiao, Bing Liu 0001. [doi]
• Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait AssessmentVida Adeli, Ivan Klabucar, Javad Rajabi, Benjamin Filtjens, Soroush Mehraban, Diwei Wang, Trung-Hieu Hoang, Minh N. Do, Hyewon Seo, Candice Müller, Daniel Boari Coelho, Claudia de Oliveira, Pieter Ginis, Moran Gilat, Alice Nieuwboer, Joke Spildooren, J. Lucas McKay, HyeokHyen Kwon, Gari D. Clifford, Christine D. Esper, Stewart A. Factor, Imari Genias, Amirhossein Dadashzadeh, Leia C. Shum, Alan L. Whone, Majid Mirmehdi, Andrea Iaboni, Babak Taati. [doi]
• VMDT: Decoding the Trustworthiness of Video Foundation ModelsYujin Potter, Zhun Wang, Nicholas Crispino, Kyle Montgomery, Alexander Xiong, Ethan Y. Chang, Francesco Pinto, Yuqi Chen, Rahul Gupta 0001, Morteza Ziyadi, Christos Christodoulopoulos 0001, Bo Li 0026, Chenguang Wang 0001, Dawn Song. [doi]
• A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated LearningXiaoli Tang 0001, Han Yu 0001, Xiaoxiao Li. [doi]
• OmniSVG: A Unified Scalable Vector Graphics Generation ModelYiying Yang, Wei Cheng, Sijin Chen, Xianfang Zeng, Fukun Yin, Jiaxu Zhang, Liao Wang, Gang Yu 0002, Xingjun Ma, Yu-Gang Jiang 0001. [doi]
• Balancing Gradient and Hessian Queries in Non-Convex OptimizationDeeksha Adil, Brian Bullins, Aaron Sidford, Chenyi Zhang 0003. [doi]
• Online Bilateral Trade With Minimal Feedback: Don't Waste Seller's TimeFrancesco Bacchiocchi, Matteo Castiglioni, Roberto Colomboni, Alberto Marchesi 0001. [doi]
• SNAP: Low-Latency Test-Time Adaptation with Sparse UpdatesHyeongheon Cha, Dong-Min Kim, Hye Won Chung, Taesik Gong, Sung-Ju Lee. [doi]
• Consistent Story Generation: Unlocking the Potential of Zigzag SamplingMingxiao Li 0002, Mang Ning, Marie-Francine Moens. [doi]
• Principled Data Augmentation for Learning to Solve Quadratic Programming ProblemsChendi Qian, Christopher Morris 0001. [doi]
• Navigating the MIL Trade-Off: Flexible Pooling for Whole Slide Image ClassificationHossein Jafarinia, Danial Hamdi, Amirhossein Alamdar, Elahe Zahiri, Soroush Vafaie Tabar, Alireza Alipanah, Nahal Mirzaie, Saeed Razavi, Amir Najafi 0002, Mohammad Hossein Rohban. [doi]
• ARIA: Training Language Agents with Intention-driven Reward AggregationRuihan Yang, Yikai Zhang 0004, Aili Chen, Xintao Wang 0001, Jiangjie Chen, Siyu Yuan, Deqing Yang, Yanghua Xiao. [doi]
• SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language ModelsPingyi Chen, Yujing Lou, Shen Cao, Jinhui Guo, Lubin Fan, Yue Wu, Lin F. Yang, Lizhuang Ma, Jieping Ye. [doi]
• AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingZhucun Xue, Jiangning Zhang, Xurong Xie, Yuxuan Cai, Yong Liu 0007, Xiangtai Li, Dacheng Tao. [doi]
• In-Context Compositional Learning vis Sparse Coding TransformerWei Chen 0124, Jingxi Yu, Zichen Miao, Qiang Qiu 0001. [doi]
• JAFAR: Jack up Any Feature at Any ResolutionPaul Couairon, Loïck Chambon, Louis Serrano, Jean-Emmanuel Haugeard, Matthieu Cord, Nicolas Thome. [doi]
• Impact of Layer Norm on Memorization and Generalization in TransformersRishi Singhal, Jung-Eun Kim. [doi]
• MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided ConversationsVardhan Dongre, Chi Gui, Shubham Garg, Hooshang Nayyeri, Gokhan Tur, Dilek Hakkani-Tur, Vikram S. Adve. [doi]
• TANDEM: Bi-Level Data Mixture Optimization with Twin NetworksJiaxing Wang, Deping Xiang, Jin Xu, Mingyang Yi, Guoqiang Gong, Zicheng Zhang, Haoran Li 0027, Pengzhang Liu, Zhen Chen 0046, Ke Zhang, Ju Fan, Qixia Jiang. [doi]
• What Matters in Data for DPO?Yu Pan, Zhongze Cai, Huaiyang Zhong, Guanting Chen 0001, Chonghuan Wang. [doi]
• Layer as Puzzle Pieces: Compressing Large Language Models through Layer ConcatenationFei Wang 0032, Li Shen 0008, Liang Ding 0006, Chao Xue 0003, Ye Liu 0014, Changxing Ding. [doi]
• Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMsGuiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu, Tianhe Gu, Ruihang Zhang, Sizhe Zhang, Junran Wu, Xiaoyue Tu, Ming Jin 0005, Qingsong Wen, Lixing Chen, Pan Zhou 0001, Lichao Sun 0001. [doi]
• UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site DetectionJigang Fan, Quanlin Wu, Shengjie Luo, Liwei Wang. [doi]
• Automatic Auxiliary Task Selection and Adaptive Weighting Boost Molecular Property PredictionZhiqiang Zhong 0001, Davide Mottin. [doi]
• ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical ConstraintsRui Xu 0026, Dakuan Lu, ZiCheng Zhao, Xiaoyu Tan, Xintao Wang 0001, Siyu Yuan, Jiangjie Chen, Yinghui Xu 0001. [doi]
• Towards Evaluating Proactive Risk Awareness of Multimodal Language ModelsYouliang Yuan, Wenxiang Jiao, Yuejin Xie, Chihao Shen, Menghan Tian, Wenxuan Wang 0001, Jen-tse Huang 0001, Pinjia He. [doi]
• Hybrid Re-matching for Continual Learning with Parameter-Efficient TuningWeicheng Wang, Guoli Jia, Xialei Liu, Liang Lin, Jufeng Yang. [doi]
• UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-IdentificationXixi Wan, Aihua Zheng, Bo Jiang 0002, Beibei Wang 0006, Chenglong Li 0002, Jin Tang 0001. [doi]
• Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction AttacksAshley Kurian, Aydin Aysu. [doi]
• Non-stationary Bandit Convex Optimization: A Comprehensive StudyXiaoqi Liu, Dorian Baudry, Julian Zimmert, Patrick Rebeschini, Arya Akhavan. [doi]
• VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech InteractionChaoyou Fu, Haojia Lin, Xiong Wang, Yifan Zhang 0004, Yunhang Shen, Xiaoyu Liu, Haoyu Cao 0001, Zuwei Long, Heting Gao, Ke Li 0015, Long Ma, Xiawu Zheng, Rongrong Ji, Xing Sun 0001, Caifeng Shan, Ran He 0001. [doi]
• An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive NoiseJohanna Düngler, Amartya Sanyal. [doi]
• Disentangled Representation Learning via Modular Compositional BiasWhie Jung, Dong-Hoon Lee, Seunghoon Hong. [doi]
• Deno-IF: Unsupervised Noisy Visible and Infrared Image Fusion MethodHan Xu 0001, Yuyang Li, Yunfei Deng, Jiayi Ma 0001, Guangcan Liu. [doi]
• Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence ModelingMónika Farsang, Radu Grosu. [doi]
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement LearningYixiu Mao, Yun Qu 0002, Qi (Cheems) Wang, Xiangyang Ji. [doi]
• Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf InteractionsHubert Baniecki, Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer, Eyke Hüllermeier, Przemyslaw Biecek. [doi]
• Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal NavigationBadi Li, Renjie Lu 0002, Yu Zhou, Jingke Meng, Wei-Shi Zheng 0001. [doi]
• DiffLiG: Diffusion-enhanced Liquid Graph with Attention Propagation for Grid-to-Station Precipitation CorrectionYuxiang Li, Yang Zhang, Guowen Li, Mengxuan Chen, Meng Jin, Fang Wang, Haohuan Fu, Juepeng Zheng. [doi]
• Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement LearningWang Lin, Wentao Hu, Liyu Jia, Kaihang Pan, Majun Zhang, Zhou Zhao 0001, Fei Wu 0001, Jingyuan Chen, Hanwang Zhang. [doi]
• Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative ModelingChenghao Xu, Guangtao Lyu, Jiexi Yan, Muli Yang, Cheng Deng 0002. [doi]
• RGB-Only Supervised Camera Parameter Optimization in Dynamic ScenesFang Li, Hao Helen Zhang, Narendra Ahuja. [doi]
• MimeQA: Towards Socially-Intelligent Nonverbal Foundation ModelsHengzhi Li, Megan Tjandrasuwita, Yi R. (May) Fung, Armando Solar-Lezama, Paul Pu Liang. [doi]
• QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced ClassificationQian Tang, Yuwen Gu, Boxiang Wang. [doi]
• Simultaneous Swap Regret Minimization via KL-CalibrationHaipeng Luo, Spandan Senapati, Vatsal Sharan. [doi]
• Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech DecodingEbrahim Feghhi, Shreyas Kaasyap, Nima Hadidi, Jonathan C. Kao. [doi]
• Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone ProgrammingZhao Song 0002, Jianfei Xue 0001, Lichen Zhang 0003. [doi]
• The Flood Complex: Large-Scale Persistent Homology on Millions of PointsFlorian Graf, Paolo Pellizzoni, Martin Uray, Stefan Huber 0001, Roland Kwitt. [doi]
• LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D ScansZhening Huang, Xiaoyang Wu 0002, Fangcheng Zhong, Hengshuang Zhao, Matthias Nießner, Joan Lasenby. [doi]
• Event-Driven Dynamic Scene Depth CompletionZhiqiang Yan 0001, Jianhao Jiao, Zhengxue Wang, Gim Hee Lee. [doi]
• MMPB: It's Time for Multi-Modal PersonalizationJaeik Kim, Woojin Kim, Woohyeon Park, Jaeyoung Do. [doi]
• Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image DetectionYue Zhou 0008, Xinan He, Kaiqing Lin, Bing Fan, Feng Ding 0007, Bin Li. [doi]
• FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with GuaranteesHoang T. Nguyen, Priya L. Donti. [doi]
• Understanding the Gain from Data Filtering in Multimodal Contrastive LearningDivyansh Pareek, Sewoong Oh, Simon S. Du. [doi]
• LT-Soups: Bridging Head and Tail Classes via Subsampled Model SoupsMasih Aminbeidokhti, Subhankar Roy, Eric Granger, Elisa Ricci 0001, Marco Pedersoli. [doi]
• Contextual Tokenization for Graph Inverted IndicesPritish Chakraborty, Indradyumna Roy, Soumen Chakrabarti, Abir De. [doi]
• FHGS: Feature-Homogenized Gaussian SplattingQigeng Duan, Benyun Zhao, Mingqiao Han, Yijun Huang, Ben M. Chen. [doi]
• Spectral Analysis of Representational Similarity with Limited NeuronsHyunmo Kang, Abdulkadir Canatar, SueYeon Chung. [doi]
• HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal DataRuizhe Liu, Pei Zhou, Qian Luo, Li Sun, Jun Cen, Yibing Song, Yanchao Yang 0001. [doi]
• Differentiable Hierarchical Visual TokenizationMarius Aasan, Martine Hjelkrem-Tan, Nico Catalano, Changkyu Choi, Adín Ramírez Rivera. [doi]
• Dimension-adapted Momentum Outscales SGDDamien Ferbach, Katie Everett, Gauthier Gidel, Elliot Paquette, Courtney Paquette. [doi]
• Distributed Multi-Agent Bandits Over Erdős-Rényi Random NetworksJingyuan Liu, Hao Qiu, Lin F. Yang, Mengfan Xu. [doi]
• Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking ReasoningJunhao Shen, Haiteng Zhao, Yuzhe Gu, Songyang Gao, Kuikun Liu, Haian Huang, Jianfei Gao 0003, Dahua Lin, Wenwei Zhang, Kai Chen 0026. [doi]
• RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal OutputsMeng-Hao Guo 0001, Xuanyu Chu, Qianrui Yang, Zhe-Han Mo, Yiqing Shen 0005, Pei-lin Li, Xinjie Lin, Jinnian Zhang, Xin-Sheng Chen, Yi Zhang 0099, Kiyohiro Nakayama, Zhengyang Geng, Houwen Peng, Han Hu 0001, Shimin Hu 0001. [doi]
• μPC: Scaling Predictive Coding to 100+ Layer NetworksFrancesco Innocenti, El Mehdi Achour, Christopher L. Buckley. [doi]
• Reasoning as an Adaptive Defense for SafetyTaeyoun Kim, Fahim Tajwar, Aditi Raghunathan, Aviral Kumar. [doi]
• Probabilistic Reasoning with LLMs for Privacy Risk EstimationJonathan Zheng, Alan Ritter, Sauvik Das, Wei (Coco) Xu. [doi]
• CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&DFrancis Ward, Teun van der Weij, Hanna Gábor, Sam Martin, Raja Mehta Moreno, Harel Lidar, Louis Makower, Thomas Jodrell, Lauren Robson. [doi]
• Incremental Sequence Classification with Temporal ConsistencyLucas Maystre, Gabriel Barello, Tudor Berariu, Aleix Cambray, Rares Dolga, Alvaro Ortega Gonzalez, Andrei Cristian Nica, David Barber. [doi]
• Constant Bit-size Transformers Are Turing CompleteQian Li, Yuyi Wang 0001. [doi]
• Scaling Language-centric Omnimodal Representation LearningChenghao Xiao, Hou Pong Chan, Hao Helen Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong 0001. [doi]
• NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent RetrievalJunchen Li, Rongzheng Wang, Yihong Huang, Qizhi Chen, Jiasheng Zhang, Shuang Liang 0002. [doi]
• The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian SketchesOmri Lev, Vishwak Srinivasan, Moshe Shenfeld, Katrina Ligett, Ayush Sekhari, Ashia C. Wilson. [doi]
• TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link PredictionZhongyi Yu, Jianqiu Wu, Zhenghao Wu, Shuhan Zhong, Weifeng Su, Chul-Ho Lee, Weipeng Zhuo. [doi]
• Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-MakingTianyuan Jia, Ziyu Li, Qing Li 0027, Xiuxing Li, Xiang Li 0001, Chen Wei, Li Yao 0002, Xia Wu 0001. [doi]
• From Pose to Muscle: Multimodal Learning for Piano Hand Muscle ElectromyographyRuofan Liu 0001, Yichen Peng, Takanori Oku, Chen-Chieh Liao, Erwin Wu, Shinichi Furuya, Hideki Koike. [doi]
• SAO-Instruct: Free-form Audio Editing using Natural Language InstructionsMichael Ungersböck, Florian Grötschla, Luca A. Lanzendörfer, June Young Yi, Changho Choi, Roger Wattenhofer. [doi]
• MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive ClusteringQiwen Gu, Xufei Wang, Junqiao Zhao, Siyue Tao, TianTian Feng, Ziqiao Wang, Guang Chen 0001. [doi]
• FlexSelect: Flexible Token Selection for Efficient Long Video UnderstandingYunzhu Zhang, Yu Lu 0019, Tianyi Wang, Fengyun Rao, Yi Yang 0001, Linchao Zhu. [doi]
• REOBench: Benchmarking Robustness of Earth Observation Foundation ModelsXiang Li 0001, Yong Tao, Siyuan Zhang, Siwei Liu 0001, Zhitong Xiong, Chunbo Luo, Lu Liu 0001, Mykola Pechenizkiy, Xiaoxiang Zhu 0001, Tianjin Huang. [doi]
• Continuous Subspace Optimization for Continual LearningQuan Cheng 0001, Yuanyu Wan, Lingyu Wu, Chenping Hou, Lijun Zhang 0005. [doi]
• Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via PromptingHaoyu Zhang, Yinan Zhang, Chaolong Ying, Xiaoying Tang, Tianshu Yu 0001. [doi]
• MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic HumansHuiyi Wang, Chun Kwang Tan, Balint Hodossy, Shirui Lyu, Pierre Schumacher, James Heald, Kai Biegun, Samo Hromadka, Maneesh Sahani, GunWoo Park, Beomsoo Shin, Jonghyeon Park, Seungbum Koo, Chenhui Zuo, Chengtian Ma, Yanan Sui, Nicklas Hansen 0001, Stone Tao, Yuan Gao, Hao Su 0001, Seungmoon Song, Letizia Gionfrida, Massimo Sartori, Guillaume Durandau, Vikash Kumar, Vittorio Caggiano. [doi]
• REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion PlanningShuguang Wang, Qian Zhou 0008, Kui Wu 0001, Dapeng Wu 0001, Wei-Bin Lee, Jianping Wang 0001. [doi]
• HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking TasksHongjin Qian, Zheng Liu 0011, Chao Gao, Yankai Wang, Defu Lian, Zhicheng Dou. [doi]
• Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCoZachary Charles, Gabriel Teston, Lucio M. Dery, John Keith Rush, Nova Fallen, Zachary Garrett, Arthur D. Szlam, Arthur Douillard. [doi]
• IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric AssistantsVivek Chavan, Yasmina Imgrund, Tung Dao, Sanwantri Bai, Bosong Wang, Ze Lu, Oliver Heimann, Jörg Krüger. [doi]
• GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution DetectionXin Gao, Jiyao Liu, Guanghao Li, Yueming Lyu, Jianxiong Gao, Weichen Yu, Ningsheng Xu, Liang Wang 0001, Caifeng Shan, Ziwei Liu 0002, Chenyang Si. [doi]
• PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient InteractionsDaeun Kyung, Hyunseung Chung, Seongsu Bae, Jiho Kim, Jae Ho Sohn, Taerim Kim, Soo-Kyung Kim, Edward Choi 0003. [doi]
• Crucible: Quantifying the Potential of Control Algorithms through LLM AgentsLianchen Jia, Chaoyang Li 0002, Qian Houde, Tianchi Huang, Jiangchuan Liu, Lifeng Sun. [doi]
• Multitask Learning with Stochastic InterpolantsHugo Negrel, Florentin Coeurdoux, Michael S. Albergo, Eric Vanden-Eijnden. [doi]
• Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM DecodingYue Guan 0003, Changming Yu, Shihan Fang, Weiming Hu 0005, Zaifeng Pan, Zheng Wang 0075, Zihan Liu 0002, Yangjie Zhou 0001, Yufei Ding 0001, Minyi Guo, Jingwen Leng. [doi]
• MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing SolverYuepeng Zheng, Fu Luo, Zhenkun Wang 0001, Yaoxin Wu, Yu Zhou 0027. [doi]
• Activation-Guided Consensus Merging for Large Language ModelsYuxuan Yao, Shuqi Liu 0001, Zehua Liu, Qintong Li, Mingyang Liu, Xiongwei Han, Zhijiang Guo, Han Wu 0004, Linqi Song. [doi]
• ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive DatasetXu Wang, Jingyuan Zhuo, Zhiyuan You, Zhiyu Tan, Yikuan Yu, Siyu Wang, Xinyi Le. [doi]
• Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge RetrievalConstantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip H. S. Torr, Neel Nanda. [doi]
• Towards Single-Source Domain Generalized Object Detection via Causal Visual PromptsChen Li 0025, Huiying Xu, Changxin Gao, Zeyu Wang, Yun Liu, Xinzhong Zhu. [doi]
• Provable Gradient Editing of Deep Neural NetworksZhe Tao, Aditya V. Thakur. [doi]
• Long-tailed Recognition with Model RebalancingJiaan Luo, Feng Hong 0004, Qiang Hu 0003, Xiaofeng Cao 0002, Feng Liu 0003, Jiangchao Yao. [doi]
• Sparse Optimistic Information Directed SamplingLudovic Schwartz, Hamish Flynn, Gergely Neu. [doi]
• Continual Model Merging without Data: Dual Projections for Balancing Stability and PlasticityEnneng Yang, Anke Tang, Li Shen 0008, Guibing Guo, Xingwei Wang 0001, Xiaochun Cao, Jie M. Zhang. [doi]
• LittleBit: Ultra Low-Bit Quantization via Latent FactorizationBanseok Lee, Dongkyu Kim, Youngcheon You, Youngmin Kim. [doi]
• Trust Region Reward Optimization and Proximal Inverse Reward Optimization AlgorithmYang Chen 0028, Menglin Zou, Jiaqi Zhang, Yitan Zhang, Junyi Yang, Gaël Gendron, Libo Zhang 0006, Jiamou Liu, Michael Witbrock. [doi]
• Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert FeedbackJanet Wang, Yunbei Zhang, Zhengming Ding, Jihun Hamm. [doi]
• Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware PermutationShuo Yang 0011, Haocheng Xi, Yilong Zhao 0002, Muyang Li, Jintao Zhang, Han Cai, Yujun Lin 0001, Xiuyu Li, Chenfeng Xu, Kelly Peng, Jianfei Chen 0001, Song Han 0003, Kurt Keutzer, Ion Stoica. [doi]
• Merlin L48 Spectrogram DatasetAaron Sun, Subhransu Maji, Grant Van Horn. [doi]
• FAIR Universe HiggsML Uncertainty Dataset and CompetitionWahid Bhimji, Ragansu Chakkappai, Po-Wen Chang, Yuan-Tang Chou, Sascha Diefenbacher, Jordan Dudley, Ibrahim Elsharkawy, Steven Farrell, Aishik Ghosh, Cristina Giordano, Isabelle Guyon, Chris Harris 0004, Yota Hashizume, Shih-Chieh Hsu, Elham E Khoda, Claudius Krause, Ang Li, Benjamin Nachman, David Rousseau, Robert Schöfbeck, Maryam Shooshtari, Dennis Schwarz, Ihsan Ullah, Daohan Wang, Yulei Zhang. [doi]
• Discrete Spatial Diffusion: Intensity-Preserving Diffusion ModelingJavier E. Santos, Agnese Marcato, Roman Colman, Nicholas Lubbers, Yen-Ting Lin. [doi]
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based DecodingXiner Li, Yulai Zhao 0002, Chenyu Wang 0003, Gabriele Scalia, Gökcen Eraslan, Surag Nair, Tommaso Biancalani, Shuiwang Ji, Aviv Regev, Sergey Levine, Masatoshi Uehara. [doi]
• Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection SynergyQing Zhao, Weijian Deng, Pengxu Wei, Ziyi Dong, Hannan Lu, Xiangyang Ji, Liang Lin. [doi]
• Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCNJiaxin Wu, Chenglong Pang, Guangxiong Chen, Jie Zhao 0011. [doi]
• Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph GenerationLin Li 0065, Chuhan Zhang, Dong Zhang, Chong Sun, Chen Li, Long Chen 0016. [doi]
• Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task PlanningSanghyun Ahn, Wonje Choi 0003, Junyong Lee, Jinwoo Park, Honguk Woo. [doi]
• MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model PretrainingZhixun Chen, Ping Guo, Wenhan Han, Yifan Zhang, Binbin Li 0001, Haobin Lin, Fengze Liu, Yan Zhao, Bingni Zhang, Taifeng Wang, Yin Zheng, Trevor Cohn, Meng Fang. [doi]
• To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RLYuda Song 0001, Dhruv Rohatgi, Aarti Singh, J. Andrew Bagnell. [doi]
• Gradient Multi-Normalization for Efficient LLM TrainingMeyer Scetbon, Chao Ma 0019, Wenbo Gong 0001, Edward Meeds. [doi]
• Improving Model Representation and Reducing KV Cache via Skip Connections with First Value HeadsZhoutong Wu, Yuan Zhang, Yiming Dong, Chenheng Zhang, Cong Fang 0001, Kun Yuan, Zhouchen Lin. [doi]
• Imitation Beyond Expectation Using Pluralistic Stochastic DominanceAli Farajzadeh, Danyal Saeed, Syed M. Abbas, Rushit N. Shah, Aadirupa Saha, Brian D. Ziebart. [doi]
• Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object DetectionYu Li, Xingyu Qiu, Yuqian Fu, Jie Chen, Tianwen Qian, Xu Zheng 0002, Danda Pani Paudel, Yanwei Fu 0001, Xuanjing Huang 0001, Luc Van Gool, Yu-Gang Jiang 0001. [doi]
• DynaGuide: Steering Diffusion Polices with Active Dynamic GuidanceMaximilian Du, Shuran Song. [doi]
• MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level GuaranteesHerbert Woisetschläger, Ryan Zhang, Shiqiang Wang 0001, Hans-Arno Jacobsen. [doi]
• Enhancing Privacy in Multimodal Federated Learning with Information TheoryTianzhe Xiao, Yichen Li 0006, Yining Qi, Yi Liu 0087, Wei Wang 0395, Haozhao Wang, Yi Wang 0004, Ruixuan Li 0001. [doi]
• Split Gibbs Discrete Diffusion Posterior SamplingWenda Chu, Zihui Wu, Yifan Chen, Yang Song, Yisong Yue. [doi]
• Mechanism Design for LLM Fine-tuning with Multiple Reward ModelsHaoran Sun, Yurong Chen, Siwei Wang, Chu Xu, Wei Chen, Xiaotie Deng. [doi]
• Counterfactual Image Editing with Disentangled Causal Latent SpaceYushu Pan, Elias Bareinboim. [doi]
• Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge DistillationWeining Ren, Hongjun Wang, Xiao Tan 0001, Kai Han 0001. [doi]
• Strategyproof Reinforcement Learning from Human FeedbackThomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska. [doi]
• Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language ModelsMingge Lu, Jingwei Sun 0001, Junqing Lin, Zechun Zhou, Guangzhong Sun. [doi]
• 2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIPYinqi Li 0001, Jiahe Zhao, Hong Chang 0001, Ruibing Hou, Shiguang Shan, Xilin Chen 0001. [doi]
• Embedding Principle of Homogeneous Neural Network for Classification ProblemJiahan Zhang, Yaoyu Zhang, Tao Luo. [doi]
• Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement LearningWenlin Zhang 0001, Xiangyang Li 0004, Kuicai Dong, Yichao Wang 0002, Pengyue Jia, Xiaopeng Li 0014, Yingyi Zhang 0001, Derong Xu, Zhaocheng Du, Huifeng Guo, Ruiming Tang, Xiangyu Zhao 0001. [doi]
• Lookahead Routing for Large Language ModelsCanbin Huang, Tianyuan Shi, Yuhua Zhu, Ruijun Chen 0001, Xiaojun Quan. [doi]
• Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image GenerationYifu Luo, Xinhao Hu, Keyu Fan, Haoyuan Sun, Zeyu Chen, Bo Xia, Tiantian Zhang 0002, Yongzhe Chang, Xueqian Wang 0001. [doi]
• DreamLight: Towards Harmonious and Consistent Image RelightingYong Liu 0033, Wenpeng Xiao, Qianqian Wang, JunLin Chen, Shiyin Wang, Yitong Wang, Xinglong Wu, Yansong Tang. [doi]
• MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant OptimizationRizhen Hu, Yutong He, Ran Yan, Mou Sun, Binhang Yuan, Kun Yuan 0001. [doi]
• NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian EstimationLongtian Qiu, Shan Ning, Jiaxuan Sun, Xuming He. [doi]
• Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMsYunqi Hong, Sohyun An, Andrew Bai, Neil Y. C. Lin, Cho-Jui Hsieh. [doi]
• Stable Port-Hamiltonian Neural NetworksFabian J. Roth, Dominik K. Klein, Maximilian Kannapinn, Jan Peters 0001, Oliver Weeger. [doi]
• macOSWorld: A Multilingual Interactive Benchmark for GUI AgentsPei Yang 0005, Hai Ci, Mike Zheng Shou. [doi]
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network VerificationDuo Zhou, Jorge Chavez, Hesun Chen, Grani A. Hanasusanto, Huan Zhang 0001. [doi]
• AR-RAG: Autoregressive Retrieval Augmentation for Image GenerationJingyuan Qi, Zhiyang Xu, Qifan Wang 0001, Lifu Huang. [doi]
• Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play ModulesYueqi Zhang, Peiwen Yuan, Yiwei Li 0001, Shaoxiong Feng, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu 0002, Kan Li 0001. [doi]
• Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPsShulun Chen, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du. [doi]
• EVODiff: Entropy-aware Variance Optimized Diffusion InferenceShigui Li, Wei Chen 0165, Delu Zeng. [doi]
• Object Concepts Emerge from MotionHaoqian Liang, Xiaohui Wang, Zhichao Li, Ya Yang, Naiyan Wang. [doi]
• Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language ModelsJunhao Dong 0001, Cong Zhang, Xinghua Qu, Zejun Ma 0001, Piotr Koniusz, Yew-Soon Ong. [doi]
• A Unified Approach to Submodular Maximization Under NoiseKshipra Bhawalkar, Yang Cai 0001, Zhe Feng 0004, Christopher Liaw, Tao Lin 0013. [doi]
• EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?Yuqian Yuan, Ronghao Dang, Long Li, Wentong Li 0001, Dian Jiao, Xin Li 0056, Deli Zhao, Fan Wang 0019, Wenqiao Zhang, Jun Xiao 0001, Yueting Zhuang. [doi]
• RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large ModelsYilang Zhang, Bingcong Li, Georgios B. Giannakis. [doi]
• Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian SplattingNan Wang 0041, Lixing Xiao, Yuantao Chen, Weiqing Xiao, Pierre Merriaux, Lei Lei, Ziyang Yan, Saining Zhang, Shaocong Xu, Chongjie Ye, Bohan Li 0015, Zhaoxi Chen 0009, Tianfan Xue, Hao Zhao 0002. [doi]
• Erasing Conceptual Knowledge from Language ModelsRohit Gandikota, Sheridan Feucht, Samuel Marks, David Bau. [doi]
• Spiral: Semantic-Aware Progressive LiDAR Scene Generation and UnderstandingDekai Zhu, Yixuan Hu, Youquan Liu, Dongyue Lu, Lingdong Kong, Slobodan Ilic. [doi]
• Generalization Bounds for Rank-sparse Neural NetworksAntoine Ledent, Rodrigo Alves, Yunwen Lei. [doi]
• Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal RepresentationsPeng Lai, Jianjie Zheng, Sijie Cheng, Yun Chen 0007, Peng Li 0030, Yang Liu 0005, Guanhua Chen 0001. [doi]
• On Universality Classes of Equivariant NetworksMarco Pacini, Gabriele Santin, Bruno Lepri, Shubhendu Trivedi. [doi]
• Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMsGeorgios Tzannetos, Parameswaran Kamalaruban, Adish Singla. [doi]
• Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational InferenceKyurae Kim, Yian Ma, Trevor Campbell, Jacob R. Gardner. [doi]
• How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy PerspectiveYanbiao Ji, Yue Ding 0001, Dan Luo 0004, Chang Liu 0078, Yuxiang Lu, Xin Xin 0003, Hongtao Lu 0001. [doi]
• Transferring Causal Effects using ProxiesManuel Iglesias-Alonso, Felix Schur, Julius von Kügelgen, Jonas Peters. [doi]
• What are you sinking? A geometric approach on attention sinkValeria Ruscio, Umberto Nanni, Fabrizio Silvestri. [doi]
• LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video GenerationHuanlin Gao, Ping Chen, Fuyuan Shi, Chao Tan, Zhaoxiang Liu, Fang Zhao, Kai Wang 0012, Shiguo Lian. [doi]
• BenchmarkCards: Standardized Documentation for Large Language Model BenchmarksAnna Sokol, Elizabeth Daly, Michael Hind, David Piorkowski, Xiangliang Zhang 0001, Nuno Moniz, Nitesh V. Chawla. [doi]
• Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution DetectionMin Wang 0034, Hao Yang 0042, Qing Cheng 0004, Jincai Huang 0001. [doi]
• Robust Hyperbolic Learning with Curvature-Aware OptimizationAhmad Bdeir, Johannes Burchert, Lars Schmidt-Thieme, Niels Landwehr. [doi]
• Unsupervised Federated Graph LearningLele Fu, Tianchi Liao, Sheng Huang, Bowen Deng 0002, Chuanfu Zhang, Shirui Pan, Chuan Chen 0001. [doi]
• Optimal Online Change Detection via Random Fourier FeaturesFlorian Kalinke, Shakeel Gavioli-Akilagun. [doi]
• Local-Global Associative Frames for Symmetry-Preserving Crystal Structure ModelingHaowei Hua, Wanyu Lin. [doi]
• Jasmine: Harnessing Diffusion Prior for Self-supervised Depth EstimationJiyuan Wang 0001, Chunyu Lin, Cheng Guan, Lang Nie, Jing He, Haodong Li, Kang Liao, Yao Zhao 0001. [doi]
• SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement LearningZhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang, Dongfei Cui, Qinjian Zhao, Hui Shen 0008, Jing Xiong, Yi Xin 0003, Yifan Jiang, Chaofan Tao, Yangfan He, Mi Zhang 0002, Shen Yan 0008. [doi]
• Gradient-Guided Epsilon Constraint Method for Online Continual LearningSong Lai 0001, Changyi Ma, Fei Zhu 0004, Zhe Zhao 0008, Xi Lin 0001, Gaofeng Meng, Qingfu Zhang 0001. [doi]
• Efficient Representativeness-Aware Coreset SelectionZihao Cheng, Binrui Wu, Zhiwei Li, Yuesen Liao, Su Zhao, Shuai Chen, Yuan Gao, Weizhong Zhang. [doi]
• From Indicators to Insights: Diversity-Optimized for Medical Series-Text Decoding via LLMsXiyuan Jin, Jing Wang 0060, Ziwei Lin, Qianru Jia, Yuqing Huang, Xiaojun Ning 0001, Zhonghua Shi, Youfang Lin. [doi]
• Cross City Traffic Flow Generation via Retrieval Augmented Diffusion ModelYudong Li, Jingyuan Wang, Xie Yu, Peiyu Wang, Qian Huang. [doi]
• GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface ReconstructionJiahe Li 0007, Jiawei Zhang, Youmin Zhang 0005, Xiao Bai 0001, Jin Zheng, Xiaohan Yu 0001, Lin Gu 0003. [doi]
• XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT ModulationBowen Chen, Brynn zhao, Haomiao Sun, Li Chen, Xu Wang, Daniel K. Du, Xinglong Wu. [doi]
• Learning Robust Vision-Language Models from Natural Latent SpacesZhangyun Wang, Ni Ding, Aniket Mahanti. [doi]
• Image Editing As Programs with Diffusion ModelsYujia Hu, Songhua Liu, Zhenxiong Tan, Xingyi Yang, Xinchao Wang. [doi]
• ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular DataPatryk Marszalek, Tomasz Kusmierczyk, Witold Wydmanski, Jacek Tabor, Marek Smieja. [doi]
• Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV ReuseRuikun Luo, Changwei Gu, Qiang He 0001, Feifei Chen 0001, Song Wu 0001, Hai Jin 0001, Yun Yang 0001. [doi]
• Self-diffusion for Solving Inverse ProblemsGuanxiong Luo, Shoujin Huang. [doi]
• The Quest for Universal Master Key Filters in DS-CNNsZahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu. [doi]
• Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning DynamicsIndrashis Das, Mahmoud Safari, Steven Adriaensen, Frank Hutter. [doi]
• Imitation Learning with Temporal Logic ConstraintsZining Fan, He Zhu. [doi]
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning ModelsKe-ji, Jiahao Xu, Tian Liang, Qiuzhi Liu, Zhiwei He 0002, Xiaoyuan Liu, Xingyu Chen, Junying Chen, Benyou Wang, Zhaopeng Tu, Haitao Mi, Dong Yu 0001. [doi]
• Orthogonal Contrastive Learning for Multi-Representation fMRI AnalysisTony Yousefnezhad. [doi]
• Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained RewardsHonghao Chen, Xingzhou Lou, Xiaokun Feng, Kaiqi Huang, Xinlong Wang. [doi]
• Implicit Reward as the Bridge: A Unified View of SFT and DPO ConnectionsBo Wang 0084, Qinyuan Cheng, Runyu Peng, Rong Bao, Peiji Li, Qipeng Guo, Linyang Li, Zhiyuan Zeng 0004, Yunhua Zhou, Xipeng Qiu. [doi]
• ProDAG: Projected Variational Inference for Directed Acyclic GraphsRyan Thompson, Edwin V. Bonilla, Robert Kohn. [doi]
• High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable modelValentin Schmutz, Ali Haydaroglu, Shuqi Wang, Yixiao Feng, Matteo Carandini, Kenneth D. Harris. [doi]
• Reasoning Models Better Express Their ConfidenceDongkeun Yoon, Seungone Kim, Sohee Yang, Sunkyoung Kim 0002, Soyeon Kim, Yongil Kim, Eunbi Choi, Yireun Kim, Minjoon Seo. [doi]
• λ-Orthogonality Regularization for Compatible Representation LearningSimone Ricci, Niccolò Biondi, Federico Pernici, Ioannis Patras, Alberto Del Bimbo. [doi]
• GoalLadder: Incremental Goal Discovery with Vision-Language ModelsAlexey Zakharov, Shimon Whiteson. [doi]
• Mitigating Semantic Collapse in Partially Relevant Video RetrievalWonJun Moon, Minseok Jung, Gilhan Park, Tae-young Kim, Cheol-Ho Cho, Woojin Jun, Jae-Pil Heo. [doi]
• Spark Transformer: Reactivating Sparsity in Transformer FFN and AttentionChong You, Kan Wu, Zhipeng Jia, Lin Chen 0003, Srinadh Bhojanapalli, Jiaxian Guo, Utku Evci, Jan Wassenberg, Praneeth Netrapalli, Jeremiah Willcock, Suvinay Subramanian, Felix Chern, Alek Andreev, Shreya Pathak, Felix X. Yu, Prateek Jain 0002, David E. Culler, Henry M. Levy, Sanjiv Kumar. [doi]
• CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan ReconstructionYiyi Liu, Chunyang Liu, Bohan Wang, Weiqin Jiao, Bojian Wu, Lubin Fan, Yuwei Chen, Fashuai Li, Biao Xiong. [doi]
• Sample-Conditional Coverage in Split-Conformal PredictionJohn C. Duchi. [doi]
• miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path ForwardAzim Ospanov, Farzan Farnia, Roozbeh Mohit. [doi]
• Asymmetric Duos: Sidekicks Improve UncertaintyTim G. Zhou, Evan Shelhamer, Geoff Pleiss. [doi]
• Revisiting Logit Distributions for Reliable Out-of-Distribution DetectionJiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang 0001, Shiguang Shan, Xilin Chen 0001. [doi]
• Fast Last-Iterate Convergence of SGD in the Smooth Interpolation RegimeAmit Attia, Matan Schliserman, Uri Sherman, Tomer Koren. [doi]
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement LearningMingyang Chen 0002, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang 0015, Huajun Chen, Fan Yang 0132, Zenan Zhou, Weipeng Chen. [doi]
• Predicting the Performance of Black-box Language Models with Follow-up QueriesDylan Sam, Marc Finzi, Zico Kolter. [doi]
• Learning Latent Variable Models via Jarzynski-adjusted Langevin AlgorithmJames Cuin, Davide Carbone, O. Deniz Akyildiz. [doi]
• EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity UnderstandingEge Özsoy, Arda Mamur, Felix Tristram, Chantal Pellegrini, Magdalena Wysocki, Benjamin Busam, Nassir Navab. [doi]
• SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQLYue Gong, Chuan Lei, Xiao Qin, Kapil Vaidya, Balakrishnan Narayanaswamy, Tim Kraska. [doi]
• Smoothed Differentiation Efficiently Mitigates Shattered Gradients in ExplanationsAdrian Hill, Neal McKee, Johannes Maeß, Stefan Bluecher, Klaus-Robert Müller. [doi]
• RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement LearningHao Gao, Shaoyu Chen, Bo Jiang 0011, Bencheng Liao, Yiang Shi, Xiaoyang Guo, Yuechuan Pu, Haoran Yin, Xiangyu Li, Xinbang Zhang, Ying Zhang, Wenyu Liu 0001, Qian Zhang 0001, Xinggang Wang. [doi]
• Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and OptimizationJiaqi Wei, Hao Zhou 0012, Xiang Zhang 0028, Di Zhang 0026, Zijie Qiu, Noah Wei, Jinzhe Li, Wanli Ouyang, Siqi Sun. [doi]
• The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification PerspectiveHaixiang Lan, Luofeng Liao, Adam N. Elmachtoub, Christian Kroer, Henry Lam, Haofeng Zhang 0002. [doi]
• Imbalances in Neurosymbolic Learning: Characterization and Mitigating StrategiesEfthymia Tsamoura, Kaifu Wang, Dan Roth 0001. [doi]
• Multimodal Bandits: Regret Lower Bounds and Optimal AlgorithmsWilliam Réveillard, Richard Combes. [doi]
• GenSpace: Benchmarking Spatially-Aware Image GenerationZehan Wang 0001, Jiayang Xu, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao 0001. [doi]
• MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video PreferenceHaibo Tong, Zhaoyang Wang 0004, Zhaorun Chen, Haonian Ji, Shi Qiu 0016, Siwei Han, Kexin Geng, Zhongkai Xue, Yiyang Zhou, Peng Xia 0005, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao. [doi]
• Optimal Neural Compressors for the Rate-Distortion-Perception TradeoffEric Lei, Hamed Hassani, Shirin Saeedi Bidokhti. [doi]
• Bio-Inspired Image RestorationYuning Cui 0001, Wenqi Ren, Alois Knoll. [doi]
• Towards Understanding Transformers in Learning Random WalksWei Shi, Yuan Cao. [doi]
• Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary NoiseSangli Teng, Harry Zhang, David Jin, Ashkan Jasour, Ram Vasudevan, Maani Ghaffari, Luca Carlone. [doi]
• Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score ModelsTaehoon Yoon, Yunhong Min, Kyeongmin Yeo, Minhyuk Sung. [doi]
• Multimodal Negative LearningBaoquan Gong, Xiyuan Gao, Pengfei Zhu 0001, Qinghua Hu, Bing Cao 0002. [doi]
• Graph Persistence goes SpectralMattie Ji, Amauri H. Souza, Vikas Garg 0001. [doi]
• Don't Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language ModelsZitong Shi, Frank Wan, Haixin Wang 0003, Ruoyan Li, Zijie Huang 0002, Wanjia Zhao, Yijia Xiao, Xiao Luo 0001, Carl Yang 0001, Yizhou Sun, Wei Wang 0010. [doi]
• Decomposing Interventional Causality into Synergistic, Redundant, and Unique ComponentsAbel Jansma. [doi]
• Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural NetworksRyien Hosseini, Filippo Simini, Venkatram Vishwanath, Rebecca Willett, Henry Hoffmann. [doi]
• Test-Time Adaptive Object Detection with Foundation ModelYingjie Gao 0001, Yanan Zhang 0005, Zhi Cai, Di Huang 0001. [doi]
• Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-TuningZailong Tian, Zhuoheng Han, Houfeng Wang, Lizi Liao. [doi]
• What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive HypothesesFederico D'Agostino, Lisa Schwetlick, Matthias Bethge, Matthias Kümmerer. [doi]
• On Evaluating Policies for Robust POMDPsMerlijn Krale, Eline M. Bovy, Maris F. L. Galesloot, Thiago D. Simão, Nils Jansen 0001. [doi]
• OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene RepresentationsChristina Kassab, Sacha Morin, Martin Büchner, Matías Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon. [doi]
• Retrospective In-Context Learning for Temporal Credit Assignment with Large Language ModelsWen-Tse Chen, Jiayu Chen, Fahim Tajwar, Hao Zhu 0011, Xintong Duan, Ruslan Salakhutdinov, Jeff G. Schneider. [doi]
• HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of ExpertsYinuo Jiang, Xiaodong Yan, Keyan Ding, Deng Zhao, Lei Liang 0002, Qiang Zhang 0026, Huajun Chen. [doi]
• Distributional Autoencoders Know the ScoreAndrej Leban. [doi]
• Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal BandsVasiliki Tassopoulou, Charis J. Stamouli, Haochang Shou, George J. Pappas, Christos Davatzikos. [doi]
• SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset CondensationHe Yang, Dongyi Lv, Song Ma, Wei Xi 0003, Jizhong Zhao. [doi]
• CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language ModelsXiao An, Jiaxing Sun 0001, Zihan Gui, Wei He 0003. [doi]
• Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex BoundaryChuyu Zhou, Tianyu Li, Chenxi Lan, Rongyu Du, Guoguo Xin, Wei Li, Guoqing Wang, Xun Liu, Hangzhou Yang. [doi]
• Compositional Reasoning with Transformers, RNNs, and Chain of ThoughtGilad Yehudai, Noah Amsel, Joan Bruna. [doi]
• A Gradient Guided Diffusion Framework for Chance Constrained ProgrammingBoyang Zhang, Zhiguo Wang, Ya-Feng Liu. [doi]
• Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language ModelsLing Li, Yao Zhou, Yuxuan Liang 0002, Fugee Tsung, Jiaheng Wei. [doi]
• Test-Time Adaptation by Causal TrimmingYingnan Liu 0002, Rui Qiao, Mong-Li Lee, Wynne Hsu. [doi]
• Boosting Resilience of Large Language Models through Causality-Driven Robust OptimizationXiaoling Zhou, Mingjie Zhang, Zhemg Lee, Yuncheng Hua, Chengli Xing, Wei Ye 0004, Flora D. Salim, Shikun Zhang. [doi]
• Iterative Self-Incentivization Empowers Large Language Models as Agentic SearchersZhengliang Shi, Lingyong Yan, Dawei Yin 0001, Suzan Verberne, Maarten de Rijke, Zhaochun Ren. [doi]
• MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow NetworksRui Jiao, Hanlin Wu, Wenbing Huang 0001, Yuxuan Song 0002, Yawen Ouyang, Yu Rong 0001, Tingyang Xu, Pengju Wang, Hao Zhou 0012, Wei-Ying Ma, Jingjing Liu, Yang Liu. [doi]
• MAP Estimation with Denoisers: Convergence Rates and GuaranteesScott Pesme, Giacomo Meanti, Michael Arbel, Julien Mairal. [doi]
• Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative ModelingMichal Balcerak, Tamaz Amiranashvili, Antonio Terpin, Suprosanna Shit, Lea Bogensperger, Sebastian Kaltenbach, Petros Koumoutsakos, Bjoern Menze. [doi]
• Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete ScenariosShengju Yu, Pei Zhang 0008, Siwei Wang 0001, Suyuan Liu, Xinhang Wan, Zhibin Dong, Tiejun Li, Xinwang Liu 0002. [doi]
• Token Embeddings Violate the Manifold HypothesisMichael Robinson 0001, Sourya Dey, Tony Chiang. [doi]
• Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored AdaptationWeibin Liao, Tianlong Wang, Yinghao Zhu, Yasha Wang, Junyi Gao, Liantao Ma. [doi]
• Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive BenchmarkHanlei Zhang, Zhuohang Li, Hua Xu 0003, Yeshuang Zhu, Peiwu Wang, Haige Zhu, Jie Zhou 0016, Jinchao Zhang 0001. [doi]
• KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network InferenceRui Peng, Yuchen Lu, Qichen Sun, Yuxing Lu, Chi Zhang, Ziru Liu, Jinzhuo Wang. [doi]
• Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with LandingKijung Jeon, Michael Muehlebach, Molei Tao. [doi]
• A Minimalist Example of Edge-of-Stability and Progressive SharpeningLiming Liu, Zixuan Zhang, Simon S. Du, Tuo Zhao. [doi]
• Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response FunctionsZhaoxian Wu, Quan Xiao, Tayfun Gokmen, Omobayode Fagbohungbe, Tianyi Chen 0002. [doi]
• The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 EducationDevan Walton, Haesol Bae. [doi]
• 3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMsMehdi Makni, Xiang Meng, Rahul Mazumder. [doi]
• Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture InfillingShuhong Zheng, Ashkan Mirzaei, Igor Gilitschenski. [doi]
• DGH: Dynamic Gaussian HairJunying Wang, Yuanlu Xu, Edith Tretschk, Ziyan Wang, Anastasia Ianina, Aljaz Bozic, Ulrich Neumann, Tony Tung. [doi]
• An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower BoundsSiyu Chen, Theodor Misiakiewicz, Ilias Zadik, Peiyuan Zhang. [doi]
• Meta-Learning Objectives for Preference OptimizationCarlo Alfano, Silvia Sapora, Jakob N. Foerster, Patrick Rebeschini, Yee Whye Teh. [doi]
• TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot LearningXudong Yan, Songhe Feng. [doi]
• Fast exact recovery of noisy matrix from few entries: the infinity norm approachBaoLinh Tran, Van Vu. [doi]
• Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative CompletionXiaojian Ding, Lin Zhao, Xian Li, Xiaoying Zhu. [doi]
• Mixture of Noise for Pre-Trained Model-Based Class-Incremental LearningKai Jiang, Zhengyan Shi, Dell Zhang, Hongyuan Zhang 0001, Xuelong Li 0001. [doi]
• Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and ClassificationZinan Lin 0001, Enshu Liu, Xuefei Ning, Junyi Zhu 0002, Wenyu Wang, Sergey Yekhanin. [doi]
• Statistical Inference under PerformativityXiang Li, Yunai Li, Huiying Zhong, Lihua Lei, Zhun Deng. [doi]
• 1)-Smoothness: Normalization and MomentumSarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin, Eduard Gorbunov, Peter Richtárik. [doi]
• Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow ModelsYingqing Guo, Yukang Yang, Hui Yuan 0002, Mengdi Wang 0001. [doi]
• Modeling Neural Activity with Conditionally Linear Dynamical SystemsVictor Geadah, Amin Nejatbakhsh, David Lipshutz, Jonathan W. Pillow, Alex H. Williams. [doi]
• Attention (as Discrete-Time Markov) ChainsYotam Erel, Olaf Dünkel, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, Amit Bermano. [doi]
• Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray AnalysisJing Hao, Yuxuan Fan, Yanpeng Sun, Kaixin Guo, Lizhuo Lin, Jinrong Yang, Qi Yong H. Ai, Lun M. Wong, Hao Tang 0005, Kuo Feng Hung. [doi]
• Computable universal online learningDariusz Kalocinski, Tomasz Steifer. [doi]
• High-Order Flow Matching: Unified Framework and Sharp Statistical RatesMaojiang Su, Jerry Yao-Chieh Hu, Yi-Chen Lee, Ning Zhu, Jui-Hui Chung, Shang Wu, Zhao Song 0002, Minshuo Chen, Han Liu 0001. [doi]
• Differentiable Constraint-Based Causal DiscoveryJincheng Zhou, Mengbo Wang 0001, Anqi He, Yumeng Zhou, Hessam Olya, Murat Kocaoglu, Bruno Ribeiro 0001. [doi]
• Towards Generalizable Detector for Generated ImageQianshu Cai, Chao Wu 0001, Yonggang Zhang 0003, Jun Yu 0002, Xinmei Tian 0001. [doi]
• Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal ModelsXu Yang, Chen Liu, Ying Wei. [doi]
• OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and DataHao Luo 0011, Zihao Yue, Wanpeng Zhang 0002, Yicheng Feng, Sipeng Zheng, Deheng Ye, Zongqing Lu 0002. [doi]
• SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAIYuzhou Nie, Zhun Wang, Yu Yang 0007, Ruizhe Jiang, Yuheng Tang, Xander Davies, Yarin Gal, Bo Li 0026, Wenbo Guo 0002, Dawn Song. [doi]
• Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation ConsistencyRenzhao Liang, Sizhe Xu 0001, Chenggang Xie, Jingru Chen, Feiyang Ren, Shu Yang, Takahiro Yabe. [doi]
• Block Coordinate Descent for Neural Networks Provably Finds Global MinimaShunta Akiyama. [doi]
• Permissioned LLMs: Enforcing Access Control in Large Language ModelsBargav Jayaraman, Virendra J. Marathe, Hamid Mozaffari, William F. Shen, Krishnaram Kenthapadi. [doi]
• Self supervised learning for in vivo localization of microelectrode arrays using raw local field potentialTianxiao He, Malhar Patel, Chenyi Li, Anna Maslarova, Mihály Vöröslakos, Nalini Ramanathan, Wei-Lun Hung, György Buzsáki, Erdem Varol. [doi]
• Visual Jenga: Discovering Object Dependencies via Counterfactual InpaintingAnand Bhattad, Konpat Preechakul, Alexei A. Efros. [doi]
• SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic UltrasoundYunke Ao, Masoud Moghani, Mayank Mittal, Manish Prajapat, Luohong Wu, Frédéric Giraud 0002, Fabio Carrillo, Andreas Krause 0001, Philipp Fürnstahl. [doi]
• Breaking the Performance Ceiling in Reinforcement Learning requires Inference StrategiesFélix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan John de Kock, Juan Claude Formanek, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Simon du Toit, Louay Ben Nessir, Refiloe Shabe, Arnol Fokam, Siddarth Singh, Ulrich A. Mbou Sob, Arnu Pretorius. [doi]
• Learning to cluster neuronal functionNina Nellen, Polina Turishcheva, Michaela Vystrcilová, Shashwat Sridhar, Tim Gollisch, Andreas S. Tolias, Alexander S. Ecker. [doi]
• The φ Curve: The Shape of Generalization through the Lens of Norm-based Capacity ControlYichen Wang, Yudong Chen 0001, Lorenzo Rosasco, Fanghui Liu 0001. [doi]
• CausalPFN: Amortized Causal Effect Estimation via In-Context LearningVahid Balazadeh Meresht, Hamidreza Kamkari, Valentin Thomas, Junwei Ma, Bingru Li, Jesse C. Cresswell, Rahul G. Krishnan. [doi]
• Non-Convex Tensor Recovery from Tube-Wise SensingTongle Wu, Ying Sun 0003. [doi]
• Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time AdaptationJingmin Zhu, Anqi Zhu, Hossein Rahmani 0001, Jun Liu 0036, Mohammed Bennamoun, Qiuhong Ke. [doi]
• From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field MicroscopyFeng He, Guodong Tan, Qiankun Li, Jun Yu, Quan Wen. [doi]
• FlexWorld: Progressively Expanding 3D Scenes for Flexible-View ExplorationLuxi Chen, Zihan Zhou, Min Zhao 0013, Yikai Wang, Ge Zhang 0009, Wenhao Huang 0001, Hao Sun 0002, Ji-Rong Wen, Chongxuan Li. [doi]
• Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM ReasoningJiwon Song, Dongwon Jo, Yulhwa Kim, Jae-Joon Kim. [doi]
• DeCaFlow: A deconfounding causal generative modelAlejandro Almodóvar, Adrián Javaloy, Juan Parras, Santiago Zazo, Isabel Valera. [doi]
• Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS DatasetMing-Hsiu Wu, Ziqian Xie, Shuiwang Ji, Degui Zhi. [doi]
• Rewind-to-Delete: Certified Machine Unlearning for Nonconvex FunctionsSiqiao Mu, Diego Klabjan. [doi]
• PINNs with Learnable QuadratureSourav Pal, Kamyar Azizzadenesheli, Vikas Singh. [doi]
• VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) ManifoldDominic Maggio, Hyungtae Lim, Luca Carlone. [doi]
• UniRelight: Learning Joint Decomposition and Synthesis for Video RelightingKai He, Ruofan Liang, Jacob Munkberg, Jon Hasselgren, Nandita Vijaykumar, Alexander Keller 0001, Sanja Fidler, Igor Gilitschenski, Zan Gojcic, Zian Wang. [doi]
• SnapMoGen: Human Motion Generation from Expressive TextsChuan Guo 0002, Inwoo Hwang, Jian Wang 0100, Bing Zhou 0001. [doi]
• Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse PlasticityHugo Ninou, Jonathan Kadmon, N. Alex Cayco-Gajic. [doi]
• Prediction-Powered Causal InferencesRiccardo Cadei, Ilker Demirel, Piersilvio De Bartolomeis, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, Francesco Locatello. [doi]
• QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy PredictionSicheng Zuo, Wenzhao Zheng, Xiaoyong Han, Longchao Yang, Yong Pan, Jiwen Lu. [doi]
• OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance ReconstructionJie Yan, Jing Liu, Zhong-Yuan Zhang. [doi]
• BecomingLit: Relightable Gaussian Avatars with Hybrid Neural ShadingJonathan Schmidt 0002, Simon Giebenhain, Matthias Nießner. [doi]
• Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement LearningHongjoon Ahn, Heewoong Choi, Jisu Han, Taesup Moon. [doi]
• Uncertainty-Sensitive Privileged LearningFan-Ming Luo, Lei Yuan 0005, Yang Yu 0001. [doi]
• Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph PredictionKunHo Heo, Gihyun Kim, Suyeon Kim, MyeongAh Cho. [doi]
• Neural EntropyAkhil Premkumar. [doi]
• Random Forest Autoencoders for Guided Representation LearningAdrien Aumon, Shuang Ni, Myriam Lizotte, Guy Wolf, Kevin J. Moon, Jake S. Rhodes. [doi]
• Novel View Synthesis from A Few Glimpses via Test-Time Natural Video CompletionYan Xu, Yixing Wang, Stella X. Yu. [doi]
• Just One Layer Norm Guarantees Stable ExtrapolationJuliusz Ziomek, George Whittle, Michael A. Osborne. [doi]
• TV-Rec: Time-Variant Convolutional Filter for Sequential RecommendationYehjin Shin, Jeongwhan Choi 0002, Seojin Kim, Noseong Park. [doi]
• GMV: A Unified and Efficient Graph Multi-View Learning FrameworkQipeng Zhu, Jie Chen, Jian Pu, Junping Zhang. [doi]
• Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement LearningHaolin Pan, Hongyu Lin, Haoran Luo, Yang Liu, Kaichun Yao, Libo Zhang 0001, Mingjie Xing, Yanjun Wu. [doi]
• Constrained Diffusers for Safe Planning and ControlJichen Zhang, Liqun Zhao, Antonis Papachristodoulou, Jack Umenberger. [doi]
• On Evaluating LLM Alignment by Evaluating LLMs as JudgesYixin Liu 0003, Pengfei Liu 0003, Arman Cohan. [doi]
• MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual CorrespondenceYue Feng, Jinwei Hu, Qijia Lu, Jiawei Niu, Li Tan, Shuo Yuan, Ziyi Yan, Yizhen Jia, Qingzhi He, Shiping Ge, Ethan Q. Chen, Wentong Li 0001, Limin Wang 0002, Jie Qin 0004. [doi]
• LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image SegmentationMd Mostafijur Rahman, Radu Marculescu. [doi]
• Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation LearningYijin Ni, Xiaoming Huo. [doi]
• Power Lines: Scaling laws for weight decay and batch size in LLM pre-trainingShane Bergsma, Nolan Dey, Gurpreet Gosal, Gavia Gray, Daria Soboleva, Joel Hestness. [doi]
• Logic.py: Bridging the Gap between LLMs and Constraint SolversPascal Kesseli, Peter W. O'Hearn, Ricardo Silveira Cabral. [doi]
• Memory-Enhanced Neural Solvers for Routing ProblemsFélix Chalumeau, Refiloe Shabe, Noah de Nicola, Arnu Pretorius, Tom Barrett, Nathan Grinsztajn. [doi]
• Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in TransformersAndrew Nam, Henry Conklin, Yukang Yang, Tom Griffiths 0001, Jonathan D. Cohen 0003, Sarah-Jane Leslie. [doi]
• SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement LearningXinbin Yuan, Jian-Jun Zhang, Kaixin Li, Zhuoxuan Cai, Lujian Yao, Jie Chen, Enguang Wang, Qibin Hou, Jinwei Chen 0003, Peng-Tao Jiang, Bo Li 0026. [doi]
• Path-Enhanced Contrastive Learning for RecommendationHaoran Sun, Fei Xiong, Yuanzhe Hu, Liang Wang 0017. [doi]
• HypoBootstrap: A Bootstrapping Framework for Inductive ReasoningSi Chen, Yifei Li, Richong Zhang. [doi]
• Risk Management for Mitigating Benchmark Failure Modes: BenchRiskSean McGregor, Vassil Tashev, Armstrong Foundjem, Aishwarya Ramasethu, Sadegh AlMahdi Kazemi Zarkouei, Chris Knotz, Kongtao Chen, Alicia Parrish, Anka Reuel-Lamparth, Heather Frase. [doi]
• CAM: A Constructivist View of Agentic Memory for LLM-Based Reading ComprehensionRui Li 0086, Zeyu Zhang 0007, Xiaohe Bo, Zihang Tian, Xu Chen 0017, Quanyu Dai, Zhenhua Dong, Ruiming Tang. [doi]
• Grids Often Outperform Implicit Neural Representation at Compressing Dense SignalsNamhoon Kim, Sara Fridovich-Keil. [doi]
• When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment InteractionsZhuo Cao, Heming Du, Bingqing Zhang, Xin Yu 0002, Xue Li 0001, Sen Wang 0001. [doi]
• ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich ManipulationJiawen Yu, Hairuo Liu, Qiaojun Yu, Jieji Ren, Ce Hao, Haitong Ding, Guangyu Huang, Guofan Huang, Yan Song, Panpan Cai, Wenqiang Zhang, Cewu Lu. [doi]
• VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to RankTianhe Wu, Jian Zou, Jie Liang 0007, Lei Zhang 0006, Kede Ma. [doi]
• QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language ModelsYutong Wang, Haiyu Wang, Sai Qian Zhang. [doi]
• SPOT: Scalable Policy Optimization with Trees for Markov Decision ProcessesXuyuan Xiong, Pedro Chumpitaz-Flores, Kaixun Hua, Cheng Hua. [doi]
• TRUST: Test-Time Refinement using Uncertainty-Guided SSM TraversesSahar Dastani, Ali Bahri, Gustavo Adolfo Vargas Hakim, Moslem Yazdanpanah, Mehrdad Noori, David Osowiechi, Samuel Barbeau, Ismail Ben Ayed, Herve Lombaert, Christian Desrosiers. [doi]
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base ModelJingcheng Hu, Yinmin Zhang, Qi Han, Daxin Jiang, Xiangyu Zhang 0005, Heung-Yeung Shum. [doi]
• Single-Step Operator Learning for Conditioned Time-Series Diffusion ModelsHui Chen, Vikas Singh. [doi]
• BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR SegmentationYujia Chen, Rui Sun 0006, Wangkai Li, Huayu Mai, Si Chen, Zhuoyuan Li, Zhixin Cheng, Tianzhu Zhang 0001. [doi]
• FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-ExpertsHeming Zou, Yunliang Zang, Wutong Xu, Yao Zhu, Xiangyang Ji. [doi]
• Space Group Equivariant Crystal DiffusionRees Chang, Angela Pak, Alex Guerra, Ni Zhan 0001, Nick Richardson, Elif Ertekin, Ryan P. Adams. [doi]
• Photography Perspective Composition: Towards Aesthetic Perspective RecommendationLujian Yao, Siming Zheng, Xinbin Yuan, Zhuoxuan Cai, Pu Wu, Jinwei Chen 0003, Bo Li 0026, Peng-Tao Jiang. [doi]
• Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioningAlexander Bodard, Panagiotis Patrinos. [doi]
• Searching Efficient Semantic Segmentation Architectures via Dynamic Path SelectionYuxi Liu 0019, Min Liu 0008, Shuai Jiang, Yi Tang, Yaonan Wang 0001. [doi]
• Limited Preference Data? Learning Better Reward Model with Latent Space SynthesisLeitian Tao, Xuefeng Du, Sharon Li 0001. [doi]
• Preserving Task-Relevant Information Under Linear Concept RemovalFloris Holstege, Shauli Ravfogel, Bram Wouters. [doi]
• Momentum Multi-Marginal Schrödinger Bridge MatchingPanagiotis Theodoropoulos, Augustinos D. Saravanos, Evangelos A. Theodorou, Guan-Horng Liu. [doi]
• Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance ReweightingRuyi An, Haicheng Huang, Huangjie Zheng, Mingyuan Zhou. [doi]
• RetrievalAttention: Accelerating Long-Context LLM Inference via Vector RetrievalDi Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen 0009, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen 0067, Fan Yang 0024, Yuqing Yang 0001, Lili Qiu. [doi]
• NeuSymEA: Neuro-symbolic Entity Alignment via Variational InferenceShengyuan Chen, Zheng Yuan 0013, Qinggang Zhang, Wen-hua, Jiannong Cao 0001, Xiao Huang 0001. [doi]
• Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domainsShizheng Wen, Arsh Kumbhat, Levi E. Lingsch, Sepehr Mousavi, Yizhou Zhao, Praveen Chandrashekar, Siddhartha Mishra. [doi]
• Analyzing Similarity Metrics for Data Selection for Language Model PretrainingDylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh, Srikumar Ramalingam, Gui Citovsky, Sanjiv Kumar. [doi]
• VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace ExpansionJaekyun Park, Hye Won Chung. [doi]
• Pessimistic Data Integration for Policy EvaluationXiangkun Wu, Ting Li, Gholamali Aminian, Armin Behnamnia, Hamid R. Rabiee 0001, Chengchun Shi. [doi]
• RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian LanguagesSaurabh Kumar, Abhayjeet Singh, Deekshitha G, Amartya Veer, Jesuraj Bandekar, Savitha Murthy, Sumit Sharma 0016, Sandhya Badiger, Sathvik Udupa, Amala Nagireddi, Srinivasa Raghavan K. M., Rohan Saxena, Jai Nanavati, Raoul Nanavati, Janani Sridharan, Arjun Singh Mehta, Ashish Seth, Sai Praneeth Reddy Mora, Prashanthi V, Gauri Date, Karthika P, Prasanta Kumar Ghosh. [doi]
• Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" TrackRylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch, Brando Miranda, Matthias Gerstgrasser, Susan Zhang, Andreas Haupt, Isha Gupta, Elyas Obbad, Jesse Dodge, Jessica Zosa Forde, Francesco Orabona, Sanmi Koyejo, David L. Donoho. [doi]
• The Promise of RL for Autoregressive Image EditingSaba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodríguez, Sai Rajeswar Mudumba, Siva Reddy, Chris Pal, Benno Krojer, Aishwarya Agrawal. [doi]
• UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal SystemsTingzhu Bi, Yicheng Pan 0002, Xinrui Jiang 0001, Huize Sun, Meng Ma 0001, Ping Wang 0003. [doi]
• Sharper Convergence Rates for Nonconvex Optimisation via Reduction MappingsEvan Markou, Thalaiyasingam Ajanthan, Stephen Gould. [doi]
• Scaling Computer-Use Grounding via User Interface Decomposition and SynthesisTianbao Xie, Jiaqi Deng, Xiaochuan Li 0003, Junlin Yang, Haoyuan Wu, Jixuan Chen, Wenjing Hu, Xinyuan Wang 0010, Yuhui Xu, Zekun Wang, Yiheng Xu, Junli Wang, Doyen Sahoo, Tao Yu 0009, Caiming Xiong. [doi]
• ConceptScope: Characterizing Dataset Bias via Disentangled Visual ConceptsJinho Choi 0005, Hyesu Lim, Steffen Schneider 0004, Jaegul Choo. [doi]
• T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic PlanningAmartya Chakraborty, Paresh Dashore, Nadia Bathaee, Anmol Jain, Anirban Das, Shi-Xiong Zhang, Sambit Sahu, Milind R. Naphade, Genta Indra Winata. [doi]
• Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian SplattingYu Chen, Rolandos-Alexandros Potamias, Evangelos Ververas, Jifei Song, Jiankang deng, Gim Hee Lee. [doi]
• On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series ForecastingYisong Fu, Fei Wang 0014, Zezhi Shao, Boyu Diao, Lin Wu 0006, Zhulin An, Chengqing Yu, Yujie Li 0008, Yongjun Xu 0001. [doi]
• Scalable Evaluation and Neural Models for Compositional GeneralizationGiacomo Camposampiero, Pietro Barbiero, Michael Hersche, Roger Wattenhofer, Abbas Rahimi. [doi]
• Variational Supervised Contrastive LearningZiwen Wang, Jiajun Fan, Thao Nguyen, Heng Ji 0001, Ge Liu. [doi]
• UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View SynthesisThanh Tung Le, Tuan Pham, Tung Nguyen, Deying Kong, Xiaohui Xie, Stephan Mandt. [doi]
• HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph LearningFrank Wan, Xiaoran Shang, Yuxin Wu, Guibin Zhang, Jinhe Bi, Liangtao Zheng, Xin Lin, Yue Liu, Yanbiao Ma, Wenke Huang 0003, Bo Du 0001. [doi]
• Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for RecommendationLeqi Zheng, Chaokun Wang, Zixin Song, Cheng Wu 0004, Shannan Yan, Jiajun Zhang 0012, Ziyang Liu 0004. [doi]
• FedRACE: A Hierarchical and Statistical Framework for Robust Federated LearningGang Yan, Sikai Yang, Wan Du. [doi]
• EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion RecognitionChristoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby, Maurice Kraus, Felix Friedrich, Huu Nguyen, Krishna Kalyan, Kourosh Nadi, Kristian Kersting, Sören Auer. [doi]
• Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural NetworksChaoyue Liu, Han Bi, Like Hui, Xiao Liu. [doi]
• The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame PredictionHuming Qiu, Zhaoxiang Wang, Mi Zhang, Xiaohan Zhang, Xiaoyu You, Min Yang 0002. [doi]
• Practical and Effective Code Watermarking for Large Language ModelsZhimeng Guo, Minhao Cheng. [doi]
• LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-TuningJunyu Chen, Junzhuo Li, Zhen Peng, Wenjie Wang, Yuxiang Ren, Long Shi, Xuming Hu. [doi]
• Neural Attention SearchDifan Deng, Marius Lindauer. [doi]
• Offline Actor-Critic for Average Reward MDPsWilliam G. Powell, Jeongyeol Kwon, Qiaomin Xie, Hanbaek Lyu. [doi]
• AutoToM: Scaling Model-based Mental Inference via Automated Agent ModelingZhining Zhang 0001, Chuanyang Jin, Mung Yao Jia, Shunchi Zhang, Tianmin Shu. [doi]
• Scalable Signature Kernel Computations via Local Neumann Series ExpansionsMatthew Tamayo-Rios, Alexander Schell, Rima Alaifari. [doi]
• Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD DrawingsXingguang Wei, Haomin Wang 0002, Shenglong Ye, Ruifeng Luo, Yanting Zhang, Lixin Gu, Jifeng Dai, Yu Qiao 0001, Wenhai Wang, Hongjie Zhang 0002. [doi]
• InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic LayoutsWeipeng Zhong, Peizhou Cao, Yichen Jin, Li Ray Luo, Wenzhe Cai, Jingli Lin, Hanqing Wang, Zhaoyang Lyu, Tai Wang, Xudong Xu, Bo Dai 0002, Jiangmiao Pang. [doi]
• Tensor-Parallelism with Partially Synchronized ActivationsItay Lamprecht, Asaf Karnieli, Yair Hanani, Niv Giladi, Daniel Soudry. [doi]
• Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous DrivingHaohong Lin, Yunzhi Zhang, Wenhao Ding, Jiajun Wu, Ding Zhao. [doi]
• LLM Interpretability with Identifiable Temporal-Instantaneous RepresentationXiangchen Song, Jiaqi Sun, Zijian Li 0001, Yujia Zheng 0001, Kun Zhang 0001. [doi]
• Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD AlgorithmClément Bénard. [doi]
• Listening to the Brain: Multi-Band sEEG Auditory Reconstruction via Dynamic Spatio-Temporal HypergraphsXueyi Zhang 0001, Ruicong Wang, Jialu Sun, Siqi Cai 0002, Haizhou Li 0001. [doi]
• Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian SplattingHyeongmin Lee, Kyungjune Baek. [doi]
• Distributionally Robust Performative OptimizationZhuangzhuang Jia, Yijie Wang, Roy Dong, Grani A. Hanasusanto. [doi]
• DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible PatchesYun Xing, Yue Cao, Nhat Chung, Jie M. Zhang, Ivor W. Tsang, Ming-Ming Cheng, Yang Liu 0003, Lei Ma 0003, Qing Guo 0005. [doi]
• One Token Embedding Is Enough to Deadlock Your Large Reasoning ModelMohan Zhang, Yihua Zhang, Jinghan Jia, Zhangyang (Atlas) Wang, Sijia Liu 0001, Tianlong Chen 0001. [doi]
• Information Retrieval Induced Safety Degradation in AI AgentsCheng Yu, Benedikt Stroebl, Diyi Yang, Orestis Papakyriakopoulos. [doi]
• Extrapolation by Association: Length Generalization Transfer In TransformersZiyang Cai, Nayoung Lee, Avi Schwarzschild, Samet Oymak, Dimitris Papailiopoulos. [doi]
• Conformal Prediction for Time-series Forecasting with Change PointsSophia Sun, Rose Yu. [doi]
• Neural Rule Lists: Learning Discretizations, Rules, and Order in One GoSascha Xu, Nils Philipp Walter, Jilles Vreeken. [doi]
• PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural NetworksPengyun Yue, Xuanlin Yang, Mingqing Xiao 0002, Zhouchen Lin. [doi]
• No-Regret Online Autobidding Algorithms in First-price AuctionsYilin Li, Yuan Deng, Wei Tang, Hanrui Zhang 0001. [doi]
• TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised LearningHongyang He, Xinyuan Song 0002, Yangfan He, Zeyu Zhang, Yanshu Li, Haochen You, Lifan Sun, Wenqiao Zhang. [doi]
• Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python CodeAugusto B. Corrêa, André Grahl Pereira, Jendrik Seipp. [doi]
• Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's LawFrederik Kunstner, Francis Bach 0001. [doi]
• Looking Into the Water by Unsupervised Learning of the Surface ShapeOri Lifschitz, Tali Treibitz, Dan Rosenbaum. [doi]
• SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert IdentificationZhenglin Lai, MengYao Liao, Bingzhe Wu, Dong Xu 0023, Zebin Zhao 0007, Zhihang Yuan, Chao Fan, JianQiang Li. [doi]
• Think Only When You Need with Large Hybrid-Reasoning ModelsLingjie Jiang, Xun Wu, Shaohan Huang, Qingxiu Dong, Zewen Chi, Li Dong 0004, Xingxing Zhang 0002, Tengchao Lv, Lei Cui 0001, Furu Wei. [doi]
• Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent KernelYilan Chen 0002, Zhichao Wang, Wei Huang 0034, Andi Han, Taiji Suzuki, Arya Mazumdar. [doi]
• A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal InferenceHarsh Parikh, Trang Quynh Nguyen, Elizabeth A. Stuart, Kara E. Rudolph, Caleb H. Miles. [doi]
• Fast Data Attribution for Text-to-Image ModelsSheng-yu Wang, Aaron Hertzmann, Alexei A. Efros, Richard Zhang 0001, Jun-Yan Zhu. [doi]
• Generalizable Reasoning through Compositional Energy MinimizationAlexandru Oarga, Yilun Du. [doi]
• Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised LearningJiawei Gu, Yidi Wang, Qingqiang Sun, Xinming Li, Xiao Luo 0001, Ziyue Qiao. [doi]
• Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?Jean Philippe Monteuuis, Cong Chen, Jonathan Petit. [doi]
• Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data SchedulerZixuan Hu, Li Shen 0008, Zhenyi Wang 0001, Yongxian Wei, Dacheng Tao. [doi]
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action ModelsYantai Yang, Yuhao Wang, Zichen Wen, Luo Zhongwei, Chang Zou, Zhipeng Zhang, Chuan Wen, Linfeng Zhang 0001. [doi]
• Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient ClippingMartin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan Honza Silovsky, Kunal Talwar, Christopher Brinton 0001, Tatiana Likhomanenko. [doi]
• One-Step Diffusion-Based Image Compression with Semantic DistillationNaifu Xue, Zhaoyang Jia, Jiahao Li 0001, Bin Li 0012, Yuan Zhang, Yan Lu 0001. [doi]
• Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models PretrainingPing Guo, Yubing Ren, Binbin Liu, Fengze Liu, Haobin Lin, Yifan Zhang, Bingni Zhang, Taifeng Wang, Yin Zheng. [doi]
• ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU DesignQijun Zhang, Yao Lu 0031, Mengming Li, Shang Liu 0006, Zhiyao Xie. [doi]
• GenPO: Generative Diffusion Models Meet On-Policy Reinforcement LearningShutong Ding, Ke Hu, Shan Zhong, Haoyang Luo, Weinan Zhang 0001, Jingya Wang 0001, Jun Wang, Ye Shi 0001. [doi]
• Near-Exponential Savings for Population Mean Estimation with Active LearningJulian M. Morimoto, Jacob Goldin, Daniel E. Ho. [doi]
• Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss LandscapesWei-Kai Chang, Rajiv Khanna. [doi]
• Accelerating Optimization via Differentiable Stopping TimeZhonglin Xie, Yiman Fong, Haoran Yuan, Zaiwen Wen. [doi]
• STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential DataMaximilian Forstenhäusler, Daniel Külzer, Christos Anagnostopoulos 0001, Shameem Puthiya Parambath, Natascha Weber. [doi]
• Detecting High-Stakes Interactions with Activation ProbesAlex McKenzie, Urja Pawar, Phil Blandfort, William Bankes, David Krueger 0001, Ekdeep Singh Lubana, Dmitrii Krasheninnikov. [doi]
• GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion PoliciesZiye Wang, Li Kang, Yiran Qin, Jiahua Ma, Zhanglin Peng, Lei Bai 0001, Ruimao Zhang. [doi]
• EUGens: Efficient, Unified and General Dense LayersSang-Min Kim, Byeongchan Kim, Arijit Sehanobish, Somnath Basu Roy Chowdhury, Rahul Kidambi, Dongseok Shim, Kumar Avinava Dubey, Snigdha Chaturvedi, Min-hwan Oh, Krzysztof Marcin Choromanski. [doi]
• BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal DynamicsZhongju Yuan, Geraint A. Wiggins, Dick Botteldooren. [doi]
• MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment RetrievalHuaying Yuan, Jian Ni, Zheng Liu 0011, Yueze Wang, Junjie Zhou 0001, Zhengyang Liang, Bo Zhao 0015, Zhao Cao, Ji-Rong Wen, Zhicheng Dou. [doi]
• Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal AssistantsLixiong Qin, Shilong Ou, Miaoxuan Zhang, Jiangning Wei, Yuhang Zhang, Xiaoshuai Song, Yuchen Liu, Mei Wang, Weiran Xu. [doi]
• DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous DrivingShuyao Shang, YunTao Chen, Yuqi Wang 0001, Yingyan Li, Zhao-Xiang Zhang 0001. [doi]
• Over-squashing in Spatiotemporal Graph Neural NetworksIvan Marisca, Jacob Bamberger, Cesare Alippi, Michael M. Bronstein. [doi]
• Variational Regularized Unbalanced Optimal Transport: Single Network, Least ActionYuhao Sun, Zhenyi Zhang, Zihan Wang, Tiejun Li, Peijie Zhou. [doi]
• Large Language Diffusion ModelsShen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, Jun Zhou 0011, Yankai Lin 0001, Ji-Rong Wen, Chongxuan Li. [doi]
• Any-stepsize Gradient Descent for Separable Data under Fenchel-Young LossesHan Bao 0002, Shinsaku Sakaue, Yuki Takezawa. [doi]
• Fully Spiking Neural Networks for Unified Frame-Event Object TrackingJingjun Yang, Liangwei Fan, Jinpu Zhang, Xiangkai Lian, Hui Shen 0004, Dewen Hu. [doi]
• Learning to Generalize: An Information Perspective on Neural ProcessesHui Li, Huafeng Liu 0001, Shuyang Lin, Jingyue Shi, Yiran Fu, Liping Jing. [doi]
• Generative Caching for Structurally Similar Prompts and ResponsesSarthak Chakraborty, Suman Nath, Xuchao Zhang, Chetan Bansal, Indranil Gupta. [doi]
• XIFBench: Evaluating Large Language Models on Multilingual Instruction FollowingZhenyu Li, Kehai Chen, Yunfei Long, Xuefeng Bai 0001, Yaoyin Zhang, Xuchen Wei, Juntao Li 0005, Min Zhang 0005. [doi]
• Structural Causal Bandits under Markov EquivalenceMin Woo Park, Andy Arditi, Elias Bareinboim, Sanghack Lee. [doi]
• Toward Interpretable Evaluation Measures for Time Series SegmentationFélix Chavelli, Paul Boniol, Michaël Thomazo. [doi]
• Can Class-Priors Help Single-Positive Multi-Label Learning?Biao Liu, Ning Xu 0009, Jie Wang, Xin Geng 0001. [doi]
• Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context RetentionXin Zou 0001, Di Lu, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Xu Zheng 0002, Linfeng Zhang 0001, Xuming Hu. [doi]
• A Unified Framework for Provably Efficient Algorithms to Estimate Shapley ValuesTyler Chen, Akshay Seshadri, Mattia Jacopo Villani, Pradeep Niroula, Shouvanik Chakrabarti, Archan Ray, Pranav Deshpande, Romina Yalovetzky, Marco Pistoia, Niraj Kumar 0005. [doi]
• Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge DistillationDail Kim, Joon-Hyuk Chang. [doi]
• Robust Ego-Exo Correspondence with Long-Term MemoryYijun Hu, Bing Fan, Xin Gu 0003, Haiqing Ren, Dongfang Liu, Heng Fan 0001, Libo Zhang 0001. [doi]
• SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D TrackingShubo Lin, Yutong Kou, Zirui Wu, Shaoru Wang, Bing Li 0001, Weiming Hu 0004, Jin Gao. [doi]
• A unified framework for establishing the universal approximation of transformer-type architecturesJingpu Cheng, Ting Lin, Zuowei Shen, Qianxiao Li. [doi]
• Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian SplattingYiren Lu 0002, Yunlai Zhou, Yiran Qiao 0001, Chaoda Song, Tuo Liang, Jing Ma 0002, Huan Wang 0014, Yu Yin 0001. [doi]
• MultiScale Contextual Bandits for Long Term ObjectivesRicha Rastogi, Yuta Saito, Thorsten Joachims. [doi]
• Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent CooperationQihe Huang, Zhengyang Zhou, Yangze Li, Kuo Yang 0002, Binwu Wang, Yang Wang. [doi]
• Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teamingAlexandra Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna M. Wallach. [doi]
• Eulerian Neural Network Informed by Chemical Transport for Air Quality ForecastingXukai Zhang, Shuliang Wang 0001, Guangyin Jin, Ziqiang Yuan, Hanning Yuan, Sijie Ruan. [doi]
• The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic NetworksVittorio Erba, Emanuele Troiani, Lenka Zdeborová, Florent Krzakala. [doi]
• Contextual Thompson Sampling via Generation of Missing DataKelly W. Zhang, Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo 0001. [doi]
• Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual TokensBohan Wang, Mingze Zhou, Zhongqi Yue, Wang Lin, Kaihang Pan, Liyu Jia, Wentao Hu, Wei Zhao, Hanwang Zhang. [doi]
• CLEAR: Command Level Annotated Dataset for Ransomware DetectionBarak Bringoltz, Elisha Halperin, Ran Feraru, Evgeny Blaichman, Amit Berman. [doi]
• MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in OncologyKiril Vasilev, Alexandre Misrahi, Eeshaan Jain, Phil F. Cheng, Petros Liakopoulos, Olivier Michielin, Michael Moor, Charlotte Bunne. [doi]
• Q-Insight: Understanding Image Quality via Visual Reinforcement LearningWeiqi Li, Xuanyu Zhang, Shijie Zhao, Yabin Zhang, Junlin Li, Li Zhang, Jian-Jun Zhang. [doi]
• Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet ArchitecturesShuqing Luo, Ye Han, Pingzhi Li, Jiayin Qin, Jie Peng 0002, Yang Zhao 0013, Yu Cao 0001, Tianlong Chen 0001. [doi]
• Procurement Auctions with Predictions: Improved Frugality for Facility LocationEric Balkanski, Nicholas DeFilippis, Vasilis Gkatzelis, Xizhi Tan. [doi]
• Re-ttention: Ultra Sparse Visual Generation via Attention Statistical ReshapeRuichen Chen, Keith G. Mills, Liyao Jiang, Chao Gao 0012, Di Niu 0002. [doi]
• Audio Super-Resolution with Latent Bridge ModelsChang Li, Zehua Chen 0005, Liyuan Wang, Jun Zhu 0001. [doi]
• From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in TransformersRyotaro Kawata, Yujin Song, Alberto Bietti, Naoki Nishikawa, Taiji Suzuki, Samuel Vaiter, Denny Wu. [doi]
• Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context LearningHaolin Yang 0003, Hakaze Cho, Yiqiao Zhong, Naoya Inoue. [doi]
• Linearization Explains Fine-Tuning in Large Language ModelsZahra Rahimi Afzal, Tara Esmaeilbeig, Mojtaba Soltanalian, Mesrob I. Ohannessian. [doi]
• Causally Reliable Concept Bottleneck ModelsGiovanni de Felice, Arianna Casanova Flores, Francesco De Santis, Silvia Santini, Johannes Schneider, Pietro Barbiero, Alberto Termine. [doi]
• Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural NetworksKorneel Van den Berghe, Stein Stroobants, Vijay Janapa Reddi, Guido de Croon. [doi]
• Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical ReasoningFeng Chen 0046, Allan Raventós, Nan Cheng, Surya Ganguli, Shaul Druckmann. [doi]
• Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited DataAndrew C. Li, Toryn Q. Klassen, Andrew Wang, Parand A. Alamdari, Sheila A. McIlraith. [doi]
• Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM AgentsQizheng Zhang, Michael Wornow, Kunle Olukotun. [doi]
• Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group CodingHanyin Wang, Zhenbang Wu, Gururaj Kolar, Hariprasad Korsapati, Brian Bartlett, Bryan Hull, Jimeng Sun 0001. [doi]
• Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion ModelsMichael Plainer, Hao Wu 0035, Leon Klein, Stephan Günnemann, Frank Noé. [doi]
• Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL BanditsYuxuan Han, José H. Blanchet, Zhengyuan Zhou. [doi]
• More effort is needed to protect pedestrian privacy in the era of AIXingchen Zhang, Zixian Zhao 0001. [doi]
• DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance ConcentrationTianteng Gu, Bei Liu 0003, Bo Xiao, Ke Zeng, Jiacheng Liu, Yanmin Qian. [doi]
• Demystifying Language Model Forgetting with Low-rank Example AssociationsXisen Jin, Xiang Ren 0001. [doi]
• Learning Skill-Attributes for Transferable Assessment in VideoKumar Ashutosh, Kristen Grauman. [doi]
• LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient RenderingJonas Kulhanek, Marie-Julie Rakotosaona, Fabian Manhardt, Christina Tsalicoglou, Michael Niemeyer, Torsten Sattler, Songyou Peng, Federico Tombari. [doi]
• HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person ScenariosKunyu Peng, Junchao Huang, Xiangsheng Huang, Di Wen 0006, Junwei Zheng, Yufan Chen 0001, Kailun Yang 0001, Jiamin Wu, Chongqing Hao, Rainer Stiefelhagen. [doi]
• Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise DifferentialsYifan Pu, Jixuan Ying, Qixiu Li, Tianzhu Ye, Dongchen Han, Xiaochen Wang, Ziyi Wang, Xinyu Shao, Gao Huang 0001, Xiu Li 0001. [doi]
• Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental DesignAndreas Schlaginhaufen, Reda Ouhamma, Maryam Kamgarpour. [doi]
• Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled LearningXiming Li 0002, Yuanchao Dai, Bing Wang 0018, Changchun Li, Jianfeng Qu, Renchu Guan. [doi]
• CCL: Causal-aware In-context Learning for Out-of-Distribution GeneralizationHoyoon Byun, Gyeongdeok Seo, Joonseong Kang, Taero Kim, Jihee Kim, Kyungwoo Song. [doi]
• PROFIT: A Specialized Optimizer for Deep Fine TuningAnirudh Srinivasan Chakravarthy, Shuai Kyle Zheng, Xin Huang, Sachithra Hemachandra, Xiao Zhang, Yuning Chai, Zhao Chen. [doi]
• LILO: Learning to Reason at the Frontier of LearnabilityThomas Foster, Anya Sims, Johannes Forkel, Jakob N. Foerster. [doi]
• GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNsAmir Ghazizadeh, Rickard Ewetz, Hao Zheng 0005. [doi]
• ShotBench: Expert-Level Cinematic Understanding in Vision-Language ModelsHongbo Liu, Jingwen He, Yi Jin, Dian Zheng, Yuhao Dong, Fan Zhang 0045, Ziqi Huang, Yinan He, Weichao Chen 0001, Yu Qiao 0001, Wanli Ouyang, Shengjie Zhao 0001, Ziwei Liu 0002. [doi]
• An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy AnnotationsSeonghwan Park 0003, Jueun Mun, Donghyun Oh, Namhoon Lee. [doi]
• Variational Task Vector CompositionBoyuan Zhang, Yingjun Du, Xiantong Zhen, Ling Shao 0001. [doi]
• Learning Stochastic Multiscale ModelsAndrew F. Ilersich, Prasanth Nair 0001. [doi]
• Analytic Energy-Guided Policy Optimization for Offline Reinforcement LearningJifeng Hu, Sili Huang, Zhejian Yang, Shengchao Hu, Li Shen 0008, Hechang Chen, Lichao Sun 0001, Yi Chang 0001, Dacheng Tao. [doi]
• Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model ComplexityMouïn Ben Ammar, David Brellmann, Arturo Mendoza, Antoine Manzanera, Gianni Franchi. [doi]
• ChatbotID: Identifying Chatbots with Granger Causality TestXiaoquan Yi, Haozhao Wang, Yining Qi, Wenchao Xu 0001, Rui Zhang 0003, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index ModelsIlias Diakonikolas, Giannis Iakovidis, Daniel Kane 0001, Lisheng Ren. [doi]
• VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement LearningLi Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu 0001, Philip H. S. Torr, Lei Bai 0001, Zhenfei Yin. [doi]
• UFM: A Simple Path towards Unified Dense Correspondence with FlowYuchen Zhang, Nikhil Varma Keetha, Chenwei Lyu, Bhuvan Jhamb, Yutian Chen, Yuheng Qiu, Jay Karhade, Shreyas Jha, Yaoyu Hu, Deva Ramanan, Sebastian A. Scherer, Wenshan Wang. [doi]
• ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied TasksPhilip Schroeder, Ondrej Biza, Thomas Weng, Hongyin Luo, Jim Glass 0001. [doi]
• Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-IdentificationZhongao Zhou, Bin Yang 0026, Wenke Huang 0003, Jun Chen 0001, Mang Ye. [doi]
• Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset SamplingJinhee Kim, Jae Jun An, Kang Eun Jeon, Jong Hwan Ko. [doi]
• InvisibleInk: High-Utility and Low-Cost Text Generation with Differential PrivacyVishnu Vinod, Krishna Pillutla, Abhradeep Guha Thakurta. [doi]
• Coloring Learning for Heterophilic Graph RepresentationMiaomiao Huang, Yuhai Zhao, Daniel Zhengkui Wang, Fenglong Ma, Yejiang Wang, Meixia Wang, Xingwei Wang 0001. [doi]
• Towards A Generalist Code Embedding Model Based On Massive Data SynthesisChaofan Li, Jianlyu Chen, Yingxia Shao, Defu Lian, Zheng Liu 0011. [doi]
• From Style to Facts: Mapping the Boundaries of Knowledge Injection with FinetuningEric Zhao 0003, Pranjal Awasthi, Nika Haghtalab. [doi]
• Continuous Thought MachinesLuke Darlow, Ciaran Regan, Sebastian Risi, Jeffrey Seely, Llion Jones. [doi]
• Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial RobustnessLongwei Wang, Ifrat Ikhtear Uddin, Kc Santosh, Chaowei Zhang, Xiao Qin, Yang Zhou. [doi]
• Bridging Theory and Practice in Link Representation with Graph Neural NetworksVeronica Lachi, Francesco Ferrini, Antonio Longa, Bruno Lepri, Andrea Passerini, Manfred Jaeger. [doi]
• Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and BeyondFeng Zhu, David Simchi-Levi. [doi]
• Toward Relative Positional Encoding in Spiking TransformersChangze Lv, Yansen Wang, Dongqi Han, Yifei Shen 0004, Xiaoqing Zheng, Xuanjing Huang 0001, Dongsheng Li 0002. [doi]
• Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based ModelsLouis Béthune, David Vigouroux, Yilun Du, Rufin VanRullen, Thomas Serre, Victor Boutin. [doi]
• FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRASongqi Zhou, Zeyuan Liu, Benben Jiang. [doi]
• Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D DetectionJianyu Wang, Yu Wang, Shengjie Zhao, Sifan Zhou. [doi]
• Characterizing control between interacting subsystems with deep Jacobian estimationAdam Eisen, Mitchell Ostrow, Sarthak Chandra, Leo Kozachkov, Earl K. Miller, Ila Fiete. [doi]
• Differentiable Cyclic Causal Discovery Under Unmeasured ConfoundersMuralikrishnna G. Sethuraman, Faramarz Fekri. [doi]
• Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer EraFeng Lu, Tong Jin, Canming Ye, Xiangyuan Lan, Yunpeng Liu 0001, Chun Yuan 0003. [doi]
• SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human ReconstructionWenyue Chen, Peng Li, Wangguandong Zheng, Chengfeng Zhao, Mengfei Li, Yaolong Zhu, Zhiyang Dou, Ronggang Wang, Yuan Liu. [doi]
• No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi 0001, Nicola Gatti 0001, Christian Kroer. [doi]
• LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?Ziyuan He, Yuxuan Wang, Jiaqi Li, Kexin Liang, Muhan Zhang. [doi]
• Generalized Category Discovery under Domain Shift: A Frequency Domain PerspectiveWei Feng 0015, ZongYuan Ge. [doi]
• Unveiling Environmental Sensitivity of Individual Gains in Influence MaximizationXinyan Su, Zhiheng Zhang, Jiyan Qiu, Zhaojuan Yue, Jun Li 0002. [doi]
• xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar MemoriesMaurice Kraus, Felix Divo, Devendra Singh Dhami, Kristian Kersting. [doi]
• Maximizing the Value of Predictions in Control: Accuracy Is Not EnoughYiheng Lin 0001, Christopher Yeh, Zaiwei Chen, Adam Wierman. [doi]
• SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only PassesYifan Yang, Zhen Zhang, Rupak Vignesh Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang. [doi]
• Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic LensSamuele Bortolotti, Emanuele Marconato, Paolo Morettin, Andrea Passerini, Stefano Teso. [doi]
• LoRASuite: Efficient LoRA Adaptation Across Large Language Model UpgradesYanan Li, Fanxu Meng 0003, Muhan Zhang, Shiai Zhu, Shangguang Wang, Mengwei Xu 0001. [doi]
• HELM: Hyperbolic Large Language Models via Mixture-of-Curvature ExpertsNeil He, Rishabh Anand, Hiren Madhu, Ali Maatouk, Smita Krishnaswamy, Leandros Tassiulas, Menglin Yang 0001, Rex Ying. [doi]
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial IntelligenceDiankun Wu, Fangfu Liu, Yi-Hsin Hung, Yueqi Duan. [doi]
• Unveiling the Compositional Ability Gap in Vision-Language Reasoning ModelTianle Li, Jihai Zhang, Yongming Rao, Yu Cheng. [doi]
• Dual-Comb Ghost Imaging with Transformer-Based Reconstruction for Optical Fiber EndomicroscopyDavid Dang, Myoung-Gyun Suh, Maodong Gao, Byoung-Jun Park, Beyonce Hu, Yucheng Jin, Wilton J. M. Kort-Kamp, Ho Wai Lee. [doi]
• SeasonBench-EA: A Multi-Source Benchmark for Seasonal Prediction and Numerical Model Post-Processing in East AsiaMengxuan Chen, Guowen Li, Ziheng Zou, Fang Wang, Jinxiao Zhang, Runmin Dong, Juepeng Zheng, Haohuan Fu. [doi]
• Rendering-Aware Reinforcement Learning for Vector Graphics GenerationJuan A. Rodríguez, Haotian Zhang, Abhay Puri, Rishav Pramanik, Aarash Feizi, Pascal Wichmann, Arnab Kumar Mondal, Mohammad Reza Samsami, Rabiul Awal, Perouz Taslakian, Spandana Gella, Sai Rajeswar Mudumba, David Vázquez 0001, Chris Pal, Marco Pedersoli. [doi]
• Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial ComplexesWei Wu, Xuan Tan, Yan Peng, Ling Chen, Fangfang Li 0004, Chuan Luo 0002. [doi]
• InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction ModelJunqi You, Chieh Hubert Lin, Weijie Lyu, Zhengbo Zhang, Ming-Hsuan Yang 0001. [doi]
• Adaptive Prediction-Powered AutoEval with Reliability and Efficiency GuaranteesSangwoo Park 0002, Matteo Zecchin, Osvaldo Simeone. [doi]
• What We Miss Matters: Learning from the Overlooked in Point Cloud TransformersYi Wang, Jiaze Wang, Ziyu Guo, Renrui Zhang, Donghao Zhou, Guangyong Chen, Anfeng Liu, Pheng-Ann Heng. [doi]
• STree: Speculative Tree Decoding for Hybrid State Space ModelsYangchao Wu, Zongyue Qin, Alex Wong 0001, Stefano Soatto. [doi]
• Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text DescriptionsJihoon Kwon, Kyle Min 0002, Jy-yong Sohn. [doi]
• Autoregressive Adversarial Post-Training for Real-Time Interactive Video GenerationShanchuan Lin, Ceyuan Yang, Hao He, Jianwen Jiang, Yuxi Ren, Xin Xia 0005, Yang Zhao 0003, Xuefeng Xiao 0001, Lu Jiang. [doi]
• Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural MotifsShih-Hsin Wang, Yuhao Huang, Taos Transue, Justin M. Baker, Jonathan Forstater, Thomas Strohmer, Bao Wang 0001. [doi]
• AdmTree: Compressing Lengthy Context with Adaptive Semantic TreesYangning Li, Shaoshen Chen, Yinghui Li, Yankai Chen 0001, Hai-Tao Zheng 0002, Hui Wang 0030, Wenhao Jiang, Philip S. Yu. [doi]
• GUI-Actor: Coordinate-Free Visual Grounding for GUI AgentsQianhui Wu, Kanzhi Cheng, Rui Yang 0010, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao 0001, Reuben Tan, Si-qin, Lars Liden, Qingwei Lin, Huan Zhang 0001, Tong Zhang 0001, Jianbing Zhang, Dongmei Zhang 0001, Jianfeng Gao 0001. [doi]
• Generative Pre-trained Autoregressive Diffusion TransformerYuan Zhang, Jiacheng Jiang, Guoqing Ma, Zhiying Lu, Bo Wang, Haoyang Huang, Jianlong Yuan, Nan Duan 0001. [doi]
• Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-TuningXiaoyu Yang, Jie Lu 0001, En Yu. [doi]
• Off-policy Reinforcement Learning with Model-based Exploration AugmentationLikun Wang, Xiangteng Zhang, Yinuo Wang, Guojian Zhan, Wenxuan Wang 0004, Haoyu Gao, Jingliang Duan, Shengbo Eben Li. [doi]
• DreamPRM: Domain-reweighted Process Reward Model for Multimodal ReasoningQi Cao, Ruiyi Wang, Ruiyi Zhang, Sai Ashish Somayajula, Pengtao Xie. [doi]
• Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual LearningFei Ye 0004, Yulong Zhao, Qihe Liu, JunLin Chen, Adrian G. Bors, Jingling Sun, Rongyao Hu, Shijie Zhou 0002. [doi]
• Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter ItYulu Qin, Dheeraj Varghese, Adam Dahlgren Lindström, Lucia Donatelli, Kanishka Misra, Najoung Kim. [doi]
• ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics SynthesisChuang Wang 0008, Haitao Zhou, Ling Luo, Qian Yu 0002. [doi]
• Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian OptimizationShogo Iwazaki. [doi]
• Position: Require Frontier AI Labs To Release Small "Analog" ModelsShriyash Upadhyay, Philip Quirke, Narmeen Oozeer, Chaithanya Bandi. [doi]
• Estimating cognitive biases with attention-aware inverse planningSounak Banerjee 0002, Daphne Cornelisse, Deepak E. Gopinath, Emily Sumner, Jonathan A. DeCastro, Guy Rosman, Eugene Vinitsky, Mark K. Ho. [doi]
• MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial ReasoningJinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi 0002, Yichen Jin, Zhaoyang Lyu, Feng Zheng 0001, Lizhuang Ma, Jiangmiao Pang. [doi]
• RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use AgentsJingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao. [doi]
• FreeInv: Free Lunch for Improving DDIM InversionYuxiang Bao, Huijie Liu, Xun Gao, Huan Fu, Guoliang Kang. [doi]
• RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled DataWenchao Ma, Dario Kneubuehler, Maurice Chu, Ian Sachs, Haomiao Jiang, Sharon X. Huang. [doi]
• The Rich and the Simple: On the Implicit Bias of Adam and SGDBhavya Vasudeva, Jung Hoon Lee, Vatsal Sharan, Mahdi Soltanolkotabi. [doi]
• DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision AssignmentSangwoo Kwon, Seong Hoon Seo, Jae W. Lee, Yeonhong Park. [doi]
• Born a Transformer - Always a Transformer? On the Effect of Pretraining on Architectural AbilitiesMayank Jobanputra, Yana Veitsman, Yash Raj Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn 0001. [doi]
• Evaluating LLMs in Open-Source GamesSwadesh Sistla, Max Kleiman-Weiner. [doi]
• Low Rank Gradients and Where to Find ThemRishi Sonthalia, Michael Murray, Guido F. Montúfar. [doi]
• Dual-Path Temporal Decoder for End-to-End Multi-Object TrackingHyunseop Kim, Juheon Jeong, Hanul Kim 0001, Yeong Jun Koh. [doi]
• A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image RegressionGiuseppe Castiglione, Christopher L. Buckley, Ivor Simpson. [doi]
• Understanding Contrastive Learning via Gaussian Mixture ModelsParikshit Bansal, Ali Kavis, Sujay Sanghavi. [doi]
• Robust Satisficing Gaussian Process Bandits Under Adversarial AttacksArtun Saday, Yasar Cahit Yildirim, Cem Tekin. [doi]
• DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural ImagesOzgur Kara, Harris Nisar, James M. Rehg. [doi]
• Representational Difference ExplanationsNeehar Kondapaneni, Oisin Mac Aodha, Pietro Perona. [doi]
• MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution ShiftsMahmoud Selim, Sriharsha Vishnu Bhat, Karl Henrik Johansson. [doi]
• Implicit Bias of Spectal Descent and Muon on Multiclass Separable DataChen Fan, Mark Schmidt 0001, Christos Thrampoulidis. [doi]
• PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric NetworkMingyao Zhou, Hao Sun 0014, Wei Xie 0008, Ming Dong 0004, Chengji Wang, Mang Ye. [doi]
• RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language ModelsJunda Zhu 0003, Jun Ai, Yujun Li, Yichun Yin, Yasheng Wang, Lifeng Shang, Qun Liu 0001. [doi]
• FLAME: Fast Long-context Adaptive Memory for Event-based VisionBiswadeep Chakraborty, Saibal Mukhopadhyay. [doi]
• Robust and Computation-Aware Gaussian ProcessesMarshal Arijona Sinaga, Julien Martinelli, Samuel Kaski. [doi]
• BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLMWen Xiong, Junzhong Ji, Jin-Duo Liu. [doi]
• GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and EditingRongyao Fang, Chengqi Duan, Kun Wang 0056, Linjiang Huang, Hao Li 0069, Hao Tian 0006, Shilin Yan, Weihao Yu 0005, Xingyu Zeng, Jifeng Dai, Xihui Liu, Hongsheng Li 0001. [doi]
• A Geometry-Aware Metric for Mode Collapse in Time Series Generative ModelsYassine Abbahaddou, Amine Mohamed Aboussalah. [doi]
• Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital HealthPavel Dolin, Weizhi Li, Gautam Dasarathy, Visar Berisha. [doi]
• RayFusion: Ray Fusion Enhanced Collaborative Visual PerceptionShaohong Wang, Lu Bin, Xinyu Xiao, Hanzhi Zhong, Bowen Pang, Tong Wang, Zhiyu Xiang, Hangguan Shan, Eryun Liu. [doi]
• SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM ReasoningXiao Liang, Zhong-Zhi Li, Yeyun Gong, Yang Wang, Hengyuan Zhang, Yelong Shen, Ying Nian Wu, Weizhu Chen. [doi]
• Inference with correlated priors using sisters cellsSina Tootoonian, Andreas T. Schaefer. [doi]
• Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language ModelsZekai Zhao, Qi Liu, Kun Zhou 0002, Zihan Liu, Yifei Shao, Zhiting Hu, Biwei Huang. [doi]
• When No Paths Lead to Rome: Benchmarking Systematic Neural Relational ReasoningAnirban Das, Irtaza Khalid, Rafael Peñaloza, Steven Schockaert. [doi]
• REP: Resource-Efficient Prompting for Rehearsal-Free Continual LearningSungho Jeon 0005, Xinyue Ma, Kwang In Kim, Myeongjae Jeon. [doi]
• Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global ConstraintsLing Zhan 0001, Junjie Huang, Xiaoyao Yu, Wenyu Chen 0004, Tao Jia 0001. [doi]
• Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior DynamicsZhenbin Wang, Lei Zhang, Wei Huang, Zhao Zhang, Zizhou Wang. [doi]
• Perturbation Bounds for Low-Rank Inverse Approximations under NoisePhuc Tran, Nisheeth K. Vishnoi. [doi]
• On the Hardness of Conditional Independence Testing In PracticeZheng He, Roman Pogodin, Yazhe Li, Namrata Deka, Arthur Gretton, Danica J. Sutherland. [doi]
• Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting ModelXiaoyang Zhang 0002, Fang He 0001, Yang Deng 0004, Dan Wang 0002. [doi]
• Fairness-aware Anomaly Detection via Fair ProjectionFeng Xiao, Xiaoying Tang, Jicong Fan 0001. [doi]
• ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic ScenesJiaye Fu, Qiankun Gao, Chengxiang Wen, Yanmin Wu, Siwei Ma 0001, Jiaqi Zhang, Jian-Jun Zhang. [doi]
• Rotary Masked Autoencoders are Versatile LearnersUros Zivanovic, Serafina Di Gioia, Andre Scaffidi, Martín de los Rios, Gabriella Contardo, Roberto Trotta. [doi]
• Safely Learning Controlled Stochastic DynamicsLuc Brogat-Motte, Alessandro Rudi, Riccardo Bonalli. [doi]
• Thompson Sampling for Multi-Objective Linear Contextual BanditSomangchan Park, Heesang Ann, Min-hwan Oh. [doi]
• L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree BiasJingxiao Zhang, Shifei Ding, Jian-Jun Zhang, Lili Guo 0001, Xuan Li 0004. [doi]
• A Semantic Parsing Framework for End-to-End Time NormalizationXin Su 0008, Sungduk Yu, Phillip Howard, Steven Bethard. [doi]
• Differentiable extensions with rounding guarantees for combinatorial optimization over permutationsRobert R. Nerem, Zhishang Luo, Akbar Rafiey, Yusu Wang 0001. [doi]
• Interactive Cross-modal Learning for Text-3D Scene RetrievalYanglin Feng, Yongxiang Li, Yuan Sun 0016, Yang Qin, Dezhong Peng, Peng Hu 0002. [doi]
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMsZhenhailong Wang, Senthil Purushwalkam, Caiming Xiong, Silvio Savarese, Heng Ji 0001, Ran Xu 0001. [doi]
• Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic RecommendationQing Yu 0004, Xiaobei Wang, Shuchang Liu 0001, Yandong Bai, Xiaoyu Yang, Xueliang Wang, Chang Meng, Shanshan Wu, Hailan Yang, Bin Wen, Huihui Xiao, Xiang Li 0189, Fan Yang 0094, Xiaoqiang Feng, Lantao Hu, Han Li 0005, Kun Gai, Lixin Zou. [doi]
• Probabilistic Stability Guarantees for Feature AttributionsHelen Jin, Anton Xue, Weiqiu You, Surbhi Goel, Eric Wong 0001. [doi]
• From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space RegularizationShoaib Ahmed Siddiqui, Adrian Weller, David Krueger 0001, Gintare Karolina Dziugaite, Michael C. Mozer, Eleni Triantafillou. [doi]
• BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-IdentificationXiaobin Liu, Jianing Li, Baiwei Guo, Wenbin Zhu, Jing Yuan. [doi]
• Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge TransferQiannan Zhang, Manqi Zhou, Zilong Bai, Chang Su 0002, Fei Wang 0001. [doi]
• Timely Clinical Diagnosis through Active Test SelectionSilas Ruhrberg Estévez, Nicolás Astorga, Mihaela van der Schaar. [doi]
• 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular VideosMengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee. [doi]
• VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept SetShufan Shen, Junshu Sun, Qingming Huang, Shuhui Wang. [doi]
• Parallelizing MCMC Across the Sequence LengthDavid M. Zoltowski, Skyler Wu, Xavier Gonzalez, Leo Kozachkov, Scott W. Linderman. [doi]
• FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion GenerationZeyu Zhang 0006, Yiran Wang, Danning Li, Dong Gong, Ian Reid 0001, Richard Hartley 0001. [doi]
• Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation LearningZihao Jing, Yan Sun, Yan Yi Li, Sugitha Janarthanan, Alana Deng, Pingzhao Hu. [doi]
• Infrequent Exploration in Linear BanditsHarin Lee, Min-hwan Oh. [doi]
• AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric ScienceChenyue Li, Wen Deng, Mengqian Lu, Binhang Yuan. [doi]
• A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical StudyYuanchao Dai, Zhengzhang Hou, Changchun Li, Yuanbo Xu, En Wang, Ximing Li 0002. [doi]
• Self-Improving Embodied Foundation ModelsSeyed Kamyar Seyed Ghasemipour, Ayzaan Wahid, Jonathan Tompson, Pannag Sanketi, Igor Mordatch. [doi]
• Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated LearningZhuang Qi, Pan Yu, Lei Meng 0001, Sijin Zhou, Han Yu 0001, Xiaoxiao Li, Xiangxu Meng. [doi]
• Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning ModelsYuheng Tang, Hongwei Li 0025, Kaijie Zhu, Michael Yang, Yangruibo Ding, Wenbo Guo 0002. [doi]
• BLEUBERI: BLEU is a surprisingly effective reward for instruction followingYapei Chang, Yekyung Kim, Michael Krumdick, Amir Zadeh, Chuan Li, Chris Tanner, Mohit Iyyer. [doi]
• Fast constrained sampling in pre-trained diffusion modelsAlexandros Graikos, Nebojsa Jojic, Dimitris Samaras. [doi]
• Learning from Delayed Feedback in Games via Extra PredictionYuma Fujimoto, Kenshi Abe, Kaito Ariu. [doi]
• Transfer Learning for Benign Overfitting in High-Dimensional Linear RegressionYeichan Kim, Ilmun Kim, Seyoung Park. [doi]
• Sample Complexity of Distributionally Robust Average-Reward Reinforcement LearningZijun Chen, Shengbo Wang, Nian Si. [doi]
• Size-adaptive Hypothesis Testing for FairnessAntonio Ferrara 0003, Francesco Cozzi, Alan Perotti, André Panisson, Francesco Bonchi. [doi]
• A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang 0003. [doi]
• IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial ScenariosYifan Li, Yuhang Chen, Anh Dao, Lichi Li, Zhongyi Cai, Zhen Tan 0001, Tianlong Chen 0001, Yu Kong 0001. [doi]
• Learning Differential Pyramid Representation for Tone MappingQirui Yang, Yinbo Li, Yihao Liu 0001, Peng-Tao Jiang, Fangpu Zhang, Qihua Cheng, Huanjing Yue, Jingyu Yang 0002. [doi]
• 4KAgent: Agentic Any Image to 4K Super-ResolutionYushen Zuo, Qi Zheng 0004, Mingyang Wu, Xinrui Jiang, Renjie Li 0003, Jian Wang 0100, Yide Zhang, Gengchen Mai, Lihong V. Wang, James Y. Zou, Xiaoyu Wang, Ming-Hsuan Yang 0001, Zhengzhong Tu. [doi]
• Are Language Models Efficient Reasoners? A Perspective from Logic ProgrammingAndreas Opedal, Yanick Zengaffinen, Haruki Shirakami, Clemente Pasti, Mrinmaya Sachan, Abulhair Saparov, Ryan Cotterell, Bernhard Schölkopf. [doi]
• IPSI: Enhancing Structural Inference with Automatically Learned Structural PriorsZhongben Gong, Xiaoqun Wu, Mingyang Zhou 0001. [doi]
• EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven AlignmentNaga Sai Abhiram Kusumba, Maitreya Patel, Kyle Min 0001, Changhoon Kim, Chitta Baral, Yezhou Yang. [doi]
• Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable AgentsVijay Veerabadran, Fanyi Xiao, Nitin Kamra, Pedro Matias 0004, Joy Chen, Caley Drooff, Brett Roads, Riley Williams, Ethan Henderson, Xuanyi Zhao, Kevin Carlberg, Joseph Tighe, Karl Ridgeway. [doi]
• FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision ComputingBinrui Shen, Yuan Liang, Shengxin Zhu. [doi]
• SGAR: Structural Generative Augmentation for 3D Human Motion RetrievalJiahang Zhang 0001, Lilang Lin, Shuai Yang 0001, Jiaying Liu 0001. [doi]
• Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data SchedulingHongtao Xu, Wenting Shen, Yuanxin Wei, Ang Wang, Guo Runfan, Tianxing Wang 0006, Yong Li 0045, Mingzhen Li 0001, Weile Jia. [doi]
• POCO: Scalable Neural Forecasting through Population ConditioningYu Duan, Hamza Tahir Chaudhry, Misha B. Ahrens, Christopher D. Harvey, Matthew G. Perich, Karl Deisseroth, Kanaka Rajan. [doi]
• PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving FrameworkWei Lin 0018, Yiwei Zhou, Junkai Zhang, Rui Shao, Zhiyuan Zhao 0005, Junyu Gao 0001, Antoni B. Chan, Xuelong Li 0001. [doi]
• Non-Line-of-Sight 3D Reconstruction with RadarHaoWen Lai, Zitong Lan, Mingmin Zhao. [doi]
• Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural NetworksHan Yu 0001, Lyumin Wu, Wenxin Zhou, Zhao Ren. [doi]
• DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPOJinyoung Park 0005, Jeehye Na, Jinyoung Kim 0007, Hyunwoo J. Kim. [doi]
• Preference Distillation via Value based Reinforcement LearningMinchan Kwon, Junwon Ko, Kangil Kim, Junmo Kim 0002. [doi]
• Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like ModelsDhruva Karkada, James B. Simon, Yasaman Bahri, Michael R. DeWeese. [doi]
• ModuLM: Enabling Modular and Multimodal Molecular Relational Learning with Large Language ModelsZhuo Chen, Yizhen Zheng, Huan Yee Koh, Hongxin Xiang, Linjiang Chen, Wenjie Du 0003, Yang Wang 0015. [doi]
• In-Context Learning of Stochastic Differential Equations with Foundation Inference ModelsPatrick Seifner, Kostadin Cvejoski, David Berghaus, César Ali Ojeda Marin, Ramsés J. Sánchez. [doi]
• Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient AdjustmentWoojun Kim, Katia Sycara. [doi]
• T-REGS: Minimum Spanning Tree Regularization for Self-Supervised LearningJulie Mordacq, David Loiseaux, Vicky Kalogeiton, Steve Oudot. [doi]
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)Liwei Jiang, Yuanjun Chai, Margaret Li, Mickel Liu, Raymond Fok, Nouha Dziri, Yulia Tsvetkov, Maarten Sap, Yejin Choi 0001. [doi]
• Activated LoRA: Fine-tuned LLMs for IntrinsicsKristjan Greenewald, Luis A. Lastras, Thomas Parnell, Vraj Shah, Lucian Popa 0001, Giulio Zizzo, Chulaka Gunasekara, Ambrish Rawat, David Cox 0003. [doi]
• Text to Sketch Generation with Multi-StylesTengjie Li, Shikui Tu, Lei Xu 0001. [doi]
• Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language ModelsSreyan Ghosh, Arushi Goel, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang Gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro. [doi]
• TAPIP3D: Tracking Any Point in Persistent 3D GeometryBowei Zhang, Lei Ke, Adam W. Harley, Katerina Fragkiadaki. [doi]
• Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image ModelsJisung Hwang, Jaihoon Kim, Minhyuk Sung. [doi]
• Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score LearningDechen Zhang, Zhenmei Shi, Yi Zhang, Yingyu Liang, Difan Zou. [doi]
• Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal InterventionHaijing Liu, Zhiyuan Song, Hefeng Wu, Tao Pu 0002, Keze Wang, Liang Lin. [doi]
• Defending Multimodal Backdoored Models by Repulsive Visual Prompt TuningZhifang Zhang, Shuo He 0001, Haobo Wang, Bingquan Shen, Lei Feng 0006. [doi]
• Estimation of Treatment Effects in Extreme and Unobserved DataJiyuan Tan, Vasilis Syrgkanis, Jose H. Blanchet. [doi]
• Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-freeStephen Zhang, Michael Stumpf. [doi]
• Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion ModelsLvmin Zhang, Shengqu Cai, Muyang Li, Gordon Wetzstein, Maneesh Agrawala. [doi]
• The Leaderboard IllusionShivalika Singh, Yiyang Nan, Alex Wang, Daniel D'Souza, Sayash Kapoor, Ahmet Üstün, Sanmi Koyejo, Yuntian Deng, Shayne Longpre, Noah A. Smith, Beyza Ermis, Marzieh Fadaee, Sara Hooker. [doi]
• ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic InstructionsYue Huang 0001, Zhengzhe Jiang, Xiaonan Luo, Kehan Guo, Haomin Zhuang, Yujun Zhou 0002, Zhengqing Yuan, Xiaoqi Sun, Jules Schleinitz, Yanbo Wang 0005, Shuhao Zhang, Mihir Surve, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang 0001. [doi]
• Sharp Gaussian approximations for Decentralized Federated LearningSoham Bonnerjee, Sayar Karmakar, Wei Biao Wu. [doi]
• MedMax: Mixed-Modal Instruction Tuning for Training Biomedical AssistantsHritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover. [doi]
• ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image GenerationYunhong Min, Daehyeon Choi, Kyeongmin Yeo, Jihyun Lee, Minhyuk Sung. [doi]
• Scaling Image Geo-Localization to Continent LevelPhilipp Lindenberger, Paul-Edouard Sarlin, Jan Hosang, Marc Pollefeys, Simon Lynen, Eduard Trulls. [doi]
• Harnessing the Computation Redundancy in ViTs to Boost Adversarial TransferabilityJiani Liu 0013, Zhiyuan Wang, Zeliang Zhang 0001, Chao Huang 0033, Susan Liang, Yunlong Tang 0002, Chenliang Xu. [doi]
• Learnable Sampler Distillation for Discrete Diffusion ModelsFeiyang Fu, Tongxian Guo, Zhaoqiang Liu. [doi]
• Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic dataTianyi Chen, Pengxiao Lin, Zhiwei Wang, Zhi-Qin John Xu. [doi]
• Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize BetterDanny Driess, Jost Tobias Springenberg, Brian Ichter, Lili Yu, Adrian Li-Bell, Karl Pertsch, Allen Z. Ren, Homer Walke, Quan Vuong, Lucy Xiaoyang Shi, Sergey Levine. [doi]
• ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language ModelsDuy M. H. Nguyen, Nghiem Tuong Diep, Trung Nguyen, Hoang Bao Le, Tai D. Nguyen, Anh Tien Nguyen, TrungTin Nguyen, Nhat Ho, Pengtao Xie, Roger Wattenhofer, Daniel Sonntag, James Y. Zou, Mathias Niepert. [doi]
• MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material InferenceWenyuan Zhang, Jimin Tang, Weiqi Zhang, Yi Fang 0006, Yu-Shen Liu, Zhizhong Han. [doi]
• Revisiting Semi-Supervised Learning in the Era of Foundation ModelsPing Zhang 0016, Zheda Mai, Quang Huy Nguyen, Wei-Lun Chao. [doi]
• Non-equilibrium Annealed Adjoint SamplerJaemoo Choi, Yongxin Chen, Molei Tao, Guan-Horng Liu. [doi]
• Native-Resolution Image SynthesisZidong Wang 0004, Lei Bai 0001, Xiangyu Yue 0001, Wanli Ouyang, Yiyuan Zhang. [doi]
• Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information ForagingHongjin Qian, Zheng Liu 0011. [doi]
• GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence SimulationsFabian Paischer, Gianluca Galletti, William Hornsby, Paul Setinek, Lorenzo Zanisi, Naomi Carey, Stanislas Pamela, Johannes Brandstetter. [doi]
• Zero-shot World Models via Search in MemoryFederico Malato, Ville Hautamäki. [doi]
• BADiff: Bandwidth Adaptive Diffusion ModelXi Zhang 0019, Hanwei Zhu, Yan Zhong, Jiamang Wang, Weisi Lin. [doi]
• Think before Recommendation: Autonomous Reasoning-enhanced RecommenderXiaoyu Kong, Junguang Jiang, Bin Liu, Ziru Xu, Zhu Han 0001, Jian Xu 0015, Bo Zheng 0007, Jiancan Wu, Xiang Wang 0010. [doi]
• Multivariate Time Series Anomaly Detection with Idempotent ReconstructionXin Sun 0018, Heng Zhou, Chao Li 0062. [doi]
• An Efficient Local Search Approach for Polarized Community Discovery in Signed NetworksLinus Aronsson, Morteza Haghir Chehreghani. [doi]
• AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial PatchesWenjun Ji, Yuxiang Fu, Luyang Ying, Deng-Ping Fan, Yuyi Wang 0001, Ming-Ming Cheng, Ivor W. Tsang, Qing Guo 0005. [doi]
• MonoLift: Learning 3D Manipulation Policies from Monocular RGB via DistillationZiru Wang, Mengmeng Wang 0005, Guang Dai, Yongliu Long, Jingdong Wang 0001. [doi]
• Quantifying Task-relevant Similarities in Representations Using Decision Variable CorrelationsYu Qian, Wilson S. Geisler, Xue-Xin Wei. [doi]
• Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural NetworksHongzhi Wang 0009, Xiubo Liang, Jinxing Han, Weidong Geng. [doi]
• Feedback-Aware MCTS for Goal-Oriented Information SeekingHarshita Chopra, Chirag Shah 0001. [doi]
• ROSE: Remove Objects with Side Effects in VideosChenxuan Miao, Yutong Feng, Jianshu Zeng, Zixiang Gao, Hantang Liu, Yunfeng Yan, Donglian Qi, Xi Chen 0119, Bin Wang, Hengshuang Zhao. [doi]
• Principled Long-Tailed Generative Modeling via Diffusion ModelsPranoy Das, Kexin Fu, Abolfazl Hashemi, Vijay Gupta 0001. [doi]
• Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware StrategyXinlong Li, Di Lin 0002, Shaoyiyi Gao, Jiaxin Li, Ruonan Liu, Qing Guo 0005. [doi]
• Multi-Agent Learning under Uncertainty: Recurrence vs. ConcentrationKyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, José H. Blanchet. [doi]
• Don't call it privacy-preserving or human-centric pose estimation if you don't measure privacyMichele Baldassini, Francesco Pistolesi, Beatrice Lazzerini. [doi]
• Restoring Pruned Large Language Models via Lost Component CompensationZijian Feng, Hanzhang Zhou, Zixiao Zhu, Tianjiao Li, Chua Jia Jim Deryl, Lee Onn Mak, Gee Wah Ng, Kezhi Mao. [doi]
• VIKING: Deep variational inference with stochastic projectionsSamuel Matthiesen, Hrittik Roy, Nicholas Krämer, Yevgen Zainchkovskyy, Stas Syrota, Alejandro Valverde Mahou, Carl Henrik Ek, Søren Hauberg. [doi]
• On the Robustness of Verbal Confidence of LLMs in Adversarial AttacksStephen Obadinma, Xiaodan Zhu 0001. [doi]
• Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided MarketsZixian Yang, Sushil Mahavir Varma, Lei Ying 0001. [doi]
• On Local Limits of Sparse Random Graphs: Color Convergence and the Refined Configuration ModelAlexander Pluska, Sagar Malhotra. [doi]
• Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation LearningTianle Zhang, Wanlong Fang, Jonathan Woo, Paridhi Latawa, Deepak A. Subramanian, Alvin Chan. [doi]
• Quartet: Native FP4 Training Can Be Optimal for Large Language ModelsRoberto L. Castro, Andrei Panferov, Rush Tabesh, Oliver Sieberling, Jiale Chen 0004, Mahdi Nikdan, Saleh Ashkboos, Dan Alistarh. [doi]
• RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation ModelsShikun Liu, Deyu Zou, Nima Shoghi, Victor Fung, Kai Liu, Pan Li 0005. [doi]
• UMA: A Family of Universal Models for AtomsBrandon M. Wood, Misko Dzamba, Xiang Fu 0005, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque, Kareem Abdelmaqsoud, Vahe Gharakhanyan, John R. Kitchin, Daniel S. Levine 0003, Kyle Michel, Anuroop Sriram, Taco S. Cohen, Abhishek Das 0002, Sushree Jagriti Sahoo, Ammar Rizvi, Zachary W. Ulissi, Larry Zitnick. [doi]
• RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platform for Embodied IntelligenceZhaoliang Wan, Zetong Bi, Zida Zhou, Hao Ren 0006, Yiming Zeng 0008, Yihan Li, Lu Qi 0001, Xu Yang 0004, Ming-Hsuan Yang 0001, Hui Cheng 0002. [doi]
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo MatchingYun Wang 0053, Junjie Hu 0003, Qiaole Dong, Yongjian Zhang, Yanwei Fu 0001, Tin Lun Lam, Dapeng Wu 0001. [doi]
• Optimal Mistake Bounds for Transductive Online LearningZachary Chase 0001, Steve Hanneke, Shay Moran, Jonathan Shafer. [doi]
• QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-ResolutionZhenwei Zhang, Fanhua Shang, Hongying Liu 0001, Liang Wang 0001, Wei Feng 0005, Yanming Hui. [doi]
• On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent AscentXinwen Zhang, Hongchang Gao. [doi]
• LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-SupervisionAnthony Fuller, Yousef Yassin, Junfeng Wen, Tarek Ibrahim, Daniel G. Kyrollos, James Green 0001, Evan Shelhamer. [doi]
• Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient DescentZiyang Wei, Jiaqi Li 0032, Zhipeng Lou, Wei Biao Wu. [doi]
• Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly DetectionYuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang 0006, Haoxin Yang, Yongwei Nie, Shengfeng He. [doi]
• Low-degree evidence for computational transition of recovery rate in stochastic block modelJingqiu Ding, Yiding Hua, Lucas Slot, David Steurer. [doi]
• RAST: Reasoning Activation in LLMs via Small-model TransferSiru Ouyang, Xinyu Zhu, Zilin Xiao, Minhao Jiang, Yu Meng 0001, Jiawei Han 0001. [doi]
• Image Super-Resolution with Guarantees via Conformalized Generative ModelsEduardo Adame, Daniel Csillag, Guilherme Tegoni Goedert. [doi]
• Non-stationary Equivariant Graph Neural Networks for Physical Dynamics SimulationChaohao Yuan, Maoji Wen, Ercan E. Kuruoglu, Yang Liu, Jia Li 0009, Tingyang Xu, Deli Zhao, Hong Cheng 0001, Yu Rong 0001. [doi]
• TRACE: Grounding Time Series in Context for Multimodal Embedding and RetrievalJialin Chen, Ziyu Zhao, Gaukhar Nurbek, Aosong Feng, Ali Maatouk, Leandros Tassiulas, Yifeng Gao, Rex Ying. [doi]
• Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM ReasoningShenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu 0001, Kai Dang, Xiong-Hui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, an Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu 0002, Gao Huang 0001, Junyang Lin. [doi]
• SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image ClassificationHsi-Ling Chen, Chun-Shien Lu, Pau-Choo Chung. [doi]
• Few-Shot Knowledge Distillation of LLMs With Counterfactual ExplanationsFaisal Hamman, Pasan Dissanayake, Yanjun Fu, Sanghamitra Dutta. [doi]
• REMI: Reconstructing Episodic Memory During Internally Driven Path PlanningZhaoze Wang, Genela Morris, Dori Derdikman, Pratik Chaudhari, Vijay Balasubramanian. [doi]
• Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential ComputationsYuchao Lin, Cong Fu 0003, Zachary Krueger, Haiyang Yu 0005, Maho Nakata, Jianwen Xie, Emine Küçükbenli, Xiaofeng Qian, Shuiwang Ji. [doi]
• From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer ReviewYaohui Zhang, Haijing Zhang, Wenlong Ji, Tianyu Hua, Nick Haber, Hancheng Cao, Weixin Liang. [doi]
• Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability GraphsAmirmohammad Farzaneh, Osvaldo Simeone. [doi]
• Architectural and Inferential Inductive Biases for Exchangeable Sequence ModelingDaksh Mittal, Leon Li, Thomson Yen, C. Guetta, Hongseok Namkoong. [doi]
• CoLT: The conditional localization test for assessing the accuracy of neural posterior estimatesTianyu Chen, Vansh Bansal, James G. Scott. [doi]
• Fact-R1: Towards Explainable Video Misinformation Detection with Deep ReasoningFanrui Zhang, Dian Li, Qiang Zhang 0051, Jun Chen, Sinbadliu, Junxiong Lin, Jiahong Yan, Jiawei Liu 0001, Zheng-Jun Zha. [doi]
• ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language ModelsWeifei Jin, Yuxin Cao, Junjie Su, Minhui Xue 0001, Jie Hao 0001, Ke Xu, Jin Song Dong 0001, Derui Wang. [doi]
• Tackling Biased Evaluators in Dueling BanditsMing Tang, Yuxuan Zhou, Chao Huang. [doi]
• Less is More: Local Intrinsic Dimensions of Contextual Language ModelsBenjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck, Renato Vukovic, Shutong Feng, Hsien-Chin Lin, Nurul Lubis, Bastian Rieck, Marcus Zibrowius, Milica Gasic. [doi]
• Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIsMantas Mazeika, Xuwang Yin, Rishub Tamirisa, Jaehyuk Lim, Bruce W. Lee, Richard Ren, Long Phan, Norman Mu, Oliver Zhang, Dan Hendrycks. [doi]
• Robust Graph Condensation via Classification Complexity MitigationJiayi Luo, Qingyun Sun, Beining Yang, Haonan Yuan, Xingcheng Fu, Yanbiao Ma, Jianxin Li 0002, Philip S. Yu. [doi]
• Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion TransformerZechuan Zhang, Ji Xie, Yu Lu 0019, Zongxin Yang, Yi Yang 0001. [doi]
• FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure ModesChristodoulos Constantinides, Dhaval Patel 0002, Shuxin Lin, Claudio Guerrero, Sunil Dagajirao Patil, Jayant Kalagnanam. [doi]
• Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE SolutionsNaoki Kiyohara, Edward Johns, Yingzhen Li. [doi]
• Incentivizing Truthful Language Models via Peer Elicitation GamesBaiting Chen, Tong Zhu, Jiale Han 0002, Lexin Li, Gang Li, Xiaowu Dai. [doi]
• Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task ConcurrencyYukun Jiang 0001, Mingjie Li 0007, Michael Backes 0001, Yang Zhang 0016. [doi]
• RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between LabelsZhiqiang Kou, Yucheng Xie, Hailin Wang 0001, Junyang Chen, Jing Wang 0113, Ming-Kun Xie, Shuo Chen 0003, Yuheng Jia, Tongliang Liu, Xin Geng 0001. [doi]
• Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image GenerationYao Teng, Fuyun Wang, Xian Liu, Zhekai Chen, Han Shi, Yu Wang 0002, Zhenguo Li, Weiyang Liu, Difan Zou, Xihui Liu. [doi]
• Flat Channels to Infinity in Neural Loss LandscapesFlavio Martinelli, Alexander van Meegen, Berfin Simsek, Wulfram Gerstner, Johanni Brea. [doi]
• Fast attention mechanisms: a tale of parallelismJingwen Liu, Hantao Yu, Clayton Sanford, Alexandr Andoni, Daniel Hsu 0001. [doi]
• IneqSearch: Hybrid Reasoning for Olympiad Inequality ProofsZhaoqun Li, Beishui Liao, Qiwei Ye. [doi]
• Instant Video Models: Universal Adapters for Stabilizing Image-Based NetworksMatthew Dutson, Nathan Labiosa, Yin Li 0003, Mohit Gupta 0001. [doi]
• Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying RegularizationSebastian Kassing, Simon Weissmann, Leif Döring. [doi]
• Does Representation Guarantee Welfare?Jakob de Raaij, Ariel D. Procaccia, Alexandros Psomas 0001. [doi]
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning ModelsSohyun An, Ruochen Wang, Tianyi Zhou 0001, Cho-Jui Hsieh. [doi]
• Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian SplattingJiawei Zhang, Youmin Zhang 0005, Fabio Tosi, Meiying Gu, Jiahe Li 0007, Xiaohan Yu 0001, Jin Zheng, Xiao Bai 0001, Matteo Poggi. [doi]
• Agents Robust to Distribution Shifts Learn Causal World Models Even Under MediationMatteo Ceriscioli, Karthika Mohan. [doi]
• SPRO: Improving Image Generation via Self-PlayRitika Jha, Aanisha Bhattacharyya, Yaman Singla, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy. [doi]
• Diffusing DeBias: Synthetic Bias Amplification for Model DebiasingMassimiliano Ciranni, Vito Paolo Pastore, Roberto Di Via, Enzo Tartaglione, Francesca Odone, Vittorio Murino. [doi]
• PSI: A Benchmark for Human Interpretation and Response in Traffic InteractionsTaotao Jing, Tina Chen, Renran Tian, Yaobin Chen, Joshua E. Domeyer, Heishiro Toyoda, Rini Sherony, Zhengming Ding. [doi]
• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of RigorAlexandra Olteanu, Su Lin Blodgett, Agathe Balayn, Angelina Wang, Fernando Diaz 0001, Flávio P. Calmon, Margaret Mitchell, Michael D. Ekstrand, Reuben Binns, Solon Barocas. [doi]
• The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture ModelKaito Takanami, Takashi Takahashi, Ayaka Sakata. [doi]
• Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement LearningRuiyao Miao, Junren Xiao, Shiya Tsang, Hui Xiong 0001, Ying Nian Wu. [doi]
• When Does Curriculum Learning Help? A Theoretical PerspectiveRaman Arora, Yunjuan Wang, Kaibo Zhang. [doi]
• Accident Anticipation via Temporal Occurrence PredictionTianhao Zhao, Yiyang Zou, Zihao Mao, Peilun Xiao, Yulin Huang, Hongda Yang, Yuxuan Li, Tracy Li, Guobin Wu, Yutian Lin. [doi]
• MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across VersionsPucheng Dang, Di Huang, Dong Li 0008, Kang Chen, Yuanbo Wen 0001, Qi Guo 0001, Xing Hu 0001. [doi]
• Influence Functions for Edge Edits in Non-Convex Graph Neural NetworksJaeseung Heo, Kyeongheung Yun, Seokwon Yoon, Moonjeong Park, Jungseul Ok, Dongwoo Kim 0002. [doi]
• DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation spaceJunchao Gong, Jingyi Xu, Ben Fei, Fenghua Ling, Wenlong Zhang, Kun Chen 0004, Wanghan Xu, Weidong Yang 0001, Xiaokang Yang 0001, Lei Bai 0001. [doi]
• How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPsSamet Demir, Zafer Dogan. [doi]
• Robust and Scalable Autonomous Reinforcement Learning in Irreversible EnvironmentsSang Hyun Lee. [doi]
• CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge TracingLeonie Bossemeyer, Samuel Heinrich, Grant Van Horn, Oisin Mac Aodha. [doi]
• Training-free Online Video Step GroundingLuca Zanella, Massimiliano Mancini, Yiming Wang 0002, Alessio Tonioni, Elisa Ricci 0001. [doi]
• Jamais Vu: Exposing the Generalization Gap in Supervised Semantic CorrespondenceOctave Mariotti, Zhipeng Du, Yash Bhalgat, Oisin Mac Aodha, Hakan Bilen. [doi]
• Self-Challenging Language Model AgentsYifei Zhou, Sergey Levine, Jason E. Weston, Xian Li 0003, Sainbayar Sukhbaatar. [doi]
• Language-Bias-Resilient Visual Question Answering via Adaptive Multi-Margin Collaborative DebiasingHuanjia Zhu, Shuyuan Zheng, Yishu Liu 0001, Sudong Cai, Bingzhi Chen. [doi]
• Scalable and adaptive prediction bands with kernel sum-of-squaresLouis Allain, Sébastien Da Veiga, Brian Staber. [doi]
• A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant FundingAlexander Goldberg, Giulia Fanti, Nihar B. Shah. [doi]
• Online Learning of Neural NetworksAmit Daniely, Idan Mehalel, Elchanan Mossel. [doi]
• ALINE: Joint Amortization for Bayesian Inference and Active Data AcquisitionDaolang Huang, Xinyi Wen, Ayush Bharti, Samuel Kaski, Luigi Acerbi. [doi]
• Reinforcement Learning with Backtracking FeedbackBilgehan Sel, Vaishakh Keshava, Phillip Wallis, Lukas Rutishauser, Ming Jin 0002, Dingcheng Li. [doi]
• X-Field: A Physically Informed Representation for 3D X-ray ReconstructionFeiran Wang, Jiachen Tao, Junyi Wu 0002, Haoxuan Wang 0002, Bin Duan, Kai Wang 0036, Zongxin Yang, Yan Yan 0002. [doi]
• WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenariosEun Chang, Zhuangqun Huang, Yiwei Liao, Sagar Ravi Bhavsar, Amogh Param, Tammy Stark, Adel Ahmadyan, Xiao Yang, Jiaqi Wang, Ahsan Abdullah, Giang Nguyen, Akil Iyer, David Hall, Elissa Li, Nicolas Scheffer, Ahmed Kirmani, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, Seungwhan Moon, Xin Luna Dong. [doi]
• FerretNet: Efficient Synthetic Image Detection via Local Pixel DependenciesShuqiao Liang, Jian Liu, Renzhang Chen, Quanlong Guan. [doi]
• When Data Can't Meet: Estimating Correlation Across Privacy BarriersAbhinav Chakraborty 0002, Arnab Auddy, T. Tony Cai. [doi]
• FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow NetworkShuo Xu, Yu Chen, Shuxia Lin, Xin Geng 0001, Xu Yang 0021. [doi]
• MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video ScenariosYang Shi 0009, Huanqian Wang, Wulin Xie, Huanyao Zhang, Lijie Zhao, Yifan Zhang 0004, Xinfeng Li, Chaoyou Fu, Zhuoer Wen, Wenting Liu, Zhuoran Zhang 0003, Xinlong Chen, Bohan Zeng, Sihan Yang, Yushuo Guan, Zhang Zhang 0001, Liang Wang 0001, Haoxuan Li 0001, Zhouchen Lin, Yuanxing Zhang, Pengfei Wan 0001, Haotian Wang 0001, Wenjing Yang 0002. [doi]
• Removing Concepts from Text-to-Image Models with Only Negative SamplesHanwen Liu, Yadong Mu. [doi]
• Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal LearningHossein Rajoli Nowdeh, Jie Ji, Xiaolong Ma, Fatemeh Afghah. [doi]
• Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLTong Yang 0007, Bo Dai 0001, Lin Xiao, Yuejie Chi. [doi]
• ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative DecodingJialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai, Xinghao Chen 0001. [doi]
• Conformal Information Pursuit for Interactively Guiding Large Language ModelsKwan Ho Ryan Chan, Yuyan Ge, Edgar Dobriban, Hamed Hassani, René Vidal. [doi]
• HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned GuidanceJiazi Bu, Pengyang Ling, Yujie Zhou, Pan Zhang 0001, Tong Wu, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Dahua Lin, Jiaqi Wang 0003. [doi]
• Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree SearchHuanjin Yao, Jiaxing Huang 0001, Wenhao Wu, Jingyi Zhang 0005, Yibo Wang 0039, Shunyu Liu 0001, Yingjie Wang, YuXin Song 0001, Haocheng Feng, Li Shen 0008, Dacheng Tao. [doi]
• Martian World Model: Controllable Video Synthesis with Physically Accurate 3D ReconstructionsLongfei Li, Zhiwen Fan, Wenyan Cong, Xinhang Liu, Yuyang Yin, Matthew Foutter, Panwang Pan, Chenyu You, Yue Wang 0041, Zhangyang (Atlas) Wang, Yao Zhao 0001, Marco Pavone 0001, Yunchao Wei. [doi]
• World Models Should Prioritize the Unification of Physical and Social DynamicsXiaoyuan Zhang, Chengdong Ma, Yizhe Huang, Weidong Huang 0008, Siyuan Qi, Song Chun Zhu, Xue Feng, Yaodong Yang 0001. [doi]
• ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and EditingHuadai Liu, Kaicheng Luo, Jialei Wang, Wen Wang 0001, Qian Chen 0003, Zhou Zhao 0001, Wei Xue 0002. [doi]
• DyMoDreamer: World Modeling with Dynamic ModulationBoxuan Zhang, Runqing Wang, Wei Xiao, Weipu Zhang, Jian Sun 0003, Gao Huang 0001, Jie Chen 0003, Gang Wang 0014. [doi]
• Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural NetworksArtur Back de Luca, George Giapitzakis, Kimon Fountoulakis. [doi]
• On scalable and efficient training of diffusion samplersMinkyu Kim, Kiyoung Seong, Dongyeop Woo, Sungsoo Ahn, Minsu Kim. [doi]
• SHAP values via sparse Fourier representationAli Gorji, Andisheh Amrollahi, Andreas Krause 0001. [doi]
• GTR-Loc: Geospatial Text Regularization Assisted Outdoor LiDAR LocalizationShangshu Yu, Wen Li 0005, Xiaotian Sun 0005, Zhimin Yuan, Xin Wang, Sijie Wang, Rui She 0001, Cheng Wang 0003. [doi]
• Beyond Least Squares: Uniform Approximation and the Hidden Cost of MisspecificationDavide Maran, Csaba Szepesvári. [doi]
• STNet: Spectral Transformation Network for Solving Operator Eigenvalue ProblemHong Wang, Yixuan Jiang, Jie Wang, Xinyi Li, Jian Luo, Huanshuo Dong. [doi]
• ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon SetsBohdan Turbal, Iryna Voitsitska, Lesia Semenova. [doi]
• From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D ScenesTianxu Wang, Zhuofan Zhang, Ziyu Zhu, Yue Fan, Jing Xiong, Pengxiang Li 0002, Xiaojian (Shawn) Ma, Qing Li 0003. [doi]
• SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time SeriesQitai Tan, Yiyun Chen, Mo Li, Ruiwen Gu, Yilin Su, Xiao-Ping (Steven) Zhang. [doi]
• Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory AccessXiang Hu, Jiaqi Leng 0003, Jun Zhao, Kewei Tu, Wei Wu. [doi]
• Tight Asymptotics of Extreme Order StatisticsJosé Correa 0001, Frederik Mallmann-Trenn, Matías Romero. [doi]
• Revisiting Bi-Linear State Transitions in Recurrent Neural NetworksReza Ebrahimi, Roland Memisevic. [doi]
• FedIGL: Federated Invariant Graph Learning for Non-IID GraphsLingren Wang, Wenxuan Tu, Jiaxin Wang, Xiong Wang, Jieren Cheng, Jingxin Liu 0006. [doi]
• A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement LearningYihuan Mao, Chongjie Zhang. [doi]
• STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible BenchmarkingSicheng Shen, Dongcheng Zhao, Linghao Feng, Zeyang Yue, Jindong Li 0001, Tenglong Li, Guobin Shen, Yi Zeng 0001. [doi]
• AlignedGen: Aligning Style Across Generated ImagesJiexuan Zhang, Yiheng Du, Qian Wang, Weiqi Li, Yu Gu, Jian-Jun Zhang. [doi]
• Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural NetworksGuobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li 0141, Feifei Zhao, Yi Zeng 0001. [doi]
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual DrawingJunfei Wu, Jian Guan 0002, Kaituo Feng, Qiang Liu 0006, Shu Wu, Liang Wang 0001, Wei Wu 0014, Tieniu Tan. [doi]
• Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlowKristiyan Sakalyan, Alessandro Palma, Filippo Guerranti, Fabian J. Theis, Stephan Günnemann. [doi]
• Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling LawsZhixuan Pan, Shaowen Wang 0002, Pengfei Liao, Jian Li. [doi]
• Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle PointsNaoya Yamamoto, Juno Kim, Taiji Suzuki. [doi]
• metaTextGrad: Automatically optimizing language model optimizersGuowei Xu 0001, Mert Yüksekgönül, Carlos Guestrin, James Y. Zou. [doi]
• ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and RobustnessYijun Liang, Ming Li 0010, Chenrui Fan, Ziyue Li, Dang Nguyen, Kwesi Cobbina, Shweta Bhardwaj, Jiuhai Chen, Fuxiao Liu, Tianyi Zhou 0001. [doi]
• Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale ProblemsSaeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida. [doi]
• PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution ModelingMinju Jo, Woojin Cho, Uvini Balasuriya Mudiyanselage, Seungjun Lee, Noseong Park, Kookjin Lee. [doi]
• FairDD: Fair Dataset DistillationQihang Zhou, Shenhao Fang, Shibo He, Wenchao Meng, Jiming Chen 0001. [doi]
• SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit TrainingJintao Zhang, Jia Wei, Haoxu Wang, Pengle Zhang, Xiaoming Xu, Haofeng Huang, Kai Jiang, Jianfei Chen 0001, Jun Zhu 0001. [doi]
• Learning and Planning Multi-Agent Tasks via an MoE-based World ModelZijie Zhao, Zhongyue Zhao, Kaixuan Xu, Yuqian Fu, Jiajun Chai, Yuanheng Zhu, Dongbin Zhao. [doi]
• Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret MinimizationMarius Potfer, Vianney Perchet. [doi]
• GuardReasoner-VL: Safeguarding VLMs via Reinforced ReasoningYue Liu 0008, Shengfang Zhai, Mingzhe Du, Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang, Xinfeng Li, Kun Wang 0056, Junfeng Fang, Jiaheng Zhang, Bryan Hooi. [doi]
• A Circular Argument: Does RoPE need to be Equivariant for Vision?Chase van de Geijn, Timo Lüddecke, Polina Turishcheva, Alexander S. Ecker. [doi]
• Image as a World: Generating Interactive World from Single Image via Panoramic Video GenerationDongnan Gui, Xun Guo 0002, Wengang Zhou 0001, Yan Lu 0001. [doi]
• HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell dataSiddharth Viswanath, Hiren Madhu, Dhananjay Bhaskar, Jake Kovalic, Dave Johnson 0004, Christopher J. Tape, Ian Adelstein, Rex Ying, Michael Perlmutter, Smita Krishnaswamy. [doi]
• DINO-Foresight: Looking into the Future with DINOEfstathios Karypidis, Ioannis Kakogeorgiou, Spyridon Gidaris, Nikos Komodakis. [doi]
• PointTruss: K-Truss for Point Cloud RegistrationYue Wu 0004, Jun Jiang, Yongzhe Yuan, Maoguo Gong, Qiguang Miao, Hao Li 0009, Mingyang Zhang 0002, Wenping Ma 0001. [doi]
• Periodic Skill DiscoveryJonghae Park, Daesol Cho, Jusuk Lee, Dongseok Shim, Inkyu Jang, H. Jin Kim. [doi]
• Self-Adapting Language ModelsAdam Zweiger, Jyothish Pari, Han Guo, Yoon Kim, Pulkit Agrawal 0001. [doi]
• SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence eraElizaveta Semenova, Siobhan Mackenzie Hall, Timothy James Hitge, Alisa Sheinkman, Jon Cockayne. [doi]
• A Markov Decision Process for Variable Selection in Branch & BoundPaul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson. [doi]
• Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER GatesHang Chen 0002, Jiaying Zhu, Xinyu Yang 0001, Wenya Wang. [doi]
• ResponseRank: Data-Efficient Reward Modeling through Preference Strength LearningTimo Kaufmann, Yannick Metz, Daniel A. Keim, Eyke Hüllermeier. [doi]
• Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural NetworksDaniel Kunin, Giovanni Luca Marchetti, Feng Chen 0046, Dhruva Karkada, James B. Simon, Michael R. DeWeese, Surya Ganguli, Nina Miolane. [doi]
• THUNDER: Tile-level Histopathology image UNDERstanding benchmarkPierre Marza, Leo Fillioux, Sofiène Boutaj, Kunal Mahatha, Christian Desrosiers, Pablo Piantanida, Jose Dolz, Stergios Christodoulidis, Maria Vakalopoulou. [doi]
• Disentangled Cross-Modal Representation Learning with Enhanced Mutual SupervisionLu Gao, Wenlan Chen, Daoyuan Wang, Fei Guo 0001, Cheng Liang 0001. [doi]
• MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry DiagnosisMengxi Xiao, Ben Liu 0002, He Li 0054, Jimin Huang, Qianqian Xie, Xiaofen Zong, Mang Ye, Min Peng 0002. [doi]
• Increasing the Utility of Synthetic Images through Chamfer GuidanceNicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat, Melissa Hall, Jakob J. Verbeek, Adriana Romero-Soriano, Michal Drozdzal. [doi]
• Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination EnhancementDerong Kong, Zhixiong Yang 0001, Shengxi Li, Shuaifeng Zhi, Li Liu 0002, Zhen Liu 0004, Jingyuan Xia. [doi]
• Exploiting Task Relationships in Continual Learning via Transferability-Aware Task EmbeddingsYanru Wu, Jianning Wang, Xiangyu Chen, Aurora, Yang Tan, Hanbing Liu, Yang Li. [doi]
• R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token RoutingTianyu Fu 0004, Yi Ge, Yichen You, Enshu Liu, Zhihang Yuan, Guohao Dai 0001, Shengen Yan, Huazhong Yang, Yu Wang 0002. [doi]
• Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image RestorationYuyang Hu, Kangfu Mei, Mojtaba Sahraee-Ardakan, Ulugbek Kamilov, Peyman Milanfar, Mauricio Delbracio. [doi]
• Generative Model Inversion Through the Lens of the Manifold HypothesisXiong Peng, Bo Han 0003, Fengfei Yu, Tongliang Liu, Feng Liu 0003, Mingyuan Zhou. [doi]
• GeoVideo: Introducing Geometric Regularization into Video Generation ModelYunpeng Bai, Shaoheng Fang, Chaohui Yu, Fan Wang 0019, Qixing Huang. [doi]
• REOrdering Patches Improves Vision ModelsDeclan Kutscher, David M. Chan, Yutong Bai, Trevor Darrell, Ritwik Gupta. [doi]
• Enhancing the Maximum Effective Window for Long-Term Time Series ForecastingJiahui Zhang, Zhengyang Zhou, Wenjie Du 0003, Yang Wang 0015. [doi]
• Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal SystemsIbrahim Alabdulmohsin, Xiaohua Zhai. [doi]
• SoPo: Text-to-Motion Generation Using Semi-Online Preference OptimizationXiaofeng Tan 0001, Hongsong Wang 0001, Xin Geng 0001, Pan Zhou. [doi]
• Interpretable Next-token Prediction via the Generalized Induction HeadEunji Kim 0002, Sriya Mantena, Weiwei Yang, Chandan Singh, Sungroh Yoon