Table of Contents

• The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and ModalitiesZhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama, Jiasen Lu, Yoon Kim. [doi]
• Enhancing End-to-End Autonomous Driving with Latent World ModelYingyan Li, Lue Fan, Jiawei He 0002, Yuqi Wang 0001, YunTao Chen, Zhaoxiang Zhang 0001, Tieniu Tan. [doi]
• DiffPuter: Empowering Diffusion Models for Missing Data ImputationHengrui Zhang, Liancheng Fang, Qitian Wu, Philip S. Yu. [doi]
• UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement LearningShicheng Liu, Minghui Zhu. [doi]
• Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-ReflectionLichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie. [doi]
• Bisimulation Metric for Model Predictive ControlYutaka Shimizu, Masayoshi Tomizuka. [doi]
• When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approachQian Chen, Lei Li 0030, Qian Li, Jianghua Wu, Akang Wang, Ruoyu Sun 0001, Xiaodong Luo, Tsung-Hui Chang, Qingjiang Shi. [doi]
• Learning Dynamics of Deep Matrix Factorization Beyond the Edge of StabilityAvrajit Ghosh, Soo Min Kwon, Rongrong Wang, Saiprasad Ravishankar, Qing Qu 0001. [doi]
• AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D ReconstructionJingnan Gao, Zhuo Chen, Xiaokang Yang 0001, Yichao Yan. [doi]
• Herald: A Natural Language Annotated Lean 4 DatasetGuoxiong Gao, Yutong Wang, Jiedong Jiang, Qi Gao, Zihan Qin, Tianyi Xu, Bin Dong 0001. [doi]
• EffoVPR: Effective Foundation Model Utilization for Visual Place RecognitionIssar Tzachor, Boaz Lerner, Matan Levy, Michael Green, Tal Berkovitz Shalev, Gavriel Habib, Dvir Samuel, Noam Korngut Zailer, Or Shimshi, Nir Darshan, Rami Ben-Ari. [doi]
• Efficient and Trustworthy Causal Discovery with Latent Variables and Complex RelationsXiu-Chuan Li, Tongliang Liu. [doi]
• RouteLLM: Learning to Route LLMs from Preference DataIsaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu 0002, Joseph E. Gonzalez, M. Waleed Kadous, Ion Stoica. [doi]
• OLMoE: Open Mixture-of-Experts Language ModelsNiklas Muennighoff, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Jacob Morrison, Sewon Min, Weijia Shi, Evan Pete Walsh, Oyvind Tafjord, Nathan Lambert 0001, Yuling Gu, Shane Arora, Akshita Bhagia, Dustin Schwenk, David Wadden, Alexander Wettig, Binyuan Hui, Tim Dettmers, Douwe Kiela, Ali Farhadi, et al.. [doi]
• Lossy Compression with Pretrained Diffusion ModelsJeremy Vonderfecht, Feng Liu. [doi]
• OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?Junjielong Xu, Qinan Zhang, Zhiqing Zhong, Shilin He, Chaoyun Zhang, Qingwei Lin, Dan Pei, Pinjia He, Dongmei Zhang, Qi Zhang 0066. [doi]
• Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression EfficiencyJiangrong Shen, Qi Xu, Gang Pan 0001, Badong Chen. [doi]
• Computing Circuits Optimization via Model-Based Circuit Genetic EvolutionZhihai Wang, Jie Wang 0005, Xilin Xia, Dongsheng Zuo, Lei Chen 0031, Yuzhe Ma, Jianye Hao, Mingxuan Yuan, Feng Wu 0001. [doi]
• Compositional simulation-based inference for time seriesManuel Glöckler, Shoji Toyota, Kenji Fukumizu, Jakob H. Macke. [doi]
• Provably Accurate Shapley Value Estimation via Leverage Score SamplingChristopher Musco, R. Teal Witter. [doi]
• CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency PatchingXingjian Wu, Xiangfei Qiu, Zhengyu Li, Yihang Wang 0004, Jilin Hu, Chenjuan Guo, Hui Xiong, Bin Yang. [doi]
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM InferenceZhenyu Zhang 0015, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li. [doi]
• AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit TopologiesJian Gao, Weidong Cao, Junyi Yang, Xuan Zhang. [doi]
• N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph LearningLiping Wang 0015, Xujia Li, Jingshu Peng, Yue Wang 0012, Chen Zhang 0010, Yan Zhou, Lei Chen 0002. [doi]
• Attention with Markov: A Curious Case of Single-layer TransformersAshok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar. [doi]
• Bayesian WeakS-to-Strong from Text Classification to GenerationZiyun Cui, Ziyang Zhang, Guangzhi Sun, Wen Wu 0007, Chao Zhang. [doi]
• Designing Mechanical Meta-Materials by Learning Equivariant FlowsMehran Mirramezani, Anne S. Meeussen, Katia Bertoldi, Peter Orbanz, Ryan P. Adams. [doi]
• An Effective Manifold-based Optimization Method for Distributionally Robust ClassificationJiawei Huang 0009, Hu Ding. [doi]
• Inner Information Analysis Algorithm for Deep Neural Network based on CommunityGuipeng Lan, Shuai Xiao 0001, Meng Xi 0001, Jiabao Wen, Jiachen Yang. [doi]
• Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful PerturbationTiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Ling Liu 0001. [doi]
• Strong Model CollapseElvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe. [doi]
• Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph GenerationMinghan Chen, Guikun Chen, Wenguan Wang, Yi Yang 0001. [doi]
• Universal generalization guarantees for Wasserstein distributionally robust modelsTam Le, Jérôme Malick. [doi]
• Poison-splat: Computation Cost Attack on 3D Gaussian SplattingJiahao Lu, Yifan Zhang, Qiuhong Shen, Xinchao Wang, Shuicheng Yan. [doi]
• Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic RegressionMichael Crawshaw, Blake Woodworth, Mingrui Liu. [doi]
• Sensor-Invariant Tactile RepresentationHarsh Gupta, Yuchen Mo, Shengmiao Jin, Wenzhen Yuan 0001. [doi]
• XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement LearningAlexander Nikulin, Ilya Zisman, Alexey Zemtsov, Vladislav Kurenkov. [doi]
• Depth Pro: Sharp Monocular Metric Depth in Less Than a SecondAlexey Bochkovskiy, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun. [doi]
• PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language InstructionsWeifeng Lin, Xinyu Wei, Renrui Zhang, Le Zhuo, Shitian Zhao, Siyuan Huang 0004, Junlin Xie, Peng Gao 0007, Hongsheng Li 0001. [doi]
• A Generic Framework for Conformal FairnessAditya T. Vadlamani, Anutam Srinivasan, Pranav Maneriker, Ali Payani, Srinivasan Parthasarathy 0001. [doi]
• Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal PerspectiveXiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li, Chengyu Wang 0001, Jun Huang 0007, Bei Yang, Xiaoxiao Xu. [doi]
• MGDA Converges under Generalized Smoothness, ProvablyQi Zhang, Peiyao Xiao, Shaofeng Zou, Kaiyi Ji. [doi]
• Shh, don't say that! Domain Certification in LLMsCornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Guillaume Kayser, Tom Rainforth, Thomas Lukasiewicz, Philip Torr 0001, Adel Bibi. [doi]
• Horizon Generalization in Reinforcement LearningVivek Myers, Catherine Ji, Benjamin Eysenbach. [doi]
• Learning system dynamics without forgettingXikun Zhang 0002, Dongjin Song, Yushan Jiang, Yixin Chen 0001, Dacheng Tao. [doi]
• ECD: A Machine Learning Benchmark for Predicting Enhanced-Precision Electronic Charge Density in Crystalline Inorganic MaterialsPin Chen, Zexin Xu, Qing Mo, Hongjin Zhong, Fengyang Xu, Yutong Lu. [doi]
• DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion ControlKaifeng Zhao 0004, Gen Li, Siyu Tang 0001. [doi]
• Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform CodingEric Lei, Hamed Hassani, Shirin Saeedi Bidokhti. [doi]
• On the Almost Sure Convergence of the Stochastic Three Points AlgorithmTaha el Bakkali el Kadi, Omar Saadi. [doi]
• Video In-context Learning: Autoregressive Transformers are Zero-Shot Video ImitatorsWentao Zhang, Junliang Guo, Tianyu He, Li Zhao, Linli Xu, Jiang Bian. [doi]
• Taming Overconfidence in LLMs: Reward Calibration in RLHFJixuan Leng, Chengsong Huang, Banghua Zhu, Jiaxin Huang 0001. [doi]
• SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document UnderstandingJian Chen, Ruiyi Zhang, Yufan Zhou, Tong Yu, Franck Dernoncourt, Jiuxiang Gu, Ryan A. Rossi, Changyou Chen, Tong Sun 0005. [doi]
• LLM Unlearning via Loss Adjustment with Only Forget DataYaxuan Wang, Jiaheng Wei, Chris Yuhao Liu, Jinlong Pang, Quan Liu, Ankit Shah 0001, Yujia Bao, Yang Liu 0018, Wei Wei. [doi]
• Policy Decorator: Model-Agnostic Online Refinement for Large Policy ModelXiu Yuan, Tongzhou Mu, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su 0001. [doi]
• Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with ChecklistZihao Zhou, Shudong Liu 0004, Maizhen Ning, Wei Liu, Jindong Wang, Derek F. Wong, Xiaowei Huang, Qiufeng Wang, Kaizhu Huang. [doi]
• Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent FlowsShuhao Cao, Francesco Brarda, Ruipeng Li, Yuanzhe Xi. [doi]
• Grokking at the Edge of Numerical StabilityLucas Prieto, Melih Barsbey, Pedro A. M. Mediano, Tolga Birdal. [doi]
• Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement LearningShumao Zhai, Ning Ge 0002. [doi]
• InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight GenerationGaurav Sahu, Abhay Puri, Juan A. Rodriguez, Amirhossein Abaskohi, Mohammad Chegini, Alexandre Drouin, Perouz Taslakian, Valentina Zantedeschi, Alexandre Lacoste, David Vázquez, Nicolas Chapados, Christopher Pal, Sai Rajeswar, Issam H. Laradji. [doi]
• MarS: a Financial Market Simulation Engine Powered by Generative Foundation ModelJunjie Li, Yang Liu, Weiqing Liu, Shikai Fang, Lewen Wang, Chang Xu, Jiang Bian. [doi]
• Efficient Exploration and Discriminative World Model Learning with an Object-Centric AbstractionAnthony GX-Chen, Kenneth Marino, Rob Fergus. [doi]
• Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM GuidanceDongmin Park, Sebin Kim, Taehong Moon, Minkyu Kim, Kangwook Lee 0001, Jaewoong Cho. [doi]
• EG4D: Explicit Generation of 4D Object without Score DistillationQi Sun, Zhiyang Guo, Ziyu Wan, Jing Nathan Yan, Shengming Yin, Wengang Zhou 0001, Jing Liao 0001, Houqiang Li. [doi]
• ProteinBench: A Holistic Evaluation of Protein Foundation ModelsFei Ye, Zaixiang Zheng, Dongyu Xue, Yuning Shen, Lihao Wang, Yiming Ma, Yan Wang, Xinyou Wang, Xiangxin Zhou, Quanquan Gu. [doi]
• Robustness Inspired Graph Backdoor DefenseZhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang. [doi]
• Adaptive Pruning of Pretrained Transformer via Differential InclusionsYizhuo Ding, Ke-fan, Yikai Wang 0002, Xinwei Sun 0001, Yanwei Fu 0001. [doi]
• Metalic: Meta-Learning In-Context with Protein Language ModelsJacob Beck, Shikha Surana, Manus McAuliffe, Oliver Bent, Thomas D. Barrett, Juan Jose Garau Luis, Paul Duckworth. [doi]
• Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic SamplersRunjia Li, Qiwei Di, Quanquan Gu. [doi]
• On the Adversarial Vulnerability of Label-Free Test-Time AdaptationShahriar Rifat, Jonathan D. Ashdown, Michael J. De Lucia, Ananthram Swami, Francesco Restuccia 0001. [doi]
• A new framework for evaluating model out-of-distribution generalisation for the biochemical domainRaúl Fernandez-Diaz, Hoang Thanh Lam, Vanessa López, Denis C. Shields. [doi]
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale ScenesYang Liu 0347, Chuanchen Luo, Zhongkai Mao, Junran Peng, Zhaoxiang Zhang 0001. [doi]
• Generating Likely Counterfactuals Using Sum-Product NetworksJiri Nemecek 0002, Tomás Pevný, Jakub Marecek. [doi]
• DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single ImageQingxuan Wu, Zhiyang Dou, Sirui Xu 0002, Soshi Shimada, Chen Wang 0049, Zhengming Yu, Yuan Liu 0025, Cheng Lin, Zeyu Cao, Taku Komura, Vladislav Golyanik, Christian Theobalt, Wenping Wang, Lingjie Liu. [doi]
• Solving New Tasks by Adapting Internet Video KnowledgeCalvin Luo, Zilai Zeng, Yilun Du, Chen Sun 0002. [doi]
• Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay PerspectiveRuichen Shao, Bei Li, Gangao Liu, Yang Chen, Zhouxiang, Jingang Wang, Xunliang Cai, Peng Li. [doi]
• A-Bench: Are LMMs Masters at Evaluating AI-generated Images?Zicheng Zhang, Haoning Wu 0001, Chunyi Li, Yingjie Zhou, Wei Sun 0029, Xiongkuo Min, Zijian Chen 0001, Xiaohong Liu 0001, Weisi Lin, Guangtao Zhai. [doi]
• Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of NoiseEnea Monzio Compagnoni, Tianlin Liu, Rustem Islamov, Frank Norbert Proske, Antonio Orvieto, Aurélien Lucchi. [doi]
• Systems with Switching Causal Relations: A Meta-Causal PerspectiveMoritz Willig, Tim Nelson Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting. [doi]
• MA2E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-EncoderSehyeok Kang, Yongsik Lee, Gahee Kim, Song Chong, Se-Young Yun. [doi]
• Digi-Q: Learning VLM Q-Value Functions for Training Device-Control AgentsHao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, Aviral Kumar. [doi]
• RecDreamer: Consistent Text-to-3D Generation via Uniform Score DistillationChenxi Zheng, Yihong Lin, Bangzhen Liu, Xuemiao Xu, Yongwei Nie, Shengfeng He. [doi]
• PIED: Physics-Informed Experimental Design for Inverse ProblemsApivich Hemachandra, Gregory Kang Ruey Lau, See-Kiong Ng, Bryan Kian Hsiang Low. [doi]
• Progressive Token Length Scaling in Transformer Encoders for Efficient Universal SegmentationAbhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker. [doi]
• Open-Set Graph Anomaly Detection via Normal Structure RegularisationQizhou Wang 0001, Guansong Pang, Mahsa Salehi, Xiaokun Xia, Christopher Leckie. [doi]
• GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse RenderingHongze Chen, Zehong Lin, Jun Zhang. [doi]
• SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound GenerationKoichi Saito, Dongjun Kim, Takashi Shibuya 0001, Chieh-Hsin Lai, Zhi Zhong, Yuhta Takida, Yuki Mitsufuji. [doi]
• Large (Vision) Language Models are Unsupervised In-Context LearnersArtyom Gadetsky, Andrei Atanov, Yulun Jiang, Zhitong Gao, Ghazal Hosseini Mighan, Amir Zamir, Maria Brbic. [doi]
• ThinK: Thinner Key Cache by Query-Driven PruningYuhui Xu, Zhanming Jie, Hanze Dong, Lei Wang 0185, Xudong Lu, Aojun Zhou, Amrita Saha, Caiming Xiong, Doyen Sahoo. [doi]
• Layout-your-3D: Controllable and Precise 3D Generation with 2D BlueprintJunwei Zhou, Xueting Li, Lu Qi, Ming-Hsuan Yang. [doi]
• Learning on One Mode: Addressing Multi-modality in Offline Reinforcement LearningMianchu Wang, Yue Jin, Giovanni Montana. [doi]
• A deep inverse-mapping model for a flapping robotic wingHadar Sharvit, Raz Karl, Tsevi Beatus. [doi]
• Causally Motivated Sycophancy Mitigation for Large Language ModelsHaoxi Li, Xueyang Tang, Jie Zhang 0076, Song Guo, Sikai Bai, Peiran Dong, Yue Yu 0001. [doi]
• PABBO: Preferential Amortized Black-Box OptimizationXinyu Zhang, Daolang Huang, Samuel Kaski, Julien Martinelli. [doi]
• MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model ConstructionHossein Resani, Behrooz Nasihatkon. [doi]
• Chemistry-Inspired Diffusion with Non-Differentiable GuidanceYuchen Shen, Chenhao Zhang, Sijie Fu, Chenghui Zhou, Newell Washburn, Barnabás Póczos. [doi]
• ActSafe: Active Exploration with Safety Constraints for Reinforcement LearningYarden As, Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, Stelian Coros, Andreas Krause 0001. [doi]
• Hierarchical World Models as Visual Whole-Body Humanoid ControllersNicklas Hansen 0001, Jyothir S. V, Vlad Sobal, Yann LeCun, Xiaolong Wang 0004, Hao Su 0001. [doi]
• Improving Data Efficiency via Curating LLM-Driven Rating SystemsJinlong Pang, Jiaheng Wei, Ankit Shah 0001, Zhaowei Zhu, Yaxuan Wang, Chen Qian 0001, Yang Liu 0018, Yujia Bao, Wei Wei 0019. [doi]
• DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsHyogon Ryu, Nahyeon Park, Hyunjung Shim. [doi]
• NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamicsZiyu Lu, Wuwei Zhang, Trung Le, Hao Wang, Uygar Sümbül, Eric Todd Shea-Brown, Lu Mi. [doi]
• BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation CapabilitiesShaozhe Hao, Xuantong Liu, Xianbiao Qi, Shihao Zhao, Bojia Zi, Rong Xiao, Kai Han 0001, Kwan-Yee K. Wong. [doi]
• A Simple yet Effective ΔΔG Predictor is An Unsupervised Antibody Optimizer and ExplainerLirong Wu, Yunfan Liu 0002, Haitao Lin, Yufei Huang 0002, Guojiang Zhao, Zhifeng Gao, Stan Z. Li. [doi]
• Generative Flows on Synthetic Pathway for Drug DesignSeonghwan Seo, Minsu Kim, Tony Shen, Martin Ester, Jinkyoo Park, Sungsoo Ahn, Woo-Youn Kim. [doi]
• X-Fi: A Modality-Invariant Foundation Model for Multimodal Human SensingXinyan Chen, Jianfei Yang. [doi]
• Diffusion Bridge Implicit ModelsKaiwen Zheng, Guande He, Jianfei Chen 0001, Fan Bao, Jun Zhu 0001. [doi]
• Feature Responsiveness Scores: Model-Agnostic Explanations for RecourseSeung Hyun Cheon, Anneke Wernerfelt, Sorelle A. Friedler, Berk Ustun. [doi]
• Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypesSullam Jeoung, Yubin Ge, Haohan Wang, Jana Diesner. [doi]
• Vision-LSTM: xLSTM as Generic Vision BackboneBenedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter. [doi]
• Interpretable Causal Representation Learning for Biological Data in the Pathway SpaceJesus de la Fuente Cedeño, Robert Lehmann 0002, Carlos Ruiz-Arenas, Jan Voges, Irene Marín-Goñi, Xabier Martinez-de-morentin, David Gomez-Cabrero, Idoia Ochoa, Jesper Tegnér, Vincenzo Lagani, Mikel Hernaez. [doi]
• PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World UnderstandingWei Chow, Jiageng Mao, Boyi Li, Daniel Seita, Vitor Campagnolo Guizilini, Yue Wang 0041. [doi]
• EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM AgentsJunting Chen, Checheng Yu, Xunzhe Zhou, Tianqi Xu, Yao Mu 0001, Mengkang Hu, Wenqi Shao, Yikai Wang, Guohao Li 0013, Lin Shao 0002. [doi]
• Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language ModelsDonghoon Kim, Minji Bae, Kyuhong Shim, Byonghyo Shim. [doi]
• MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMsYusu Qian, Hanrong Ye, Jean-Philippe Fauconnier, Peter Grasch, Yinfei Yang, Zhe Gan. [doi]
• Enhanced Diffusion Sampling via Extrapolation with Multiple ODE SolutionsJinyoung Choi, Junoh Kang, Bohyung Han. [doi]
• The robustness of differentiable Causal Discovery in misspecified ScenariosHuiyang Yi, Yanyan He, Duxin Chen, Mingyu Kang, He Wang 0006, Wenwu Yu. [doi]
• Diffusion Transformers for Tabular Data Time Series GenerationFabrizio Garuti, Enver Sangineto, Simone Luetto, Lorenzo Forni, Rita Cucchiara. [doi]
• More RLHF, More Trust? On The Impact of Preference Alignment On TrustworthinessAaron Jiaxun Li, Satyapriya Krishna, Himabindu Lakkaraju. [doi]
• SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningHoJoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone 0001, Takuma Seno. [doi]
• ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample V-EnsembleTianyuan Chen, Ronglong Cai, Faguo Wu, Xiao Zhang. [doi]
• Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts ReasoningMinheng Ni, Yutao Fan, Lei Zhang 0006, Wangmeng Zuo. [doi]
• Reasoning Elicitation in Language Models via Counterfactual FeedbackAlihan Hüyük, Xinnuo Xu, Jacqueline R. M. A. Maasch, Aditya V. Nori, Javier González 0002. [doi]
• TFG-Flow: Training-free Guidance in Multimodal Generative FlowHaowei Lin, Shanda Li, Haotian Ye, Yiming Yang, Stefano Ermon, Yitao Liang, Jianzhu Ma. [doi]
• Geometry of Lightning Self-Attention: Identifiability and DimensionNathan W. Henry, Giovanni Luca Marchetti, Kathlén Kohn. [doi]
• CogCoM: A Visual Language Model with Chain-of-Manipulations ReasoningJi Qi, Ming Ding 0004, Weihan Wang, Yushi Bai, Qingsong Lv, Wenyi Hong, Bin Xu 0001, Lei Hou 0001, Juanzi Li, Yuxiao Dong, Jie Tang 0001. [doi]
• Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningYuankai Luo, Hongkang Li, Qijiong Liu, Lei Shi 0002, Xiao-Ming Wu. [doi]
• Kronecker Mask and Interpretive Prompts are Language-Action Video LearnersJingyi Yang, Zitong Yu, Xiuming Ni, Jia He, Hui Li. [doi]
• Neural Spacetimes for DAG Representation LearningHaitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong 0001, Michael M. Bronstein. [doi]
• RevisEval: Improving LLM-as-a-Judge via Response-Adapted ReferencesQiyuan Zhang, Yufei Wang, Tiezheng Yu, Yuxin Jiang, Chuhan Wu, Liangyou Li, Yasheng Wang, Xin Jiang 0002, Lifeng Shang, Ruiming Tang, Fuyuan Lyu, Chen Ma 0001. [doi]
• Simulating Human-like Daily Activities with Desire-driven AutonomyYiding Wang, Yuxuan Chen, Fangwei Zhong, Long Ma, Yizhou Wang. [doi]
• Heavy-Tailed Diffusion ModelsKushagra Pandey, Jaideep Pathak, Yilun Xu, Stephan Mandt, Michael S. Pritchard, Arash Vahdat, Morteza Mardani. [doi]
• CBQ: Cross-Block Quantization for Large Language ModelsXin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li 0002, Jie Hu 0021, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang 0001. [doi]
• Debiasing Federated Learning with Correlated Client ParticipationZhenyu Sun, Ziyang Zhang, Zheng Xu 0002, Gauri Joshi, Pranay Sharma, Ermin Wei. [doi]
• Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-MakingJincheng Wang, Penny Karanasou, Pengyuan Wei, Elia Gatti, Diego Martínez Plasencia, Dimitrios Kanoulas. [doi]
• Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?Xueru Wen, Jie Lou, Yaojie Lu 0001, Hongyu Lin, Xingyu, Xinyu Lu, Ben He, Xianpei Han, Debing Zhang, Le Sun 0001. [doi]
• Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion ModelsNajwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg 0001. [doi]
• Interactive Adjustment for Human Trajectory Prediction with Individual FeedbackJianhua Sun 0003, Yuxuan Li, Liang Chai, Cewu Lu. [doi]
• The impact of allocation strategies in subset learning on the expressive power of neural networksOfir Schlisselberg, Ran Darshan. [doi]
• Prioritized Generative ReplayRenhao Wang, Kevin Frans, Pieter Abbeel, Sergey Levine, Alexei A. Efros. [doi]
• Think while You Generate: Discrete Diffusion with Planned DenoisingSulin Liu, Juno Nam, Andrew Campbell, Hannes Stärk, Yilun Xu, Tommi S. Jaakkola, Rafael Gómez-Bombarelli. [doi]
• Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and BeyondCostin-Andrei Oncescu, Sanket Purandare, Stratos Idreos, Sham M. Kakade. [doi]
• NarrativeBridge: Enhancing Video Captioning with Causal-Temporal NarrativeAsmar Nadeem, Faegheh Sardari, Robert Dawes, Syed Sameed Husain, Adrian Hilton 0001, Armin Mustafa. [doi]
• Monet: Mixture of Monosemantic Experts for TransformersJungwoo Park, Ahn Young Jin, Kee-Eung Kim, Jaewoo Kang. [doi]
• Deconstructing Denoising Diffusion Models for Self-Supervised LearningXinlei Chen, Zhuang Liu 0003, Saining Xie, Kaiming He. [doi]
• Estimating the Probabilities of Rare Outputs in Language ModelsGabriel Wu, Jacob Hilton. [doi]
• Segment Any 3D Object with LanguageSeungjun Lee, Yuyang Zhao, Gim Hee Lee. [doi]
• Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss FunctionLinlin Yu, Bowen Yang, Tianhao Wang, Kangshuo Li, Feng Chen. [doi]
• Selective Unlearning via Representation Erasure Using Domain Adversarial TrainingNazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy 0001, Gintare Karolina Dziugaite. [doi]
• A Benchmark for Semantic Sensitive Information in LLMs OutputsQingjie Zhang, Han Qiu 0001, Di Wang, Yiming Li 0004, Tianwei Zhang 0004, Wenyu Zhu, Haiqin Weng, Liu Yan, Chao Zhang 0008. [doi]
• Has the Deep Neural Network learned the Stochastic Process? An Evaluation ViewpointHarshit Kumar, Beomseok Kang, Biswadeep Chakraborty, Saibal Mukhopadhyay. [doi]
• Causal Representation Learning from Multimodal Biomedical ObservationsYuewen Sun, Lingjing Kong, Guangyi Chen 0002, Loka Li, Gongxu Luo, Zijian Li 0001, Yixuan Zhang, Yujia Zheng, Mengyue Yang, Petar Stojanov, Eran Segal, Eric P. Xing, Kun Zhang. [doi]
• Training Neural Networks as Recognizers of Formal LanguagesAlexandra Butoi, Ghazal Khalighinejad, Anej Svete, Josef Valvoda, Ryan Cotterell, Brian DuSell. [doi]
• Safety-Prioritizing Curricula for Constrained Reinforcement LearningCevahir Köprülü, Thiago D. Simão, Nils Jansen 0001, Ufuk Topcu. [doi]
• Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under AmbiguitiesZheyuan Zhang, Fengyuan Hu, Jayjun Lee, Freda Shi, Parisa KordJamshidi, Joyce Chai, Ziqiao Ma 0001. [doi]
• Control-oriented Clustering of Visual Latent RepresentationHan Qi, Haocheng Yin, Heng Yang. [doi]
• VSTAR: Generative Temporal Nursing for Longer Dynamic Video SynthesisYumeng Li, William H. Beluch, Margret Keuper, Dan Zhang 0003, Anna Khoreva. [doi]
• Holographic Node Representations: Pre-training Task-Agnostic Node EmbeddingsBeatrice Bevilacqua, Joshua Robinson 0001, Jure Leskovec, Bruno Ribeiro 0001. [doi]
• Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion ModelsTianQi Chen, Shujian Zhang, Mingyuan Zhou. [doi]
• Emergent Orientation Maps - - Mechanisms, Coding Efficiency and RobustnessHaixin Zhong, Haoyu Wang, Wei P. Dai, Yuchao Huang, Mingyi Huang, Rubin Wang, Anna Wang Roe, Yuguo Yu. [doi]
• Multi-Robot Motion Planning with Diffusion ModelsYorai Shaoul, Itamar Mishani, Shivam Vats, Jiaoyang Li 0001, Maxim Likhachev. [doi]
• Scaling FP8 training to trillion-token LLMsMaxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry. [doi]
• Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape ViewKaiyue Wen, Zhiyuan Li 0005, Jason S. Wang, David Leo Wright Hall, Percy Liang, Tengyu Ma 0001. [doi]
• Energy-Based Diffusion Language Models for Text GenerationMinkai Xu, Tomas Geffner, Karsten Kreis, Weili Nie, Yilun Xu, Jure Leskovec, Stefano Ermon, Arash Vahdat. [doi]
• Jailbreaking as a Reward Misspecification ProblemZhihui Xie 0002, Jiahui Gao, Lei Li 0039, Zhenguo Li, Qi Liu 0049, Lingpeng Kong. [doi]
• Boosting the visual interpretability of CLIP via adversarial fine-tuningShizhan Gong, Haoyu Lei, Qi Dou 0001, Farzan Farnia. [doi]
• Cross-Modal Safety Mechanism Transfer in Large Vision-Language ModelsShicheng Xu, Liang Pang, Yunchang Zhu, Huawei Shen, Xueqi Cheng. [doi]
• Understanding Factual Recall in Transformers via Associative MemoriesEshaan Nichani, Jason D. Lee, Alberto Bietti. [doi]
• Image Watermarks are Removable using Controllable Regeneration from Clean NoiseYepeng Liu, Yiren Song, Hai Ci, Yu Zhang, Haofan Wang, Mike Zheng Shou, Yuheng Bu. [doi]
• Accelerating Training with Neuron Interaction and Nowcasting NetworksBoris Knyazev 0001, Abhinav Moudgil, Guillaume Lajoie, Eugene Belilovsky, Simon Lacoste-Julien. [doi]
• Episodic Novelty Through Temporal DistanceYuhua Jiang, Qihan Liu, Yiqin Yang, Xiaoteng Ma, Dianyu Zhong, Hao Hu 0006, Jun Yang 0028, Bin Liang 0001, Bo Xu 0002, Chongjie Zhang, Qianchuan Zhao. [doi]
• Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language ModelsGuanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu 0002, Chang Zhou, Jingren Zhou 0001. [doi]
• Iterative Label Refinement Matters More than Preference Optimization under Weak SupervisionYaowen Ye, Cassidy Laidlaw, Jacob Steinhardt. [doi]
• Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation DataPhillip Si, Peng Chen. [doi]
• AdaGrad under Anisotropic SmoothnessYuxing Liu, Rui Pan 0002, Tong Zhang 0001. [doi]
• Variational Best-of-N AlignmentAfra Amini, Tim Vieira, Elliott Ash, Ryan Cotterell. [doi]
• Re-evaluating Open-ended Evaluation of Large Language ModelsSiqi Liu 0002, Ian Gemp, Luke Marris, Georgios Piliouras, Nicolas Heess, Marc Lanctot. [doi]
• Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic FlowsXiangxin Zhou, Yi Xiao, Haowei Lin, Xinheng He, Jiaqi Guan, Yang Wang, Qiang Liu, Feng Zhou, Liang Wang, Jianzhu Ma. [doi]
• Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initializationTaishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki 0001. [doi]
• Robust Conformal Prediction with a Single Binary CertificateSoroush H. Zargarbashi, Aleksandar Bojchevski. [doi]
• Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal NoisesZirun Guo, Tao Jin 0004. [doi]
• Gradient correlation is a key ingredient to accelerate SGD with momentumJulien Hermant, Marien Renaud, Jean-François Aujol, Charles Dossal, Aude Rondepierre. [doi]
• Tracing Representation Progression: Analyzing and Enhancing Layer-Wise SimilarityJiachen Jiang, Jinxin Zhou, Zhihui Zhu. [doi]
• VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web TasksLawrence Keunho Jang, Yinheng Li, Dan Zhao, Charles Ding, Justin Lin, Paul Pu Liang, Rogerio Bonatti, Kazuhito Koishida. [doi]
• Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented GenerationShengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, Jian Guo. [doi]
• Sparse Learning for State Space Models on MobileXuan Shen, Hangyu Zheng, Yifan Gong 0004, Zhenglun Kong, Changdi Yang, Zheng Zhan 0001, Yushu Wu, Xue Lin 0001, Yanzhi Wang, Pu Zhao 0001, Wei Niu 0002. [doi]
• MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference OptimizationYougang Lyu, Lingyong Yan, Zihan Wang 0002, Dawei Yin, Pengjie Ren, Maarten de Rijke, Zhaochun Ren. [doi]
• DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural NetworksWei Liu, Li Yang, Mingxuan Zhao, Shuxun Wang, Jin Gao, Wenjuan Li, Bing Li, Weiming Hu. [doi]
• Homomorphism Expressivity of Spectral Invariant Graph Neural NetworksJingchu Gai, Yiheng Du, Bohang Zhang, Haggai Maron, Liwei Wang 0001. [doi]
• Steering Protein Family Design through Profile Bayesian FlowJingjing Gong, Yu Pei, Siyu Long, Yuxuan Song, Zhe Zhang, Wenhao Huang, Ziyao Cao, Shuyi Zhang, Hao Zhou, Wei-Ying Ma. [doi]
• Toward Exploratory Inverse Constraint Inference with Generative Diffusion VerifiersRunyi Zhao, Sheng Xu, Bo Yue, Guiliang Liu. [doi]
• Trusted Multi-View Classification via Evolutionary Multi-View FusionXinyan Liang, Pinhan Fu, Yuhua Qian, Qian Guo, Guoqing Liu. [doi]
• Exploring Learning Complexity for Efficient Downstream Dataset PruningWenyu Jiang, Zhenlong Liu, Zejian Xie, Songxin Zhang, Bingyi Jing, Hongxin Wei. [doi]
• Glad: A Streaming Scene Generator for Autonomous DrivingBin Xie, Yingfei Liu, Tiancai Wang, Jiale Cao, Xiangyu Zhang 0005. [doi]
• VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding TasksZiyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, Wenhu Chen. [doi]
• OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics GenerationYuchen Lin, Chenguo Lin, Jianjin Xu, Yadong Mu. [doi]
• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank AdaptationTeng Hu, Jiangning Zhang, Ran Yi, Hongrui Huang, Yabiao Wang, Lizhuang Ma. [doi]
• Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model AlignmentMingzhi Wang, Chengdong Ma, Qizhi Chen, Linjian Meng, Yang Han, Jiancong Xiao, Zhaowei Zhang, Jing Huo, Weijie J. Su, Yaodong Yang 0001. [doi]
• PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemsBocheng Zeng, Qi Wang, Mengtao Yan, Yang Liu, Ruizhi Chengze, Yi Zhang, Hongsheng Liu, Zidong Wang, Hao Sun. [doi]
• OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language ModelsJunda Wu, Xintong Li, Ruoyu Wang, Yu Xia 0007, Yuxin Xiong, Jianing Wang, Tong Yu, Xiang Chen, Branislav Kveton, Lina Yao 0001, Jingbo Shang, Julian J. McAuley. [doi]
• InversionGNN: A Dual Path Network for Multi-Property Molecular OptimizationYifan Niu, Ziqi Gao, Tingyang Xu, Yang Liu 0165, Yatao Bian, Yu Rong 0001, JunZhou Huang, Jia Li 0009. [doi]
• Round and Round We Go! What makes Rotary Positional Encodings useful?Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Velickovic. [doi]
• Revisiting Multi-Permutation Equivariance through the Lens of irreducible RepresentationsYonatan Sverdlov, Ido Springer, Nadav Dym. [doi]
• Epistemic Monte Carlo Tree SearchYaniv Oren, Viliam Vadocz, Matthijs T. J. Spaan, Wendelin Boehmer. [doi]
• ElasticTok: Adaptive Tokenization for Image and VideoWilson Yan, Volodymyr Mnih, Aleksandra Faust, Matei Zaharia, Pieter Abbeel, Hao Liu. [doi]
• UniCoTT: A Unified Framework for Structural Chain-of-Thought DistillationXianwei Zhuang, Zhihong Zhu, Zhichang Wang, Xuxin Cheng, Yuexian Zou. [doi]
• Decision Tree Induction Through LLMs via Semantically-Aware EvolutionTennison Liu, Nicolas Huynh, Mihaela van der Schaar. [doi]
• MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification PredictionCheng Tan 0012, Zhenxiao Cao, Zhangyang Gao, Lirong Wu, Siyuan Li 0002, Yufei Huang 0002, Jun Xia 0001, Bozhen Hu, Stan Z. Li. [doi]
• Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and AttentionTongzhou Liao, Barnabás Póczos. [doi]
• BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RLYu-Heng Hung, Kai-Jie Lin, Yu-Heng Lin, Chien-Yi Wang, Cheng Sun, Ping-Chun Hsieh. [doi]
• Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal ChoiceJian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths 0001. [doi]
• Disentangling 3D Animal Pose Dynamics with Scrubbed Conditional Latent VariablesJoshua Huang Wu, Hari Koneru, James Russell Ravenel, Anshuman Sabath, James Michael Roach, Shaun Sze-Xian Lim, Michael R. Tadross, Alex H. Williams, Timothy W. Dunn. [doi]
• Improving Long-Text Alignment for Text-to-Image Diffusion ModelsLuping Liu, Chao Du, Tianyu Pang, Zehan Wang 0001, Chongxuan Li, Dong Xu. [doi]
• No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth DataDaniel Cai, Randall Balestriero. [doi]
• A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization ProblemsShulan Zhu, Chenglong Bao, Defeng Sun, Yancheng Yuan. [doi]
• Reinforcement Learning from Imperfect Corrective Actions and Proxy RewardsZhaohui Jiang, Xuening Feng, Paul Weng, Yifei Zhu, Yan Song, Tianze Zhou, Yujing Hu, Tangjie Lv, Changjie Fan. [doi]
• GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time AlignmentYuancheng Xu, Udari Madhushani Sehwag, Alec Koppel, Sicheng Zhu, Bang An 0001, Furong Huang, Sumitra Ganesh. [doi]
• LLM-SR: Scientific Equation Discovery via Programming with Large Language ModelsParshin Shojaee, Kazem Meidani, Shashank Gupta, Amir Barati Farimani, Chandan K. Reddy. [doi]
• Unlocking Global Optimality in Bilevel Optimization: A Pilot StudyQuan Xiao, Tianyi Chen. [doi]
• RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUsXi Xie, Yuebo Luo, Hongwu Peng, Caiwen Ding. [doi]
• ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion SamplerSerin Yang, Taesung Kwon, Jong Chul Ye. [doi]
• Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent SystemsGuibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, Tianlong Chen 0001. [doi]
• Regularizing Energy among Training Samples for Out-of-Distribution GeneralizationYiting Chen 0003, Qitian Wu, Junchi Yan. [doi]
• Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning ProcessTian Ye 0011, Zicheng Xu, Yuanzhi Li, Zeyuan Allen Zhu. [doi]
• Quantitative Approximation for Neural Operators in Nonlinear Parabolic EquationsTakashi Furuya, Koichi Taniguchi, Satoshi Okuda. [doi]
• An Evolved Universal Transformer MemoryEdoardo Cetin, Qi Sun, Tianyu Zhao 0001, Yujin Tang. [doi]
• Generation and Comprehension Hand-in-Hand: Vision-guided Expression Diffusion for Boosting Referring Expression Generation and ComprehensionJingcheng Ke, Jun-Cheng Chen, I-Hong Jhuo, Chia-Wen Lin, Yen-Yu Lin. [doi]
• Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving SequencesAlan Nawzad Amin, Nate Gruver, Yilun Kuang, Yucen Lily Li, Hunter Elliott, Calvin McCarter, Aniruddh Raghu, Peyton Greenside, Andrew Gordon Wilson. [doi]
• MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?Yifan Zhang 0004, Huanyu Zhang, Haochen Tian, Chaoyou Fu, Shuangqing Zhang, Junfei Wu, Feng Li, Kun Wang, Qingsong Wen, Zhang Zhang 0001, Liang Wang 0001, Rong Jin 0001. [doi]
• Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale BenchmarkHaining Yu, Yizhou Sun. [doi]
• Selective induction Heads: How Transformers Select Causal Structures in ContextFrancesco D'Angelo, Francesco Croce, Nicolas Flammarion. [doi]
• RNNs are not Transformers (Yet): The Key Bottleneck on In-Context RetrievalKaiyue Wen, Xingyu Dang, Kaifeng Lyu. [doi]
• Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image DenoisingZhengwei Yin, Hongjun Wang 0007, Guixu Lin, Weihang Ran, Yinqiang Zheng. [doi]
• Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular SystemsYunyang Li, Zaishuo Xia, Lin Huang, Xinran Wei, Samuel Harshe, Han Yang, Erpai Luo, Zun Wang, Jia Zhang, Chang Liu, Bin Shao, Mark Gerstein. [doi]
• GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and GaussiansShuyi Jiang, QiHao Zhao, Hossein Rahmani 0001, De Wen Soh, Jun Liu 0036, Na Zhao. [doi]
• TULIP: Token-length Upgraded CLIPIvona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki M. Asano, Nanne van Noord, Marcel Worring, Cees G. M. Snoek. [doi]
• HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model DebuggingMuxi Chen, Chenchen Zhao, Qiang Xu 0001. [doi]
• No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion ModelsSeyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber. [doi]
• Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented DiffusionZhenwei Wang 0003, Tengfei Wang 0002, Zexin He, Gerhard Petrus Hancke, Ziwei Liu 0002, Rynson W. H. Lau. [doi]
• TC-MoE: Augmenting Mixture of Experts with Ternary Expert ChoiceShen Yan, Xingyan Bin, Sijun Zhang, Yisen Wang 0001, Zhouchen Lin. [doi]
• Incorporating Visual Correspondence into Diffusion Model for Virtual Try-OnSiqi Wan, Jingwen Chen, Yingwei Pan, Ting Yao, Tao Mei 0001. [doi]
• HQ-Edit: A High-Quality Dataset for Instruction-based Image EditingMude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang, Peng Wang, Cihang Xie, Yuyin Zhou. [doi]
• DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories SearchMurong Yue, Wenlin Yao, Haitao Mi, Dian Yu 0001, Ziyu Yao, Dong Yu. [doi]
• HART: Efficient Visual Generation with Hybrid Autoregressive TransformerHaotian Tang, Yecheng Wu, Shang Yang, Enze Xie, Junsong Chen, Junyu Chen, Zhuoyang Zhang, Han Cai, Yao Lu 0006, Song Han 0003. [doi]
• MamKO: Mamba-based Koopman operator for modeling and predictive controlZhaoyang Li, Minghao Han, Xunyuan Yin. [doi]
• Language Models Are Implicitly ContinuousSamuele Marro, Davide Evangelista, X. Angelo Huang, Emanuele La Malfa, Michele Lombardi 0001, Michael J. Wooldridge. [doi]
• DynFrs: An Efficient Framework for Machine Unlearning in Random ForestShurong Wang, Zhuoyang Shen, Xinbao Qiao, Tongning Zhang, Meng Zhang. [doi]
• Simple, Good, Fast: Self-Supervised World Models Free of BaggageJan Robine, Marc Höftmann, Stefan Harmeling. [doi]
• Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language ModelsPit Neitemeier, Björn Deiseroth, Constantin Eichenberg, Lukas Balles. [doi]
• Emergence of a High-Dimensional Abstraction Phase in Language TransformersEmily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Lei Yu, Alessandro Laio, Marco Baroni. [doi]
• Once-for-All: Controllable Generative Image Compression with Dynamic Granularity AdaptationAnqi Li, Feng Li 0037, Yuxi Liu, Runmin Cong, Yao Zhao 0001, Huihui Bai 0001. [doi]
• DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement LearningChao Li, Ziwei Deng, Chenxing Lin, Wenqi Chen, Yongquan Fu, Weiquan Liu, Chenglu Wen, Cheng Wang 0003, Siqi Shen. [doi]
• High-quality Text-to-3D Character Generation with SparseCubes and Sparse TransformersJiachen Qian, Hongye Yang, Shuang Wu, Jingxi Xu 0001, Feihu Zhang. [doi]
• Looking into User's Long-term Interests through the Lens of Conservative Evidential LearningDingrong Wang, Krishna Prasad Neupane, Ervine Zheng, Qi Yu 0001. [doi]
• Ensembles of Low-Rank Expert AdaptersYinghao Li, Vianne R. Gao, Chao Zhang, MohamadAli Torkamani. [doi]
• Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and EfficiencyJerry Yao-Chieh Hu, Wei-Po Wang, Ammar Gilani, Chenyang Li, Zhao Song 0002, Han Liu 0001. [doi]
• MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked TransformerYilin Wang, Chuan Guo 0002, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng 0001. [doi]
• Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised LearningSheng Li 0019, Qitao Tan, Yue Dai 0005, Zhenglun Kong, Tianyu Wang, Jun Liu, Ao Li 0004, Ninghao Liu, Yufei Ding 0001, Xulong Tang, Geng Yuan. [doi]
• MrSteve: Instruction-Following Agents in Minecraft with What-Where-When MemoryJunyeong Park, Junmo Cho, Sungjin Ahn. [doi]
• Fengbo: a Clifford Neural Operator pipeline for 3D PDEs in Computational Fluid DynamicsAlberto Pepe, Mattia Montanari, Joan Lasenby. [doi]
• Beyond Next Token Prediction: Patch-Level Training for Large Language ModelsChenze Shao, Fandong Meng, Jie Zhou. [doi]
• Debiasing Mini-Batch Quadratics for Applications in Deep LearningLukas Tatzel, Bálint Mucsányi, Osane Hackel, Philipp Hennig. [doi]
• Counterfactual RealizabilityArvind Raghavan, Elias Bareinboim. [doi]
• Quantifying Generalization Complexity for Large Language ModelsZhenting Qi, Hongyin Luo, Xuliang Huang, Zhuokai Zhao, Yibo Jiang, Xiangjun Fan, Himabindu Lakkaraju, James R. Glass. [doi]
• Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype ConstructionShengju Yu, Zhibin Dong, Siwei Wang, Pei Zhang 0008, Yi Zhang, Xinwang Liu, Naiyang Guan, Tiejun Li, Yiu-ming Cheung. [doi]
• FaceShot: Bring Any Character into LifeJunyao Gao 0002, Yanan Sun 0005, Fei Shen, Xin Jiang 0010, Zhening Xing, Kai Chen 0026, Cairong Zhao. [doi]
• Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree SearchJonathan Light, Min Cai, Weiqin Chen 0003, Guanzhi Wang, Xiusi Chen, Wei Cheng, Yisong Yue, Ziniu Hu. [doi]
• DyCAST: Learning Dynamic Causal Structure from Time SeriesYue Cheng, Bochen Lyu, Weiwei Xing, Zhanxing Zhu. [doi]
• Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language ModelsBiao Yi, Tiansheng Huang, Sishuo Chen, Tong Li 0011, Zheli Liu, Zhixuan Chu, Yiming Li 0004. [doi]
• Wasserstein-Regularized Conformal Prediction under General Distribution ShiftRui Xu, Chao Chen, Yue Sun, Parvathinathan Venkitasubramaniam, Sihong Xie. [doi]
• Re-Aligning Language to Visual Objects with an Agentic WorkflowYuming Chen, Jiangyan Feng, Haodong Zhang, Lijun Gong, Feng Zhu 0006, Rui Zhao 0001, Qibin Hou, Ming-Ming Cheng, Yibing Song. [doi]
• SafeDiffuser: Safe Planning with Diffusion Probabilistic ModelsWei Xiao 0003, Tsun-Hsuan Wang, Chuang Gan, Ramin M. Hasani, Mathias Lechner, Daniela Rus. [doi]
• Reasoning with Latent Thoughts: On the Power of Looped TransformersNikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi. [doi]
• SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?John Yang, Carlos E. Jimenez, Alex L. Zhang, Kilian Lieret, Joyce Yang, Xindi Wu, Ori Press, Niklas Muennighoff, Gabriel Synnaeve, Karthik R. Narasimhan, Diyi Yang, Sida Wang 0001, Ofir Press. [doi]
• Self-Normalized Resets for Plasticity in Continual LearningVivek F. Farias, Adam Daniel Jozefiak. [doi]
• Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion ModelsYongjin Yang, Sihyeon Kim, Hojung Jung, Sangmin Bae, Sangmook Kim, Se-Young Yun, Kimin Lee. [doi]
• Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck PerspectiveZeyu Gan, Yong Liu. [doi]
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMsSungmin Cha, Sungjun Cho, Dasol Hwang, Moontae Lee. [doi]
• Probabilistic Conformal Prediction with Approximate Conditional ValidityVincent Plassier, Alexander Fishkov, Mohsen Guizani, Maxim Panov, Eric Moulines. [doi]
• L3Ms - Lagrange Large Language ModelsGuneet S. Dhillon, Xingjian Shi, Yee Whye Teh, Alex Smola. [doi]
• The Optimization Landscape of SGD Across the Feature Learning StrengthAlexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan. [doi]
• Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human FeedbackZexu Sun, Yiju Guo, Yankai Lin, Xu Chen 0017, Qi Qi 0003, Xing Tang 0007, Xiuqiang He 0001, Ji-Rong Wen. [doi]
• Federated Domain Generalization with Data-free On-server Matching GradientTrong-Binh Nguyen, Duong Minh Nguyen, Jinsun Park, Viet Quoc Pham, Won-Joo Hwang. [doi]
• Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive RepresentationsYupei Yang, Biwei Huang, Fan Feng, Xinyue Wang, Shikui Tu, Lei Xu 0001. [doi]
• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous AgentsChristopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William E. Bishop, Wei Li, Folawiyo Campbell-Ajala, Daniel Kenji Toyama, Robert James Berry, Divya Tyamagundlu, Timothy P. Lillicrap, Oriana Riva. [doi]
• Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large ModelsXiongye Xiao, Heng Ping, Chenyu Zhou, Defu Cao, Yaxing Li, Yizhuo Zhou, Shixuan Li, Nikos Kanakaris, Paul Bogdan. [doi]
• Enhancing Robust Fairness via Confusional Spectral RegularizationGaojie Jin, Sihao Wu, Jiaxu Liu 0001, Tianjin Huang, Ronghui Mu. [doi]
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in SportsYi Xu, Yun Fu. [doi]
• Flow matching achieves almost minimax optimal convergenceKenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama. [doi]
• SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative RefinementAntonis Antoniades, Albert Örwall, Kexun Zhang, Yuxi Xie, Anirudh Goyal, William Yang Wang. [doi]
• Severing Spurious Correlations with Data PruningVarun Mulchandani, Jung-Eun Kim. [doi]
• MixEval-X: Any-to-any Evaluations from Real-world Data MixtureJinjie Ni, Yifan Song, Deepanway Ghosal, Bo Li, David Junhao Zhang, Xiang Yue, Fuzhao Xue, Yuntian Deng, Zian Zheng 0001, Kaichen Zhang, Mahir Shah, Kabir Jain, Yang You 0001, Michael Shieh. [doi]
• Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation ModelsJeffrey Gu, Serena Yeung-Levy. [doi]
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language ModelYushu Li, Yongyi Su, Adam Goodge, Kui Jia, Xun Xu 0002. [doi]
• Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate RolloutBharat Srikishan, Daniel O'Malley, Mohamed Mehana, Nicholas Lubbers, Nikhil Muralidhar. [doi]
• Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifoldSixin Zhang. [doi]
• CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsZheng Chong, Xiao Dong, Haoxiang Li, Shiyue Zhang, Wenqing Zhang, Hanqing Zhao, Xujie Zhang, Dongmei Jiang, Xiaodan Liang. [doi]
• Computational Explorations of Total Variation DistanceArnab Bhattacharyya 0001, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, Aduri Pavan, N. V. Vinodchandran. [doi]
• Latent Radiance Fields with 3D-aware 2D RepresentationsChaoyi Zhou, Xi Liu, Feng Luo, Siyu Huang. [doi]
• Controllable Context Sensitivity and the Knob Behind ItJulian Minder, Kevin Du, Niklas Stoehr, Giovanni Monea, Chris Wendler, Robert West 0001, Ryan Cotterell. [doi]
• Extending Mercer's expansion to indefinite and asymmetric kernelsSungwoo Jeong, Alex Townsend. [doi]
• Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement LearningRui Yang, Jie Wang 0005, Qijie Peng, Ruibo Guo, Guoping Wu, Bin Li 0025. [doi]
• Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal ControlCarles Domingo-Enrich, Michal Drozdzal, Brian Karrer, Ricky T. Q. Chen. [doi]
• MuHBoost: Multi-Label Boosting For Practical Longitudinal Human Behavior ModelingNguyen T. Thach, Patrick Habecker, Anika R. Eisenbraun, Alex Mason, Kimberly Tyler, Bilal Khan 0002, Hau Chan. [doi]
• RECAST: Reparameterized, Compact weight Adaptation for Sequential TasksNazia Tasnim, Bryan A. Plummer. [doi]
• Continuous Diffusion for Mixed-Type Tabular DataMarkus Mueller, Kathrin Gruber, Dennis Fok. [doi]
• VisualAgentBench: Towards Large Multimodal Models as Visual Foundation AgentsXiao Liu 0036, Tianjie Zhang, Yu Gu 0016, Iat Long Iong, Xixuan Song, Yifan Xu, Shudan Zhang, Hanyu Lai, Jiadai Sun, Xinyue Yang, Yu Yang, Zehan Qi, Shuntian Yao, Xueqiao Sun, Siyi Cheng, Qinkai Zheng, Hao Yu, Hanchen Zhang, Wenyi Hong, Ming Ding 0004, et al.. [doi]
• AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile SensorsRuoxuan Feng, Jiangyu Hu, Wenke Xia, Tianci Gao, Ao Shen, Yuhao Sun, Bin Fang, Di Hu 0001. [doi]
• JPEG Inspired Deep LearningAhmed H. Salamah, Kaixiang Zheng, Yiwen Liu, En-Hui Yang. [doi]
• Instruct-SkillMix: A Powerful Pipeline for LLM Instruction TuningSimran Kaur 0001, Simon Park 0002, Anirudh Goyal, Sanjeev Arora. [doi]
• Ranking-aware adapter for text-driven image ordering with CLIPWei-Hsiang Yu, Yen-Yu Lin, Ming-Hsuan Yang 0001, Yi-Hsuan Tsai. [doi]
• Bounds on Lp Errors in Density Ratio Estimation via f-Divergence Loss FunctionsYoshiaki Kitazawa. [doi]
• Guaranteed Generation from Large Language ModelsMinbeom Kim, Thibaut Thonet, Jos Rozen, Hwaran Lee, Kyomin Jung, Marc Dymetman. [doi]
• Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representationsLorenzo Basile, Santiago Acevedo, Luca Bortolussi, Fabio Anselmi, Alex Rodriguez. [doi]
• UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion ModelsFanghua Yu, Jinjin Gu, Jinfan Hu, Zheyuan Li, Chao Dong 0005. [doi]
• Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic ProcessesGeorg Manten, Cecilia Casolo, Emilio Ferrucci, Søren Wengel Mogensen, Cristopher Salvi, Niki Kilbertus. [doi]
• MixMax: Distributional Robustness in Function Space via Optimal Data MixturesAnvith Thudi, Chris J. Maddison. [doi]
• Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology ImagesSichen Zhu, Yuchen Zhu, Molei Tao, Peng Qiu. [doi]
• DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RLMathias Jackermeier, Alessandro Abate. [doi]
• Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control TasksMichael T. Matthews, Michael Beukman, Chris Lu 0001, Jakob Nicolaus Foerster. [doi]
• InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information ShapingYunchao Zhang, Guandao Yang, Leonidas J. Guibas, Yanchao Yang 0001. [doi]
• From Commands to Prompts: LLM-based Semantic File System for AIOSZeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu 0001, Mengnan Du, Dong Deng 0001, Yongfeng Zhang. [doi]
• Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised DataJiajie Li 0002, Brian R. Quaranto, Chenhui Xu, Ishan Mishra, Ruiyang Qin, Dancheng Liu, Peter C. W. Kim, Jinjun Xiong. [doi]
• MuirBench: A Comprehensive Benchmark for Robust Multi-image UnderstandingFei Wang 0060, Xingyu Fu, James Y. Huang, Zekun Li 0007, Qin Liu 0010, Xiaogeng Liu, Mingyu Derek Ma, Nan Xu, Wenxuan Zhou, Kai Zhang 0008, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li, Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang 0012, Hoifung Poon, et al.. [doi]
• How DNNs break the Curse of Dimensionality: Compositionality and Symmetry LearningArthur Jacot, Seok Hoan Choi, Yuxiao Wen. [doi]
• FlowDec: A flow-based full-band general audio codec with high perceptual qualitySimon Welker, Matthew Le 0001, Ricky T. Q. Chen, Wei-Ning Hsu, Timo Gerkmann, Alexander Richard, Yi-Chiao Wu. [doi]
• Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task LearningYuxiang Lu, Shengcao Cao, Yu-Xiong Wang. [doi]
• RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language ModelsYoungJun Lee, Doyoung Kim, Junhyeok Kang, Jihwan Bang, Hwanjun Song, Jae-Gil Lee 0001. [doi]
• Differentiable Optimization of Similarity Scores Between Models and BrainsNathan Cloos, Moufan Li, Markus Siegel, Scott L. Brincat, Earl K. Miller, Guangyu Robert Yang, Christopher J. Cueva. [doi]
• Training-Free Activation Sparsity in Large Language ModelsJames Liu, Pragaash Ponnusamy, Tianle Cai, Han Guo, Yoon Kim, Ben Athiwaratkun. [doi]
• Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based PriorsChen Ma 0003, Xinjie Xu, Shuyu Cheng, Qi Xuan. [doi]
• Lipschitz Bandits in Optimal SpaceXiaoyi Zhu, Zengfeng Huang. [doi]
• OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification InferenceDujian Ding, Bicheng Xu, Laks V. S. Lakshmanan. [doi]
• LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-MeshJing Wen, Alexander G. Schwing, Shenlong Wang. [doi]
• A Conditional Independence Test in the Presence of DiscretizationBoyang Sun, Yu Yao, Guang-Yuan Hao, Yumou Qiu, Kun Zhang. [doi]
• Discrete Diffusion Schrödinger Bridge Matching for Graph TransformationJun Hyeong Kim, Seonghwan Kim 0004, Seokhyun Moon, Hyeongwoo Kim, Jeheon Woo, Woo-Youn Kim. [doi]
• Deep MMD Gradient Flow without adversarial trainingAlexandre Galashov, Valentin De Bortoli, Arthur Gretton. [doi]
• Learning Dynamics of LLM FinetuningYi Ren, Danica J. Sutherland. [doi]
• PiCO: Peer Review in LLMs based on Consistency OptimizationKun-Peng Ning, Shuo Yang, Yuyang Liu, Jia-Yu Yao, Zhen-Hui Liu, Yonghong Tian 0001, Yibing Song, Li Yuan 0007. [doi]
• Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language ModelLongrong Yang, Dong Shen, Chaoxiang Cai, Fan Yang, Tingting Gao, Di Zhang, Xi Li. [doi]
• Can a Large Language Model be a Gaslighter?Wei Li 0076, Luyao Zhu, Yang Song, Ruixi Lin, Rui Mao 0010, Yang You. [doi]
• BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulationDiego Garcia Cerdas, Christina Sartzetaki, Magnus Petersen, Gemma Roig, Pascal Mettes, Iris I. A. Groen. [doi]
• Syntactic and Semantic Control of Large Language Models via Sequential Monte CarloJoão Loula, Benjamin LeBrun, Li Du, Ben Lipkin, Clemente Pasti, Gabriel Grand, Tianyu Liu 0004, Yahya Emara, Marjorie Freedman, Jason Eisner, Ryan Cotterell, Vikash Mansinghka 0001, Alexander K. Lew, Tim Vieira, Timothy J. O'Donnell. [doi]
• Benchmarking Predictive Coding Networks - Made SimpleLuca Pinchetti, Chang Qi, Oleh Lokshyn, Cornelius Emde, Amine M'Charrak, Mufeng Tang, Simon Frieder, Bayar Menzat, Gaspard Oliviers, Rafal Bogacz, Thomas Lukasiewicz, Tommaso Salvatori. [doi]
• From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic DataZheyang Xiong, Vasilis Papageorgiou, Kangwook Lee 0001, Dimitris Papailiopoulos. [doi]
• Shape as Line Segments: Accurate and Flexible Implicit Surface RepresentationSiyu Ren, Junhui Hou. [doi]
• MIND: Math Informed syNthetic Dialogues for Pretraining LLMsSyeda Nahida Akter, Shrimai Prabhumoye, John Kamalu, Sanjeev Satheesh, Eric Nyberg, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro. [doi]
• Understanding Virtual Nodes: Oversquashing and Node HeterogeneityJoshua Southern, Francesco Di Giovanni, Michael M. Bronstein, Johannes F. Lutzeyer. [doi]
• Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-TuningYeoreum Lee, Jinwook Jung, Sungyong Baik. [doi]
• An Optimal Discriminator Weighted Imitation Perspective for Reinforcement LearningHaoran Xu 0003, Shuozhe Li, Harshit Sikchi, Scott Niekum, Amy Zhang 0001. [doi]
• Biologically Plausible Brain Graph TransformerCiyuan Peng, Yuelong Huang, Qichao Dong, Shuo Yu 0001, Feng Xia 0001, Chengqi Zhang, Yaochu Jin. [doi]
• Deep Signature: Characterization of Large-Scale Molecular DynamicsTiexin Qin, Mengxu Zhu, Chunyang Li, Terry Lyons, Hong Yan 0001, Haoliang Li. [doi]
• DRL: Decomposed Representation Learning for Tabular Anomaly DetectionHangting Ye, He Zhao 0001, Wei Fan 0010, Mingyuan Zhou, Dandan Guo, Yi Chang 0001. [doi]
• MCNC: Manifold-Constrained Reparameterization for Neural CompressionChayne Thrash, Reed Andreas, Ali Abbasi 0008, Parsa Nooralinejad, Soroush Abbasi Koohpayegani, Hamed Pirsiavash, Soheil Kolouri. [doi]
• Breaking the log⁡(1/Δ2) Barrier: Better Batched Best Arm Identification with Adaptive GridsTianyuan Jin, Qin Zhang 0001, Dongruo Zhou. [doi]
• On the Benefits of Memory for Modeling Time-Dependent PDEsRicardo Buitrago Ruiz, Tanya Marwah, Albert Gu, Andrej Risteski. [doi]
• OASIS Uncovers: High-Quality T2I Models, Same Old StereotypesSepehr Dehdashtian, Gautam Sreekumar, Vishnu Boddeti. [doi]
• Generalization Bounds for Canonicalization: A Comparative Study with Group AveragingBehrooz Tahmasebi, Stefanie Jegelka. [doi]
• Test-time Adaptation for Image Compression with Distribution RegularizationKecheng Chen, Pingping Zhang, Tiexin Qin, Shiqi Wang 0001, Hong Yan 0001, Haoliang Li. [doi]
• Distance-Based Tree-Sliced Wasserstein DistanceHoang V. Tran, Minh-Khoi Nguyen-Nhat, Huyen-Trang Pham, Thanh T. Chu, Tam Le, Tan Minh Nguyen. [doi]
• Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion ModelHan Lin, Jaemin Cho 0001, Abhay Zala, Mohit Bansal. [doi]
• Scaling up Masked Diffusion Models on TextShen Nie, Fengqi Zhu, Chao Du, Tianyu Pang, Qian Liu, Guangtao Zeng, Min Lin, Chongxuan Li. [doi]
• Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive LearningNan Jiang, Chengxiao Wang, Kevin Liu, Xiangzhe Xu, Lin Tan 0001, Xiangyu Zhang 0001, Petr Babkin. [doi]
• Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-ProbingQi Le, Enmao Diao, Ziyan Wang, Xinran Wang, Jie Ding 0002, Li Yang, Ali Anwar 0001. [doi]
• Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text ClassificationHsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao, Wei-Yun Ma, Pu-Jen Cheng. [doi]
• HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token MiningMinjae Jeong, Yechan Hwang, Jaejin Lee, Sungyoon Jung, Won Hwa Kim. [doi]
• Training Language Models to Self-Correct via Reinforcement LearningAviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D. Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M. Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal M. P. Behbahani, Aleksandra Faust. [doi]
• Forget the Data and Fine-Tuning! Just Fold the Network to CompressDong Wang, Haris Sikic, Lothar Thiele, Olga Saukh. [doi]
• Speech Robust Bench: A Robustness Benchmark For Speech RecognitionMuhammad A. Shah, David Solans Noguero, Mikko A. Heikkilä, Bhiksha Raj, Nicolas Kourtellis. [doi]
• MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation MethodsZukang Xu, Yuxuan Yue, Xing Hu 0010, Dawei Yang, Zhihang Yuan, Zixu Jiang, Zhixuan Chen, Jiangyong Yu, Chen Xu, Sifan Zhou. [doi]
• HAMSTER: Hierarchical Action Models for Open-World Robot ManipulationYi Li 0038, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, Caelan Reed Garrett, Fabio Ramos 0001, Dieter Fox, Anqi Li 0001, Abhishek Gupta 0004, Ankit Goyal 0001. [doi]
• BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural DynamicsKeyi Shen, Jiangwei Yu, Jose Barreiros, Huan Zhang, Yunzhu Li. [doi]
• Local Patterns Generalize Better for Novel AnomaliesYalong Jiang. [doi]
• Let Your Features Tell The Differences: Understanding Graph Convolution By Feature SplittingYilun Zheng, Xiang Li, Sitao Luan, Xiaojiang Peng, Lihui Chen. [doi]
• Learning Spatial-Semantic Features for Robust Video Object SegmentationXin Li 0034, Deshui Miao, Zhenyu He 0001, Yaowei Wang 0001, Huchuan Lu, Ming-Hsuan Yang 0001. [doi]
• Taming Transformer Without Using Learning Rate WarmupXianbiao Qi, Yelin He, Jiaquan Ye, Chun-Guang Li, Bojia Zi, Xili Dai, Qin Zou 0001, Rong Xiao 0003. [doi]
• Style Outweighs Substance: Failure Modes of LLM Judges in Alignment BenchmarkingBenjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar, Raz Besaleli, Samuel Dooley, Max Cembalest, John P. Dickerson. [doi]
• EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face GenerationJiajian Xie, Shengyu Zhang, Mengze Li, Chengfei Lv, Zhou Zhao, Fei Wu. [doi]
• Data-centric Prediction Explanation via Kernelized Stein DiscrepancyMahtab Sarvmaili, Hassan Sajjad 0001, Ga Wu. [doi]
• EvA: Erasing Spurious Correlations with ActivationsQiyuan He, Kai Xu, Angela Yao. [doi]
• Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural RepresentationQing Wu, Chenhe Du, Xuanyu Tian, Jingyi Yu, Yuyao Zhang, Hongjiang Wei. [doi]
• ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG CapabilitiesPeng Xu 0008, Wei Ping, Xianchao Wu, Chejian Xu, Zihan Liu 0001, Mohammad Shoeybi, Bryan Catanzaro. [doi]
• 4K4DGen: Panoramic 4D Generation at 4K ResolutionRenjie Li, Panwang Pan, Bangbang Yang, Dejia Xu, Shijie Zhou 0003, Xuanyang Zhang, Zeming Li, Achuta Kadambi, Zhangyang Wang, Zhengzhong Tu, Zhiwen Fan. [doi]
• Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing ModelsHanmo Liu, Shimin Di, Jialiang Wang, Zhili Wang, Jiachuan Wang, Xiaofang Zhou 0001, Lei Chen 0002. [doi]
• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional VideosYufan Zhou, Zhaobo Qi, Lingshuai Lin, Junqi Jing, Tingting Chai, Beichen Zhang, Shuhui Wang, Weigang Zhang. [doi]
• Temporal Difference Learning: Why It Can Be Fast and How It Will Be FasterPatrick Schnell, Luca Guastoni, Nils Thuerey. [doi]
• GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEsKalliopi Basioti, Pritish Sahu, Tony Qingze Liu, Zihao Xu 0001, Hao Wang 0014, Vladimir Pavlovic 0001. [doi]
• On Large Language Model Continual UnlearningChongyang Gao, Lixu Wang, Kaize Ding, Chenkai Weng, Xiao Wang, Qi Zhu. [doi]
• Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative StudyLili Zhao 0002, Yang Wang, Qi Liu, Mengyun Wang, Wei Chen 0156, Zhichao Sheng, Shijin Wang 0001. [doi]
• Learning a Fast Mixing Exogenous Block MDP using a Single TrajectoryAlexander Levine 0001, Peter Stone 0001, Amy Zhang 0001. [doi]
• PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future ScoresGuangyi Wang, Yuren Cai, Lijiang Li, Wei Peng 0009, Song-Zhi Su. [doi]
• Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language RecognitionXinyu Tian, Shu Zou, Zhaoyuan Yang, Mengqi He, Jing Zhang 0052. [doi]
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language ModelsSamuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller. [doi]
• pMoE: Prompting Diverse Experts Together Wins More in Visual AdaptationShentong Mo, Xufang Luo, Dongsheng Li 0002. [doi]
• Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequencesNiklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer. [doi]
• CtrLoRA: An Extensible and Efficient Framework for Controllable Image GenerationYifeng Xu, Zhenliang He, Shiguang Shan, Xilin Chen 0001. [doi]
• OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner FrameworkJunliang Chen, Huaiyuan Xu, Yi Wang 0068, Lap-Pui Chau. [doi]
• Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field GenerationKangfu Mei, Mo Zhou, Vishal M. Patel. [doi]
• Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic AlignmentYizhi Song, Liu He, Zhifei Zhang, Soo Ye Kim, He Zhang 0004, Wei Xiong 0008, Zhe Lin 0001, Brian L. Price, Scott Cohen, Jianming Zhang 0001, Daniel G. Aliaga. [doi]
• Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image GenerationLokesh Veeramacheneni, Moritz Wolter, Hilde Kuehne, Juergen Gall. [doi]
• One Hundred Neural Networks and Brains Watching Videos: Lessons from AlignmentChristina Sartzetaki, Gemma Roig, Cees G. M. Snoek, Iris I. A. Groen. [doi]
• Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic LearningHaque Ishfaq, Guangyuan Wang, Sami Nur Islam, Doina Precup. [doi]
• Conservative Contextual Bandits: Beyond Linear RepresentationsRohan Deb, Mohammad Ghavamzadeh, Arindam Banerjee 0001. [doi]
• From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual ModalitiesWanpeng Zhang 0002, Zilong Xie, Yicheng Feng, Yijiang Li, Xingrun Xing, Sipeng Zheng, Zongqing Lu 0002. [doi]
• Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided QueriesHang Chen, Chufeng Tang, Xiao Li 0028, Xiaolin Hu 0001. [doi]
• A Closer Look at Machine Unlearning for Large Language ModelsXiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen, Weiming Zhang 0001, Min Lin. [doi]
• Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak AttacksZi Wang, Divyam Anshumaan, Ashish Hooda, Yudong Chen, Somesh Jha. [doi]
• CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and RerankingTarun Suresh, Revanth Gangi Reddy, Yifei Xu, Zach Nussbaum, Andriy Mulyar, Brandon Duderstadt, Heng Ji. [doi]
• Sparse Autoencoders Do Not Find Canonical Units of AnalysisPatrick Leask, Bart Bussmann, Michael T. Pearce, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Lee Sharkey, Neel Nanda. [doi]
• Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate ShiftZhen Zhang, Xin Liu, Shaoli Wang, Jiaye Teng. [doi]
• SC-OmniGS: Self-Calibrating Omnidirectional Gaussian SplattingHuajian Huang, Yingshu Chen, Longwei Li, Hui Cheng, Tristan Braud, Yajie Zhao, Sai Kit Yeung. [doi]
• Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?Letitia Parcalabescu, Anette Frank. [doi]
• Learn Your Reference Model for Real Good AlignmentAlexey Gorbatovski, Boris Shaposhnikov, Alexey Malakhov, Nikita Surnachev, Yaroslav Aksenov, Ian Maksimov, Nikita Balagansky, Daniil Gavrilov. [doi]
• Diverse Preference Learning for Capabilities and AlignmentStewart Slocum, Asher Parker-Sartori, Dylan Hadfield-Menell. [doi]
• DynaPrompt: Dynamic Test-Time Prompt TuningZehao Xiao, Shilin Yan, Jack Hong, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiayi Shen, Cheems Wang, Cees G. M. Snoek. [doi]
• Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed FeaturesDaeho Um, Yoonji Lee, Jiwoong Park, Seulki Park, Yuneil Yeo, Seong-Jin Ahn 0002. [doi]
• Recovering Manifold Structure Using Ollivier Ricci CurvatureTristan Luca Saidi, Abigail Hickok, Andrew J. Blumberg. [doi]
• PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision TransformerPierre-David Letourneau, Manish Kumar Singh 0002, Hsin-Pai Cheng, Shizhong Han, Yunxiao Shi, Dalton Jones, Matthew Harper Langston, Hong Cai, Fatih Porikli. [doi]
• Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient AttentionsZhihao He, Hang Yu 0002, Zi Gong, Shizhan Liu, Jianguo Li, Weiyao Lin. [doi]
• Gap-Dependent Bounds for Q-Learning using Reference-Advantage DecompositionZhong Zheng, Haochen Zhang, Lingzhou Xue. [doi]
• AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language ModelsKim Sung-Bin, Oh Hyun-Bin, JungMok Lee, Arda Senocak, Joon Son Chung, Tae Hyun Oh. [doi]
• Skill Expansion and Composition in Parameter SpaceTenglong Liu, Jianxiong Li, Yinan Zheng, Haoyi Niu, Yixing Lan, Xin Xu, Xianyuan Zhan. [doi]
• A General Framework for Off-Policy Learning with Partially-Observed RewardRikiya Takehi, Masahiro Asami, Kosuke Kawakami, Yuta Saito. [doi]
• Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMsZhaowei Zhang, Fengshuo Bai, Qizhi Chen, Chengdong Ma, Mingzhi Wang, Haoran Sun, Zilong Zheng, Yaodong Yang 0001. [doi]
• Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge DistillationMd. Imtiaz Hossain, Sharmen Akhter, Choong Seon Hong, Eui-nam Huh. [doi]
• RGB-Event ISP: The Dataset and BenchmarkYunfan Lu, Yanlin Qian, Ziyang Rao, Junren Xiao, Liming Chen, Hui Xiong. [doi]
• SimpleTM: A Simple Baseline for Multivariate Time Series ForecastingHui Chen, Viet Luong, Lopamudra Mukherjee, Vikas Singh. [doi]
• TAU-106K: A New Dataset for Comprehensive Understanding of Traffic AccidentYixuan Zhou 0001, Long Bai, Sijia Cai, Bing Deng, Xing Xu 0001, Heng Tao Shen. [doi]
• GTR: Improving Large 3D Reconstruction Models through Geometry and Texture RefinementPeiye Zhuang, Songfang Han, Chaoyang Wang 0001, Aliaksandr Siarohin, Jiaxu Zou, Michael Vasilkovsky, Vladislav Shakhrai, Sergei Korolev, Sergey Tulyakov, Hsin-Ying Lee 0001. [doi]
• BingoGuard: LLM Content Moderation Tools with Risk LevelsFan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Divyansh Agarwal, Caiming Xiong, Chien-Sheng Wu. [doi]
• FasterCache: Training-Free Video Diffusion Model Acceleration with High QualityZhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao 0001, Ziwei Liu 0002, Kwan-Yee K. Wong. [doi]
• A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training LoopsShi Fu, Yingjie Wang, Yuzhu Chen, Xinmei Tian 0001, Dacheng Tao. [doi]
• Fast Uncovering of Protein Sequence Diversity from Structureluca alessandro silva, Barthélémy Meynard-Piganeau, Carlo Lucibello, Christoph Feinauer. [doi]
• Bandit Learning in Matching Markets with IndifferenceFang Kong 0002, Jingqi Tang, Mingzhu Li, Pinyan Lu, John C. S. Lui, Shuai Li 0010. [doi]
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsFangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun 0002, Qian Liu, Sida Wang 0001, Tao Yu 0009. [doi]
• SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised LearningLun Huang, Qiang Qiu 0001, Guillermo Sapiro. [doi]
• I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution MapsJunseo Park, Hyeryung Jang. [doi]
• Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQAZhen Yang, Ziwei Du, Minghan Zhang, Wei Du, Jie Chen, Zhen Duan, Shu Zhao. [doi]
• Addressing Label Shift in Distributed Learning via Entropy Regularization​Zhiyuan Wu, Changkyu Choi, Xiangcheng Cao, Volkan Cevher, Ali Ramezani-Kebrya. [doi]
• Ada-K Routing: Boosting the Efficiency of MoE-based LLMsTongtian Yue, Longteng Guo, Jie Cheng, Xuange Gao, Hua Huang, Jing Liu 0001. [doi]
• DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control AgentTaiyi Wang, Zhihao Wu, Jianheng Liu, Jianye Hao, Jun Wang 0012, Kun Shao. [doi]
• EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric VideosJilan Xu, Yifei Huang 0002, Baoqi Pei, Junlin Hou, Qingqiu Li, Guo Chen 0006, Yuejie Zhang, Rui Feng 0001, Weidi Xie. [doi]
• SOAP: Improving and Stabilizing Shampoo using Adam for Language ModelingNikhil Vyas 0001, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham M. Kakade. [doi]
• Efficient Inference for Large Language Model-based Generative RecommendationXinyu Lin 0001, Chaoqun Yang 0002, Wenjie Wang 0007, Yongqi Li 0001, Cunxiao Du, Fuli Feng, See-Kiong Ng, Tat-Seng Chua. [doi]
• Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned PolicyJiangxing Wang, Zongqing Lu 0002. [doi]
• SynFlowNet: Design of Diverse and Novel Molecules with Synthesis ConstraintsMiruna T. Cretu, Charles Harris, Ilia Igashov, Arne Schneuing, Marwin H. S. Segler, Bruno E. Correia, Julien Roy, Emmanuel Bengio, Pietro Lio. [doi]
• Both Ears Wide Open: Towards Language-Driven Spatial Audio GenerationPeiwen Sun, Sitong Cheng, Xiangtai Li, Zhen Ye, Huadai Liu, Honggang Zhang 0002, Wei Xue, Yike Guo. [doi]
• MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt SynthesisJun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Qi He, Wangmeng Xiang, Hanyuan Chen, Jin-Peng Lan, Xianhui Lin, Kang Zhu, Bin Luo 0008, Yifeng Geng, Xuansong Xie, Alexander G. Hauptmann. [doi]
• LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual LearningLiangzu Peng, Juan Elenter, Joshua Agterberg, Alejandro Ribeiro, René Vidal. [doi]
• gRNAde: Geometric Deep Learning for 3D RNA inverse designChaitanya K. Joshi, Arian Rokkum Jamasb, Ramón Viñas Torné 0001, Charles Harris, Simon V. Mathis, Alex Morehead, Rishabh Anand, Pietro Lio. [doi]
• Adversarial Machine UnlearningZonglin Di, Sixie Yu, Yevgeniy Vorobeychik, Yang Liu 0018. [doi]
• Personalized Representation from Personalized GenerationShobhita Sundaram, Julia Chae, Yonglong Tian, Sara Beery, Phillip Isola. [doi]
• IterGen: Iterative Semantic-aware Structured LLM Generation with BacktrackingShubham Ugare, Rohan Gumaste, Tarun Suresh, Gagandeep Singh 0001, Sasa Misailovic. [doi]
• Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object DetectionChuhan Zhang, Chaoyang Zhu, Pingcheng Dong, Long Chen, Dong Zhang. [doi]
• Aligning Language Models with Demonstrated FeedbackOmar Shaikh, Michelle S. Lam, Joey Hejna, Yijia Shao, Hyundong Justin Cho, Michael S. Bernstein, Diyi Yang. [doi]
• Flat Reward in Policy Parameter Space Implies Robust Reinforcement LearningHyun-Kyu Lee, Sung Whan Yoon. [doi]
• How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node EmbeddingsNikolaos Nakis, Niels Raunkjær Holm, Andreas Lyhne Fiehn, Morten Mørup. [doi]
• Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User InterfaceWenyue Hua, Mengting Wan, Jagannath Shashank Subramanya Sai Vadrevu, Ryan Nadel, Yongfeng Zhang, Chi Wang. [doi]
• Alchemy: Amplifying Theorem-Proving Capability Through Symbolic MutationShaonan Wu, Shuai Lu, Yeyun Gong, Nan Duan, Ping Wei. [doi]
• Can Textual Gradient Work in Federated Learning?Minghui Chen, Ruinan Jin, Wenlong Deng, Yuanyuan Chen, Zhi Huang, Han Yu 0001, Xiaoxiao Li. [doi]
• Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object DetectionHongru Yan, Yu Zheng 0015, Yueqi Duan. [doi]
• Understanding and Enhancing the Transferability of Jailbreaking AttacksRunqi Lin, Bo Han 0003, Fengwang Li, Tongliang Liu. [doi]
• Residual Deep Gaussian Processes on ManifoldsKacper Wyrwal, Andreas Krause 0001, Viacheslav Borovitskiy. [doi]
• Gradient descent with generalized Newton's methodZhiqi Bu, Shiyun Xu. [doi]
• EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled FlowYufei Huang 0002, Yunshu Liu, Lirong Wu, Haitao Lin, Cheng Tan 0012, Odin Zhang, Zhangyang Gao, Siyuan Li 0002, Zicheng Liu 0006, Yunfan Liu 0002, Tailin Wu, Stan Z. Li. [doi]
• Data Shapley in One Training RunJiachen T. Wang, Prateek Mittal, Dawn Song, Ruoxi Jia 0001. [doi]
• MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for MambaMasakazu Yoshimura, Teruaki Hayashi, Yota Maeda. [doi]
• Tell me about yourself: LLMs are aware of their learned behaviorsJan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua, Owain Evans. [doi]
• InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face RestorationSenmao Li, Kai Wang 0060, Joost van de Weijer 0001, Fahad Shahbaz Khan, Chun-Le Guo, Shiqi Yang, Yaxing Wang, Jian Yang 0003, Ming-Ming Cheng. [doi]
• PhysPDE: Rethinking PDE Discovery and a Physical Hypothesis Selection BenchmarkMingquan Feng, Yixin Huang, Yizhou Liu, Bofang Jiang, Junchi Yan. [doi]
• GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian SplattingChangkun Liu 0001, Shuai Chen, Yash Bhalgat, Siyan Hu, Ming Cheng, Zirui Wang, Victor Adrian Prisacariu, Tristan Braud. [doi]
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning EngineeringJun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, Aleksander Madry, Lilian Weng. [doi]
• Optimal Learning of Kernel Logistic Regression for Complex Classification ScenariosHongwei Wen, Annika Betken, Hanyuan Hang. [doi]
• Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with NothingZhangchen Xu, Fengqing Jiang, Luyao Niu, Yuntian Deng, Radha Poovendran, Yejin Choi 0001, Bill Yuchen Lin. [doi]
• Learning Structured Universe Graph with Outlier OOD Detection for Partial MatchingZetian Jiang, Jiaxin Lu, Haizhao Fan, Tianzhe Wang, Junchi Yan. [doi]
• Private Mechanism Design via Quantile EstimationYuanyuan Yang, Tao Xiao, Bhuvesh Kumar, Jamie H. Morgenstern. [doi]
• A Simple Framework for Open-Vocabulary Zero-Shot SegmentationThomas Stegmüller, Tim Lebailly, Nikola Dukic, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran. [doi]
• Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data GenerationLinda He, Jue Wang, Maurice Weber, Shang Zhu, Ben Athiwaratkun, Ce Zhang. [doi]
• Extendable and Iterative Structure Learning Strategy for Bayesian NetworksHamid Kalantari, Russell Greiner, Pouria Ramazi. [doi]
• Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning TracesDijia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng. [doi]
• New Algorithms for the Learning-Augmented k-means ProblemJunyu Huang, Qilong Feng, Ziyun Huang, Zhen Zhang 0025, Jinhui Xu 0001, Jianxin Wang 0001. [doi]
• MotherNet: Fast Training and Inference via Hyper-Network TransformersAndreas C. Mueller, Carlo Curino, Raghu Ramakrishnan 0001. [doi]
• LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak SupervisionJiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim. [doi]
• Global Convergence in Neural ODEs: Impact of Activation FunctionsTianxiang Gao, Siyuan Sun, Hailiang Liu, Hongyang Gao. [doi]
• Distribution-Specific Agnostic Conditional Classification With HalfspacesJizhou Huang, Brendan Juba. [doi]
• Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in BiomedicineKonstantin Hemker, Nikola Simidjievski, Mateja Jamnik. [doi]
• IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt LearningQuan Zhang, Yuxin Qi, Xi Tang, Jinwei Fang, Xi Lin, Ke Zhang, Chun Yuan. [doi]
• Understanding Optimization in Deep Learning with Central FlowsJeremy Cohen 0001, Alex Damian, Ameet Talwalkar, J. Zico Kolter, Jason D. Lee. [doi]
• Teaching LLMs How to Learn with Contextual Fine-TuningYounwoo Choi, Muhammad Adil Asif, Ziwen Han, John Willes, Rahul G. Krishnan. [doi]
• nGPT: Normalized Transformer with Representation Learning on the HypersphereIlya Loshchilov, Cheng-Ping Hsieh, Simeng Sun, Boris Ginsburg. [doi]
• Inference Optimal VLMs Need Fewer Visual Tokens and More ParametersKevin Y. Li, Sachin Goyal, João D. Semedo, J. Zico Kolter. [doi]
• Collab: Controlled Decoding using Mixture of Agents for LLM AlignmentSouradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag, Soumya Suvra Ghosal, Jiahao Qiu, Mengdi Wang, Dinesh Manocha, Furong Huang, Alec Koppel, Sumitra Ganesh. [doi]
• Building Interactable Replicas of Complex Articulated Objects via Gaussian SplattingYu Liu, Baoxiong Jia, Ruijie Lu, Junfeng Ni, Song Chun Zhu, Siyuan Huang 0001. [doi]
• Generalization and Distributed Learning of GFlowNetsTiago Silva, Amauri H. Souza, Omar Rivasplata, Vikas Garg 0001, Samuel Kaski, Diego Mesquita. [doi]
• Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based CoresetsXu Wang, Fuyou Miao, Wenjie Liu, Yan Xiong. [doi]
• Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model PretrainingJie Cheng 0009, Ruixi Qiao, Yingwei Ma, Binhua Li, Gang Xiong 0001, Qinghai Miao, Yongbin Li, Yisheng Lv. [doi]
• TAU-106K: A New Dataset for Comprehensive Understanding of Traffic AccidentYixuan Zhou 0001, Long Bai, Sijia Cai, Bing Deng, Xing Xu 0001, Heng Tao Shen. [doi]
• Can Knowledge Editing Really Correct Hallucinations?Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani, Kai Shu. [doi]
• Training-Free Dataset Pruning for Instance SegmentationYalun Dai, Lingao Xiao, Ivor W. Tsang, Yang He 0002. [doi]
• Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEsChristian Klötergens, Vijaya Krishna Yalavarthi, Randolf Scholz, Maximilian Stubbemann, Stefan Born, Lars Schmidt-Thieme. [doi]
• Object-Centric Pretraining via Target Encoder BootstrappingNikola Dukic, Tim Lebailly, Tinne Tuytelaars. [doi]
• When Graph Neural Networks Meet Dynamic Mode DecompositionDai Shi, Lequan Lin, Andi Han, Zhiyong Wang 0001, Yi Guo 0001, Junbin Gao. [doi]
• Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsJonas Hübotter, Sascha Bongni, Ido Hakimi, Andreas Krause 0001. [doi]
• AdaManip: Adaptive Articulated Object Manipulation Environments and Policy LearningYuanfei Wang, Xiaojie Zhang, Ruihai Wu, Yu Li, Yan Shen 0035, Mingdong Wu, Zhaofeng He, Yizhou Wang 0001, Hao Dong 0003. [doi]
• Nonlinear multiregion neural dynamics with parametric impulse response communication channelsMatthew Dowling, Cristina Savin. [doi]
• T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory StitchingZizheng Pan, Bohan Zhuang, De-An Huang, Weili Nie, Zhiding Yu, Chaowei Xiao, Jianfei Cai 0001, Anima Anandkumar. [doi]
• On Quantizing Neural Representation for Variable-Rate Video CodingJunqi Shi, Zhujia Chen, Hanfei Li, Qi Zhao, Ming Lu, Tong Chen 0004, Zhan Ma. [doi]
• Scalable Mechanistic Neural NetworksJiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello. [doi]
• Following the Human Thread in Social NavigationLuca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, Lamberto Ballan, Fabio Galasso. [doi]
• Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational PathologyPei Liu 0008, Luping Ji, Jiaxiang Gou, Bo Fu 0007, Mao Ye 0001. [doi]
• Kolmogorov-Arnold TransformerXingyi Yang, Xinchao Wang. [doi]
• VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot PlanningYichao Liang, Nishanth Kumar, Hao Tang 0008, Adrian Weller, Joshua B. Tenenbaum, Tom Silver, João F. Henriques, Kevin Ellis. [doi]
• Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive AttacksMaksym Andriushchenko, Francesco Croce, Nicolas Flammarion. [doi]
• How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?Seongyun Lee, Geewook Kim, Jiyeon Kim, Hyunji Lee, Hoyeon Chang, Sue Hyun Park, Minjoon Seo. [doi]
• PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank ReductionShangyu Chen, Zizheng Pan, Jianfei Cai 0001, Dinh Q. Phung. [doi]
• Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference OptimizationJunkang Wu, Yuexiang Xie, Zhengyi Yang 0007, Jiancan Wu, Jiawei Chen 0007, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He 0001. [doi]
• TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal ModelsLeigang Qu, Haochuan Li, Tan Wang, Wenjie Wang 0007, Yongqi Li 0001, Liqiang Nie, Tat-Seng Chua. [doi]
• ConFIG: Towards Conflict-free Training of Physics Informed Neural NetworksQiang Liu, Mengyu Chu, Nils Thuerey. [doi]
• When do GFlowNets learn the right distribution?Tiago da Silva, Rodrigo Barreto Alves, Eliezer de Souza da Silva, Amauri H. Souza, Vikas Garg 0001, Samuel Kaski, Diego Mesquita. [doi]
• AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing AttacksVan Nguyen 0002, Tingmin Wu, Xingliang Yuan, Marthie Grobler, Surya Nepal, Carsten Rudolph. [doi]
• Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation SystemsZhenting Qi, Hanlin Zhang, Eric P. Xing, Sham M. Kakade, Himabindu Lakkaraju. [doi]
• Partial Gromov-Wasserstein MetricYikun Bai, Rocio Diaz Martin, Abihith Kothapalli, Hengrong Du, Xinran Liu, Soheil Kolouri. [doi]
• Binary Losses for Density Ratio EstimationWerner Zellinger. [doi]
• Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised DisentanglementXueyao Zhang, Xiaohui Zhang, Kainan Peng, Zhenyu Tang, Vimal Manohar, Yingru Liu, Jeff Hwang, Dangna Li, Yuhao Wang, Julian Chan, Yuan Huang, Zhizheng Wu 0001, Mingbo Ma. [doi]
• RefactorBench: Evaluating Stateful Reasoning in Language Agents Through CodeDhruv Gautam, Spandan Garg, Jinu Jang, Neel Sundaresan, Roshanak Zilouchian Moghaddam. [doi]
• OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with TextQingyun Li, Zhe Chen, Weiyun Wang, Wenhai Wang, Shenglong Ye, Zhenjiang Jin, Guanzhou Chen 0004, Yinan He, Zhangwei Gao, Erfei Cui, Jiashuo Yu, Hao Tian 0006, Jiasheng Zhou, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Bo Zhang, Pinlong Cai, et al.. [doi]
• Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement LearningDohyeong Kim, Mineui Hong, Jeongho Park, Songhwai Oh. [doi]
• CoInD: Enabling Logical Compositions in Diffusion ModelsSachit Gaudi, Gautam Sreekumar, Vishnu Boddeti. [doi]
• GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D GenerationDingdong Yang, Yizhi Wang, Konrad Schindler, Ali Mahdavi-Amiri, Hao Zhang 0002. [doi]
• Large Scale Knowledge WashingYu Wang 0170, Ruihan Wu, Zexue He, Xiusi Chen, Julian J. McAuley. [doi]
• Locality Alignment Improves Vision-Language ModelsIan Connick Covert, Tony Sun, James Zou 0001, Tatsunori Hashimoto. [doi]
• Accelerating Goal-Conditioned Reinforcement Learning Algorithms and ResearchMichal Bortkiewicz, Wladyslaw Palucki, Vivek Myers, Tadeusz Dziarmaga, Tomasz Arczewski, Lukasz Kucinski, Benjamin Eysenbach. [doi]
• Hierarchically Encapsulated Representation for Protocol Design in Self-Driving LabsYu-Zhe Shi, Mingchen Liu, Fanxu Meng, Qiao Xu, Zhangqian Bi, Kun He 0001, Lecheng Ruan, Qining Wang. [doi]
• Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge AcquisitionJiyeon Kim, Hyunji Lee, Hyowon Cho, Joel Jang, Hyeonbin Hwang, Seungpil Won, Youbin Ahn, Dohaeng Lee, Minjoon Seo. [doi]
• QERA: an Analytical Framework for Quantization Error ReconstructionCheng Zhang, Jeffrey T. H. Wong, Can Xiao, George Anthony Constantinides, Yiren Zhao. [doi]
• Projection Head is Secretly an Information BottleneckZhuo Ouyang, Kaiwen Hu, Qi Zhang, Yifei Wang 0001, Yisen Wang 0001. [doi]
• Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-NormDu Chen, Geoffrey A. Chua. [doi]
• Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM AttacksManohar Kaul, Aditya Saibewar, Sadbhavana Babar. [doi]
• GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set MatchingZiming Zhang, Fangzhou Lin, Haotian Liu, Jose Morales, Haichong Zhang, Kazunori D. Yamada, Vijaya B. Kolachalama, Venkatesh Saligrama. [doi]
• GDrag: Towards General-Purpose Interactive Editing with Anti-ambiguity Point DiffusionXiaojian Lin, Hanhui Li, Yuhao Cheng, Yiqiang Yan, Xiaodan Liang. [doi]
• StringLLM: Understanding the String Processing Capability of Large Language ModelsXilong Wang, Hao Fu, Jindong Wang 0001, Neil Zhenqiang Gong. [doi]
• ClimaQA: An Automated Evaluation Framework for Climate Question Answering ModelsVeeramakali Vignesh Manivannan, Yasaman Jafari, Srikar Eranky, Spencer Ho, Rose Yu, Duncan Watson-Parris, Yian Ma, Leon Bergen, Taylor Berg-Kirkpatrick. [doi]
• Building, Reusing, and Generalizing Abstract Representations from Concrete SequencesShuchen Wu, Mirko Thalmann, Peter Dayan, Zeynep Akata, Eric Schulz. [doi]
• Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad GeneralizationJingrong Wei, Long Chen. [doi]
• Stabilized Neural Prediction of Potential Outcomes in Continuous TimeKonstantin Hess, Stefan Feuerriegel. [doi]
• Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order OptimizationZhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang. [doi]
• FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty. [doi]
• Score-based Self-supervised MRI DenoisingJiachen Tu, Yaokun Shi, Fan Lam. [doi]
• Grounding Multimodal Large Language Model in GUI WorldWeixian Lei, Difei Gao, Mike Zheng Shou. [doi]
• DataEnvGym: Data Generation Agents in Teacher Environments with Student FeedbackZaid Khan 0001, Elias Stengel-Eskin, Jaemin Cho 0001, Mohit Bansal. [doi]
• Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player GamesYanzheng Chen, Jun Yu. [doi]
• Training Robust Ensembles Requires Rethinking Lipschitz ContinuityAli Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran. [doi]
• Adaptive Energy Alignment for Accelerating Test-Time AdaptationWonjeong Choi, Do-Yeon Kim 0001, Jungwuk Park, Jungmoon Lee, Younghyun Park, Dong-Jun Han, Jaekyun Moon. [doi]
• CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMsDung Manh Nguyen, Thang Chau Phan, Nam Le Hai, Tien-Thong Doan, Nam V. Nguyen, Quang Pham, Nghi D. Q. Bui. [doi]
• Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear ProgrammingHaoyang Liu 0002, Jie Wang 0005, Zijie Geng, Xijun Li, Yuxuan Zong, Fangzhou Zhu, Jianye Hao, Feng Wu 0001. [doi]
• Balancing Bias in Two-sided Markets for Fair Stable MatchingsSiyuan Wu, Leong Hou U, Panagiotis Karras. [doi]
• Intent3D: 3D Object Detection in RGB-D Scans Based on Human IntentionWeitai Kang, Mengxue Qu, Jyoti Kini, Yunchao Wei, Mubarak Shah, Yan Yan 0002. [doi]
• DisPose: Disentangling Pose Guidance for Controllable Human Image AnimationHongxiang Li, Yaowei Li, Yuhang Yang, Junjie Cao, Zhihong Zhu, Xuxin Cheng, Long Chen. [doi]
• PEARL: Parallel Speculative Decoding with Adaptive Draft LengthTianyu Liu, Yun Li, Qitan Lv, Kai Liu, Jianchen Zhu, Winston Hu, Xiao Sun. [doi]
• Compute-Constrained Data SelectionJunjie Oscar Yin, Alexander M. Rush. [doi]
• VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded TextTianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu 0001, Bang Liu, Yoshua Bengio. [doi]
• Logic-Logit: A Logic-Based Approach to Choice ModelingShuhan Zhang, Wendi Ren, Shuang Li 0002. [doi]
• A Quantum Circuit-Based Compression Perspective for Parameter-Efficient LearningChen-yu Liu, Chao-Han Huck Yang, Hsi-Sheng Goan, Min-Hsiu Hsieh. [doi]
• Refining CLIP's Spatial Awareness: A Visual-Centric PerspectiveCongpei Qiu, Yanhao Wu, Wei Ke 0003, Xiuxiu Bai, Tong Zhang 0023. [doi]
• Direct Distributional Optimization for Provable Alignment of Diffusion ModelsRyotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki. [doi]
• An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual PixelsDuy-Kien Nguyen, Mido Assran, Unnat Jain, Martin R. Oswald, Cees G. M. Snoek, Xinlei Chen. [doi]
• Regret-Optimal List Replicable Bandit Learning: Matching Upper and Lower BoundsMichael Chen, Aduri Pavan, N. V. Vinodchandran, Ruosong Wang, Lin Yang 0011. [doi]
• ViSAGe: Video-to-Spatial Audio GenerationJaeyeon Kim, Heeseung Yun, Gunhee Kim. [doi]
• Measuring And Improving Engagement of Text-to-Image Generation ModelsVarun Khurana, Yaman Kumar Singla, Jayakumar Subramanian, Changyou Chen, Rajiv Ratn Shah, Zhiqiang Xu, Balaji Krishnamurthy. [doi]
• InstantSwap: Fast Customized Concept Swapping across Sharp Shape DifferencesChenyang Zhu 0007, Kai Li 0012, Yue Ma, Longxiang Tang, Chengyu Fang, Chubin Chen, Qifeng Chen, Xiu Li 0001. [doi]
• GameArena: Evaluating LLM Reasoning through Live Computer GamesLanxiang Hu, Qiyu Li, Anze Xie, Nan Jiang, Ion Stoica, Haojian Jin, Hao Zhang 0025. [doi]
• Better Instruction-Following Through Minimum Bayes RiskIan Wu, Patrick Fernandes, Amanda Bertsch, Seungone Kim, Sina Khoshfetrat Pakazad, Graham Neubig. [doi]
• Intrinsic User-Centric Interpretability through Global Mixture of ExpertsVinitra Swamy, Syrielle Montariol, Julian Blackwell, Jibril Frej, Martin Jaggi, Tanja Käser. [doi]
• ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific DiscoveryZiru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, Vishal Dey, Mingyi Xue, Frazier N. Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao 0001, Yu Su 0001, Huan Sun 0001. [doi]
• ScImage: How good are multimodal large language models at scientific text-to-image generation?Leixin Zhang, Steffen Eger, Yinjie Cheng, Weihe Zhai, Jonas Belouadi, Fahimeh Moafian, Zhixue Zhao. [doi]
• In vivo cell-type and brain region classification via multimodal contrastive learningHan Yu, Hanrui Lyu, YiXun Xu, Charlie Windolf, Eric Kenji Lee, Fan Yang, Andrew M. Shelton, Olivier Winter, International Brain Laboratory, Eva L. Dyer, Chandramouli Chandrasekaran, Nicholas A. Steinmetz, Liam Paninski, Cole Lincoln Hurwitz. [doi]
• On Linear Representations and Pretraining Data Frequency in Language ModelsJack Merullo, Noah A. Smith, Sarah Wiegreffe, Yanai Elazar. [doi]
• NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding ModelsChankyu Lee, Rajarshi Roy 0003, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping. [doi]
• Towards Understanding Text Hallucination of Diffusion Models via Local Generation BiasRui Lu, Runzhe Wang, Kaifeng Lyu, Xitai Jiang, Gao Huang 0001, Mengdi Wang. [doi]
• A Decade's Battle on Dataset Bias: Are We There Yet?Zhuang Liu 0003, Kaiming He. [doi]
• Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal ControlSongyuan Zhang, Oswin So, Mitchell Black 0001, Chuchu Fan. [doi]
• Tight Clusters Make Specialized ExpertsStefan K. Nielsen, Rachel S. Y. Teo, Laziz U. Abdullaev, Tan Minh Nguyen. [doi]
• Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for ReasoningCharlie Victor Snell, Jaehoon Lee 0001, Kelvin Xu, Aviral Kumar. [doi]
• What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen 0041, Chunhua Shen. [doi]
• Charting the Design Space of Neural Graph Representations for Subgraph MatchingVaibhav Raj, Indradyumna Roy, Ashwin Ramachandran, Soumen Chakrabarti, Abir De. [doi]
• Inference Scaling for Long-Context Retrieval Augmented GenerationZhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui 0001, Rolf Jagerman, Hansi Zeng, Zhen Qin 0001, Dong Wang, Xuanhui Wang, Michael Bendersky. [doi]
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionShoubin Yu, Jaehong Yoon, Mohit Bansal. [doi]
• Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuningChongjie Si, Zhiyi Shi, Shifan Zhang, Xiaokang Yang 0001, Hanspeter Pfister, Wei Shen 0002. [doi]
• Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image PyramidMingxin Huang, Yuliang Liu, Dingkang Liang, Lianwen Jin, Xiang Bai. [doi]
• Fitting Networks with a Cancellation TrickJiashun Jin, Jingming Wang. [doi]
• Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured DataBinghui Li, Yuanzhi Li. [doi]
• An Undetectable Watermark for Generative Image ModelsSam Gunn, Xuandong Zhao, Dawn Song. [doi]
• Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and BenchmarksZixuan Xiong, Guangwei Xu, Wenkai Zhang, Yuan Miao, Xuan Wu, LinHai, Ruijie Guo, Hai-Tao Zheng. [doi]
• To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningZayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett. [doi]
• Distilling Dataset into Neural FieldDonghyeok Shin, HeeSun Bae, Gyuwon Sim, Wanmo Kang, Il-Chul Moon. [doi]
• Fine-tuning can Help Detect Pretraining Data from Large Language ModelsHengxiang Zhang, Songxin Zhang, Bingyi Jing, Hongxin Wei. [doi]
• Geometry of Neural Reinforcement Learning in Continuous State and Action SpacesSaket Tiwari, Omer Gottesman, George Konidaris 0001. [doi]
• LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model MergingKe Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jiménez, François Fleuret, Pascal Frossard. [doi]
• Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement LearningHongye Cao, Fan Feng, Meng Fang, Shaokang Dong, Tianpei Yang, Jing Huo, Yang Gao 0001. [doi]
• Open-World Reinforcement Learning over Long Short-Term ImaginationJiajian Li, Qi Wang, Yunbo Wang, Xin Jin, Yang Li, Wenjun Zeng 0001, Xiaokang Yang 0001. [doi]
• Geometric Inductive Biases of Deep Networks: The Role of Data and ArchitectureSajad Movahedi, Antonio Orvieto, Seyed-Mohsen Moosavi-Dezfooli. [doi]
• Learning Evolving Tools for Large Language ModelsGuoxin Chen, Zhong Zhang, Xin Cong, Fangda Guo, Yesai Wu, Yankai Lin, Wenzheng Feng, Yasheng Wang. [doi]
• Faster Inference of Flow-Based Generative Models via Improved Data-Noise CouplingAram Davtyan, Leello Tadesse Dadi, Volkan Cevher, Paolo Favaro. [doi]
• Weighted-Reward Preference Optimization for Implicit Model FusionZiyi Yang, Fanqi Wan, Longguang Zhong, Tianyuan Shi, Xiaojun Quan. [doi]
• Effective Interplay between Sparsity and Quantization: From Theory to PracticeSimla Burcu Harma, Ayan Chakraborty 0005, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh. [doi]
• Latent Bayesian Optimization via Autoregressive Normalizing FlowsSeunghun Lee, Jinyoung Park, Jaewon Chu, Minseo Yoon, Hyunwoo J. Kim. [doi]
• Towards Hierarchical Rectified FlowYichi Zhang, Yici Yan, Alexander G. Schwing, Zhizhen Zhao 0001. [doi]
• Leave-One-Out Stable Conformal PredictionKiljae Lee, Yuan Zhang. [doi]
• Scaling Laws for Downstream Task Performance in Machine TranslationBerivan Isik, Natalia Ponomareva 0001, Hussein Hazimeh 0001, Dimitris Paparas, Sergei Vassilvitskii, Sanmi Koyejo. [doi]
• SMI-Editor: Edit-based SMILES Language Model with Fragment-level SupervisionKangjie Zheng, Siyue Liang, Junwei Yang, Bin Feng, Zequn Liu, Wei Ju, Zhiping Xiao 0001, Ming Zhang 0004. [doi]
• Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models BetterEnshu Liu, Junyi Zhu 0002, Zinan Lin 0001, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang 0002. [doi]
• Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion ModelsAlireza Ganjdanesh, Reza Shirkavand, Shangqian Gao, Heng Huang. [doi]
• Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionJingcun Wang, Yu-Guang Chen, Ing-Chao Lin, Bing Li 0005, Grace Li Zhang. [doi]
• KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted NetworksDominik Scheuer, Frederic Runge, Jörg K. H. Franke, Michael T. Wolfinger, Christoph Flamm, Frank Hutter. [doi]
• Improved Diffusion-based Generative Model with Better Adversarial RobustnessZekun Wang 0001, Mingyang Yi, Shuchen Xue, Zhenguo Li, Ming Liu 0004, Bing Qin 0001, Zhiming Ma. [doi]
• Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion ModelJincheng Zhong, Xiangcheng Zhang, Jianmin Wang 0001, Mingsheng Long. [doi]
• Shedding Light on Time Series Classification using Interpretability Gated NetworksYunshi Wen, Tengfei Ma 0001, Ronny Luss, Debarun Bhattacharjya, Achille Fokoue, Anak Agung Julius. [doi]
• Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture WarpingTianhao (Walter) Wu, Jing Yang, Zhilin Guo 0001, Jingyi Wan, Fangcheng Zhong, Cengiz Öztireli. [doi]
• Learning Harmonized Representations for Speculative SamplingLefan Zhang, Xiaodan Wang, Yanhua Huang, Ruiwen Xu. [doi]
• Competitive Fair Scheduling with PredictionsTianming Zhao 0002, Chunqiu Xia, Xiaomin Chang, Chunhao Li, Wei Li 0058, Albert Y. Zomaya. [doi]
• Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal SamplingHritik Bansal, Arian Hosseini, Rishabh Agarwal, Vinh Q. Tran 0002, Mehran Kazemi. [doi]
• Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling PerformanceJiasheng Ye, Peiju Liu, Tianxiang Sun, Jun Zhan, Yunhua Zhou, Xipeng Qiu. [doi]
• Rethinking Spiking Neural Networks from an Ensemble Learning PerspectiveYongqi Ding, Lin Zuo, Mengmeng Jing, Pei He, Hanpu Deng. [doi]
• Tractable Multi-Agent Reinforcement Learning through Behavioral EconomicsEric Mazumdar, Kishan Panaganti, Laixi Shi. [doi]
• Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality PerspectivesZeliang Zhang, Susan Liang, Daiki Shimada, Chenliang Xu. [doi]
• Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion ModelsSaurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao, Christian Simon, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao 0001, Shusuke Takahashi, Yuki Mitsufuji. [doi]
• Differentiable Rule Induction from Raw Sequence InputsKun Gao 0003, Katsumi Inoue, Yongzhi Cao, Hanpin Wang, Yang Feng. [doi]
• Towards Understanding Why FixMatch Generalizes Better Than Supervised LearningJingyang Li, Jiachun Pan, Vincent Y. F. Tan, Kim-Chuan Toh, Pan Zhou 0002. [doi]
• MatExpert: Decomposing Materials Discovery By Mimicking Human ExpertsQianggang Ding, Santiago Miret, Bang Liu. [doi]
• CollabEdit: Towards Non-destructive Collaborative Knowledge EditingJiamu Zheng, Jinghuai Zhang, Tianyu Du, Xuhong Zhang 0002, Jianwei Yin, Tao Lin. [doi]
• Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion AttacksTianqu Zhuang, Hongyao Yu, Yixiang Qiu, Hao Fang, Bin Chen 0011, Shu-Tao Xia. [doi]
• GNNs Getting ComFy: Community and Feature Similarity Guided RewiringCelia Rubio-Madrigal, Adarsh Jamadandi, Rebekka Burkholz. [doi]
• WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language ModelsShengda Fan, Xin Cong, Yuepeng Fu, Zhong Zhang, Shuyan Zhang, Yuanwei Liu, Yesai Wu, Yankai Lin, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor MixturesXiaoyi Mai, Zhenyu Liao 0001. [doi]
• On Stochastic Contextual Bandits with Knapsacks in Small Budget RegimeHengquan Guo, Xin Liu. [doi]
• Online Preference Alignment for Language Models via Count-based ExplorationChenjia Bai, Yang Zhang, Shuang Qiu, Qiaosheng Zhang, Kang Xu, Xuelong Li. [doi]
• Physics of Language Models: Part 3.2, Knowledge ManipulationZeyuan Allen Zhu, Yuanzhi Li. [doi]
• An Effective Theory of Bias AmplificationArjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis Dohmatob. [doi]
• ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language ModelsSeonghwan Park, Jaehyeon Jeong, Yongjun Kim, Jaeho Lee 0001, Namhoon Lee. [doi]
• Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LNPengxiang Li, Lu Yin 0006, Shiwei Liu 0003. [doi]
• How Much is Unseen Depends Chiefly on Information About the SeenSeongmin Lee, Marcel Boehme. [doi]
• Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein GeometryJannis Chemseddine, Christian Wald, Richard Duong, Gabriele Steidl. [doi]
• Comparing noisy neural population dynamics using optimal transport distancesAmin Nejatbakhsh, Victor Geadah, Alex H. Williams, David Lipshutz. [doi]
• Variational Diffusion Posterior Sampling with Midpoint GuidanceBadr Moufad, Yazid Janati, Lisa Bedin, Alain Oliviero Durmus, Randal Douc, Eric Moulines, Jimmy Olsson. [doi]
• Reducing Hallucinations in Large Vision-Language Models via Latent Space SteeringSheng Liu, Haotian Ye, James Zou. [doi]
• Linear Multistep Solver Distillation for Fast Sampling of Diffusion ModelsYuchen Liang, Xiangzhong Fang, Hanting Chen, Yunhe Wang. [doi]
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis ApproachYuchen Liang, Peizhong Ju, Yingbin Liang, Ness B. Shroff. [doi]
• I-Con: A Unifying Framework for Representation LearningShaden Naif Alshammari, John R. Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton. [doi]
• Learning Transformer-based World Models with Contrastive Predictive CodingMaxime Burchi, Radu Timofte. [doi]
• Execution-guided within-prompt search for programming-by-exampleGust Verbruggen, Ashish Tiwari 0001, Mukul Singh, Vu Le 0002, Sumit Gulwani. [doi]
• CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at InferenceAmirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi. [doi]
• Complementary Label Learning with Positive Label Guessing and Negative Label EnhancementYuhang Li, Zhuying Li, Yuheng Jia. [doi]
• VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference AccelerationDezhan Tu, Danylo Vashchilenko, Yuzhe Lu, Panpan Xu. [doi]
• Find A Winning Sign: Sign Is All We Need to Win the LotteryJunghun Oh, Sungyong Baik, Kyoung Mu Lee. [doi]
• Accelerating Diffusion Transformers with Token-wise Feature CachingChang Zou, Xuyang Liu, Ting Liu, Siteng Huang, Linfeng Zhang 0001. [doi]
• Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language ModelsJingcheng Deng, Zihao Wei, Liang Pang, Hanxing Ding, Huawei Shen, Xueqi Cheng. [doi]
• PN-GAIL: Leveraging Non-optimal Information from Imperfect DemonstrationsQiang Liu, Huiqiao Fu, Kaiqiang Tang, Chunlin Chen, Daoyi Dong. [doi]
• Separation Power of Equivariant Neural NetworksMarco Pacini, Xiaowen Dong 0001, Bruno Lepri, Gabriele Santin. [doi]
• DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned ModelsWenlong Deng, Yize Zhao, Vala Vakilian, Minghui Chen, Xiaoxiao Li, Christos Thrampoulidis. [doi]
• Neural Fluid Simulation on Geometric SurfacesHaoxiang Wang, Tao Yu 0007, Hui Qiao, Qionghai Dai. [doi]
• Conformal Prediction Sets Can Cause Disparate ImpactJesse C. Cresswell, Bhargava Kumar, Yi Sui, Mouloud Belbahri. [doi]
• MAP: Multi-Human-Value Alignment PaletteXinran Wang, Qi Le, Ammar Ahmed, Enmao Diao, Yi Zhou 0015, Nathalie Baracaldo, Jie Ding 0002, Ali Anwar 0001. [doi]
• Tool-Planner: Task Planning with Clusters across Multiple ToolsYanming Liu, Xinyue Peng, Jiannan Cao, Shi-Bo, Yuwei Zhang, Xuhong Zhang 0002, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du. [doi]
• Decentralized Optimization with Coupled ConstraintsDemyan Yarmoshik, Alexander Rogozin, Nikita Kiselev, Daniil Dorin, Alexander Gasnikov, Dmitry Kovalev. [doi]
• Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop SchedulingSirui Li, Wenbin Ouyang, Yining Ma, Cathy Wu 0002. [doi]
• GOAL: A Generalist Combinatorial Optimization Agent LearnerDarko Drakulic, Sofia Michel, Jean-Marc Andreoli. [doi]
• Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR DataMichael Wornow, Suhana Bedi, Miguel Angel Fuentes Hernandez, Ethan Steinberg, Jason Alan Fries, Christopher Ré, Sanmi Koyejo, Nigam Shah. [doi]
• Noisy Test-Time Adaptation in Vision-Language ModelsChentao Cao, Zhun Zhong, Zhanke Zhou, Tongliang Liu, Yang Liu 0018, Kun Zhang 0001, Bo Han 0003. [doi]
• Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence AnalysisGuangchen Lan, Dong-Jun Han, Abolfazl Hashemi, Vaneet Aggarwal, Christopher Brinton 0001. [doi]
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera ControlSherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace, Guocheng Qian, Michael Vasilkovsky, Hsin-Ying Lee 0001, Chaoyang Wang 0001, Jiaxu Zou, Andrea Tagliasacchi, David B. Lindell, Sergey Tulyakov. [doi]
• Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language BootstrappingYue Yang, Shuibo Zhang, Kaipeng Zhang, Yi Bin, Yu Wang 0002, Ping Luo 0002, Wenqi Shao. [doi]
• Enhancing Clustered Federated Learning: Integration of Strategies and Improved MethodologiesYongxin Guo, Xiaoying Tang 0002, Tao Lin. [doi]
• OmniSep: Unified Omni-Modality Sound Separation with Query-MixupXize Cheng, Siqi Zheng, Zehan Wang 0001, Minghui Fang 0002, Ziang Zhang, Rongjie Huang 0001, Shengpeng Ji, Jialong Zuo, Tao Jin 0004, Zhou Zhao 0001. [doi]
• SIMPL: Scalable and hassle-free optimisation of neural representations from behaviourTom M. George, Pierre Glaser, Kim Stachenfeld, Caswell Barry, Claudia Clopath. [doi]
• SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse ViewpointsJianhong Bai, Menghan Xia, Xintao Wang 0002, Ziyang Yuan, Zuozhu Liu, Haoji Hu, Pengfei Wan 0001, Di Zhang. [doi]
• Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem SolvingJin Zhang, Flood Sung, Zhilin Yang, Yang Gao 0029, Chongjie Zhang. [doi]
• STAFF: Speculative Coreset Selection for Task-Specific Fine-tuningXiaoyu Zhang, Juan Zhai, ShiQing Ma, Chao Shen 0001, Tianlin Li, Weipeng Jiang, Yang Liu. [doi]
• LongGenBench: Benchmarking Long-Form Generation in Long Context LLMsYuhao Wu, Ming Shan Hee, Zhiqiang Hu, Roy Ka-Wei Lee. [doi]
• TabWak: A Watermark for Tabular Diffusion ModelsChaoyi Zhu, Jiayi Tang, Jeroen M. Galjaard, Pin-Yu Chen, Robert Birke, Cornelis Bos, Lydia Y. Chen. [doi]
• Scaling Long Context Training Data by Long-Distance ReferralsYonghao Zhuang 0001, Lanxiang Hu, Longfei Yun, Souvik Kundu 0009, Zhengzhong Liu 0001, Eric P. Xing, Hao Zhang 0025. [doi]
• TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task TypesJiankang Chen, Tianke Zhang, Changyi Liu, Haojie Ding, Yaya Shi, Cheng Feng, Huihui Xiao, Bin Wen, Fan Yang 0094, Tingting Gao, Di Zhang. [doi]
• A CLIP-Powered Framework for Robust and Generalizable Data SelectionSuorong Yang, Peng Ye 0006, Wanli Ouyang, Dongzhan Zhou, Furao Shen. [doi]
• Tailoring Mixup to Data for CalibrationQuentin Bouniot, Pavlo Mozharovskyi, Florence d'Alché-Buc. [doi]
• Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware SubspaceJinluan Yang, Anke Tang, Didi Zhu, Zhengyu Chen, Li Shen, Fei Wu. [doi]
• From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal JungleKaustubh Vyas, Damien Graux, Yijun Yang, Sébastien Montella, Chenxin Diao, Wendi Zhou, Pavlos Vougiouklis, Ruofei Lai, Yang Ren, Keshuang Li, Jeff Z. Pan. [doi]
• Neural Stochastic Differential Equations for Uncertainty-Aware Offline RLCevahir Köprülü, Franck Djeumou, Ufuk Topcu. [doi]
• RazorAttention: Efficient KV Cache Compression Through Retrieval HeadsHanlin Tang, Yang Lin, Jing Lin, Qingsen Han, Danning Ke, Shikuan Hong, Yiwu Yao, Gongyi Wang. [doi]
• Mitigating Reward Over-Optimization in RLHF via Behavior-Supported RegularizationJuntao Dai, Taiye Chen, Yaodong Yang 0001, Qian Zheng, Gang Pan 0001. [doi]
• Timer-XL: Long-Context Transformers for Unified Time Series ForecastingYong Liu, Guo Qin, Xiangdong Huang 0001, Jianmin Wang 0001, Mingsheng Long. [doi]
• Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory PredictionZilin Fang, David Hsu, Gim Hee Lee. [doi]
• Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor AttacksNguyen Hung-Quang, Ngoc-Hieu Nguyen, The-Anh Ta, Thanh Nguyen-Tang, Kok Seng Wong, Hoang Thanh-Tung, Khoa D. Doan. [doi]
• MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec TransformerYuancheng Wang, Haoyue Zhan, Liwei Liu, Ruihong Zeng, Haotian Guo, Jiachen Zheng, Qiang Zhang, Xueyao Zhang, Shunsi Zhang, Zhizheng Wu 0001. [doi]
• BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge DistillationZhengrui Guo, Fangxu Zhou, Wei Wu, Qichen Sun, Lishuang Feng, Jinzhuo Wang, Hao Chen 0011. [doi]
• On the Transfer of Object-Centric Representation LearningAniket Rajiv Didolkar, Andrii Zadaianchuk, Anirudh Goyal, Michael Curtis Mozer, Yoshua Bengio, Georg Martius, Maximilian Seitzer. [doi]
• On the Hölder Stability of Multiset and Graph Neural NetworksYair Davidson, Nadav Dym. [doi]
• Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionMarco Mistretta, Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini 0001, Andrew D. Bagdanov. [doi]
• Logicbreaks: A Framework for Understanding Subversion of Rule-based InferenceAnton Xue, Avishree Khare, Rajeev Alur, Surbhi Goel, Eric Wong 0001. [doi]
• CryoFM: A Flow-based Foundation Model for Cryo-EM DensitiesYi Zhou, Yilai Li, Jing Yuan, Quanquan Gu. [doi]
• (Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep LearningMargaret Li, Sneha Kudugunta, Luke Zettlemoyer. [doi]
• Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte CarloShengyu Feng, Xiang Kong, Shuang Ma, Aonan Zhang, Dong Yin, Chong Wang, Ruoming Pang, Yiming Yang. [doi]
• Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)Subba Reddy Oota, Akshett Rai Jindal, Ishani Mondal, Khushbu Pahwa, Satya Sai Srinath Namburi GNVV, Manish Shrivastava 0001, Maneesh Kumar Singh 0002, Bapi Raju Surampudi, Manish Gupta 0001. [doi]
• AlphaEdit: Null-Space Constrained Knowledge Editing for Language ModelsJunfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He 0001, Tat-Seng Chua. [doi]
• MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE SolversAo Li, Wei Fang, Hongbo Zhao, Le Lu, Ge Yang, Minfeng Xu. [doi]
• Controlling Space and Time with Diffusion ModelsDaniel Watson, Saurabh Saxena, Lala Li, Andrea Tagliasacchi, David J. Fleet. [doi]
• EmbedLLM: Learning Compact Representations of Large Language ModelsRichard Zhuang, Tianhao Wu 0002, Zhaojin Wen, Andrew Li, Jiantao Jiao, Kannan Ramchandran. [doi]
• Robust Feature Learning for Multi-Index Models in High DimensionsAlireza Mousavi Hosseini, Adel Javanmard, Murat A. Erdogdu. [doi]
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web AgentsKe Yang 0003, Yao Liu 0009, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, Huzefa Rangwala. [doi]
• Text-to-Image Rectified Flow as Plug-and-Play PriorsXiaofeng Yang, Cheng Chen, XuLei Yang, Fayao Liu, Guosheng Lin. [doi]
• On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data PoisoningYongyi Su, Yushu Li, Nanqing Liu, Kui Jia, XuLei Yang, Chuan-Sheng Foo, Xun Xu 0002. [doi]
• Don't stop me Now: Embedding based Scheduling for LLMSRana Shahout, Eran Malach, Chunwei Liu, Weifan Jiang, Minlan Yu, Michael Mitzenmacher. [doi]
• Modeling dynamic social vision highlights gaps between deep learning and humansKathy Garcia, Emalie McMahon, Colin Conwell, Michael F. Bonner, Leyla Isik. [doi]
• Reward Learning from Multiple Feedback TypesYannick Metz, András Geiszl, Raphaël Baur, Mennatallah El-Assady. [doi]
• Linear Partial Gromov-Wasserstein EmbeddingYikun Bai, Abihith Kothapalli, Hengrong Du, Rocio Diaz Martin, Soheil Kolouri. [doi]
• Brain-inspired Lp-Convolution benefits large kernels and aligns better with visual cortexJea Kwon, Sungjun Lim 0002, Kyungwoo Song, C. Justin Lee. [doi]
• WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement LearningZehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Jiadai Sun, Xinyue Yang, Yu Yang, Shuntian Yao, Wei Xu 0017, Jie Tang 0001, Yuxiao Dong. [doi]
• MA-RLHF: Reinforcement Learning from Human Feedback with Macro ActionsYekun Chai, Haoran Sun, Huang Fang, Shuohuan Wang, Yu Sun, Hua Wu 0003. [doi]
• Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative ModelsMazda Moayeri, Sriram Balasubramanian, Samyadeep Basu, Priyatham Kattakinda, Atoosa Malemir Chegini, Robert Brauneis, Soheil Feizi. [doi]
• Harnessing Webpage UIs for Text-Rich Visual UnderstandingJunpeng Liu, Tianyue Ou, Yifan Song, Yuxiao Qu, Wai Lam, Chenyan Xiong, Wenhu Chen, Graham Neubig, Xiang Yue. [doi]
• Sequential Controlled Langevin DiffusionsJunhua Chen, Lorenz Richter, Julius Berner, Denis Blessing, Gerhard Neumann, Anima Anandkumar. [doi]
• Systematic Outliers in Large Language ModelsYongqi An, Xu Zhao 0003, Tao Yu 0013, Ming Tang 0001, Jinqiao Wang. [doi]
• Q-SFT: Q-Learning for Language Models via Supervised Fine-TuningJoey Hong, Anca D. Dragan, Sergey Levine. [doi]
• Streamlining Redundant Layers to Compress Large Language ModelsXiaodong Chen, Yuxuan Hu, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen 0001. [doi]
• T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask LearningNabarun Goswami, Hanqin Wang, Tatsuya Harada. [doi]
• Probing the Latent Hierarchical Structure of Data via Diffusion ModelsAntonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart. [doi]
• AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled DemonstrationsPei Zhou, Ruizhe Liu, Qian Luo, Fan Wang, Yibing Song, Yanchao Yang 0001. [doi]
• ZETA: Leveraging Z-order Curves for Efficient Top-k AttentionQiuhao Zeng, Jerry Huang, Peng Lu, Gezheng Xu, Boxing Chen, Charles Ling 0001, Boyu Wang 0004. [doi]
• Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHFShicong Cen, Jincheng Mei, Katayoon Goshvadi, Hanjun Dai, Tong Yang, Sherry Yang 0001, Dale Schuurmans, Yuejie Chi, Bo Dai 0001. [doi]
• Is Your Multimodal Language Model Oversensitive to Safe Queries?Xirui Li, Hengguang Zhou, Ruochen Wang, Tianyi Zhou 0001, Minhao Cheng, Cho-Jui Hsieh. [doi]
• Fantastic Copyrighted Beasts and How (Not) to Generate ThemLuxi He, Yangsibo Huang, Weijia Shi, Tinghao Xie, Haotian Liu, Yue Wang, Luke Zettlemoyer, Chiyuan Zhang, Danqi Chen 0001, Peter Henderson 0002. [doi]
• Decomposition Polyhedra of Piecewise Linear FunctionsMarie-Charlotte Brandenburg, Moritz Leo Grillo, Christoph Hertrich. [doi]
• Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional DivergenceFrederik Pahde, Maximilian Dreyer, Moritz Weckbecker, Leander Weber, Christopher J. Anders, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin. [doi]
• Sparse components distinguish visual pathways & their alignment to neural networksAmmar I Marvi, Nancy Kanwisher, Meenakshi Khosla. [doi]
• Support is All You Need for Certified VAE TrainingChangming Xu, Debangshu Banerjee, Deepak Vasisht, Gagandeep Singh 0001. [doi]
• Generalized Video Moment RetrievalYou Qin, Qilong Wu, Yicong Li 0004, Wei Ji 0008, Li Li 0091, Pengcheng Cai, Lina Wei, Roger Zimmermann. [doi]
• Transformers are Universal In-context LearnersTakashi Furuya, Maarten V. De Hoop, Gabriel Peyré. [doi]
• BIRD: A Trustworthy Bayesian Inference Framework for Large Language ModelsYu Feng 0013, Ben Zhou, Weidong Lin, Dan Roth. [doi]
• RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation LearningChenglong Kang, Xiaoyi Liu, Fei Guo 0001. [doi]
• Commit0: Library Generation from ScratchWenting Zhao, Nan Jiang, Celine Lee, Justin T. Chiu, Claire Cardie, Matthias Gallé, Alexander M. Rush. [doi]
• LARP: Tokenizing Videos with a Learned Autoregressive Generative PriorHanyu Wang, Saksham Suri, Yixuan Ren, Hao Chen, Abhinav Shrivastava. [doi]
• Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language ModelsFrancisco Eiras, Aleksandar Petrov, Philip Torr 0001, M. Pawan Kumar, Adel Bibi. [doi]
• Accelerating 3D Molecule Generation via Jointly Geometric Optimal TransportHaokai Hong, Wanyu Lin, Kc Tan. [doi]
• Intermediate Layer Classifiers for OOD generalizationArnas Uselis, Seong Joon Oh. [doi]
• Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-InstructChristopher Ackerman, Nina Panickssery. [doi]
• Circuit Transformer: A Transformer That Preserves Logical EquivalenceXihan Li 0001, Xing Li, Lei Chen 0002, Xing Zhang, Mingxuan Yuan, Jun Wang 0012. [doi]
• OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction DataShubham Toshniwal, Wei Du, Ivan Moshkov, Branislav Kisacanin, Alexan Ayrapetyan, Igor Gitman. [doi]
• Efficient Imitation under MisspecificationNicolas A. Espinosa Dice, Sanjiban Choudhury, Wen Sun 0002, Gokul Swamy. [doi]
• Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral PerspectiveYushun Dong, Patrick Soga, Yinhan He, Song Wang, Jundong Li. [doi]
• Online-to-Offline RL for Agent AlignmentXu Liu, Haobo Fu, Stefano V. Albrecht, Qiang Fu, Shuai Li. [doi]
• Revisiting Convolution Architecture in the Realm of DNA Foundation ModelsYu Bo, Weian Mao, Yanjun Shao, Weiqiang Bai, Peng Ye 0006, Xinzhu Ma, Junbo Zhao, Hao Chen 0041, Chunhua Shen. [doi]
• Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to AdvancesShilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, Adams Wai-Kin Kong. [doi]
• Unifying Causal Representation Learning with the Invariance PrincipleDingling Yao, Dario Rancati, Riccardo Cadei, Marco Fumero, Francesco Locatello. [doi]
• ContextGNN: Beyond Two-Tower Recommendation SystemsYiwen Yuan, Zecheng Zhang, Xinwei He, Akihiro Nitta, Weihua Hu, Manan Shah, Blaz Stojanovic, Shenyang Huang, Jan Eric Lenssen, Jure Leskovec, Matthias Fey. [doi]
• Anyprefer: An Agentic Framework for Preference Data SynthesisYiyang Zhou, Zhaoyang Wang, Tianle Wang 0009, Shangyu Xing, Peng Xia, Bo Li, Kaiyuan Zheng, Zijian Zhang 0010, Zhaorun Chen, Wenhao Zheng, Xuchao Zhang, Chetan Bansal, Weitong Zhang, Ying Wei, Mohit Bansal, Huaxiu Yao. [doi]
• Can LLMs Solve Longer Math Word Problems Better?Xin Xu, Tong Xiao, Zitong Chao, Zhenya Huang, Can Yang, Yang Wang 0020. [doi]
• Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced ExplorationQintong Li, Jiahui Gao, Sheng Wang, Renjie Pi, Xueliang Zhao, Chuan Wu, Xin Jiang, Zhenguo Li, Lingpeng Kong. [doi]
• Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light TransportLvmin Zhang, Anyi Rao, Maneesh Agrawala. [doi]
• State Space Model Meets Transformer: A New Paradigm for 3D Object DetectionChuxin Wang, Wenfei Yang, Xiang Liu, Tianzhu Zhang. [doi]
• Ferret-UI 2: Mastering Universal User Interface Understanding Across PlatformsZhangheng Li, Keen You, Haotian Zhang, Di Feng, Harsh Agrawal, Xiujun Li, Mohana Prasad Sathya Moorthy, Jeffrey Nichols 0001, Yinfei Yang, Zhe Gan. [doi]
• DELIFT: Data Efficient Language model Instruction Fine-TuningIshika Agarwal, KrishnaTeja Killamsetty, Lucian Popa 0001, Marina Danilevsky. [doi]
• Emergence of meta-stable clustering in mean-field transformer modelsGiuseppe Bruno, Federico Pasqualotto, Andrea Agazzi. [doi]
• Preference Elicitation for Offline Reinforcement LearningAlizée Pace, Bernhard Schölkopf, Gunnar Rätsch, Giorgia Ramponi. [doi]
• SRSA: Skill Retrieval and Adaptation for Robotic Assembly TasksYijie Guo, Bingjie Tang, Iretiayo Akinola, Dieter Fox, Abhishek Gupta 0004, Yashraj Narang. [doi]
• Advancing Prompt-Based Methods for Replay-Independent General Continual LearningZhiqi Kang, Liyuan Wang, Xingxing Zhang, Karteek Alahari. [doi]
• What Makes a Maze Look Like a Maze?Joy Hsu, Jiayuan Mao, Joshua B. Tenenbaum, Noah D. Goodman, Jiajun Wu 0001. [doi]
• Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal TransportMilena Gazdieva, Jaemoo Choi, Alexander Kolesov, Jaewoong Choi, Petr Mokrov, Alexander Korotin. [doi]
• When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs" for Human-AI InteractionZhenchang Xing, Yang Liu 0003, Zhuo Cheng, Qing Huang, Dehai Zhao, Daniel Sun 0006, Chenhua Liu. [doi]
• Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching PriorsLin-Zhuo Chen, Kangjie Liu, Youtian Lin, Zhihao Li 0002, Siyu Zhu 0001, Xun Cao, Yao Yao 0008. [doi]
• A Formal Framework for Understanding Length Generalization in TransformersXinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn 0001. [doi]
• CAX: Cellular Automata Accelerated in JAXMaxence Faldor, Antoine Cully. [doi]
• Data Unlearning in Diffusion ModelsSilas Alberti, Kenan Hasanaliyev, Manav Shah, Stefano Ermon. [doi]
• AuroraCap: Efficient, Performant Video Detailed Captioning and a New BenchmarkWenhao Chai, Enxin Song, Yilun Du, Chenlin Meng, Vashisht Madhavan, Omer Bar-Tal, Jenq-Neng Hwang, Saining Xie, Christopher D. Manning. [doi]
• TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse AttentionLijie Yang 0003, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia. [doi]
• MOFFlow: Flow Matching for Structure Prediction of Metal-Organic FrameworksNayoung Kim, seongsu Kim, Minsu Kim, Jinkyoo Park, Sungsoo Ahn. [doi]
• Language Agents Meet Causality - Bridging LLMs and Causal World ModelsJohn Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov. [doi]
• Variational Search DistributionsDaniel M. Steinberg, Rafael Oliveira 0001, Cheng Soon Ong, Edwin V. Bonilla. [doi]
• On the Performance Analysis of Momentum Method: A Frequency Domain PerspectiveXianliang Li, Jun Luo, Zhiwei Zheng, Hanxiao Wang, Li Luo, Lingkun Wen, Linlong Wu, Sheng Xu 0004. [doi]
• Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model AccuracyYangsibo Huang, Daogao Liu, Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Milad Nasr, Amer Sinha, Chiyuan Zhang. [doi]
• Online Clustering with Nearly Optimal ConsistencyT.-H. Hubert Chan, Shaofeng H.-C. Jiang, Tianyi Wu, Mengshi Zhao. [doi]
• Towards hyperparameter-free optimization with differential privacyRuixuan Liu, Zhiqi Bu. [doi]
• NVS-Solver: Video Diffusion Model as Zero-Shot Novel View SynthesizerMeng You, Zhiyu Zhu, Hui Liu 0032, Junhui Hou. [doi]
• QPM: Discrete Optimization for Globally Interpretable Image ClassificationThomas Norrenbrock, Timo Kaiser, Sovan Biswas, Ramesh Manuvinakurike, Bodo Rosenhahn. [doi]
• Connecting Federated ADMM to BayesSiddharth Swaroop, Mohammad Emtiyaz Khan, Finale Doshi-Velez. [doi]
• TimeMixer++: A General Time Series Pattern Machine for Universal Predictive AnalysisShiyu Wang 0001, Jiawei Li, Xiaoming Shi, Zhou Ye, Baichuan Mo, Wenze Lin, Shengtong Ju, Zhixuan Chu, Ming Jin 0005. [doi]
• One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt LearningWenxi Lv, Qinliang Su, Wenchao Xu 0001. [doi]
• Deep Distributed Optimization for Large-Scale Quadratic ProgrammingAugustinos D. Saravanos, Hunter Kuperman, Alex Oshin, Arshiya Taj Abdul, Vincent Pacelli, Evangelos Theodorou. [doi]
• AgentStudio: A Toolkit for Building General Virtual AgentsLongtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An 0001, Shuicheng Yan. [doi]
• Multi-objective antibody design with constrained preference optimizationMilong Ren, ZaiKai He, Haicang Zhang. [doi]
• GenSE: Generative Speech Enhancement via Language Models using Hierarchical ModelingJixun Yao, Hexin Liu, Chen Chen 0075, Yuchen Hu, Engsiong Chng, Lei Xie. [doi]
• Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone EnsemblingCristian Rodriguez Opazo, Ehsan Abbasnejad, Damien Teney, Hamed Damirchi, Edison Marrese-Taylor, Anton van den Hengel. [doi]
• MGCFNN: A Neural MultiGrid Solver with Novel Fourier Neural Network for High Wave Number Helmholtz EquationsYan Xie, Minrui Lv, Chensong Zhang. [doi]
• Exploring the Camera Bias of Person Re-identificationMyungseo Song, Jin-Woo Park, Jong-Seok Lee. [doi]
• E(n) Equivariant Topological Neural NetworksClaudio Battiloro, Ege Karaismailoglu, Mauricio Tec, George Dasoulas, Michelle Audirac, Francesca Dominici. [doi]
• A Multi-Power Law for Loss Curve Prediction Across Learning Rate SchedulesKairong Luo, Haodong Wen, Shengding Hu, Zhenbo Sun, Zhiyuan Liu, Maosong Sun 0001, Kaifeng Lyu, Wenguang Chen. [doi]
• IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video SynthesisShitong Shao, Zikai Zhou, Bai Lichen, Haoyi Xiong, Zeke Xie. [doi]
• TODO: Enhancing LLM Alignment with Ternary PreferencesYuxiang Guo, Lu Yin 0006, Bo Jiang, Jiaqi Zhang. [doi]
• Discrete Distribution NetworksLei Yang. [doi]
• Optimality and Adaptivity of Deep Neural Features for Instrumental Variable RegressionJuno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li. [doi]
• Streaming Video Question-Answering with In-context Video KV-Cache RetrievalShangzhe Di, Zhelun Yu, Guanghao Zhang, Haoyuan Li, Tao Zhong, Hao Cheng, Bolin Li, Wanggui He, Fangxun Shu, Hao Jiang. [doi]
• EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior GenerationCarl Qi, Dan Haramati, Tal Daniel, Aviv Tamar, Amy Zhang 0001. [doi]
• TLDR: Token-Level Detective Reward Model for Large Vision Language ModelsDeqing Fu, Tong Xiao, Rui Wang, Wang Zhu 0001, Pengchuan Zhang, Guan Pang, Robin Jia, Lawrence Chen 0002. [doi]
• Generating CAD Code with Vision-Language Models for 3D DesignsKamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Haider Zaidi, Megan Langwasser, Wei Xu, Matthew C. Gombolay. [doi]
• Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg ExtrapolationMarina Sheshukova, Denis Belomestny, Alain Oliviero Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov. [doi]
• dEBORA: Efficient Bilevel Optimization-based low-Rank AdaptationEmanuele Zangrando, Sara Venturini, Francesco Rinaldi, Francesco Tudisco. [doi]
• Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional DistributionsJianxin Zhang, Josh Viktorov, Doosan Jung, Emily Pitler. [doi]
• Edge-aware Image Smoothing with Relative Wavelet Domain RepresentationHuiqing Qi, Xiaoliu Luo, Tingting Li, Fang Li. [doi]
• FreeVS: Generative View Synthesis on Free Driving TrajectoryQitai Wang, Lue Fan, Yuqi Wang, YunTao Chen, Zhaoxiang Zhang 0001. [doi]
• Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box SystemsDaniel Mackinlay, Russell Tsuchida, Daniel Edward Pagendam, Petra Kuhnert. [doi]
• Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language ModelsShaotian Yan, Chen Shen 0003, Wenxiao Wang 0001, Liang Xie 0003, Junjie Liu, Jieping Ye. [doi]
• Mitigating Spurious Correlations in Zero-Shot Multimodal ModelsShenyu Lu, Junyi Chai 0004, Xiaoqian Wang 0001. [doi]
• Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic SpaceZhiliang Chen, Xinyuan Niu 0001, Chuan-Sheng Foo, Bryan Kian Hsiang Low. [doi]
• The Belief State TransformerEdward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford 0001, Dinesh Jayaraman, Alex Lamb, John Langford. [doi]
• ASTrA: Adversarial Self-supervised Training with Adaptive-AttacksPrakash Chandra Chhipa, Gautam Vashishtha, Settur Jithamanyu, Rajkumar Saini, Mubarak Shah, Marcus Liwicki. [doi]
• Analytic DAG Constraints for Differentiable DAG LearningZhen Zhang 0008, Ignavier Ng, Dong Gong, Yuhang Liu, Mingming Gong, Biwei Huang, Kun Zhang 0001, Anton van den Hengel, Javen Qinfeng Shi. [doi]
• Anti-Exposure Bias in Diffusion ModelsJunyu Zhang, Daochang Liu, Eunbyung Park, Shichao Zhang 0001, Chang Xu. [doi]
• Proactive Agent: Shifting LLM Agents from Reactive Responses to Active AssistanceYaxi Lu, Shenzhi Yang, Cheng Qian, Guirong Chen, Qinyu Luo, Yesai Wu, Huadong Wang, Xin Cong, Zhong Zhang, Yankai Lin, Weiwen Liu, Yasheng Wang, Zhiyuan Liu 0001, Fangming Liu, Maosong Sun 0001. [doi]
• Robust System Identification: Finite-sample Guarantees and Connection to RegularizationHyuk Park 0005, Grani A. Hanasusanto, Yingying Li. [doi]
• MeshAnything: Artist-Created Mesh Generation with Autoregressive TransformersYiwen Chen, Tong He 0001, Di Huang, Weicai Ye, Sijin Chen, Jiaxiang Tang, Zhongang Cai, Lei Yang 0045, Gang Yu 0002, Guosheng Lin, Chi Zhang 0007. [doi]
• Lightweight Predictive 3D Gaussian SplatsJunli Cao, Vidit Goel, Chaoyang Wang 0001, Anil Kag, Ju Hu, Sergei Korolev, Chenfanfu Jiang, Sergey Tulyakov, Jian Ren 0005. [doi]
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image SynthesisJinbin Bai, Tian Ye 0001, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong 0003, Lei Zhu 0003, Shuicheng Yan. [doi]
• Learning to Discover Regulatory Elements for Gene Expression PredictionXingyu Su, Haiyang Yu 0005, Degui Zhi, Shuiwang Ji. [doi]
• IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language ModelYatai Ji, Shilong Zhang, Jie Wu 0001, Peize Sun, Weifeng Chen, Xuefeng Xiao 0001, Sidi Yang, Yujiu Yang, Ping Luo 0002. [doi]
• Satisficing Regret Minimization in BanditsQing Feng, Tianyi Ma, Ruihao Zhu. [doi]
• Do LLMs "know" internally when they follow instructions?Juyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Kwan Ho Ryan Chan, Shirley You Ren, Andrew C. Miller, Udhyakumar Nallasamy, Jaya Narain. [doi]
• Streaming Video Understanding and Multi-round Interaction with Memory-enhanced KnowledgeHaomiao Xiong, Zongxin Yang, Jiazuo Yu, Yunzhi Zhuge, Lu Zhang 0053, Jiawen Zhu, Huchuan Lu. [doi]
• ContraDiff: Planning Towards High Return States via Contrastive LearningYixiang Shan, Zhengbang Zhu, Ting Long, Qifan Liang, Yi Chang 0001, Weinan Zhang 0001, Liang Yin. [doi]
• Balanced Ranking with Relative Centrality: A multi-core periphery perspectiveChandra Sekhar Mukherjee, Jiapeng Zhang. [doi]
• ECHOPulse: ECG Controlled Echocardio-gram Video GenerationYiwei Li 0002, Sekeun Kim, Zihao Wu 0001, Hanqi Jiang, Yi Pan 0001, Pengfei Jin, Sifan Song, Yucheng Shi, Xiaowei Yu, Tianze Yang, Tianming Liu 0001, Quanzheng Li, Xiang Li 0001. [doi]
• Score-based free-form architectures for high-dimensional Fokker-Planck equationsFeng Liu, Faguo Wu, Xiao Zhang 0004. [doi]
• REvolve: Reward Evolution with Large Language Models using Human FeedbackRishi Hazra, Alkis Sygkounas, Andreas Persson, Amy Loutfi, Pedro Zuidberg Dos Martires. [doi]
• Adapt-∞: Scalable Continual Multimodal Instruction Tuning via Dynamic Data SelectionAdyasha Maharana, Jaehong Yoon, Tianlong Chen 0001, Mohit Bansal. [doi]
• Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations InterpretabilityZhiyu Zhu, Zhibo Jin, Jiayu Zhang 0001, Nan Yang, Jiahao Huang, Jianlong Zhou, Fang Chen 0001. [doi]
• SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity ReductionLu Dai, Yijie Xu, Jinhui Ye, Hao Liu, Hui Xiong. [doi]
• Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed MethodsLise Le Boudec, Emmanuel de Bézenac, Louis Serrano, Ramon Daniel Regueiro-Espino, Yuan Yin, Patrick Gallinari. [doi]
• Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental ControlXianghui Ze, Zhenbo Song, Qiwei Wang, Jianfeng Lu 0003, Yujiao Shi. [doi]
• Monte Carlo Planning with Large Language Model for Text-Based Game AgentsZijing Shi, Meng Fang, Ling Chen. [doi]
• Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical PhysicsSebastian Sanokowski, Wilhelm Franz Berghammer, Haoyu Peter Wang, Martin Ennemoser, Sepp Hochreiter, Sebastian Lehner. [doi]
• Audio Large Language Models Can Be Descriptive Speech Quality EvaluatorsChen Chen 0075, Yuchen Hu, Siyin Wang, Helin Wang, Zhehuai Chen, Chao Zhang, Chao-Han Huck Yang, Engsiong Chng. [doi]
• Heavy-Tailed Diffusion with Denoising Levy Probabilistic ModelsDario Shariatian, Umut Simsekli, Alain Oliviero Durmus. [doi]
• GraphBridge: Towards Arbitrary Transfer Learning in GNNsLi Ju, Xingyi Yang, Qi Li, Xinchao Wang. [doi]
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsMaksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J. Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies. [doi]
• Your Mixture-of-Experts LLM Is Secretly an Embedding Model for FreeZiyue Li, Tianyi Zhou. [doi]
• Differentiation and Specialization of Attention Heads via the Refined Local Learning CoefficientGeorge Wang, Jesse Hoogland, Stan van Wingerden, Zach Furman, Daniel Murfet. [doi]
• A Theoretical Framework for Partially-Observed Reward States in RLHFChinmaya Kausik, Mirco Mutti, Aldo Pacchiano, Ambuj Tewari. [doi]
• Is Large-scale Pretraining the Secret to Good Domain Generalization?Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Bryan A. Plummer, Kate Saenko. [doi]
• A Theory for Token-Level Harmonization in Retrieval-Augmented GenerationShicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng. [doi]
• Protecting against simultaneous data poisoning attacksNeel Alex, Shoaib Ahmed Siddiqui, Amartya Sanyal, David Krueger 0001. [doi]
• ForecastBench: A Dynamic Benchmark of AI Forecasting CapabilitiesEzra Karger, Houtan Bastani, Chen Yueh-Han, Zachary Jacobs, Danny Halawi, Fred Zhang, Philip Tetlock. [doi]
• Uncovering Gaps in How Humans and LLMs Interpret Subjective LanguageErik Jones, Arjun Patrawala, Jacob Steinhardt. [doi]
• When narrower is better: the narrow width limit of Bayesian parallel branching neural networksZechen Zhang, Haim Sompolinsky. [doi]
• DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual GroundingHenry Zheng, Hao Shi, Qihang Peng, Yong Xien Chng, Rui Huang, Yepeng Weng, Zhongchao Shi, Gao Huang 0001. [doi]
• InCoDe: Interpretable Compressed Descriptions For Image GenerationArmand Comas Massague, Aditya Chattopadhyay, Feliu Formosa, Changyu Liu, Octavia I. Camps, René Vidal. [doi]
• Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based ApproachQi Liu, Xinhao Zheng, Xudong Lu, Qinxiang Cao, Junchi Yan. [doi]
• Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with StructureSamet Demir, Zafer Dogan. [doi]
• Breaking Neural Network Scaling Laws with ModularityAkhilan Boopathy, Sunshine Jiang, William Yue, Jaedong Hwang, Abhiram Iyer, Ila R. Fiete. [doi]
• ProtPainter: Draw or Drag Protein via Topology-guided DiffusionZhengxi Lu, Shizhuo Cheng, Tintin Jiang, Yan Zhang, Min Zhang. [doi]
• GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits LearningZulfikar Alom, Tran Gia Bao Ngo, Murat Kantarcioglu, Cuneyt Gurcan Akcora. [doi]
• Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep LearningBerken Utku Demirel, Christian Holz 0001. [doi]
• LoRA-X: Bridging Foundation Models with Training-Free Cross-Model AdaptationFarzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli. [doi]
• Predictive Inverse Dynamics Models are Scalable Learners for Robotic ManipulationYang Tian, Sizhe Yang, Jia Zeng, Ping Wang, Dahua Lin, Hao Dong 0003, Jiangmiao Pang. [doi]
• Efficient Policy Evaluation with Safety Constraint for Reinforcement LearningClaire Chen, Shuze Daniel Liu, Shangtong Zhang. [doi]
• MotionClone: Training-Free Motion Cloning for Controllable Video GenerationPengyang Ling, Jiazi Bu, Pan Zhang 0001, Xiaoyi Dong, Yuhang Zang, Tong Wu, Huaian Chen, Jiaqi Wang 0003, Yi Jin 0002. [doi]
• Proving Olympiad Inequalities by Synergizing LLMs and Symbolic ReasoningZenan Li, Zhaoyu Li, Wen Tang, Xian Zhang, Yuan Yao 0001, Xujie Si, Fan Yang, Kaiyu Yang, Xiaoxing Ma. [doi]
• The adaptive complexity of parallelized log-concave samplingHuanjian Zhou, Baoxiang Wang 0001, Masashi Sugiyama. [doi]
• MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map ConstructionJing Yang, Minyue Jiang, Sen Yang, Xiao Tan 0001, Yingying Li, Errui Ding, Jingdong Wang 0001, Hanli Wang. [doi]
• 3D-Spatial Multimodal MemoryXueyan Zou, Yuchen Song, Ri-Zhao Qiu, Xuanbin Peng, Jianglong Ye, Sifei Liu, Xiaolong Wang 0004. [doi]
• eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum ChannelsAlexander C. DeRieux, Walid Saad. [doi]
• Progressive Mixed-Precision Decoding for Efficient LLM InferenceHao Mark Chen, Fuwen Tan, Alexandros Kouris, Royson Lee, Hongxiang Fan, Stylianos I. Venieris. [doi]
• Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation ModelLong Le, Jason Xie, William Liang, Hung-Ju Wang, Yue Yang, Yecheng Jason Ma, Kyle Vedder, Arjun Krishna, Dinesh Jayaraman, Eric Eaton. [doi]
• Learning Molecular Representation in a CellGang Liu 0025, Srijit Seal, John Arevalo, Zhenwen Liang, Anne E. Carpenter, Meng Jiang 0001, Shantanu Singh. [doi]
• Efficiently Parameterized Neural Metriplectic SystemsAnthony Gruber, Kookjin Lee, Haksoo Lim, Noseong Park, Nathaniel Trask. [doi]
• Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector AblationXinpeng Wang 0003, Chengzhi Hu, Paul Röttger, Barbara Plank. [doi]
• Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?Sravanti Addepalli, Yerram Varun, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain 0002. [doi]
• Decision Information Meets Large Language Models: The Future of Explainable Operations ResearchYansen Zhang, Qingcan Kang, Wing Yin Yu, Hailei Gong, Xiaojin Fu, Xiongwei Han, Tao Zhong, Chen Ma. [doi]
• When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn SettingsJérémy Perez, Grgur Kovac, Corentin Léger, Cédric Colas, Gaia Molinaro, Maxime Derex, Pierre-Yves Oudeyer, Clément Moulin-Frier. [doi]
• YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel CorpusGarrett Tanzer, Biao Zhang 0006. [doi]
• Deep Linear Probe Generators for Weight Space LearningJonathan Kahana, Eliahu Horwitz, Imri Shuval, Yedid Hoshen. [doi]
• Spiking Vision Transformer with Saccadic AttentionShuai Wang, Malu Zhang, Dehao Zhang, Ammar Belatreche, Yichen Xiao, Yu Liang, Yimeng Shan, Qian Sun, Enqi Zhang, Yang Yang. [doi]
• Long-Sequence Recommendation Models Need Decoupled EmbeddingsNingya Feng, Junwei Pan, Jialong Wu 0001, Baixu Chen, Ximei Wang, Qian Li 0016, Xian Hu, Jie Jiang 0015, Mingsheng Long. [doi]
• SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuningMinJun Kim, Jongjin Kim 0001, U Kang. [doi]
• RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object DetectionJingtong Yue, Zhiwei Lin, Xin Lin, Xiaoyu Zhou, Xiangtai Li, Lu Qi, Yongtao Wang, Ming-Hsuan Yang 0001. [doi]
• Preble: Efficient Distributed Prompt Scheduling for LLM ServingVikranth Srivatsa, Zijian He, Reyna Abhyankar, Dongming Li, Yiying Zhang 0005. [doi]
• VILA-U: a Unified Foundation Model Integrating Visual Understanding and GenerationYecheng Wu, Zhuoyang Zhang, Junyu Chen, Haotian Tang, Dacheng Li, Yunhao Fang, Ligeng Zhu, Enze Xie, Hongxu Yin, Li Yi, Song Han 0003, Yao Lu 0006. [doi]
• Training-free LLM-generated Text Detection by Mining Token Probability SequencesYihuai Xu, Yongwei Wang, Yifei Bi, Huangsen Cao, Zhouhan Lin, Yu Zhao, Fei Wu 0001. [doi]
• Transition Path Sampling with Improved Off-Policy Training of Diffusion Path SamplersKiyoung Seong, Seonghyun Park 0004, Seonghwan Kim 0004, Woo-Youn Kim, Sungsoo Ahn. [doi]
• Going Beyond Static: Understanding Shifts with Time-Series AttributionJiashuo Liu, Nabeel Seedat, Peng Cui 0001, Mihaela van der Schaar. [doi]
• MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language ModelsPei Wang, Yanan Wu, Noah Wang, Jiaheng Liu, Xiaoshuai Song, Z. Y. Peng, Ken Deng, Chenchen Zhang, Jiakai Wang, Junran Peng, Ge Zhang, Hangyu Guo, Zhaoxiang Zhang 0001, Wenbo Su, Bo Zheng 0007. [doi]
• Semialgebraic Neural Networks: From roots to representationsS. David Mis, Matti Lassas, Maarten V. De Hoop. [doi]
• TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference TreesWeibin Liao, Xu Chu, Yasha Wang. [doi]
• MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networksCarlo Abate, Filippo Maria Bianchi. [doi]
• FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language ModelsZhanwei Zhang, Shizhao Sun, Wenxiao Wang 0001, Deng Cai 0001, Jiang Bian. [doi]
• See What You Are Told: Visual Attention Sink in Large Multimodal ModelsSeil Kang, Jinyeong Kim, Junhyeok Kim 0002, Seong Jae Hwang. [doi]
• MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing AgentsYanqi Dai, Huanran Hu, Lei Wang 0198, Shengjie Jin, Xu Chen 0017, Zhiwu Lu 0001. [doi]
• On the Relation between Trainability and Dequantization of Variational Quantum Learning ModelsElies Gil-Fuster, Casper Gyurik, Adrián Pérez-Salinas, Vedran Dunjko. [doi]
• Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion ModelsJinxu Lin, Linwei Tao, Minjing Dong, Chang Xu. [doi]
• CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent CooperationJie Liu 0043, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees G. M. Snoek, Jan-Jakob Sonke, Efstratios Gavves. [doi]
• Federated Few-Shot Class-Incremental LearningMuhammad Anwar Ma'sum, Mahardhika Pratama, Lin Liu 0003, Habibullah, Ryszard Kowalczyk. [doi]
• AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-ResolutionYun Zhang, Wei Li 0002, Simiao Li, Hanting Chen, Zhijun Tu, Bingyi Jing, Shaohui Lin, Jie Hu 0021, Wenjia Wang. [doi]
• Scalable Bayesian Learning with posteriorsSamuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett, Daniel Simpson. [doi]
• SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion TransformersEnze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin 0001, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu 0006, Song Han 0003. [doi]
• Aligned LLMs Are Not Aligned Browser AgentsPriyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Elaine T. Chang, Vaughn Robinson, Shuyan Zhou, Matt Fredrikson, Sean M. Hendryx, Summer Yue, Zifan Wang 0001. [doi]
• Linear SCM Identification in the Presence of Confounders and Gaussian NoiseVahideh Sanjaroonpouri, Pouria Ramazi. [doi]
• SEBRA : Debiasing through Self-Guided Bias RankingAdarsh Kappiyath, Abhra Chaudhuri, Ajay Kumar Jaiswal, Ziquan Liu, Yunpeng Li, Xiatian Zhu, Lu Yin 0006. [doi]
• TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning BenchmarksIvan Rubachev, Nikolay Kartashev, Yury Gorishniy, Artem Babenko. [doi]
• Test-time Adaptation for Cross-modal Retrieval with Query ShiftHaobin Li, Peng Hu 0002, Qianjun Zhang, Xi Peng 0001, XitingLiu, Mouxing Yang. [doi]
• Physics-Informed Diffusion ModelsJan-Hendrik Bastek, Waiching Sun, Dennis M. Kochmann. [doi]
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLMohammadreza Pourreza, Hailong Li, Ruoxi Sun 0002, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, Sercan Ö. Arik. [doi]
• Generative Monoculture in Large Language ModelsFan Wu, Emily Black, Varun Chandrasekaran. [doi]
• Ready-to-React: Online Reaction Policy for Two-Character Interaction GenerationZhi Cen, Huaijin Pi, Sida Peng, Qing Shuai, Yujun Shen, Hujun Bao, Xiaowei Zhou 0001, Ruizhen Hu. [doi]
• Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text MatchingRenjie Pan 0001, Jihao Dong, Hua Yang 0001. [doi]
• FOSP: Fine-tuning Offline Safe Policy through World ModelsChenyang Cao, Yucheng Xin, Silang Wu, Longxiang He, Zichen Yan, Junbo Tan, Xueqian Wang 0001. [doi]
• COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 TrainingHaocheng Xi, Han Cai, Ligeng Zhu, Yao Lu 0006, Kurt Keutzer, Jianfei Chen, Song Han 0003. [doi]
• Latent Action Pretraining from VideosSeonghyeon Ye, Joel Jang, Byeongguk Jeon, Se June Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee, Jianfeng Gao 0001, Luke Zettlemoyer, Dieter Fox, Minjoon Seo. [doi]
• Frequency-Guided Masking for Enhanced Vision Self-Supervised LearningAmin Karimi Monsefi, Mengxi Zhou, Nastaran Karimi Monsefi, Ser-Nam Lim, Wei-Lun Chao, Rajiv Ramnath. [doi]
• Towards Continuous Reuse of Graph Models via Holistic Memory DiversificationZiyue Qiao, Junren Xiao, Qingqiang Sun, Meng Xiao 0001, Xiao Luo 0001, Hui Xiong 0001. [doi]
• Block-Attention for Efficient PrefillingDongyang Ma, Yan Wang, Tian Lan. [doi]
• EmbodiedSAM: Online Segment Any 3D Thing in Real TimeXiuwei Xu, Huangxing Chen, Linqing Zhao, Ziwei Wang, Jie Zhou, Jiwen Lu. [doi]
• On Bits and Bandits: Quantifying the Regret-Information Trade-offItai Shufaro, Nadav Merlis, Nir Weinberger, Shie Mannor. [doi]
• Learning Partial Graph Matching via Optimal Partial TransportGathika Ratnayaka, James Nichols, Qing Wang. [doi]
• Underdamped Diffusion Bridges with Applications to SamplingDenis Blessing, Julius Berner, Lorenz Richter, Gerhard Neumann. [doi]
• Accelerating neural network training: An analysis of the AlgoPerf competitionPriya Kasimbeg, Frank Schneider 0001, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl. [doi]
• Accelerating Inference of Retrieval-Augmented Generation via Sparse Context SelectionYun Zhu, Jia-Chen Gu, Caitlin Sikora, Ho Ko, Yinxiao Liu, Chu-Cheng Lin, Lei Shu 0004, Liangchen Luo, Lei Meng 0008, Bang Liu, Jindong Chen. [doi]
• Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintsMihaela C. Stoian, Eleonora Giunchiglia. [doi]
• Range, not Independence, Drives Modularity in Biologically Inspired RepresentationsWill Dorrell, Kyle Hsu, Luke Hollingsworth, Jin Hwa Lee, Jiajun Wu 0001, Chelsea Finn, Peter E. Latham, Timothy Edward John Behrens, James C. R. Whittington. [doi]
• Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model EnsemblingYuxuan Yao, Han Wu 0004, Mingyang Liu, Sichun Luo, Xiongwei Han, Jie Liu, Zhijiang Guo, Linqi Song. [doi]
• More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed RoutingSagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence Hunter, Matt Jones 0002. [doi]
• Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion ModelsShuhong Zheng, Zhipeng Bao, Ruoyu Zhao, Martial Hebert, Yu-Xiong Wang. [doi]
• RaSA: Rank-Sharing Low-Rank AdaptationZhiwei He, Zhaopeng Tu, Xing Wang, Xingyu Chen, Zhijie Wang, Jiahao Xu, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang. [doi]
• CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip DesignWenji Fang, Shang Liu, Jing Wang, Zhiyao Xie. [doi]
• How Much is a Noisy Image Worth? Data Scaling Laws for Ambient DiffusionGiannis Daras, Yeshwanth Cherapanamjeri, Constantinos Daskalakis. [doi]
• Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset ConstraintJiafei Lyu, Mengbei Yan, Zhongjian Qiao, Runze Liu 0002, Xiaoteng Ma, Deheng Ye, Jingwen Yang, Zongqing Lu 0002, Xiu Li 0001. [doi]
• AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk CategoriesYi Zeng 0005, Yu Yang 0011, Andy Zhou, Jeffrey Ziwei Tan, Yuheng Tu, Yifan Mai, Kevin Klyman, Minzhou Pan, Ruoxi Jia 0001, Dawn Song, Percy Liang, Bo Li. [doi]
• Dense Video Object Captioning from Disjoint SupervisionXingyi Zhou, Anurag Arnab, Chen Sun 0002, Cordelia Schmid. [doi]
• VibeCheck: Discover and Quantify Qualitative Differences in Large Language ModelsLisa Dunlap, Krishna Mandal, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez. [doi]
• DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic ScenesHengwei Bian, Lingdong Kong, Haozhe Xie, Liang Pan, Yu Qiao 0001, Ziwei Liu 0002. [doi]
• Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion ModelsYong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji. [doi]
• Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient ReasonsShahaf Bassan, Ron Eliav, Shlomit Gur. [doi]
• SaLoRA: Safety-Alignment Preserved Low-Rank AdaptationMingjie Li 0007, Wai Man Si, Michael Backes 0001, Yang Zhang 0016, Yisen Wang 0001. [doi]
• Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State FusionChaodong Xiao, Minghan Li 0001, Zhengqiang Zhang, Deyu Meng, Lei Zhang 0006. [doi]
• Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State SamplingTimothée G. Leleu, Sam Reifenstein. [doi]
• Vision Language Models are In-Context Value LearnersYecheng Jason Ma, Joey Hejna, Chuyuan Fu, Dhruv Shah, Jacky Liang, Zhuo Xu, Sean Kirmani, Peng Xu 0010, Danny Driess, Ted Xiao, Osbert Bastani, Dinesh Jayaraman, Wenhao Yu 0003, Tingnan Zhang, Dorsa Sadigh, Fei Xia 0002. [doi]
• MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse UpcyclingRachel S. Y. Teo, Tan Minh Nguyen. [doi]
• DPLM-2: A Multimodal Diffusion Protein Language ModelXinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, Quanquan Gu. [doi]
• OmniRe: Omni Urban Scene ReconstructionZiyu Chen, Jiawei Yang, Jiahui Huang, Riccardo de Lutio, Janick Martinez Esturo, Boris Ivanovic, Or Litany, Zan Gojcic, Sanja Fidler, Marco Pavone 0001, Li Song, Yue Wang. [doi]
• Fast and Slow Streams for Online Time Series Forecasting Without Information LeakageYing-yee Ava Lau, Zhiwen Shao, Dit-Yan Yeung. [doi]
• Directional Gradient Projection for Robust Fine-Tuning of Foundation ModelsChengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira. [doi]
• Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision ProcessesHaotian Wu, Gongpu Chen, Deniz Gündüz. [doi]
• Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion ModelsDvir Samuel, Barak Meiri, Haggai Maron, Yoad Tewel, Nir Darshan, Shai Avidan, Gal Chechik, Rami Ben-Ari. [doi]
• Large Language Models Often Say One Thing and Do AnotherRuoxi Xu, Hongyu Lin, Xianpei Han, Jia Zheng, Weixiang Zhou, Le Sun 0001, Yingfei Sun. [doi]
• ParFam - (Neural Guided) Symbolic Regression via Continuous Global OptimizationPhilipp Scholl 0003, Katharina Bieker, Hillary Hauger, Gitta Kutyniok. [doi]
• Dynamic Loss-Based Sample Reweighting for Improved Large Language Model PretrainingDaouda Sow, Herbert Woisetschläger, Saikiran Bulusu, Shiqiang Wang 0001, Hans-Arno Jacobsen, Yingbin Liang. [doi]
• Endowing Visual Reprogramming with Adversarial RobustnessShengjie Zhou, Xin Cheng, Haiyang Xu, Ming Yan 0008, Tao Xiang 0001, Feng Liu, Lei Feng 0006. [doi]
• Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math ProblemsTian Ye 0011, Zicheng Xu, Yuanzhi Li, Zeyuan Allen Zhu. [doi]
• High-Precision Dichotomous Image Segmentation via Probing Diffusion CapacityQian Yu, Peng-Tao Jiang, Hao Zhang 0063, Jinwei Chen, Bo Li 0115, Lihe Zhang, Huchuan Lu. [doi]
• Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic SelectionLei Shen, Zhenheng Tang, Lijun Wu, Yonggang Zhang 0003, Xiaowen Chu 0001, Tao Qin, Bo Han 0003. [doi]
• Rational Decision-Making Agent with Learning Internal Utility JudgmentYining Ye, Xin Cong, Shizuo Tian, Yujia Qin, Chong Liu, Yankai Lin, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Interpreting Language Reward Models via Contrastive ExplanationsJunqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lécué, Manuela Veloso. [doi]
• Physics of Language Models: Part 3.3, Knowledge Capacity Scaling LawsZeyuan Allen Zhu, Yuanzhi Li. [doi]
• UniDetox: Universal Detoxification of Large Language Models via Dataset DistillationHuimin Lu, Masaru Isonuma, Junichiro Mori, Ichiro Sakata. [doi]
• A Solvable Attention for Neural Scaling LawsBochen Lyu, Di Wang, Zhanxing Zhu. [doi]
• Infilling Score: A Pretraining Data Detection Algorithm for Large Language ModelsNegin Raoof, Litu Rout, Giannis Daras, Sujay Sanghavi, Constantine Caramanis, Sanjay Shakkottai, Alex Dimakis. [doi]
• Group Downsampling with Equivariant Anti-aliasingMd Ashiqur Rahman, Raymond A. Yeh. [doi]
• PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-TaskJing Wang, Ao Ma, Jiasong Feng, Dawei Leng, Yuhui Yin, Xiaodan Liang. [doi]
• Faster Diffusion Sampling with Randomized Midpoints: Sequential and ParallelShivam Gupta 0002, Linda Cai, Sitan Chen. [doi]
• Associative memory and dead neuronsVladimir Fanaskov, Ivan V. Oseledets. [doi]
• PersonalLLM: Tailoring LLMs to Individual PreferencesThomas P. Zollo, Andrew Wei Tung Siah, Naimeng Ye, Ang Li, Hongseok Namkoong. [doi]
• Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHFTengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah, Alexander Rakhlin. [doi]
• SymDiff: Equivariant Diffusion via Stochastic SymmetrisationLeo Zhang, Kianoosh Ashouritaklimi, Yee Whye Teh, Rob Cornish. [doi]
• Collaborative Discrete-Continuous Black-Box Prompt Learning for Language ModelsHualin Zhang, Haozhen Zhang, Zhekai Liu, Bin Gu 0001, Yi Chang 0001. [doi]
• Large Language Models can Become Strong Self-DetoxifiersChing Yun Ko, Pin-Yu Chen, Payel Das, Youssef Mroueh, Soham Dan, Georgios Kollias, Subhajit Chaudhury, Tejaswini Pedapati, Luca Daniel. [doi]
• 3D StreetUnveiler with Semantic-aware 2DGS - a simple baselineJingwei Xu, Yikai Wang 0002, Yiqun Zhao, Yanwei Fu 0001, Shenghua Gao. [doi]
• Video Action DifferencingJames Burgess, Xiaohan Wang, Yuhui Zhang, Anita Rau, Alejandro Lozano, Lisa Dunlap, Trevor Darrell, Serena Yeung-Levy. [doi]
• MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMsJiarui Zhang 0002, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski. [doi]
• ReGenesis: LLMs can Grow into Reasoning Generalists via Self-ImprovementXiangyu Peng, Congying Xia, Xinyi Yang 0002, Caiming Xiong, Chien-Sheng Wu, Chen Xing. [doi]
• DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM InferenceJinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin. [doi]
• Improving Unsupervised Constituency Parsing via Maximizing Semantic InformationJunjie Chen, Xiangheng He, Yusuke Miyao, Danushka Bollegala. [doi]
• LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer VisionMateusz Pach, Koryna Lewandowska, Jacek Tabor, Bartosz Michal Zielinski, Dawid Damian Rymarczyk. [doi]
• Multimodal Situational SafetyKaiwen Zhou, Chengzhi Liu, Xuandong Zhao, Anderson Compalas, Dawn Song, Xin Eric Wang. [doi]
• BlendRL: A Framework for Merging Symbolic and Neural Policy LearningHikaru Shindo, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting. [doi]
• Meta-Dynamical State Space Models for Integrative Neural Data AnalysisAyesha Vermani, Josue Nassar, Hyungju Jeon, Matthew Dowling, Il Memming Park. [doi]
• SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEGShanglin Li, Motoaki Kawanabe, Reinmar J. Kobler. [doi]
• Scalable Decentralized Learning with TeleportationYuki Takezawa, Sebastian U. Stich. [doi]
• Effective and Efficient Time-Varying Counterfactual Prediction with State-Space ModelsHaotian Wang 0001, Haoxuan Li 0001, Hao Zou 0001, Haoang Chi, Long Lan, Wanrong Huang, Wenjing Yang 0002. [doi]
• I2VControl-Camera: Precise Video Camera Control with Adjustable Motion StrengthWanquan Feng, Jiawei Liu 0001, Pengqi Tu, Tianhao Qi, Mingzhen Sun, Tianxiang Ma, Songtao Zhao, SiYu Zhou 0002, Qian He. [doi]
• Tuning-Free Bilevel Optimization: New Algorithms and Convergence AnalysisYifan Yang, Hao Ban, Minhui Huang, Shiqian Ma, Kaiyi Ji. [doi]
• Efficient Causal Decision Making with One-sided FeedbackJianing Chu, Shu Yang, Wenbin Lu, Pulak Ghosh. [doi]
• CLIPDrag: Combining Text-based and Drag-based Instructions for Image EditingZiqi Jiang, Zhen Wang, Long Chen. [doi]
• Locality-aware Gaussian Compression for Fast and High-quality RenderingSeungjoo Shin, Jaesik Park, Sunghyun Cho. [doi]
• FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement LearningWoosung Koh, Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang, Junghyun Lee, Se-Young Yun. [doi]
• From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian EstimationNikita Kotelevskii, Vladimir Kondratyev, Martin Takác 0001, Eric Moulines, Maxim Panov. [doi]
• TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell ClassificationBo Hu, Tat-Jen Cham. [doi]
• LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Zhengbo Wang, Jian Liang 0001, Ran He 0001, Zilei Wang, Tieniu Tan. [doi]
• Discrete Copula DiffusionAnji Liu, Oliver Broadrick, Mathias Niepert, Guy Van den Broeck. [doi]
• Why In-Context Learning Models are Good Few-Shot Learners?Shiguang Wu 0002, Yaqing Wang 0002, Quanming Yao. [doi]
• Data Selection via Optimal Control for Language ModelsYuxian Gu, Li Dong, Hongning Wang, Yaru Hao, Qingxiu Dong, Furu Wei, Minlie Huang. [doi]
• Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic GamesRunyu Lu, Yuanheng Zhu, Dongbin Zhao. [doi]
• Enhancing Compositional Text-to-Image Generation with Reliable Random SeedsShuangqi Li, Hieu Le 0001, Jingyi Xu, Mathieu Salzmann. [doi]
• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior PredictionJarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Cheng-Hao Liu, Sarthak Mittal, Nouha Dziri, Michael M. Bronstein, Pranam Chatterjee, Alexander Tong 0001, Joey Bose. [doi]
• Point-SAM: Promptable 3D Segmentation Model for Point CloudsYuchen Zhou, Jiayuan Gu, Tung Yen Chiang, Fanbo Xiang, Hao Su. [doi]
• Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNsMichael Scholkemper, Xinyi Wu, Ali Jadbabaie, Michael T. Schaub. [doi]
• Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic EnvironmentsHongjin Su, Ruoxi Sun 0002, Jinsung Yoon, Pengcheng Yin, Tao Yu 0009, Sercan Ö. Arik. [doi]
• DebGCD: Debiased Learning with Distribution Guidance for Generalized Category DiscoveryYuanpei Liu, Kai Han 0001. [doi]
• Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and OptimizationZichen Wang, Yaokun Ji, Jianing Tian, Shuangjia Zheng. [doi]
• RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object DetectionJingtong Yue, Zhiwei Lin, Xin Lin, Xiaoyu Zhou, Xiangtai Li, Lu Qi, Yongtao Wang, Ming-Hsuan Yang 0001. [doi]
• Linear combinations of latents in generative models: subspaces and beyondErik Bodin, Alexandru I. Stere, Dragos D. Margineantu, Carl Henrik Ek, Henry Moss. [doi]
• Density estimation with LLMs: a geometric investigation of in-context learning trajectoriesToni J. B. Liu, Nicolas Boullé, Raphaël Sarfati, Christopher J. Earls. [doi]
• The Crucial Role of Samplers in Online Direct Preference OptimizationRuizhe Shi, Runlong Zhou, Simon Shaolei Du. [doi]
• Language Model Alignment in Multilingual Trolley ProblemsZhijing Jin 0001, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu 0004, Fernando Gonzalez Adauto, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi 0001, Bernhard Schölkopf. [doi]
• What Are Good Positional Encodings for Directed Graphs?Yinan Huang, Haoyu Peter Wang, Pan Li. [doi]
• Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention FormulationItamar Zimerman, Ameen Ali, Lior Wolf. [doi]
• Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based AgentsHanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, Yongfeng Zhang. [doi]
• Forte : Finding Outliers with Representation Typicality EstimationDebargha Ganguly, Warren Richard Morningstar, Andrew Seohwan Yu, Vipin Chaudhary. [doi]
• Can Large Language Models Understand Symbolic Graphics Programs?Zeju Qiu, Weiyang Liu, Haiwen Feng, Zhen Liu 0019, Tim Z. Xiao, Katherine M. Collins, Joshua B. Tenenbaum, Adrian Weller, Michael J. Black, Bernhard Schölkopf. [doi]
• Semantic Aware Representation Learning for Lifelong LearningFahad Sarfraz, Elahe Arani, Bahram Zonooz. [doi]
• GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian SplattingJunzhe Jiang 0003, Chun Gu, Yurui Chen, Li Zhang 0040. [doi]
• HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsSeanie Lee, Haebin Seong, Dong-Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner 0002, Yoshua Bengio, Juho Lee 0001, Sung Ju Hwang. [doi]
• Progressive Compositionality in Text-to-Image Generative ModelsXu Han, Linghao Jin, Xiaofeng Liu, Paul Pu Liang. [doi]
• Comparing Targeting Strategies for Maximizing Social Welfare with Limited ResourcesVibhhu Sharma, Bryan Wilder. [doi]
• MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language ModelsFanqing Meng, Jin Wang, Chuanhao Li 0001, Quanfeng Lu, Hao Tian 0006, Tianshuo Yang, Jiaqi Liao, Xizhou Zhu, Jifeng Dai, Yu Qiao 0001, Ping Luo 0002, Kaipeng Zhang, Wenqi Shao. [doi]
• Visually Consistent Hierarchical Image ClassificationSeulki Park, Youren Zhang, Stella X. Yu, Sara Beery, Jonathan Huang. [doi]
• How new data permeates LLM knowledge and how to dilute itChen Sun, Renat Aksitov, Andrey Zhmoginov, Nolan Andrew Miller, Max Vladymyrov, Ulrich Rueckert, Been Kim, Mark Sandler 0002. [doi]
• Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker ModelZhiwei Xu, Zhiyu Ni, Yixin Wang, Wei Hu. [doi]
• ColPali: Efficient Document Retrieval with Vision Language ModelsManuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, Pierre Colombo. [doi]
• Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale BenchmarkBing Cao 0002, Quanhao Lu, Jiekang Feng, Qilong Wang 0001, Pengfei Zhu 0001, Qinghua Hu. [doi]
• OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing AgentsZhaolin Hu, Yixiao Zhou, Zhongan Wang, Xin Li, Weimin Yang, Hehe Fan, Yi Yang. [doi]
• SimulPL: Aligning Human Preferences in Simultaneous Machine TranslationDonglei Yu, Yang Zhao, Jie Zhu, Yangyifan Xu, Yu Zhou, Chengqing Zong. [doi]
• Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from ImagesAiqing Zhu, Yuting Pan, Qianxiao Li. [doi]
• Differentiable Causal Discovery for Latent Hierarchical Causal ModelsParjanya Prajakta Prashant, Ignavier Ng, Kun Zhang 0001, Biwei Huang. [doi]
• Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's FormulaYoussef Shehata, Benjamin J. Holzschuh, Nils Thuerey. [doi]
• Aioli: A Unified Optimization Framework for Language Model Data MixingMayee F. Chen, Michael Y. Hu, Nicholas Lourie, KyungHyun Cho, Christopher Ré. [doi]
• LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenShaolei Zhang, Qingkai Fang, Zhe Yang, Yang Feng 0004. [doi]
• A3D: Does Diffusion Dream about 3D Alignment?Savva Victorovich Ignatyev, Nina Konovalova, Daniil Selikhanovych, Oleg Voynov, Nikolay Patakin, Ilya Olkov, Dmitry Senushkin, Alexey Artemov, Anton Konushin, Alexander Filippov, Peter Wonka, Evgeny Burnaev. [doi]
• Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty QuantificationSantiago Cortes-Gomez, Carlos Miguel Patiño, Yewon Byun, Steven Wu 0001, Eric Horvitz, Bryan Wilder. [doi]
• Systematic Relational Reasoning With Epistemic Graph Neural NetworksIrtaza Khalid, Steven Schockaert. [doi]
• Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein InteractionsXiaoran Jiao, Weian Mao, Wengong Jin, Peiyuan Yang, Hao Chen 0012, Chunhua Shen. [doi]
• Adversaries With Incentives: A Strategic Alternative to Adversarial RobustnessMaayan Ehrenberg, Roy Ganz, Nir Rosenfeld. [doi]
• Highly Efficient Self-Adaptive Reward Shaping for Reinforcement LearningHaozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima, Tze-Yun Leong. [doi]
• Neuroplastic Expansion in Deep Reinforcement LearningJiashun Liu, Johan Samir Obando-Ceron, Aaron C. Courville, Ling Pan. [doi]
• Optimizing (L0, L1)-Smooth Functions by Gradient MethodsDaniil Vankov, Anton Rodomanov, Angelia Nedich, Lalitha Sankar, Sebastian U. Stich. [doi]
• F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AIXu Zheng 0003, Farhad Shirani 0001, Zhuomin Chen, Chaohao Lin, Wei Cheng 0002, Wenbo Guo 0002, Dongsheng Luo. [doi]
• LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative DecodingDoohyuk Jang, Sihwan Park 0001, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu 0009, Sungyub Kim, Eunho Yang. [doi]
• Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making SystemsRuochen Jiao, Shaoyuan Xie, Justin Yue, Takami Sato, Lixu Wang, Yixuan Wang, Qi Alfred Chen, Qi Zhu 0002. [doi]
• MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelsMohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi. [doi]
• VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon ManipulationKuo-Han Hung, Pang-Chi Lo, Jia-Fong Yeh, Han-Yuan Hsu, Yi-Ting Chen, Winston H. Hsu. [doi]
• ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide SequencingShaorong Chen, Jun Xia 0001, Jingbo Zhou, Lecheng Zhang, Zhangyang Gao, Bozhen Hu, Cheng Tan 0012, Wenjie Du, Stan Z. Li. [doi]
• Aligned Datasets Improve Detection of Latent Diffusion-Generated ImagesAnirudh Sundara Rajan, Utkarsh Ojha, Jedidiah Schloesser, Yong Jae Lee. [doi]
• Bootstrapped Model Predictive ControlYuhang Wang, Hanwei Guo, Sizhe Wang, Long Qian, Xuguang Lan. [doi]
• MovieDreamer: Hierarchical Generation for Coherent Long Visual SequencesCanyu Zhao, Mingyu Liu, Wen Wang 0015, Weihua Chen, Fan Wang 0019, Hao Chen 0041, Bo Zhang 0025, Chunhua Shen. [doi]
• Accurate and Scalable Graph Neural Networks via Message InvarianceZhihao Shi, Jie Wang, Zhiwei Zhuang, Xize Liang, Bin Li, Feng Wu. [doi]
• POGEMA: A Benchmark Platform for Cooperative Multi-Agent PathfindingAlexey Skrynnik, Anton Andreychuk, Anatolii Borzilov, Alexander Chernyavskiy, Konstantin S. Yakovlev, Aleksandr Panov. [doi]
• 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric RenderingZhongpai Gao, Benjamin Planche, Meng Zheng 0002, Anwesa Choudhuri, Terrence Chen, Ziyan Wu 0001. [doi]
• TopoGaussian: Inferring Internal Topology Structures from Visual CluesXiaoyu Xiong, Changyu Hu, Chunru Lin, Pingchuan Ma 0002, Chuang Gan, Tao Du 0001. [doi]
• Pareto Prompt OptimizationGuang Zhao, Byung-Jun Yoon, Gilchan Park, Shantenu Jha, Shinjae Yoo, Xiaoning Qian. [doi]
• Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision ModelsJiyang Zheng, Jialiang Shen, Yu Yao 0005, Min Wang, Yang Yang, Dadong Wang, Tongliang Liu. [doi]
• Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly DetectionGuojin Zhong, Pan Wang 0011, Jin Yuan 0002, Zhiyong Li 0001, Long Chen 0016. [doi]
• Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain AdaptationZhixiang Chi, Li Gu, Huan Liu 0014, Ziqiang Wang, Yanan Wu, Yang Wang 0003, Konstantinos N. Plataniotis. [doi]
• Towards General-Purpose Model-Free Reinforcement LearningScott Fujimoto, Pierluca D'Oro, Amy Zhang 0001, Yuandong Tian, Michael Rabbat. [doi]
• Accelerating Neural ODEs: A Variational Formulation-based ApproachHongjue Zhao, Yuchen Wang, Hairong Qi 0001, Zijie Huang 0002, Han Zhao 0002, Lui Sha, Huajie Shao. [doi]
• LoCoDL: Communication-Efficient Distributed Learning with Local Training and CompressionLaurent Condat, Arto Maranjyan, Peter Richtárik. [doi]
• Unlocking the Potential of Model Calibration in Federated LearningYun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher Brinton 0001. [doi]
• Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on GraphsYuzhou Chen, Yulia R. Gel. [doi]
• A Theory of Initialisation's Impact on SpecialisationDevon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M. Saxe, Stefano Sarao Mannelli. [doi]
• Exploring the Design Space of Visual Context Representation in Video MLLMsYifan Du 0002, Yuqi Huo, Kun Zhou 0002, Zijia Zhao, Haoyu Lu, Han Huang, Xin Zhao, Bingning Wang, Weipeng Chen, Ji-Rong Wen. [doi]
• Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target PropagationSatoki Ishikawa, Rio Yokota, Ryo Karakida. [doi]
• SMT: Fine-Tuning Large Language Models with Sparse MatricesHaoze He, Juncheng B. Li, Xuan Jiang, Heather Miller. [doi]
• Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a PosteriorTongda Xu, Xiyan Cai, Xinjie Zhang, Xingtong Ge, Dailan He, Ming Sun, Jingjing Liu, Ya-Qin Zhang, Jian Li, Yan Wang. [doi]
• Graph Neural Networks for Edge Signals: Orientation Equivariance and InvarianceDominik Fuchsgruber, Tim Postuvan, Stephan Günnemann, Simon Geisler. [doi]
• How to Evaluate Reward Models for RLHFEvan Frick, Tianle Li, Connor Chen, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Jiantao Jiao, Banghua Zhu, Joseph E. Gonzalez, Ion Stoica. [doi]
• An Intelligent Agentic System for Complex Image Restoration ProblemsKaiwen Zhu, Jinjin Gu, Zhiyuan You, Yu Qiao 0001, Chao Dong 0005. [doi]
• Beyond FVD: An Enhanced Evaluation Metrics for Video Generation Distribution QualityGe Ya Luo, Gian Mario Favero, Zhi Hao Luo, Alexia Jolicoeur-Martineau, Christopher Pal. [doi]
• Mitigating Memorization in Language ModelsMansi Sakarvadia, Aswathy Ajith, Arham Mushtaq Khan, Nathaniel C. Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian T. Foster, Michael W. Mahoney. [doi]
• SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random GeneratorsRasoul Shafipour, David Harrison, Maxwell Horton, Jeffrey Marker, Houman Bedayat, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi, Saman Naderiparizi. [doi]
• Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual InformationXinhao Zhong, Bin Chen 0011, Hao Fang 0011, Xulin Gu, Shu-Tao Xia, En-Hui Yang. [doi]
• What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative ModelsAhmed Imtiaz Humayun, Ibtihel Amara, Cristina Nader Vasconcelos, Deepak Ramachandran, Candice Schumann, Junfeng He, Katherine A. Heller, Golnoosh Farnadi, Negar Rostamzadeh, Mohammad Havaei. [doi]
• Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent LearningFan Yao, Yuwei Cheng, Ermin Wei, Haifeng Xu. [doi]
• Compositional Entailment Learning for Hyperbolic Vision-Language ModelsAvik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Fabio Galasso, Pascal Mettes. [doi]
• Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement LearningZijian Guo, Weichao Zhou, Shengao Wang, Wenchao Li 0001. [doi]
• ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion ModelsJianrong Lu, Zhiyu Zhu, Junhui Hou. [doi]
• CPSample: Classifier Protected Sampling for Guarding Training Data During DiffusionJoshua Kazdan, Hao Sun, Jiaqi Han, Felix Petersen, Frederick Vu, Stefano Ermon. [doi]
• Fully-inductive Node Classification on Arbitrary GraphsJianan Zhao 0002, Zhaocheng Zhu, Mikhail Galkin 0001, Hesham Mostafa, Michael M. Bronstein, Jian Tang 0005. [doi]
• Multi-objective Differentiable Neural Architecture SearchRhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley, Josif Grabocka, Frank Hutter. [doi]
• Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation LearningHanlin Yang, Jian Yao, Weiming Liu 0004, Qing Wang, Hanmin Qin, Hansheng Kong, Kirk Tang, Jiechao Xiong, Chao Yu, Kai Li 0022, Junliang Xing, Hongwu Chen, Juchao Zhuo, Qiang Fu 0016, Yang Wei, Haobo Fu. [doi]
• Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous InferenceMatthew Riemer, Gopeshh Subbaraj, Glen Berseth, Irina Rish. [doi]
• RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement LearningQianlan Yang, Yu-Xiong Wang. [doi]
• Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech SynthesisWeiwei Lin 0002, Chenhang He. [doi]
• Boltzmann priors for Implicit Transfer OperatorsJuan Viguera Diez, Mathias Jacob Schreiner, Ola Engkvist, Simon Olsson. [doi]
• Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie GroupsZakhar Shumaylov, Peter Zaika, James Rowbottom, Ferdia Sherry, Melanie Weber 0001, Carola-Bibiane Schönlieb. [doi]
• TEASER: Token Enhanced Spatial Modeling for Expressions ReconstructionYunfei Liu, Lei Zhu, Lijian Lin, Ye Zhu, Ailing Zhang, Yu Li. [doi]
• Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral ActivityDaiyao Yi, Hao Dong, Michael James Higley, Anne Churchland, Shreya Saxena. [doi]
• Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text DetectionGuangsheng Bao, Yanbin Zhao, Juncai He, Yue Zhang. [doi]
• Deep Weight Factorization: Sparse Learning Through the Lens of Artificial SymmetriesChris Kolb, Tobias Weber, Bernd Bischl, David Rügamer. [doi]
• Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature FinetuningYang You 0004, Yixin Li, Congyue Deng, Yue Wang 0036, Leonidas J. Guibas. [doi]
• Learning Interleaved Image-Text Comprehension in Vision-Language Large ModelsChenyu Zhou, Mengdan Zhang, Peixian Chen, Chaoyou Fu, Yunhang Shen, Xiawu Zheng, Xing Sun, Rongrong Ji. [doi]
• Last-Iterate Convergence Properties of Regret-Matching Algorithms in GamesYang Cai 0001, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-wei Lee, Haipeng Luo, Weiqiang Zheng. [doi]
• As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback LossXin Mao, Huimin Xu, Feng-Lin Li, Ziqi Jin, Wang Chen, Wei Zhang 0218, Anh Tuan Luu. [doi]
• Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts ModelsKeisuke Kamahori, Tian Tang, Yile Gu, Kan Zhu, Baris Kasikci. [doi]
• Dimension Agnostic Neural ProcessesHyungi Lee, Chaeyun Jang, Dongbok Lee, Juho Lee 0001. [doi]
• DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsGuangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han 0003. [doi]
• SVG: 3D Stereoscopic Video Generation via Denoising Frame MatrixPeng Dai 0003, Feitong Tan, Qiangeng Xu, David Futschik, Ruofei Du, Sean Fanello, Xiaojuan Qi 0001, Yinda Zhang 0001. [doi]
• Selective Aggregation for Low-Rank Adaptation in Federated LearningPengxin Guo, Shuang Zeng, Yanran Wang, Huijie Fan, Feifei Wang, Liangqiong Qu. [doi]
• Better than Your Teacher: LLM Agents that learn from Privileged AI FeedbackSanjiban Choudhury, Paloma Sodhi. [doi]
• SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM TrainingTianjin Huang, Ziquan Zhu, Gaojie Jin, Lu Liu, Zhangyang Wang, Shiwei Liu 0003. [doi]
• GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPSSaman Kazemkhani, Aarav Pandya, Daphne Cornelisse, Brennan Shacklett, Eugene Vinitsky. [doi]
• Discovering Group Structures via Unitary Representation LearningDongsung Huh. [doi]
• Zero-shot Imputation with Foundation Inference Models for Dynamical SystemsPatrick Seifner, Kostadin Cvejoski, Antonia Körner, Ramsés J. Sánchez. [doi]
• Neural Functions for Learning Periodic SignalWoojin Cho, Minju Jo, Kookjin Lee, Noseong Park. [doi]
• Ensembling Diffusion Models via Adaptive Feature AggregationCong Wang 0034, Kuan Tian, Yonghang Guan, Fei Shen, Zhiwei Jiang, Qing Gu 0001, Jun Zhang. [doi]
• Towards Optimal Multi-draft Speculative DecodingZhengmian Hu, Tong Zheng, Vignesh Viswanathan, Ziyi Chen 0002, Ryan A. Rossi, Yihan Wu, Dinesh Manocha, Heng Huang. [doi]
• Do Mice Grok? Glimpses of Hidden Progress in Sensory CortexTanishq Kumar, Blake Bordelon, Cengiz Pehlevan, Venkatesh N. Murthy, Samuel J. Gershman. [doi]
• Test of Time: A Benchmark for Evaluating LLMs on Temporal ReasoningBahare Fatemi, Mehran Kazemi, Anton Tsitsulin, Karishma Malkan, Jinyeong Yim, John Palowitch, Sungyong Seo, Jonathan Halcrow, Bryan Perozzi. [doi]
• Integral Performance Approximation for Continuous-Time Reinforcement Learning ControlBrent A. Wallace, Jennie Si. [doi]
• Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image GenerationAbdelrahman Eldesokey, Peter Wonka. [doi]
• ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift RegularizationThe Viet Bui, Thanh Hong Nguyen, Tien Anh Mai. [doi]
• To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier TransformationWanlin Zhang, WeiChen Lin, Ruomin Huang, Shihong Song, Hu Ding. [doi]
• SFESS: Score Function Estimators for k-Subset SamplingKlas Wijk, Ricardo Vinuesa, Hossein Azizpour. [doi]
• Adversarial Generative Flow Network for Solving Vehicle Routing ProblemsNi Zhang, Jingfeng Yang, Zhiguang Cao, Xu Chi. [doi]
• Zero-shot forecasting of chaotic systemsYuanzhao Zhang, William Gilpin. [doi]
• TRENDy: Temporal Regression of Effective Nonlinear DynamicsMatthew Ricci, Guy Pelc, Zoe Piran, Noa Moriel, Mor Nitzan. [doi]
• Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGBowen Jin, Jinsung Yoon, Jiawei Han 0001, Sercan Ö. Arik. [doi]
• Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical NeedsBowen Gao, Haichuan Tan, Yanwen Huang, Minsi Ren, Xiao Huang, Wei-Ying Ma, Ya-Qin Zhang, Yanyan Lan. [doi]
• BP-Modified Local Loss for Efficient Training of Deep Neural NetworksLianhai Ren, Qianxiao Li. [doi]
• LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal ModelsJunyan Ye, Baichuan Zhou, Zilong Huang, Junan Zhang, Tianyi Bai, Hengrui Kang, Jun He, Honglin Lin, Zihao Wang, Tong Wu, Zhizheng Wu 0001, Yiping Chen, Dahua Lin, Conghui He, Weijia Li. [doi]
• Neural Exploratory Landscape Analysis for Meta-Black-Box-OptimizationZeyuan Ma, Jiacheng Chen, Hongshu Guo, Yue-jiao Gong. [doi]
• UniDrive: Towards Universal Driving Perception Across Camera ConfigurationsYe Li, Wenzhao Zheng, Xiaonan Huang, Kurt Keutzer. [doi]
• Efficient Alternating Minimization with Applications to Weighted Low Rank ApproximationZhao Song 0002, Mingquan Ye, Junze Yin, Lichen Zhang 0003. [doi]
• RAPID: Retrieval Augmented Training of Differentially Private Diffusion ModelsTanqiu Jiang, Changjiang Li, Fenglong Ma, Ting Wang. [doi]
• HELM: Hierarchical Encoding for mRNA Language ModelingMehdi Yazdani-Jahromi, Mangal Prakash, Tommaso Mansi, Artem Moskalev, Rui Liao. [doi]
• FACTS: A Factored State-Space Framework for World ModellingNanbo Li, Firas Laakom, Yucheng Xu, Wenyi Wang, Jürgen Schmidhuber. [doi]
• FlashMask: Efficient and Rich Mask Extension of FlashAttentionGuoxia Wang, Jinle Zeng, Xiyuan Xiao, Siming Wu, Jiabin Yang, Lujing Zheng, Zeyu Chen, Jiang Bian, Dianhai Yu, Haifeng Wang. [doi]
• Hadamrnn: Binary and Sparse Ternary orthogonal RNNsArmand Foucault, François Malgouyres, Franck Mamalet. [doi]
• Self-Improvement in Language Models: The Sharpening MechanismAudrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy. [doi]
• SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-trainingNie Lin, Takehiko Ohkawa, Yifei Huang 0002, Mingfang Zhang 0002, Minjie Cai, Ming Li, Ryosuke Furuta, Yoichi Sato. [doi]
• A Graph Enhanced Symbolic Discovery Framework For Efficient Logic OptimizationYinqi Bai, Jie Wang 0005, Lei Chen 0031, Zhihai Wang, Yufei Kuang, Mingxuan Yuan, Jianye Hao, Feng Wu 0001. [doi]
• Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement LearningWesley A. Suttle, Aamodh Suresh, Carlos Nieto-Granda. [doi]
• Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap FunctionsWei Yao, Haian Yin, Shangzhi Zeng, Jin Zhang. [doi]
• Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced ReasoningMd Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier, Yann LeCun, Irina Rish, Ravid Shwartz-Ziv, Christopher Pal. [doi]
• Adaptive Retention & Correction: Test-Time Training for Continual LearningHaoran Chen, Micah Goldblum, Zuxuan Wu, Yu-Gang Jiang 0001. [doi]
• T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance DesignJiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao 0002, Robinson Piramuthu, Wenhu Chen, William Yang Wang. [doi]
• Optimal Brain ApoptosisMingyuan Sun, Zheng Fang 0001, Jiaxu Wang, Junjie Jiang, Delei Kong, Chenming Hu, Yuetong Fang, Renjing Xu. [doi]
• Standardizing Structural Causal ModelsWeronika Ormaniec, Scott Sussex, Lars Lorch, Bernhard Schölkopf, Andreas Krause 0001. [doi]
• To Code or Not To Code? Exploring Impact of Code in Pre-trainingViraat Aryabumi, Yixuan Su, Raymond Ma, Adrien Morisot, Ivan Zhang, Acyr Locatelli, Marzieh Fadaee, Ahmet Üstün, Sara Hooker. [doi]
• AgentRefine: Enhancing Agent Generalization through Refinement TuningDayuan Fu, Keqing He 0001, Yejie Wang, Wentao Hong, Zhuoma Gongque, Weihao Zeng, Wei Wang, Jingang Wang, Xunliang Cai, Weiran Xu. [doi]
• TorchTitan: One-stop PyTorch native solution for production ready LLM pretrainingWanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-Chin Huang, Iris Zhang, Wei Feng, Howard Huang, Junjie Wang, Sanket Purandare, Gokul Nadathur, Stratos Idreos. [doi]
• Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNsSteve Azzolin, Antonio Longa, Stefano Teso, Andrea Passerini. [doi]
• MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout GuidanceXierui Wang, Siming FU, Qihan Huang, Wanggui He, Hao Jiang. [doi]
• Safety Representations for Safer Policy LearningKaustubh Mani, Vincent Mai, Charlie Gauthier, Annie S. Chen, Samer B. Nashed, Liam Paull. [doi]
• A Transfer Attack to Image WatermarksYuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Zhenqiang Gong. [doi]
• ELBOing Stein: Variational Bayes with Stein Mixture InferenceOla Rønning, Eric T. Nalisnick, Christophe Ley, Padhraic Smyth, Thomas Hamelryck. [doi]
• mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language ModelsJiabo Ye, Haiyang Xu 0001, Haowei Liu, Anwen Hu, Ming Yan 0008, Qi Qian 0001, Ji Zhang 0011, Fei Huang 0002, Jingren Zhou 0001. [doi]
• Diffusion Bridge AutoEncoders for Unsupervised Representation LearningYeongmin Kim, Kwanghyeon Lee, Minsang Park, Byeonghu Na, Il-Chul Moon. [doi]
• Linear Mode Connectivity in Differentiable Tree EnsemblesRyuichi Kanoh, Mahito Sugiyama. [doi]
• Provably Robust Explainable Graph Neural Networks against Graph Perturbation AttacksJiate Li, Meng Pang, Yun Dong, Jinyuan Jia 0001, Binghui Wang. [doi]
• ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud RestorationYoungseok Kim 0002, Sunwook Hwang, Hyung-Sin Kim, Saewoong Bahk. [doi]
• Efficient Automated Circuit Discovery in Transformers using Contextual DecompositionAliyah R. Hsu, Georgia Zhou, Yeshwanth Cherapanamjeri, Yaxuan Huang, Anobel Y. Odisho, Peter R. Carroll, Bin Yu 0001. [doi]
• Training Language Models on Synthetic Edit Sequences Improves Code SynthesisUlyana Piterbarg, Lerrel Pinto, Rob Fergus. [doi]
• Zero-Shot Natural Language ExplanationsFawaz Sammani, Nikos Deligiannis. [doi]
• Cauchy-Schwarz RegularizersSueda Taner, Ziyi Wang, Christoph Studer. [doi]
• On the Price of Differential Privacy for Hierarchical ClusteringChengyuan Deng, Jie Gao 0001, Jalaj Upadhyay, Chen Wang 0027, Samson Zhou. [doi]
• GANDALF: Generative AttentioN based Data Augmentation and predictive modeLing Framework for personalized cancer treatmentAishwarya Jayagopal, Yanrong Zhang, Robert John Walsh, Tuan Zea Tan, Anand D. Jeyasekharan, Vaibhav Rajan. [doi]
• Autoregressive Video Generation without Vector QuantizationHaoge Deng, Ting Pan, Haiwen Diao, Zhengxiong Luo, Yufeng Cui, Huchuan Lu, Shiguang Shan, Yonggang Qi, Xinlong Wang. [doi]
• TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language ModelsMakoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba. [doi]
• Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMsJie Zhang 0071, Zhongqi Wang, Mengqi Lei, Zheng Yuan 0005, Bei Yan, Shiguang Shan, Xilin Chen 0001. [doi]
• Inverse Constitutional AI: Compressing Preferences into PrinciplesArduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Samuel Albanie, Robert D. Mullins. [doi]
• Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from ObservationAnish Abhijit Diwan, Julen Urain, Jens Kober, Jan Peters 0001. [doi]
• VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in MeteorologyYi Xiao, Qilong Jia, Kun Chen, Lei Bai 0001, Wei Xue. [doi]
• What's New in My Data? Novelty Exploration via Contrastive GenerationMasaru Isonuma, Ivan Titov. [doi]
• Self-supervised contrastive learning performs non-linear system identificationRodrigo González Laiz, Tobias Schmidt, Steffen Schneider 0001. [doi]
• Curriculum-aware Training for Discriminating Molecular Property Prediction ModelsHansi Yang, Quanming Yao, James Kwok. [doi]
• Revisiting a Design Choice in Gradient Temporal Difference LearningXiaochi Qian, Shangtong Zhang. [doi]
• Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level AlignmentPritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan Ö. Arik, Tomas Pfister. [doi]
• Robust Transfer of Safety-Constrained Reinforcement Learning AgentsMarkel Zubia, Thiago D. Simão, Nils Jansen 0001. [doi]
• Wayward Concepts In Multimodal ModelsBrandon Trabucco, Max Gurinas, Kyle Doherty, Russ Salakhutdinov. [doi]
• Learning How Hard to Think: Input-Adaptive Allocation of LM ComputationMehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas. [doi]
• SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference AccelerationJintao Zhang, Jia Wei, Pengle Zhang, Jun Zhu, Jianfei Chen. [doi]
• FedTMOS: Efficient One-Shot Federated Learning with Tsetlin MachineShannon How Shi Qi, Jagmohan Chauhan, Geoff V. Merrett, Jonathon S. Hare. [doi]
• Strategic Classification With ExternalitiesSafwan Hossain, Evi Micha, Yiling Chen 0001, Ariel D. Procaccia. [doi]
• Spurious Forgetting in Continual Learning of Language ModelsJunhao Zheng, Xidi Cai, Shengjie Qiu, Qianli Ma 0001. [doi]
• Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent DebateYexiang Liu, Jie Cao 0002, Zekun Li, Ran He 0001, Tieniu Tan. [doi]
• Identification of Intermittent Temporal Latent ProcessYuke Li, Yujia Zheng 0001, Guangyi Chen 0002, Kun Zhang 0001, Heng Huang. [doi]
• Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsHossein Mirzaei, Mackenzie W. Mathis. [doi]
• On the Crucial Role of Initialization for Matrix FactorizationBingcong Li, Liang Zhang, Aryan Mokhtari, Niao He. [doi]
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic PoliciesRuijie Zheng, Yongyuan Liang, Shuaiyi Huang, Jianfeng Gao 0001, Hal Daumé III, Andrey Kolobov, Furong Huang, Jianwei Yang. [doi]
• Revealing the 3D Cosmic Web through Gravitationally Constrained Neural FieldsBrandon Zhao, Aviad Levis, Liam Connor, Pratul P. Srinivasan, Katherine L. Bouman. [doi]
• Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose EstimationHuan Ren, Wenfei Yang, Xiang Liu, Shifeng Zhang, Tianzhu Zhang. [doi]
• How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for DistributionsTal Herman, Guy N. Rothblum. [doi]
• Bayesian Analysis of Combinatorial Gaussian Process BanditsJack Sandberg, Niklas Åkerblom, Morteza Haghir Chehreghani. [doi]
• POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy DecompositionYuta Saito, Jihan Yao, Thorsten Joachims. [doi]
• The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMsHong Li, Nanxi Li, Yuanjie Chen, Jianbin Zhu, Qinlu Guo, Cewu Lu, Yong-Lu Li 0001. [doi]
• WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the WildBill Yuchen Lin, Yuntian Deng, Khyathi Raghavi Chandu, Abhilasha Ravichander, Valentina Pyatkin, Nouha Dziri, Ronan Le Bras 0001, Yejin Choi 0001. [doi]
• Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?Yuheng Li, Panpan Wang, Haipeng Chen. [doi]
• xFinder: Large Language Models as Automated Evaluators for Reliable EvaluationQingchen Yu, Zifan Zheng, Shichao Song, Zhiyu Li, Feiyu Xiong, Bo Tang, Ding Chen. [doi]
• Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsZijia Zhao, Haoyu Lu, Yuqi Huo, Yifan Du 0002, Tongtian Yue, Longteng Guo, Bingning Wang, Weipeng Chen, Jing Liu 0001. [doi]
• Self-Improving Robust Preference OptimizationEugene Choi, Arash Ahmadian, Matthieu Geist, Olivier Pietquin, Mohammad Gheshlaghi Azar. [doi]
• Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal TransportSiqi Zeng 0001, Sixian Du, Makoto Yamada, Han Zhao 0002. [doi]
• Efficient Jailbreak Attack sequences on Large Language Models via Multi-Armed Bandit-based Context switchingAditya Ramesh, Shivam Bhardwaj, Aditya Saibewar, Manohar Kaul. [doi]
• MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific HypothesesZonglin Yang 0001, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou. [doi]
• D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language ModelsZhongwei Wan, Xinjian Wu, Yu Zhang, Yi Xin, Chaofan Tao, Zhihong Zhu, Xin Wang, Siqi Luo, Jing Xiong, Longyue Wang, Mi Zhang 0002. [doi]
• OmniEdit: Building Image Editing Generalist Models Through Specialist SupervisionCong Wei, Zheyang Xiong, Weiming Ren, Xeron Du, Ge Zhang, Wenhu Chen. [doi]
• VideoShield: Regulating Diffusion-based Video Generation Models via WatermarkingRunyi Hu, Jie Zhang 0073, Yiming Li 0004, Jiwei Li 0001, Qing Guo 0005, Han Qiu 0001, Tianwei Zhang 0004. [doi]
• COPER: Correlation-based Permutations for Multi-View ClusteringRan Eisenberg, Jonathan Svirsky, Ofir Lindenbaum. [doi]
• Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image AnimationJiahao Cui 0003, Hui Li, Yao Yao, Hao Zhu, Hanlin Shang, Kaihui Cheng, Hang Zhou 0009, Siyu Zhu, Jingdong Wang 0001. [doi]
• DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat GenerationChenguo Lin, Panwang Pan, Bangbang Yang, Zeming Li, Yadong Mu. [doi]
• MorphoDiff: Cellular Morphology Painting with Diffusion ModelsZeinab Navidi, Jun Ma, Esteban Miglietta, Le Liu, Anne E. Carpenter, Beth A. Cimini, Benjamin Haibe-Kains, Bo Wang 0044. [doi]
• Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware OptimizationHao Dong, Eleni N. Chatzi, Olga Fink. [doi]
• Transformers Provably Solve Parity Efficiently with Chain of ThoughtJuno Kim, Taiji Suzuki. [doi]
• JudgeLM: Fine-tuned Large Language Models are Scalable JudgesLianghui Zhu, Xinggang Wang, Xinlong Wang. [doi]
• LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal ModelsFeng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, Chunyuan Li. [doi]
• Improving Neural Optimal Transport via Displacement InterpolationJaemoo Choi, Yongxin Chen, Jaewoong Choi. [doi]
• Generating Freeform Endoskeletal RobotsMuhan Li, Lingji Kong, Sam Kriegman. [doi]
• The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs RevisitedFloriano Tori, Vincent Holst, Vincent Ginis. [doi]
• Bundle Neural Network for message diffusion on graphsJacob Bamberger, Federico Barbero, Xiaowen Dong 0001, Michael M. Bronstein. [doi]
• Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial RecordingsDi Wu, Siyuan Li, Chen Feng, Lu Cao, Yue Zhang, Jie Yang, Mohamad Sawan. [doi]
• Durable Quantization Conditioned Misalignment Attack on Large Language ModelsPeiran Dong, Haowei Li, Song Guo 0001. [doi]
• Memory Efficient Transformer Adapter for Dense PredictionsDong Zhang, Rui Yan, Pingcheng Dong, Kwang-Ting Cheng. [doi]
• Mastering Task Arithmetic: τJp as a Key Indicator for Weight DisentanglementKotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryosuke Yamaki, Ryotaro Shimizu, Yuki Saito, Julian J. McAuley, Hiroki Naganuma. [doi]
• Misspecified Q-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation ErrorAlly Yalei Du, Lin Yang 0011, Ruosong Wang. [doi]
• How Feature Learning Can Improve Neural Scaling LawsBlake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan. [doi]
• Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement LearningYixian Zhang, Huaze Tang, Huijing Lin, Wenbo Ding 0001. [doi]
• Exploring Prosocial Irrationality for LLM Agents: A Social Cognition ViewXuan Liu 0001, Jie Zhang 0076, Haoyang Shang, Song Guo 0001, Chengxu Yang, Quanyan Zhu. [doi]
• SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head AvatarsJaeseong Lee, Taewoong Kang, Marcel C. Bühler, Min-Jung Kim 0001, Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo. [doi]
• Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool UsageZhi Gao, Bofei Zhang, Pengxiang Li 0002, Xiaojian Ma 0001, Tao Yuan, Yue Fan, Yuwei Wu 0001, Yunde Jia, Song Chun Zhu, Qing Li 0003. [doi]
• First-Person Fairness in ChatbotsTyna Eloundou, Alex Beutel, David G. Robinson, Keren Gu, Anna-Luisa Brakman, Pamela Mishkin, Meghan Shah, Johannes Heidecke, Lilian Weng, Adam Tauman Kalai. [doi]
• Edge Prompt Tuning for Graph Neural NetworksXingbo Fu, Yinhan He, Jundong Li. [doi]
• Proxy Denoising for Source-Free Domain AdaptationSong Tang 0001, Wenxin Su, Yan Gan, Mao Ye 0001, Jianwei Dr. Zhang, Xiatian Zhu. [doi]
• Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-PassingDiaaeldin Taha, James Chapman 0007, Marzieh Eidi, Karel Devriendt, Guido Montúfar. [doi]
• Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts ModelsKeisuke Kamahori, Tian Tang, Yile Gu, Kan Zhu, Baris Kasikci. [doi]
• Autoregressive Pretraining with Mamba in VisionSucheng Ren, Xianhang Li, Haoqin Tu, Feng Wang, Fangxun Shu, Lei Zhang, Jieru Mei, Linjie Yang, Peng Wang, Heng Wang, Alan L. Yuille, Cihang Xie. [doi]
• Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust OptimizationShuang Liu, Yihan Wang, Yifan Zhu, Yibo Miao, Xiao-Shan Gao. [doi]
• Nesterov acceleration in benignly non-convex landscapesKanan Gupta, Stephan Wojtowytsch. [doi]
• Learning local equivariant representations for quantum operatorsZhanghao Zhouyin, Zixi Gan, Shishir Kumar Pandey, Linfeng Zhang 0002, Qiangqiang Gu 0003. [doi]
• Watermark Anything With Localized MessagesTom Sander, Pierre Fernandez, Alain Oliviero Durmus, Teddy Furon, Matthijs Douze. [doi]
• Capturing the Temporal Dependence of Training Data InfluenceJiachen T. Wang, Dawn Song, James Zou 0001, Prateek Mittal, Ruoxi Jia 0001. [doi]
• Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can BalanceSiyu Sun, Han Lu, Jiangtong Li, Yichen Xie 0002, Tianjiao Li, Xiaokang Yang 0001, Liqing Zhang 0001, Junchi Yan. [doi]
• Counterfactual Concept Bottleneck ModelsGabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich. [doi]
• XAIguiFormer: explainable artificial intelligence guided transformer for brain disorder identificationHanning Guo, Farah Abdellatif, Yu Fu, N. Jon Shah, Abigail Morrison, Jürgen Dammers. [doi]
• Rethinking Shapley Value for Negative Interactions in Non-convex GamesWonjoon Chang, Myeongjin Lee, Jaesik Choi. [doi]
• REMEDY: Recipe Merging Dynamics in Large Vision-Language ModelsDidi Zhu, Yibing Song, Tao Shen 0002, Ziyu Zhao 0001, Jinluan Yang, Min Zhang 0005, Chao Wu 0001. [doi]
• Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward HackingParia Rashidinejad, Yuandong Tian. [doi]
• Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image SegmentationLaurin Lux, Alexander H. Berger, Alexander Weers, Nico Stucki, Daniel Rueckert, Ulrich Bauer, Johannes C. Paetzold. [doi]
• STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy LearningMarius Memmel, Jacob Berg, Bingqing Chen, Abhishek Gupta 0004, Jonathan Francis. [doi]
• Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?Seth Aycock, David Stap, Di Wu, Christof Monz, Khalil Sima'an. [doi]
• SoftCVI: Contrastive variational inference with self-generated soft labelsDaniel Ward, Mark Beaumont, Matteo Fasiolo. [doi]
• Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment LearningQinghao Ye, Xianhan Zeng, Fu Li, Chunyuan Li, Haoqi Fan 0001. [doi]
• CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMsJinLan Fu, huangfushenzhen, Hao Fei 0001, Xiaoyu Shen, Bryan Hooi, Xipeng Qiu, See-Kiong Ng. [doi]
• Learning and aligning single-neuron invariance manifolds in visual cortexMohammad Bashiri, Luca Baroni, Ján Antolík, Fabian H. Sinz. [doi]
• MeshMask: Physics-Based Simulations with Masked Graph Neural NetworksPaul Garnier, Vincent Lannelongue, Jonathan Viquerat, Elie Hachem. [doi]
• Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward ModelingGuiyu Zhang, Huan-ang Gao, Zijian Jiang, Hao Zhao 0002, Zhedong Zheng. [doi]
• PPT: Patch Order Do Matters In Time Series Pretext TaskJaeho Kim, Kwangryeol Park, Sukmin Yun, Seulki Lee. [doi]
• Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D ScenesJianqi Chen, Panwen Hu, Xiaojun Chang, Zhenwei Shi, Michael Kampffmeyer, Xiaodan Liang. [doi]
• Hidden in the Noise: Two-Stage Robust Watermarking for ImagesKasra Arabi, Benjamin Feuer, R. Teal Witter, Chinmay Hegde, Niv Cohen. [doi]
• Unsupervised Model Tree Heritage RecoveryEliahu Horwitz, Asaf Shul, Yedid Hoshen. [doi]
• What to align in multimodal contrastive learning?Benoit Dufumier, Javiera Castillo-Navarro, Devis Tuia, Jean-Philippe Thiran. [doi]
• Stabilizing Reinforcement Learning in Differentiable Multiphysics SimulationEliot Xing, Vernon Luk, Jean Oh. [doi]
• σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial ExamplesAntonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo. [doi]
• Scalable Decision-Making in Stochastic Environments through Learned Temporal AbstractionBaiting Luo, Ava Pettet, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay. [doi]
• Designing Concise ConvNets with Columnar StagesAshish Kumar 0006, Jaesik Park. [doi]
• IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image GenerationXinchen Zhang, Ling Yang 0006, Guohao Li 0001, Yaqi Cai, Jiake Xie, Yong Tang, Yujiu Yang, Mengdi Wang, Bin Cui 0001. [doi]
• MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video GenerationAkio Hayakawa, Masato Ishii, Takashi Shibuya 0001, Yuki Mitsufuji. [doi]
• Capability Localization: Capabilities Can be Localized rather than Individual KnowledgeXiusheng Huang, Jiaxiang Liu, Yequan Wang, Jun Zhao 0001, Kang Liu 0001. [doi]
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of EncodersMin Shi, Fuxiao Liu, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yilin Zhao, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, Bryan Catanzaro, Andrew Tao, Jan Kautz, Zhiding Yu, Guilin Liu. [doi]
• InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian SplattingChenxin Li, Hengyu Liu 0007, Zhiwen Fan, Wuyang Li, Yifan Liu 0010, Panwang Pan, Yixuan Yuan. [doi]
• Efficient Biological Data Acquisition through Inference Set DesignIhor Neporozhnii, Julien Roy, Emmanuel Bengio, Jason S. Hartford. [doi]
• Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMsFeilong Tang, Zile Huang, Chengzhi Liu, Qiang Sun, Harry Yang, Ser-Nam Lim. [doi]
• Learning to Search from Demonstration SequencesDixant Mittal, Liwei Kang, Wee Sun Lee. [doi]
• Rewarding Progress: Scaling Automated Process Verifiers for LLM ReasoningAmrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, Aviral Kumar. [doi]
• LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and CaptioningZhe Li, Weihao Yuan 0001, Yisheng He, Lingteng Qiu, Shenhao Zhu, Xiaodong Gu 0004, Weichao Shen, Yuan Dong, Zilong Dong, Laurence Tianruo Yang. [doi]
• A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline DemonstrationsSheng Xu, Bo Yue, Hongyuan Zha, Guiliang Liu. [doi]
• Quality Measures for Dynamic Graph Generative ModelsRyien Hosseini, Filippo Simini, Venkatram Vishwanath, Rebecca Willett, Henry Hoffmann. [doi]
• Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical DataXinran Liu, Yikun Bai, Rocio Diaz Martin, Kaiwen Shi, Ashkan Shahbazi, Bennett Allan Landman, Catie Chang, Soheil Kolouri. [doi]
• MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth PriorsQingming Liu, Yuan Liu 0025, Jiepeng Wang 0001, Xianqiang Lyu, Peng Wang 0099, Wenping Wang, Junhui Hou. [doi]
• Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic GraphsYuhan Chen 0007, Yihong Luo, Yifan Song, Pengwen Dai, Jing Tang 0004, Xiaochun Cao. [doi]
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous DrivingXiaosong Jia, Junqi You, Zhiyuan Zhang, Junchi Yan. [doi]
• Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and GenerationYikun Zhang, Geyan Ye, Chaohao Yuan, Bo Han 0003, Long-Kai Huang, Jianhua Yao 0001, Wei Liu 0005, Yu Rong 0001. [doi]
• Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMsSiyan Zhao, Mingyi Hong 0001, Yang Liu 0165, Devamanyu Hazarika, Kaixiang Lin. [doi]
• One Step Diffusion via Shortcut ModelsKevin Frans, Danijar Hafner, Sergey Levine, Pieter Abbeel. [doi]
• Standard Gaussian Process is All You Need for High-Dimensional Bayesian OptimizationZhitong Xu, Haitao Wang 0001, Jeff M. Phillips, Shandian Zhe. [doi]
• SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language ModelsHaotian Xia, Zhengbang Yang, Junbo Zou, Rhys Tracy, Yuqing Wang, Chi Lu, Christopher Lai, Yanjun He, Xun Shao, Zhuoqing Xie, Yuan-Fang Wang, Weining Shen, Hanjie Chen. [doi]
• Expected Sliced Transport PlansXinran Liu, Rocio Diaz Martin, Yikun Bai, Ashkan Shahbazi, Matthew Thorpe, Akram Aldroubi, Soheil Kolouri. [doi]
• Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy FilteringKlaus-Rudolf Kladny, Bernhard Schölkopf, Michael Muehlebach. [doi]
• UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language ModelsXin Xu, Jiaxin Zhang, Tianhao Chen, Zitong Chao, Jishan Hu, Can Yang. [doi]
• Online Reinforcement Learning in Non-Stationary Context-Driven EnvironmentsPouya Hamadanian, Arash Nasr-Esfahany, Malte Schwarzkopf, Siddhartha Sen, Mohammad Alizadeh. [doi]
• Concept-ROT: Poisoning Concepts in Large Language Models with Model EditingKeltin Grimes, Marco Christiani, David Shriver, Marissa Catherine Connor. [doi]
• Tracking objects that change in appearance with phase synchronySabine Muzellec, Drew Linsley, Alekh Karkada Ashok, Ennio Mingolla, Girik Malik, Rufin VanRullen, Thomas Serre. [doi]
• Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward RepresentationJingbo Sun, Songjun Tu, Qichao Zhang, Haoran Li 0010, Xin Liu 0039, Yaran Chen, Ke Chen, Dongbin Zhao. [doi]
• Rethinking Visual Counterfactual Explanations Through Region ConstraintBartlomiej Sobieski, Jakub Grzywaczewski, Bartlomiej Sadlej, Matthew Tivnan, Przemyslaw Biecek. [doi]
• Learning to Solve Differential Equation Constrained Optimization ProblemsVincenzo Di Vito Francesco, Mostafa Mohammadian, Kyri Baker, Ferdinando Fioretto. [doi]
• Positive-Unlabeled Diffusion Models for Preventing Sensitive Data GenerationHiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka, Tomoya Yamashita. [doi]
• Interaction Asymmetry: A General Principle for Learning Composable AbstractionsJack Brady, Julius von Kügelgen, Sébastien Lachapelle, Simon Buchholz, Thomas Kipf, Wieland Brendel. [doi]
• Large Language Models Meet Symbolic Provers for Logical Reasoning EvaluationChengwen Qi, Ren Ma, Bowen Li 0002, He Du, Binyuan Hui, Jinwang Wu, Yuanjun Laili, Conghui He. [doi]
• MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language ModelsJiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen 0001, Kang Liu 0001, Jun Zhao 0001. [doi]
• Human-Aligned Chess With a Bit of SearchYiming Zhang 0022, Athul Paul Jacob, Vivian Lai, Daniel Fried, Daphne Ippolito. [doi]
• PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model PatchesRana Muhammad Shahroz, Pingzhi Li, Sukwon Yun, Zhenyu Wang, Shahriar Nirjon, Chau-Wai Wong, Tianlong Chen. [doi]
• Beyond Interpretability: The Gains of Feature Monosemanticity on Model RobustnessQi Zhang, Yifei Wang 0001, Jingyi Cui, Xiang Pan, Qi Lei, Stefanie Jegelka, Yisen Wang 0001. [doi]
• The Pitfalls of Memorization: When Memorization Hurts GeneralizationReza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent. [doi]
• The Foundations of Tokenization: Statistical and Computational ConcernsJuan Luis Gastaldi, John Terilla, Luca Malagutti, Brian DuSell, Tim Vieira, Ryan Cotterell. [doi]
• Chunk-Distilled Language ModelingYanhong Li, Karen Livescu, Jiawei Zhou. [doi]
• Small Models are LLM Knowledge Triggers for Medical Tabular PredictionJiahuan Yan, Jintai Chen, Chaowen Hu, Bo Zheng 0011, Yaojun Hu, Jimeng Sun 0001, Jian Wu 0001. [doi]
• Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet MiningWonhyeok Choi, Kyumin Hwang, Wei Peng, Minwoo Choi, Sunghoon Im. [doi]
• Differential learning kinetics govern the transition from memorization to generalization during in-context learningAlex Nguyen, Gautam Reddy. [doi]
• Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement LearningLinjiajie Fang, Ruoxue Liu, Jing Zhang, Wenjia Wang, Bingyi Jing. [doi]
• Surprising Effectiveness of pretraining Ternary Language Model at ScaleAyush Kaushal, Tejas Vaidhya, Arnab Kumar Mondal, Tejas Pandey, Aaryan Bhagat, Irina Rish. [doi]
• ImProver: Agent-Based Automated Proof OptimizationRiyaz Ahuja, Jeremy Avigad, Prasad Tetali, Sean Welleck. [doi]
• On the Importance of Language-driven Representation Learning for Heterogeneous Federated LearningYunlu Yan, Chun-Mei Feng 0001, Wangmeng Zuo, Salman H. Khan 0001, Yong Liu 0026, Lei Zhu 0003. [doi]
• SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model CompressionXin Wang 0120, Yu Zheng 0022, Zhongwei Wan, Mi Zhang 0002. [doi]
• MADGEN: Mass-Spec attends to De Novo Molecular generationYinkai Wang, Xiaohui Chen, Liping Liu, Soha Hassoun. [doi]
• QA-Calibration of Language Model Confidence ScoresPutra Manggala, Atalanti-Anastasia Mastakouri, Elke Kirschbaum, Shiva Prasad Kasiviswanathan, Aaditya Ramdas. [doi]
• Real2Code: Reconstruct Articulated Objects via Code GenerationZhao Mandi, Yijia Weng, Dominik Bauer, Shuran Song. [doi]
• InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemmaXiaoxuan Hou, Jiayi Yuan 0002, Joel Z. Leibo, Natasha Jaques. [doi]
• Do LLM Agents Have Regret? A Case Study in Online Learning and GamesChanwoo Park, Xiangyu Liu, Asuman E. Ozdaglar, Kaiqing Zhang. [doi]
• Permute-and-Flip: An optimally stable and watermarkable decoder for LLMsXuandong Zhao, Lei Li 0005, Yu-Xiang Wang 0003. [doi]
• JetFormer: An autoregressive generative model of raw images and textMichael Tschannen, André Susano Pinto, Alexander Kolesnikov 0003. [doi]
• UniRestore3D: A Scalable Framework For General Shape RestorationYuang Wang, Yujian Zhang, Sida Peng, Xingyi He, Haoyu Guo, Yujun Shen, Hujun Bao, Xiaowei Zhou 0001. [doi]
• GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in GraphsDongzhuoran Zhou, Evgeny Kharlamov, Egor V. Kostylev. [doi]
• KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural NetworksTaoran Fang, Tianhong Gao, Chunping Wang 0001, Yihao Shang, Wei Chow, Lei Chen, Yang Yang 0009. [doi]
• Grounding Continuous Representations in Geometry: Equivariant Neural FieldsDavid R. Wessels, David M. Knigge, Riccardo Valperga, Samuele Papa, Sharvaree P. Vadgama, Efstratios Gavves, Erik J. Bekkers. [doi]
• NetMoE: Accelerating MoE Training through Dynamic Sample PlacementXinyi Liu, Yujie Wang, Fangcheng Fu, Xupeng Miao, Shenhan Zhu, Xiaonan Nie, Bin Cui 0001. [doi]
• Safety Alignment Should be Made More Than Just a Few Tokens DeepXiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma 0010, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson 0002. [doi]
• EqNIO: Subequivariant Neural Inertial OdometryRoyina Karegoudra Jayanth, Yinshuang Xu, Ziyun Wang 0001, Evangelos Chatzipantazis, Kostas Daniilidis, Daniel Gehrig. [doi]
• Multi-Label Node Classification with Label Influence PropagationYifei Sun 0002, Zemin Liu, Bryan Hooi, Yang Yang 0009, Rizal Fathony, Jia Chen, Bingsheng He. [doi]
• DEPfold: RNA Secondary Structure Prediction as Dependency ParsingKe Wang, Shay B. Cohen. [doi]
• Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box modelsThéo Bourdais, Houman Owhadi. [doi]
• Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and SearchYang Li, Jiale Ma, Wenzheng Pan, Runzhong Wang, Haoyu Geng, Nianzu Yang, Junchi Yan. [doi]
• CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric AwarenessKhyathi Raghavi Chandu, Linjie Li, Anas Awadalla, Ximing Lu, Jae Sung Park, Jack Hessel, Lijuan Wang, Yejin Choi 0001. [doi]
• OptionZero: Planning with Learned OptionsPo-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu. [doi]
• Affine Steerable Equivariant Layer for Canonicalization of Neural NetworksYikang Li, Yeqing Qiu, Yuxuan Chen, Zhouchen Lin. [doi]
• Selective induction Heads: How Transformers Select Causal Structures in ContextFrancesco D'Angelo, Francesco Croce, Nicolas Flammarion. [doi]
• LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph GenerationMufei Li, Viraj Shitole, Eli Chien, Changhai Man, Zhaodong Wang, Srinivas, Ying Zhang, Tushar Krishna, Pan Li 0005. [doi]
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank StructuresYiming Chen, Yuan Zhang, Liyuan Cao, Kun Yuan, Zaiwen Wen. [doi]
• MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual KnowledgeYuntao Du 0001, Kailin Jiang, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li 0003. [doi]
• Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve RenderingYibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu, Rui Ma 0011. [doi]
• Self-Supervised Diffusion Models for Electron-Aware Molecular Representation LearningGyoung S. Na, Chanyoung Park 0001. [doi]
• Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive LearningWei Wu, Can Liao, Zizhen Deng, Zhengrui Guo, Jinzhuo Wang. [doi]
• Unlearning-based Neural InterpretationsChing Lam Choi, Alexandre Duplessis, Serge J. Belongie. [doi]
• Revisiting Random Walks for Learning on GraphsJinwoo Kim, Olga Zaghen, Ayhan Suleymanzade, Youngmin Ryou, Seunghoon Hong. [doi]
• LASeR: Towards Diversified and Generalizable Robot Design with Large Language ModelsJunru Song, Yang Yang, Huan Xiao, Wei Peng, Wen Yao, Feifei Wang. [doi]
• DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image GenerationJing He, Haodong Li, huyongzhe, Guibao Shen, Yingjie Cai, Weichao Qiu, Ying-Cong Chen. [doi]
• Language-Image Models with 3D UnderstandingJang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang 0036, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krähenbühl, Yan Wang 0051, Marco Pavone 0001. [doi]
• Formation of Representations in Neural NetworksLiu Ziyin 0001, Isaac L. Chuang, Tomer Galanti, Tomaso A. Poggio. [doi]
• Benchmarking LLMs' Judgments with No Gold StandardShengwei Xu, Yuxuan Lu 0001, Grant Schoenebeck, Yuqing Kong. [doi]
• Not All Language Model Features Are One-Dimensionally LinearJoshua Engels, Eric J. Michaud, Isaac Liao, Wes Gurnee, Max Tegmark. [doi]
• Efficient Evolutionary Search Over Chemical Space with Large Language ModelsHaorui Wang, Marta Skreta, Cher Tian Ser, Wenhao Gao 0001, Lingkai Kong, Felix Strieth-Kalthoff, Chenru Duan, Yuchen Zhuang, Yue Yu, Yanqiao Zhu 0001, Yuanqi Du, Alán Aspuru-Guzik, Kirill Neklyudov, Chao Zhang 0014. [doi]
• Text4Seg: Reimagining Image Segmentation as Text GenerationMengcheng Lan, Chaofeng Chen, Yue Zhou 0005, Jiaxing Xu, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang 0001. [doi]
• ADMM for Structured Fractional MinimizationGanzhao Yuan. [doi]
• Is In-Context Learning Sufficient for Instruction Following in LLMs?Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion. [doi]
• Locality Sensitive Avatars From VideoChunjin Song, Zhijie Wu, Shih-Yang Su, Bastian Wandt, Leonid Sigal, Helge Rhodin. [doi]
• RMP-SAM: Towards Real-Time Multi-Purpose Segment AnythingShilin Xu, Haobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen 0026, Yunhai Tong, Bernard Ghanem, Xiangtai Li, Ming-Hsuan Yang 0001. [doi]
• Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical PerformanceDimitris Oikonomou, Nicolas Loizou. [doi]
• Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention GateByung-Hyun Lee, Sungjin Lim, Seunggyu Lee, Dong Un Kang, Se Young Chun. [doi]
• Toward Generalizing Visual Brain Decoding to Unseen SubjectsXiangtao Kong, Kexin Huang, Ping Li, Lei Zhang 0006. [doi]
• PaPaGei: Open Foundation Models for Optical Physiological SignalsArvind Pillai, Dimitris Spathis, Fahim Kawsar, Mohammad Malekzadeh. [doi]
• Benign Overfitting in Out-of-Distribution Generalization of Linear ModelsShange Tang, Jiayun Wu, Jianqing Fan, Chi Jin 0001. [doi]
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative IntelligenceWeize Chen, Ziming You, Ran Li, Yitong Guan, Chen Qian, Chenyang Zhao, Cheng Yang 0002, Ruobing Xie, Zhiyuan Liu, Maosong Sun 0001. [doi]
• DeciMamba: Exploring the Length Extrapolation Potential of MambaAssaf Ben-Kish, Itamar Zimerman, Shady Abu Hussein, Nadav Cohen 0001, Amir Globerson, Lior Wolf, Raja Giryes. [doi]
• From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQZhaojing Wen, Qiulin Zhang, Yuan Zhang, Rudan Chen, Xichao Yang, Di Xie, Jiang Zhu. [doi]
• Law of the Weakest Link: Cross Capabilities of Large Language ModelsMing Zhong 0005, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong, Chenguang Zhu 0001, Zhengxing Chen, Liang Tan, Chloe Bi, Mike Lewis, Sravya Popuri, Sharan Narang, Melanie Kambadur, Dhruv Mahajan 0001, Sergey Edunov, Jiawei Han 0001, Laurens van der Maaten. [doi]
• Realistic Evaluation of Deep Partial-Label Learning AlgorithmsWei Wang 0373, Dong-Dong Wu, Jindong Wang 0001, Gang Niu 0001, Min-Ling Zhang, Masashi Sugiyama. [doi]
• From Lazy to Rich: Exact Learning Dynamics in Deep Linear NetworksClémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra M. Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M. Saxe. [doi]
• Accelerating Task Generalisation with Multi-Level Skill HierarchiesThomas P. Cannon, Özgür Simsek. [doi]
• SymmCD: Symmetry-Preserving Crystal Generation with Diffusion ModelsDaniel Levy, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Qiang Zhu, Kin Long Kelvin Lee, Mikhail Galkin 0001, Santiago Miret, Siamak Ravanbakhsh. [doi]
• No Preference Left Behind: Group Distributional Preference OptimizationBinwei Yao, Zefan Cai, Yun-Shiuan Chuang, Shanglin Yang, Ming Jiang 0018, Diyi Yang, Junjie Hu. [doi]
• Transformers Struggle to Learn to SearchAbulhair Saparov, Srushti Ajay Pawar, Shreyas Pimpalgaonkar, Nitish Joshi, Richard Yuanzhe Pang, Vishakh Padmakumar, Mehran Kazemi, Najoung Kim, He He 0001. [doi]
• SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal CoordinationShuo Ma 0001, Yingwei Zhang 0002, Yiqiang Chen 0001, Hualei Wang, Yuan Jin, Wei Zhang, Ziyu Jia. [doi]
• EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical AlignmentYifei Xing 0001, Xiangyuan Lan, Ruiping Wang 0001, Dongmei Jiang, Wenjun Huang, Qingfang Zheng, Yaowei Wang 0001. [doi]
• McEval: Massively Multilingual Code EvaluationLinzheng Chai, Shukai Liu, Jian Yang 0030, Yuwei Yin, Ke Jin, Jiaheng Liu, Tao Sun, Ge Zhang 0009, Changyu Ren, Hongcheng Guo, Noah Wang, Boyang Wang, Xianjie Wu, Bing Wang, Tongliang Li, Liqun Yang, Sufeng Duan, Zhaoxiang Zhang 0001, Zhoujun Li 0001. [doi]
• On the Identification of Temporal Causal Representation with Instantaneous DependenceZijian Li 0001, Yifan Shen, Kaitao Zheng, Ruichu Cai, Xiangchen Song, Mingming Gong, Guangyi Chen 0002, Kun Zhang 0001. [doi]
• Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation LearningYichi Zhang 0009, Zhuo Chen 0007, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang 0015, Huajun Chen. [doi]
• Attributing Culture-Conditioned Generations to Pretraining CorporaHuihan Li 0001, Arnav Goel, Keyu He, Xiang Ren 0001. [doi]
• SWEb: A Large Web Dataset for the Scandinavian LanguagesTobias Norlund, Tim Isbister, Amaru Cuba Gyllensten, Paul Gabriel dos Santos, Danila Petrelli, Ariel Ekgren, Magnus Sahlgren. [doi]
• REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph RewiringTaewon Kim, Hyunjin Seo, Sungsoo Ahn, Eunho Yang. [doi]
• Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost SubsidyIshank Juneja, Carlee Joe-Wong, Osman Yagan. [doi]
• Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean DataJingyang Ou, Shen Nie, Kaiwen Xue, Fengqi Zhu, Jiacheng Sun, Zhenguo Li, Chongxuan Li. [doi]
• Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search MethodsAkira Ito 0002, Masanori Yamada, Atsutoshi Kumagai. [doi]
• DUALFormer: Dual Graph TransformerJiaming Zhuo, Yuwei Liu, Yintong Lu, Ziyi Ma, Kun Fu, Chuan Wang 0002, Yuanfang Guo, Zhen Wang 0004, Xiaochun Cao, Liang Yang 0002. [doi]
• A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationLiang Chen 0024, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu 0001, Baobao Chang. [doi]
• AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention DisruptionJoonsung Jeon, Woo-Jae Kim, Suhyeon Ha, Sooel Son, Sung-Eui Yoon. [doi]
• Aligning Human Motion Generation with Human PerceptionsHaoru Wang, Wentao Zhu 0004, Luyi Miao, Yishu Xu, Feng Gao 0014, Qi Tian 0001, Yizhou Wang 0001. [doi]
• Learning 3D Perception from Others' PredictionsJinsu Yoo, Zhenyang Feng, Tai-Yu Pan, Yihong Sun, Cheng Perng Phoo, Xiangyu Chen, Mark E. Campbell, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao. [doi]
• Walk the Talk? Measuring the Faithfulness of Large Language Model ExplanationsKatie Matton, Robert Ness, John V. Guttag, Emre Kiciman. [doi]
• Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language ModelsHanzhu Chen, Xu Shen 0001, Jie Wang 0005, Zehao Wang, Qitan Lv, Junjie He, Rong Wu, Feng Wu, Jieping Ye. [doi]
• RocketEval: Efficient automated LLM evaluation via grading checklistTianjun Wei, Wei Wen, Ruizhi Qiao, Xing Sun 0001, Jianghong Ma. [doi]
• Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-TuningTianci Liu 0003, Ruirui Li 0002, Yunzhe Qi, Hui Liu 0031, Xianfeng Tang, Tianqi Zheng, Qingyu Yin, Monica Xiao Cheng, Jun Huan, Haoyu Wang 0004, Jing Gao 0004. [doi]
• Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing RobustnessXianglu Wang, Hu Ding. [doi]
• In Search of Forgotten Domain GeneralizationPrasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel. [doi]
• Integrative Decoding: Improving Factuality via Implicit Self-consistencyYi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao, Song Wang, Yuji Zhang 0002, Wenjun Hou, Kaishuai Xu, Wenge Liu, Wenjie Li 0002, Jian Jiao 0007, Qi Chen 0009, Peng Cheng 0005, Wayne Xiong. [doi]
• Do Large Language Models Truly Understand Geometric Structures?Xiaofeng Wang, Yiming Wang, Wenhong Zhu, Rui Wang. [doi]
• Diffusion Policy Policy OptimizationAllen Z. Ren, Justin Lidard, Lars Lien Ankile, Anthony Simeonov, Pulkit Agrawal 0001, Anirudha Majumdar, Benjamin Burchfiel, Hongkai Dai, Max Simchowitz. [doi]
• Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian GeometryZiheng Chen, Yue Song, Xiaojun Wu 0001, Gaowen Liu, Nicu Sebe. [doi]
• Attention as a HypernetworkSimon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu. [doi]
• Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsJungwon Park, Jungmin Ko, Dongnam Byun, Jangwon Suh, Wonjong Rhee. [doi]
• TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi DiagramMingxi Lei, Chunwei Ma, Meng Ding, Yufan Zhou, Ziyun Huang, Jinhui Xu 0001. [doi]
• CREAM: Consistency Regularized Self-Rewarding Language ModelsZhaoyang Wang, Weilei He, Zhiyuan Liang, Xuchao Zhang, Chetan Bansal, Ying Wei, Weitong Zhang, Huaxiu Yao. [doi]
• Uncovering Latent Memories in Large Language ModelsSunny Duan, Mikail Khona, Abhiram Iyer, Rylan Schaeffer, Ila R. Fiete. [doi]
• Test-time Adaptation for Regression by Subspace AlignmentKazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai, Tomoki Hamagami. [doi]
• Reward Dimension Reduction for Scalable Multi-Objective Reinforcement LearningGiseung Park, Youngchul Sung. [doi]
• How Far Are We from True Unlearnability?Kai Ye, LiangCai Su, Chenxiong Qian. [doi]
• OpenPRM: Building Open-domain Process-based Reward Models with Preference TreesKaiyan Zhang, Jiayuan Zhang, Haoxin Li, Xuekai Zhu, Ermo Hua, Xingtai Lv, Ning Ding 0002, Biqing Qi, Bowen Zhou 0002. [doi]
• Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample OptimizationZichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang 0008, Zicheng Liu 0001, Lijuan Wang, Qiang Qiu. [doi]
• Learn hybrid prototypes for multivariate time series anomaly detectionKe-Yuan Shen. [doi]
• Automated Design of Agentic SystemsShengran Hu, Cong Lu, Jeff Clune. [doi]
• Equivariant Neural Functional Networks for TransformersHoang V. Tran, Thieu Vo, An Nguyen The, Tho Tran Huu, Minh-Khoi Nguyen-Nhat, Thanh Tran, Duy-Tung Pham, Tan Minh Nguyen. [doi]
• ReGen: Generative Robot Simulation via Inverse DesignPhat Tan Nguyen, Tsun-Hsuan Wang, Zhang-Wei Hong, Erfan Aasi, Andrew Silva, Guy Rosman, Sertac Karaman, Daniela Rus. [doi]
• Lr0.Fm: low-Resolution Zero-Shot Classification Benchmark for Foundation ModelsPriyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S. Rawat. [doi]
• Adaptive Length Image Tokenization via Recurrent AllocationShivam Duggal, Phillip Isola, Antonio Torralba 0001, William T. Freeman. [doi]
• Video-STaR: Self-Training Enables Video Instruction Tuning with Any SupervisionOrr Zohar, Xiaohan Wang, Yonatan Bitton, Idan Szpektor, Serena Yeung-Levy. [doi]
• PINP: Physics-Informed Neural Predictor with latent estimation of fluid flowsHuaguan Chen, Yang Liu, Hao Sun. [doi]
• MMSearch: Unveiling the Potential of Large Models as Multi-modal Search EnginesDongzhi Jiang, Renrui Zhang, Ziyu Guo, Yanmin Wu, Jiayi Lei, Pengshuo Qiu, Pan Lu, Zehui Chen, Guanglu Song, Peng Gao 0007, Yu Liu 0015, Chunyuan Li, Hongsheng Li 0001. [doi]
• Words in Motion: Extracting Interpretable Control Vectors for Motion TransformersÖmer Sahin Tas, Royden Wagner. [doi]
• Sparse autoencoders reveal selective remapping of visual concepts during adaptationHyesu Lim, Jinho Choi 0005, Jaegul Choo, Steffen Schneider 0004. [doi]
• Protein Language Model Fitness is a Matter of PreferenceCade W. Gordon, Amy X. Lu, Pieter Abbeel. [doi]
• Towards Neural Scaling Laws for Time Series Foundation ModelsQingren Yao, Chao-Han Huck Yang, Renhe Jiang, Yuxuan Liang, Ming Jin 0005, Shirui Pan. [doi]
• Adapting Multi-modal Large Language Model to Concept Drift From Pre-training OnwardsXiaoyu Yang, Jie Lu, En Yu. [doi]
• Learning the Complexity of Weakly Noisy Quantum StatesYusen Wu, Bujiao Wu, Yanqi Song, Xiao Yuan 0002, Jingbo Wang 0001. [doi]
• Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented GenerationTobias Leemann, Periklis Petridis, Giuseppe Vietri, Dionysis Manousakas, Aaron Roth 0001, Sergül Aydöre. [doi]
• B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught ReasonersWeihao Zeng, Yuzhen Huang, Lulu Zhao, Yijun Wang, Zifei Shan, Junxian He. [doi]
• Should VLMs be Pre-trained with Image Data?Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre, Kushal Arora, Igor Vasiljevic, Benjamin Burchfiel, Shuran Song, Russ Tedrake, Thomas Kollar, Ludwig Schmidt, Achal Dave. [doi]
• Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence GuaranteesShahryar Zehtabi, Dong-Jun Han, Rohit Parasnis, Seyyedali Hosseinalipour, Christopher G. Brinton. [doi]
• Matrix Product Sketching via Coordinated SamplingMajid Daliri, Juliana Freire, Danrong Li, Christopher Musco. [doi]
• I Can Hear You: Selective Robust Training for Deepfake Audio DetectionZirui Zhang, Wei Hao, Aroon Sankoh, William Lin, Emanuel Mendiola-Ortiz, Junfeng Yang, Chengzhi Mao. [doi]
• Controlled LLM Decoding via Discrete Auto-regressive BiasingPatrick Pynadath, Ruqi Zhang. [doi]
• Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective OptimizationHansi Yang, James T. Kwok. [doi]
• MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly DetectionXi Jiang 0009, Jian Li 0062, Hanqiu Deng, Yong Liu 0032, Bin-Bin Gao, Yifeng Zhou, Jialin Li, Chengjie Wang, Feng Zheng. [doi]
• Transformers are Universal In-context LearnersTakashi Furuya, Maarten V. De Hoop, Gabriel Peyré. [doi]
• On the Modeling Capabilities of Large Language Models for Sequential Decision MakingMartin Klissarov, R. Devon Hjelm, Alexander T. Toshev, Bogdan Mazoure. [doi]
• Asymmetric Factorized Bilinear Operation for Vision TransformerJunjie Wu, Qilong Wang 0001, Jiangtao Xie, Pengfei Zhu 0001, Qinghua Hu. [doi]
• Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representationsYudi Xie, Weichen Huang, Esther Alter, Jeremy Schwartz, Joshua B. Tenenbaum, James J. DiCarlo. [doi]
• Minimalistic Predictions for Online Class Constraint SchedulingDorian Guyot, Alexandra Anna Lassota. [doi]
• PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual TrainingCong Chen, Mingyu Liu, Chenchen Jing, Yizhou Zhou, Fengyun Rao, Hao Chen, Bo Zhang 0046, Chunhua Shen. [doi]
• Bayesian Regularization of Latent RepresentationChukwudi Paul Obite, Zhi Chang, Keyan Wu, Shiwei Lan. [doi]
• The Complexity of Two-Team Polymatrix Games with Independent AdversariesAlexandros Hollender, Gilbert Maystre, Sai Ganesh Nagarajan. [doi]
• Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple BaselineHongjoon Ahn, Jinu Hyeon, Youngmin Oh, Bosun Hwang, Taesup Moon. [doi]
• GETS: Ensemble Temperature Scaling for Calibration in Graph Neural NetworksDingyi Zhuang, Chonghe Jiang, Yunhan Zheng, Shenhao Wang, Jinhua Zhao. [doi]
• Planning in Natural Language Improves LLM Search for Code GenerationEvan Z. Wang, Federico Cassano, Catherine Wu, Yunfeng Bai, William Song, Vaskar Nath, Ziwen Han, Sean M. Hendryx, Summer Yue, Hugh Zhang. [doi]
• PaLD: Detection of Text Partially Written by Large Language ModelsEric Lei, Hsiang Hsu, Chun-Fu Chen 0001. [doi]
• Demystifying the Token Dynamics of Deep Selective State Space ModelsThieu Vo, Duy-Tung Pham, Xin T. Tong, Tan Minh Nguyen. [doi]
• Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical LimitsAshish J. Khisti, MohammadReza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic, Christos Louizos. [doi]
• Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph FormToshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo. [doi]
• Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal ModelChunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Xuezhe Ma, Luke Zettlemoyer, Omer Levy. [doi]
• DSPO: Direct Score Preference Optimization for Diffusion Model AlignmentHuaisheng Zhu, Teng Xiao, Vasant G. Honavar. [doi]
• Graph-Guided Scene Reconstruction from Images with 3D Gaussian SplattingChong Cheng, Gaochao Song, Yiyang Yao, Qinzheng Zhou, Gangjian Zhang, Hao Wang. [doi]
• MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based EnergyHaitian Jiang, Renjie Liu 0001, Zengfeng Huang, Yichuan Wang 0002, Xiao Yan 0002, Zhenkun Cai, Minjie Wang, David Wipf. [doi]
• Group-robust Sample Reweighting for Subpopulation Shifts via Influence FunctionsRui Qiao 0006, Zhaoxuan Wu, Jingtan Wang 0001, Pang Wei Koh, Bryan Kian Hsiang Low. [doi]
• Interpreting the Second-Order Effects of Neurons in CLIPYossi Gandelsman, Alexei A. Efros, Jacob Steinhardt. [doi]
• Convex Formulations for Training Two-Layer ReLU Neural NetworksKarthik Prakhya, Tolga Birdal, Alp Yurtsever. [doi]
• EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh GenerationJiaxiang Tang, Zhaoshuo Li, Zekun Hao, Xian Liu, Gang Zeng, Ming-Yu Liu, Qinsheng Zhang. [doi]
• Discrete Codebook World Models for Continuous ControlAidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao 0014, Kevin Sebastian Luck, Arno Solin, Joni Pajarinen. [doi]
• Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves AlignmentChenliang Li, Siliang Zeng, Zeyi Liao, Jiaxiang Li, Dongyeop Kang, Alfredo García 0001, Mingyi Hong 0001. [doi]
• Backdooring Vision-Language Models with Out-Of-Distribution DataWeimin Lyu, Jiachen Yao, Saumya Gupta, Lu Pang 0006, Tao Sun 0009, Lingjie Yi, Lijie Hu, Haibin Ling, Chao Chen 0012. [doi]
• Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual DataSeiji Maekawa, Hayate Iso, Nikita Bhutani. [doi]
• Visual Agents as Fast and Slow ThinkersGuangyan Sun, Mingyu Jin, Zhenting Wang, Cheng-Long Wang, Siqi Ma, Qifan Wang, Tong Geng, Ying Nian Wu, Yongfeng Zhang, Dongfang Liu. [doi]
• Valid Conformal Prediction for Dynamic GNNsEd Davis, Ian Gallagher, Daniel John Lawson, Patrick Rubin-Delanchy. [doi]
• A Sanity Check for AI-generated Image DetectionShilin Yan, Ouxiang Li, Jiayin Cai, Yanbin Hao, Xiaolong Jiang, Yao Hu 0002, Weidi Xie. [doi]
• INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement LearningYuqian Fu, Yuanheng Zhu, Jian Zhao, Jiajun Chai, Dongbin Zhao. [doi]
• LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy AttentionsRavindran Kannan, Chiranjib Bhattacharyya, Praneeth Kacham, David P. Woodruff. [doi]
• The Same but Different: Structural Similarities and Differences in Multilingual Language ModelingRuochen Zhang, Qinan Yu, Matianyu Zang, Carsten Eickhoff, Ellie Pavlick. [doi]
• Learning Continually by Spectral RegularizationAlex Lewandowski, Michal Bortkiewicz, Saurabh Kumar 0004, András György 0001, Dale Schuurmans, Mateusz Ostaszewski, Marlos C. Machado. [doi]
• Personalized Visual Instruction TuningRenjie Pi, Jianshu Zhang 0003, Tianyang Han, Jipeng Zhang, Rui Pan 0002, Tong Zhang 0001. [doi]
• Intelligence at the Edge of ChaosShiyang Zhang, Aakash Patel, Syed Asad Rizvi, Nianchen Liu, Sizhuang He, Amin Karbasi, Emanuele Zappala, David van Dijk. [doi]
• HyperPLR: Hypergraph Generation through Projection, Learning, and ReconstructionWeihuang Wen, Tianshu Yu. [doi]
• Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning ModelRundong He, Yicong Dong, Lanzhe Guo, Yilong Yin, Tailin Wu. [doi]
• A Large-scale Training Paradigm for Graph Generative ModelsYu Wang 0160, Ryan A. Rossi, Namyong Park, Huiyuan Chen, Nesreen K. Ahmed, Puja Trivedi, Franck Dernoncourt, Danai Koutra, Tyler Derr. [doi]
• CR-CTC: Consistency regularization on CTC for improved speech recognitionZengwei Yao, Wei Kang 0006, Xiaoyu Yang 0005, Fangjun Kuang, Liyong Guo, Han Zhu 0004, Zengrui Jin, Zhaoqing Li, Long Lin, Daniel Povey. [doi]
• A Unified Theory of Quantum Neural Network Loss LandscapesEric Ricardo Anschütz. [doi]
• Near, far: Patch-ordering enhances vision foundation models' scene understandingValentinos Pariza, Mohammadreza Salehi, Gertjan J. Burghouts, Francesco Locatello, Yuki M. Asano. [doi]
• Confidence Elicitation: A New Attack Vector for Large Language ModelsBrian Formento, Chuan-Sheng Foo, See-Kiong Ng. [doi]
• Faster Cascades via Speculative DecodingHarikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim 0001, Neha Gupta, Aditya Krishna Menon, Sanjiv Kumar. [doi]
• Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuningAnh Tong, Thanh Nguyen-Tang, Dongeun Lee 0001, Duc Nguyen, Toan M. Tran, David Leo Wright Hall, Cheongwoong Kang, Jaesik Choi. [doi]
• Language Models Need Inductive Biases to Count InductivelyYingshan Chang, Yonatan Bisk. [doi]
• VideoPhy: Evaluating Physical Commonsense for Video GenerationHritik Bansal, Zongyu Lin, Tianyi Xie, Zeshun Zong, Michal Yarom, Yonatan Bitton, Chenfanfu Jiang, Yizhou Sun, Kai-Wei Chang, Aditya Grover. [doi]
• Training-Free Diffusion Model Alignment with Sampling DemonsPo-Hung Yeh, Kuang-Huei Lee, Jun-Cheng Chen. [doi]
• Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding ClusteringKha Pham, Hung Le 0002, Man Ngo, Truyen Tran 0001. [doi]
• Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-ContextSpencer Frei, Gal Vardi. [doi]
• Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA AdaptersRoberto Garcia, Jerry Weihong Liu, Daniel Sorvisto, Sabri Eyuboglu. [doi]
• Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous DrivingXiang Li, Pengfei Li 0007, Yupeng Zheng, Wei Sun, Yan Wang, Yilun Chen. [doi]
• MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of ShardsSheng Wang, Liheng Chen, Pengan Chen, Jingwei Dong, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu. [doi]
• Quality over Quantity in Attention Layers: When Adding More Heads HurtsNoah Amsel, Gilad Yehudai, Joan Bruna. [doi]
• Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion ModelKeda Tao, Jinjin Gu, Yulun Zhang 0001, Xiucheng Wang, Nan Cheng. [doi]
• Multiagent Finetuning: Self Improvement with Diverse Reasoning ChainsVighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba 0001, Shuang Li 0013, Igor Mordatch. [doi]
• ADIFF: Explaining audio difference using natural languageSoham Deshmukh, Shuo Han, Rita Singh, Bhiksha Raj. [doi]
• Group Distributionally Robust Dataset Distillation with Risk MinimizationSaeed Vahidian, Mingyu Wang, Jianyang Gu, Vyacheslav Kungurtsev, Wei Jiang 0009, Yiran Chen 0001. [doi]
• Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM InferenceZongyue Qin, Ziniu Hu, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun. [doi]
• u-μP: The Unit-Scaled Maximal Update ParametrizationCharlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Yuri Prince, Björn Deiseroth, Andrés Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr. [doi]
• GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt OptimizersSarkar Snigdha Sarathi Das, Ryo Kamoi, Bo Pang 0004, Yusen Zhang 0001, Caiming Xiong, Rui Zhang 0037. [doi]
• Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model AlignmentGregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Edgar Schönfeld, Ali K. Thabet, Jonas Kohler. [doi]
• The Utility and Complexity of In- and Out-of-Distribution Machine UnlearningYoussef Allouah, Joshua Kazdan, Rachid Guerraoui, Sanmi Koyejo. [doi]
• Convergent Privacy Loss of Noisy-SGD without Convexity and SmoothnessEli Chien, Pan Li 0005. [doi]
• ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language ModelsJeonghoon Shim, Gyuhyeon Seo, Cheongsu Lim, Yohan Jo. [doi]
• Fast Summation of Radial Kernels via QMC SlicingJohannes Hertrich, Tim Jahn, Michael Quellmalz. [doi]
• Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement LearningTian-Shuo Liu, Xu-Hui Liu, Ruifeng Chen 0003, Lixuan Jin, Pengyuan Wang, Zhilong Zhang, Yang Yu 0001. [doi]
• On the Benefits of Attribute-Driven Graph Domain AdaptationRuiyi Fang, Bingheng Li, Zhao Kang 0001, Qiuhao Zeng, Nima Hosseini Dashtbayaz, Ruizhi Pu, Charles Ling 0001, Boyu Wang 0004. [doi]
• On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared RepresentationsGuojun Xiong, Shufan Wang, Daniel Jiang, Jian Li. [doi]
• Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File SelectionZiqing Fan, Siyuan Du, Shengchao Hu, Pingjie Wang, Li Shen 0008, Ya Zhang 0002, Dacheng Tao, Yanfeng Wang 0001. [doi]
• Looped Transformers for Length GeneralizationYing Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee 0001. [doi]
• Doubly Optimal Policy Evaluation for Reinforcement LearningShuze Daniel Liu, Claire Chen, Shangtong Zhang. [doi]
• HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA ExpertsMengqi Liao, Wei Chen 0015, Junfeng Shen, Shengnan Guo 0001, Huaiyu Wan. [doi]
• Generative Classifiers Avoid Shortcut SolutionsAlexander Cong Li, Ananya Kumar, Deepak Pathak. [doi]
• ImpScore: A Learnable Metric For Quantifying The Implicitness Level of SentencesYuxin Wang 0006, Xiaomeng Zhu, Weimin Lyu, Saeed Hassanpour, Soroush Vosoughi. [doi]
• GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-trainingRenqiu Xia, MingSheng Li, Hancheng Ye, Wenjie Wu, Hongbin Zhou, Jiakang Yuan, Tianshuo Peng, Xinyu Cai, Xiangchao Yan, Bin Wang 0065, Conghui He, Botian Shi, Tao Chen 0003, Junchi Yan, Bo Zhang 0069. [doi]
• ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback EnvironmentsHojae Han, Seung-won Hwang, Rajhans Samdani, Yuxiong He. [doi]
• Efficient Sparse PCA via Block-DiagonalizationAlberto Del Pia, Dekun Zhou, Yinglun Zhu. [doi]
• Semantic Image Inversion and Editing using Rectified Stochastic Differential EquationsLitu Rout, Yujia Chen 0001, Nataniel Ruiz, Constantine Caramanis, Sanjay Shakkottai, Wen-Sheng Chu. [doi]
• Collapsed Language Models Promote FairnessJingxuan Xu, Wuyang Chen 0001, Linyi Li, Yao Zhao 0001, Yunchao Wei. [doi]
• DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchHuajian Xin, Z. Z. Ren, Junxiao Song, Zhihong Shao, Wanjia Zhao, Haocheng Wang, Bo Liu, Liyue Zhang, Xuan Lu, Qiushi Du, Wenjun Gao, Haowei Zhang, Qihao Zhu, Dejian Yang, Zhibin Gou, Z. F. Wu, Fuli Luo, Chong Ruan. [doi]
• 3D Vision-Language Gaussian SplattingQucheng Peng, Benjamin Planche, Zhongpai Gao, Meng Zheng 0002, Anwesa Choudhuri, Terrence Chen, Chen Chen, Ziyan Wu 0001. [doi]
• Large Language Models are Interpretable LearnersRuochen Wang, Si Si, Felix X. Yu, Dorothea Wiesmann Rothuizen, Cho-Jui Hsieh, Inderjit S. Dhillon. [doi]
• Discrete Latent Plans via Semantic Skill AbstractionsHaobin Jiang, Jiangxing Wang, Zongqing Lu 0002. [doi]
• Class Distribution-induced Attention Map for Open-vocabulary Semantic SegmentationsDong Un Kang, Hayeon Kim, Se Young Chun. [doi]
• LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion ModelsHantao Zhang, Yuhe Liu, Jiancheng Yang, Shouhong Wan, Xinyuan Wang, Wei Peng, Pascal Fua. [doi]
• The Ramanujan Library - Automated Discovery on the Hypergraph of Integer RelationsItay Beit Halachmi, Ido Kaminer. [doi]
• NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language ModelsZheng Yi Ho, Siyuan Liang, Sen Zhang 0006, Yibing Zhan, Dacheng Tao. [doi]
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community RetrievalPengcheng Jiang, Cao Xiao, Minhao Jiang, Parminder Bhatia, Taha A. Kass-Hout, Jimeng Sun 0001, Jiawei Han 0001. [doi]
• Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced DatasetYiqin Yang, Quanwei Wang, Chenghao Li 0002, Hao Hu 0006, Chengjie Wu, Yuhua Jiang, Dianyu Zhong, Ziyou Zhang, Qianchuan Zhao, Chongjie Zhang, Bo Xu. [doi]
• Do Deep Neural Network Solutions Form a Star Domain?Ankit Sonthalia, Alexander Rubinstein 0002, Ehsan Abbasnejad, Seong Joon Oh. [doi]
• Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and EvaluationTengfei Ma 0002, Xiang Song 0003, Wen Tao, Mufei Li, Jiani Zhang 0003, Xiaoqin Pan, Yijun Wang 0002, Bosheng Song, Xiangxiang Zeng. [doi]
• CViT: Continuous Vision Transformer for Operator LearningSifan Wang, Jacob H. Seidman, Shyam Sankaran, Hanwen Wang, George J. Pappas, Paris Perdikaris. [doi]
• CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux ModellingMatthew Fortier, Mats Leon Richter, Oliver Sonnentag, Christopher Pal. [doi]
• PEARL: Parallel Speculative Decoding with Adaptive Draft LengthTianyu Liu, Yun Li, Qitan Lv, Kai Liu, Jianchen Zhu, Winston Hu, Xiao Sun. [doi]
• Qinco2: Vector Compression and Search with Improved Implicit Neural CodebooksThéophane Vallaeys, Matthew J. Muckley, Jakob Verbeek, Matthijs Douze. [doi]
• Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight ForgettingSuraj Anand, Michael A. Lepori, Jack Merullo, Ellie Pavlick. [doi]
• TIPS: Text-Image Pretraining with Spatial awarenessKevis-Kokitsi Maninis, Kaifeng Chen, Soham Ghosh, Arjun Karpur, Koert Chen, Ye Xia, Bingyi Cao, Daniel Salz, Guangxing Han, Jan Dlabal, Dan Gnanapragasam, Mojtaba Seyedhosseini, Howard Zhou, André Araújo 0001. [doi]
• The Computational Complexity of Circuit Discovery for Inner InterpretabilityFederico Adolfi, Martina G. Vilas, Todd Wareham. [doi]
• TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement LearningGe Li, Dong Tian, Hongyi Zhou, Xinkai Jiang, Rudolf Lioutikov, Gerhard Neumann. [doi]
• UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic SegmentationTao Zhang, Jinyong Wen, Zhen Chen, Kun Ding, Shiming Xiang, Chunhong Pan. [doi]
• Scaling and evaluating sparse autoencodersLeo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu 0003. [doi]
• SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal BudgetZihao Wang, Bin Cui, Shaoduo Gan. [doi]
• Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement LearningXinran Li, Xiaolu Wang, Chenjia Bai, Jun Zhang. [doi]
• Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz EstimatesConnor Mooney, Zhongjian Wang, Jack Xin, Yifeng Yu. [doi]
• Pangea: A Fully Open Multilingual Multimodal LLM for 39 LanguagesXiang Yue, Yueqi Song, Akari Asai, Seungone Kim, Jean de Dieu Nyandwi, Simran Khanuja, Anjali Kantharuban, Lintang Sutawika, Sathyanarayanan Ramamoorthy, Graham Neubig. [doi]
• Machine Unlearning Fails to Remove Data Poisoning AttacksMartin Pawelczyk, Jimmy Z. Di, Yiwei Lu 0001, Gautam Kamath 0001, Ayush Sekhari, Seth Neel. [doi]
• Hummingbird: High Fidelity Image Generation via Multimodal Context AlignmentMinh-Quan Le, Gaurav Mittal, Tianjian Meng, A S. M. Iftekhar, Vishwas Suryanarayanan, Barun Patra, Dimitris Samaras, Mei Chen. [doi]
• MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane RepresentationSiyi Jiao, Wenzheng Zeng, Yerong Li, Huayu Zhang, Changxin Gao, Nong Sang, Mike Zheng Shou. [doi]
• Calibrating LLMs with Information-Theoretic Evidential Deep LearningYawei Li, David Rügamer, Bernd Bischl, Mina Rezaei. [doi]
• Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion ModelChunming He, Chengyu Fang, Yulun Zhang 0001, Longxiang Tang, Jinfa Huang, Kai Li, Zhenhua Guo 0001, Xiu Li 0001, Sina Farsiu. [doi]
• QuaDiM: A Conditional Diffusion Model For Quantum State Property EstimationYehui Tang, Mabiao Long, Junchi Yan. [doi]
• SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text GenerationSong Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari. [doi]
• Towards Generalization Bounds of GCNs for Adversarially Robust Node ClassificationWen Wen, Han Li, Tieliang Gong, Hong Chen 0004. [doi]
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional SamplersYuchen Liang, Peizhong Ju, Yingbin Liang, Ness B. Shroff. [doi]
• Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU NetworksDevon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe. [doi]
• Efficient Model Editing with Task-Localized Sparse Fine-tuningLeonardo Iurada, Marco Ciccone, Tatiana Tommasi. [doi]
• Efficient and Accurate Explanation Estimation with Distribution CompressionHubert Baniecki, Giuseppe Casalicchio, Bernd Bischl, Przemyslaw Biecek. [doi]
• Input Space Mode Connectivity in Deep Neural NetworksJakub Vrábel, Ori Shem-Ur, Yaron Oz, David Krueger 0001. [doi]
• Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-SolvingYangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, Yiming Yang. [doi]
• TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion InterpolationHaiyang Liu, Xingchao Yang, Tomoya Akiyama, Yuantian Huang, Qiaoge Li, Shigeru Kuriyama, Takafumi Taketomi. [doi]
• Learning to engineer protein flexibilityPetr Kouba, Joan Planas-Iglesias, Jirí Damborský, Jirí Sedlár, Stanislav Mazurenko, Josef Sivic. [doi]
• Motion-Agent: A Conversational Framework for Human Motion Generation with LLMsQi Wu, Yubo Zhao, Yifan Wang, Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang. [doi]
• Learning to Discretize Denoising Diffusion ODEsVinh Tong, Dung-Trung Hoang, Anji Liu, Guy Van den Broeck, Mathias Niepert. [doi]
• Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation ModelsCong Lu, Shengran Hu, Jeff Clune. [doi]
• SysCaps: Language Interfaces for Simulation Surrogates of Complex SystemsPatrick Emami, Zhaonan Li, Saumya Sinha, Truc Nguyen. [doi]
• Uni2Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D DetectionYubin Wang, Zhikang Zou, Xiaoqing Ye, Xiao Tan 0001, Errui Ding, Cairong Zhao. [doi]
• Advantage-Guided Distillation for Preference Alignment in Small Language ModelsShiping Gao, Fanqi Wan, Jiajian Guo, Xiaojun Quan, Qifan Wang. [doi]
• SG-I2V: Self-Guided Trajectory Control in Image-to-Video GenerationKoichi Namekata, Sherwin Bahmani, Ziyi Wu, Yash Kant, Igor Gilitschenski, David B. Lindell. [doi]
• Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed SmoothnessMichael Crawshaw, Mingrui Liu. [doi]
• CAKE: Cascading and Adaptive KV Cache Eviction with Layer PreferencesZiran Qin, Yuchen Cao, Mingbao Lin, Wen Hu, Shixuan Fan, Ke Cheng, Weiyao Lin, Jianguo Li. [doi]
• Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic TeacherYong Guo, Shulian Zhang, Haolin Pan, Jing Liu 0048, Yulun Zhang 0001, Jian Chen 0011. [doi]
• F3Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from VideosZhaoyu Liu, Kan Jiang, Murong Ma, Zhe Hou, Yun Lin 0001, Jin Song Dong. [doi]
• On the Fourier analysis in the SO(3) space : the EquiLoPO NetworkDmitrii Zhemchuzhnikov, Sergei Grudinin. [doi]
• Lines of Thought in Large Language ModelsRaphaël Sarfati, Toni J. B. Liu, Nicolas Boullé, Christopher J. Earls. [doi]
• Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language ModelsCe Zhang 0009, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia P. Sycara, Yaqi Xie 0001. [doi]
• Reveal Object in Lensless Photography via Region Gaze and AmplificationXiangjun Yin, HuiHui Yue. [doi]
• Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate RegressionShuang Liang, Guido Montúfar. [doi]
• Natural Language Inference Improves Compositionality in Vision-Language ModelsPaola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé III, Rachel Rudinger. [doi]
• Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image ClassificationMehdi Naouar, Hanne Raum, Jens Rahnfeld, Yannick Vogt, Joschka Boedecker, Gabriel Kalweit, Maria Kalweit. [doi]
• 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D WorldsHengshuo Chu, Xiang Deng, Qi Lv, Xiaoyang Chen, Yinchuan Li, Jianye Hao, Liqiang Nie. [doi]
• Adaptive Camera Sensor for Vision ModelsEunsu Baek, Sunghwan Han, Taesik Gong, Hyung-Sin Kim. [doi]
• ICLR: In-Context Learning of RepresentationsCore Francisco Park, Andrew Lee, Ekdeep Singh Lubana, Yongyi Yang, Maya Okawa, Kento Nishi, Martin Wattenberg, Hidenori Tanaka. [doi]
• Tamper-Resistant Safeguards for Open-Weight LLMsRishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti, Tarun Suresh, Maxwell Lin, Justin Wang, Rowan Wang, Ron Arel, Andy Zou, Dawn Song, Bo Li 0026, Dan Hendrycks, Mantas Mazeika. [doi]
• Does Training with Synthetic Data Truly Protect Privacy?Yunpeng Zhao, Jie Zhang 0081. [doi]
• Progressive Parameter Efficient Transfer Learning for Semantic SegmentationNan Zhou, Huiqun Wang, Yaoyan Zheng, Di Huang 0001. [doi]
• LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge BasesArmin Toroghi, Ali Pesaranghader, Tanmana Sadhu, Scott Sanner. [doi]
• How to Find the Exact Pareto Front for Multi-Objective MDPs?Yining Li, Peizhong Ju, Ness B. Shroff. [doi]
• Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative PerceptionZihan Ding, Jiahui Fu 0003, Si Liu 0001, HongYu Li, Siheng Chen, Hongsheng Li, Shifeng Zhang, Xu Zhou. [doi]
• DelTA: An Online Document-Level Translation Agent Based on Multi-Level MemoryYutong Wang, Jiali Zeng, Xuebo Liu, Derek F. Wong, Fandong Meng, Jie Zhou, Min Zhang. [doi]
• Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-FaithfulnessBaolong Bi, Shenghua Liu, Yiwei Wang 0001, Lingrui Mei, Junfeng Fang, Hongcheng Gao, Shiyu Ni, Xueqi Cheng. [doi]
• STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor ScenesJiawei Yang 0002, Jiahui Huang, Boris Ivanovic, Yuxiao Chen 0008, Yan Wang 0051, Boyi Li, Yurong You, Apoorva Sharma, Maximilian Igl, Péter Karkus, Danfei Xu, Yue Wang 0041, Marco Pavone 0001. [doi]
• Towards Faster Decentralized Stochastic Optimization with Communication CompressionRustem Islamov, Yuan Gao, Sebastian U. Stich. [doi]
• Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural CollapseArthur Jacot, Peter Súkeník, Zihan Wang, Marco Mondelli. [doi]
• GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D ManipulationYangtao Chen, Zixuan Chen, Junhui Yin, Jing Huo, Pinzhuo Tian, Jieqi Shi, Yang Gao. [doi]
• HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy GenerationHanxiang Ren, Li Sun, Xulong Wang, Pei Zhou, Zewen Wu, Siyan Dong, Difan Zou, Youyi Zheng, Yanchao Yang 0001. [doi]
• Supervised and Semi-Supervised Diffusion Maps with Label-Driven DiffusionHarel Mendelman, Ronen Talmon. [doi]
• Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein DesignMelis Ilayda Bal, Pier Giuseppe Sessa, Mojmir Mutny, Andreas Krause 0001. [doi]
• LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation modelsZiqi Lu, Heng Yang, Danfei Xu, Boyi Li, Boris Ivanovic, Marco Pavone 0001, Yue Wang 0041. [doi]
• Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression ErrorsSungyoon Lee, Sokbae Lee. [doi]
• No Need to Talk: Asynchronous Mixture of Language ModelsAnastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert. [doi]
• Learning Causal Alignment for Reliable Disease DiagnosisMingzhou Liu 0001, Ching-Wen Lee, Xinwei Sun 0001, Xueqing Yu, Yu Qiao 0001, Yizhou Wang 0001. [doi]
• Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusionEnrico Ventura, Beatrice Achilli, Gianluigi Silvestri, Carlo Lucibello, Luca Ambrogioni. [doi]
• MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound GenerationTrung X. Pham, Tri Ton, Chang D. Yoo. [doi]
• Endless Jailbreaks with Bijection LearningBrian R. Y. Huang, Maximilian Li, Leonard Tang. [doi]
• Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned DatasetsYudong Chen 0002, Xuwei Xu, Frank de Hoog, Jiajun Liu, Sen Wang 0001. [doi]
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental LearningYichen Wu, Hongming Piao, Long-Kai Huang, Renzhen Wang, Wanhua Li 0001, Hanspeter Pfister, Deyu Meng, Kede Ma, Ying Wei 0001. [doi]
• Language Imbalance Driven Rewarding for Multilingual Self-improvingWen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang. [doi]
• OmniBind: Large-scale Omni Multimodal Representation via Binding SpacesZehan Wang 0001, Ziang Zhang, Minjie Hong, Hang Zhang, Luping Liu, Rongjie Huang 0001, Xize Cheng, Shengpeng Ji, Tao Jin 0004, Hengshuang Zhao, Zhou Zhao 0001. [doi]
• Limits of Deep Learning: Sequence Modeling through the Lens of Complexity TheoryNikola Zubic, Federico Soldà, Aurelio L. Sulser, Davide Scaramuzza 0001. [doi]
• Adding Conditional Control to Diffusion Models with Reinforcement LearningYulai Zhao 0002, Masatoshi Uehara, Gabriele Scalia, Sun-Yuan Kung, Tommaso Biancalani, Sergey Levine, Ehsan Hajiramezanali. [doi]
• Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive TransformerHao Luo, Zongqing Lu. [doi]
• Tighter Privacy Auditing of DP-SGD in the Hidden State Threat ModelTudor Ioan Cebere, Aurélien Bellet, Nicolas Papernot. [doi]
• Release the Powers of Prompt Tuning: Cross-Modality Prompt TransferNingyuan Zhang, Jie Lu 0001, Keqiuyin Li, Zhen Fang 0001, Guangquan Zhang 0001. [doi]
• Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra CostsSeveri Rissanen, Markus Heinonen, Arno Solin. [doi]
• Certifying Counterfactual Bias in LLMsIsha Chaudhary, Qian Hu, Manoj Kumar 0007, Morteza Ziyadi, Rahul Gupta 0001, Gagandeep Singh 0001. [doi]
• Repulsive Latent Score Distillation for Solving Inverse ProblemsNicolas Zilberstein, Morteza Mardani, Santiago Segarra. [doi]
• CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution ShiftsJihye Choi, Jayaram Raghuram, Yixuan Li 0001, Somesh Jha. [doi]
• Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One StepMingyuan Zhou, Huangjie Zheng, Yi Gu, Zhendong Wang, Hai Huang. [doi]
• RuAG: Learned-rule-augmented Generation for Large Language ModelsYudi Zhang 0007, Pei Xiao 0007, Lu Wang 0029, Chaoyun Zhang, Meng Fang, Yali Du 0001, Yevgeniy Puzyrev, Randolph Yao, Si-qin, Qingwei Lin, Mykola Pechenizkiy, Dongmei Zhang 0001, Saravan Rajmohan, Qi Zhang 0066. [doi]
• It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale OptimisationSohan Patnaik, Milan Aggarwal, Sumit Bhatia, Balaji Krishnamurthy. [doi]
• Democratic Training Against Universal Adversarial PerturbationsBing Sun, Jun Sun 0001, Wei Zhao. [doi]
• Searching for Optimal Solutions with LLMs via Bayesian OptimizationDhruv Agarwal 0003, Manoj Ghuhan Arivazhagan, Rajarshi Das, Sandesh Swamy, Sopan Khosla, Rashmi Gangadharaiah. [doi]
• BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak AttacksYunhan Zhao, Xiang Zheng, Lin Luo, Yige Li, Xingjun Ma, Yu-Gang Jiang 0001. [doi]
• Erasing Concept Combination from Text-to-Image Diffusion ModelHongyi Nie, Quanming Yao, Yang Liu, Zhen Wang 0004, Yatao Bian. [doi]
• Incremental Causal Effect for Time to Treatment InitializationAndrew Ying, Zhichen Zhao, Ronghui Xu. [doi]
• ϕ-Update: A Class of Policy Update Methods with Policy Convergence GuaranteeWenye Li 0002, Jiacai Liu, Ke Wei. [doi]
• CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation LearningShaofeng Zhang, Qiang Zhou, Sitong Wu, Haoru Tan, Zhibin Wang, Jinfa Huang, Junchi Yan. [doi]
• Adversarial Latent Feature Augmentation for FairnessHoin Jung, Junyi Chai 0004, Xiaoqian Wang 0001. [doi]
• Learning-Augmented Search Data StructuresChunkai Fu, Brandon G. Nguyen, Jung Hoon Seo, Ryan S. Zesch, Samson Zhou. [doi]
• LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model AdaptationCan Jin, Ying Li, Mingyu Zhao, Shiyu Zhao, Zhenting Wang, Xiaoxiao He, Ligong Han, Tong Che, Dimitris N. Metaxas. [doi]
• Prototype antithesis for biological few-shot class-incremental learningBinghao Liu, Han Yang, Fang Wan, Fei Gu. [doi]
• BrainOOD: Out-of-distribution Generalizable Brain Network AnalysisJiaxing Xu, Yongqiang Chen, Xia Dong, Mengcheng Lan, Tiancheng Huang, Qingtian Bian, James Cheng, Yiping Ke. [doi]
• Robust Root Cause Diagnosis using In-Distribution InterventionsLokesh Nagalapatti, Ashutosh Srivastava, Sunita Sarawagi, Amit Sharma. [doi]
• MindSimulator: Exploring Brain Concept Localization via Synthetic fMRIGuangyin Bao, Qi Zhang 0020, Zixuan Gong, Zhuojia Wu, Duoqian Miao 0001. [doi]
• MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation ModelsChejian Xu, Jiawei Zhang 0002, Zhaorun Chen, Chulin Xie, Mintong Kang, Yujin Potter, Zhun Wang, Zhuowen Yuan, Alexander Xiong, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng 0005, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Xuandong Zhao, Francesco Pinto, Zhen Xiang, et al.. [doi]
• Dataset Ownership Verification in Contrastive Pre-trained ModelsYuechen Xie, Jie Song, Mengqi Xue, Haofei Zhang, Xingen Wang, Bingde Hu, Genlang Chen, Mingli Song. [doi]
• Task Descriptors Help Transformers Learn Linear Models In-ContextRuomin Huang, Rong Ge. [doi]
• ADAM Optimization with Adaptive Batch SelectionGyu-Yeol Kim, Min-hwan Oh. [doi]
• Bayesian Image Regression with Soft-thresholded Conditional Autoregressive PriorYuliang Xu, Jian Kang 0003. [doi]
• MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex ProofsAndreas Opedal, Haruki Shirakami, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan. [doi]
• Hyperbolic Genome EmbeddingsRaiyan R. Khan, Philippe Chlenski, Itsik Pe'er. [doi]
• FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World ModelChongkai Gao, Haozhuo Zhang, Zhixuan Xu, Zhehao Cai, Lin Shao 0002. [doi]
• What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary TraitsHarish Babu Manogaran, M. Maruf, Arka Daw, Kazi Sajeed Mehrab, Caleb Patrick Charpentier, Josef C. Uyeda, Wasila M. Dahdul, Matthew J. Thompson, Elizabeth G. Campolongo, Kaiya L. Provost, Wei-Lun Chao, Tanya Y. Berger-Wolf, Paula M. Mabee, Hilmar Lapp, Anuj Karpatne. [doi]
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time SamplingYuejiang Liu, Jubayer Ibn Hamid, Annie Xie, Yoonho Lee 0001, Max Du, Chelsea Finn. [doi]
• Holistically Evaluating the Environmental Impact of Creating Language ModelsJacob Morrison, Clara Na, Jared Fernandez, Tim Dettmers, Emma Strubell, Jesse Dodge. [doi]
• SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene ReconstructionJihwan Yoon, Sangbeom Han, Jaeseok Oh, Minsik Lee. [doi]
• Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language ModelsEunseop Yoon, Hee Suk Yoon, Mark A. Hasegawa-Johnson, Chang D. Yoo. [doi]
• Causal Graph Transformer for Treatment Effect Estimation Under Unknown InterferenceAnpeng Wu, Haiyi Qiu, Zhengming Chen, Zijian Li 0001, Ruoxuan Xiong, Fei Wu 0001, Kun Zhang 0001. [doi]
• Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse FactorizationVladimír Boza, Vladimír Macko. [doi]
• Language Models are Advanced AnonymizersRobin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev. [doi]
• PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh RepresentationsNamgyu Kang, Jaemin Oh, Youngjoon Hong, Eunbyung Park. [doi]
• Can We Talk Models Into Seeing the World Differently?Paul Gavrikov, Jovita Lukasik, Steffen Jung 0001, Robert Geirhos, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper. [doi]
• Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous GraspingZiye Huang, Haoqi Yuan, Yuhui Fu 0005, Zongqing Lu 0002. [doi]
• Longhorn: State Space Models are Amortized Online LearnersBo Liu 0042, Rui Wang, Lemeng Wu, Yihao Feng, Peter Stone 0001, Qiang Liu 0001. [doi]
• Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion InversionKaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu-Hua, Huazhe Xu. [doi]
• ACE: All-round Creator and Editor Following Instructions via Diffusion TransformerZhen Han, Zeyinzi Jiang, Yulin Pan, Jingfeng Zhang, Chaojie Mao, Chen-Wei Xie, Yu Liu 0063, Jingren Zhou 0001. [doi]
• Reassessing How to Compare and Improve the Calibration of Machine Learning ModelsMuthu Chidambaram, Rong Ge 0001. [doi]
• A Multiscale Frequency Domain Causal Framework for Enhanced Pathological AnalysisXiaoyu Cui, Weixing Chen, Jiandong Su. [doi]
• FIG: Flow with Interpolant Guidance for Linear Inverse ProblemsYici Yan, Yichi Zhang, Xiangming Meng, Zhizhen Zhao 0001. [doi]
• Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter EfficientWenlong Wang, Ivana Dusparic, Yucheng Shi, Ke Zhang, Vinny Cahill. [doi]
• Grounding Video Models to Actions through Goal Conditioned ExplorationYunhao Luo, Yilun Du. [doi]
• The AdEMAMix Optimizer: Better, Faster, OlderMatteo Pagliardini, Pierre Ablin, David Grangier. [doi]
• A Differentiable Rank-Based Objective for Better Feature LearningKrunoslav Lehman Pavasovic, Giulio Biroli, Levent Sagun. [doi]
• Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized ProgrammingYilun Hao, Yang Zhang, Chuchu Fan. [doi]
• Weak to Strong Generalization for Large Language Models with Multi-capabilitiesYucheng Zhou, Jianbing Shen, Yu Cheng 0001. [doi]
• Differentiable Integer Linear ProgrammingZijie Geng, Jie Wang, Xijun Li, Fangzhou Zhu, Jianye Hao, Bin Li, Feng Wu. [doi]
• Animate Your Thoughts: Reconstruction of Dynamic Natural Vision from Human Brain ActivityYizhuo Lu, Changde Du, Chong Wang, Xuanliu Zhu, Liuyun Jiang, Xujin Li, Huiguang He. [doi]
• Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement LearningShijie Liu, Andrew Craig Cullen, Paul Montague, Sarah Monazam Erfani, Benjamin I. P. Rubinstein. [doi]
• Improved Finite-Particle Convergence Rates for Stein Variational Gradient DescentSayan Banerjee, Krishna Balasubramanian, Promit Ghosal. [doi]
• Query-based Knowledge Transfer for Heterogeneous Learning EnvironmentsNorah Alballa, Wenxuan Zhang, Ziquan Liu, Ahmed M. Abdelmoniem, Mohamed Elhoseiny, Marco Canini. [doi]
• Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature CompensatorXin Zhang 0092, Jiawei Du, Ping Liu 0004, Joey Tianyi Zhou. [doi]
• Bonsai: Gradient-free Graph Condensation for Node ClassificationMridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana, Sayan Ranu. [doi]
• Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble DecodingYeongjae Cho, Keonwoo Kim, Taebaek Hwang, Sungzoon Cho. [doi]
• Model-based Offline Reinforcement Learning with Lower Expectile Q-LearningKwanyoung Park, Youngwoon Lee. [doi]
• Model Editing as a Robust and Denoised variant of DPO: A Case Study on ToxicityRheeya Uppaal, Apratim Dey, Yiting He, Yiqiao Zhong, Junjie Hu 0001. [doi]
• Privacy Auditing of Large Language ModelsAshwinee Panda, Xinyu Tang 0003, Christopher A. Choquette-Choo, Milad Nasr, Prateek Mittal. [doi]
• Advancing Out-of-Distribution Detection via Local NeuroplasticityAlessandro Canevaro, Julian Schmidt, Mohammad Sajad Marvi, Hang Yu, Georg Martius, Julian Jordan. [doi]
• Deep Networks Learn Features From Local Discontinuities in the Label FunctionPrithaj Banerjee, Harish Guruprasad Ramaswamy, Mahesh Lorik Yadav, Chandra Shekar Lakshminarayanan. [doi]
• Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal FusionJinbiao Chen, Jiahai Wang, Zhiguang Cao, Yaoxin Wu. [doi]
• Stiefel Flow Matching for Moment-Constrained Structure ElucidationAustin Henry Cheng, Alston Lo, Kin Long Kelvin Lee, Santiago Miret, Alán Aspuru-Guzik. [doi]
• Training-Free Message Passing for Learning on HypergraphsBohan Tang, Zexi Liu, Keyue Jiang, Siheng Chen, Xiaowen Dong 0001. [doi]
• CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science MasteryXiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma Gongque, Jianing Yu, Qiuna Tan, Weiran Xu. [doi]
• Selective Label Enhancement Learning for Test-Time AdaptationYihao Hu 0004, Congyu Qiao, Xin Geng 0001, Ning Xu 0009. [doi]
• Uncovering Overfitting in Large Language Model EditingMengqi Zhang, Xiaotian Ye, Qiang Liu, Shu Wu, Pengjie Ren, Zhumin Chen. [doi]
• ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot LearningZihan Ye, Shreyank N. Gowda, Shiming Chen 0002, Xiaowei Huang 0001, Haotian Xu, Fahad Shahbaz Khan, Yaochu Jin, Kaizhu Huang, Xiaobo Jin. [doi]
• AnoLLM: Large Language Models for Tabular Anomaly DetectionChe-Ping Tsai, Ganyu Teng, Phillip Wallis, Wei Ding. [doi]
• NatureLM-audio: an Audio-Language Foundation Model for BioacousticsDavid Robinson, Marius Miron, Masato Hagiwara, Olivier Pietquin. [doi]
• Infinite-Resolution Integral Noise Warping for Diffusion ModelsYitong Deng, Winnie Lin, Lingxiao Li, Dmitriy Smirnov 0001, Ryan D. Burgert, Ning Yu, Vincent Dedun, Mohammad H. Taghavi. [doi]
• Do as We Do, Not as You Think: the Conformity of Large Language ModelsZhiyuan Weng, Guikun Chen, Wenguan Wang. [doi]
• Forgetting Transformer: Softmax Attention with a Forget GateZhixuan Lin, Evgenii Nikishin, Xu Owen He, Aaron C. Courville. [doi]
• Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical ReasoningHyun Ryu, Gyeongman Kim, Hyemin S. Lee, Eunho Yang. [doi]
• End-to-end Learning of Gaussian Mixture Priors for Diffusion SamplerDenis Blessing, Xiaogang Jia, Gerhard Neumann. [doi]
• Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension abilityYujin Han, Lei Xu, Sirui Chen, Difan Zou, Chaochao Lu. [doi]
• API Pack: A Massive Multi-Programming Language Dataset for API Call GenerationZhen Guo, Adriana Meza Soria, Wei Sun, Yikang Shen, Rameswar Panda. [doi]
• Dynamic Assortment Selection and Pricing with Censored Preference FeedbackJung Hun Kim, Min-hwan Oh. [doi]
• ActionReasoningBench: Reasoning about Actions with and without Ramification ConstraintsDivij Handa, Pavel Dolin, Shrinidhi Kumbhar, Tran Cao Son, Chitta Baral. [doi]
• A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal DiscoveryYingyu Lin, Yuxing Huang, Wenqin Liu, Haoran Deng, Ignavier Ng, Kun Zhang 0001, Mingming Gong, Yian Ma, Biwei Huang. [doi]
• Energy-based Backdoor Defense Against Federated Graph LearningGuancheng Wan, Zitong Shi, Wenke Huang, Guibin Zhang, Dacheng Tao, Mang Ye. [doi]
• OGBench: Benchmarking Offline Goal-Conditioned RLSeohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine. [doi]
• The Geometry of Categorical and Hierarchical Concepts in Large Language ModelsKiho Park 0001, Yo Joong Choe, Yibo Jiang, Victor Veitch. [doi]
• Mini-batch Coresets for Memory-efficient Language Model Training on Data MixturesDang Nguyen, Wenhan Yang, Rathul Anand, Yu Yang 0007, Baharan Mirzasoleiman. [doi]
• BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral DataParsa Vahidi, Omid G. Sani, Maryam Shanechi. [doi]
• LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression ComprehensionAmaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord. [doi]
• Problem-Parameter-Free Federated LearningWenjing Yan, Kai Zhang, Xiaolu Wang, Xuanyu Cao. [doi]
• Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language ModelsÁngela López-Cardona, Carlos Segura, Alexandros Karatzoglou, Sergi Abadal, Ioannis Arapakis. [doi]
• Expressivity of Neural Networks with Random Weights and Learned BiasesEzekiel Williams, Alexandre Payeur, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Matthew G. Perich, Luca Mazzucato, Guillaume Lajoie. [doi]
• Boosting Multiple Views for pretrained-based Continual LearningQuyen Tran, Tung Lam Tran, Khanh Doan, Toan Tran 0003, Dinh Q. Phung, Khoat Than, Trung Le. [doi]
• Fast training and sampling of Restricted Boltzmann MachinesNicolas Béreux, Aurélien Decelle, Cyril Furtlehner, Lorenzo Rosset, Beatriz Seoane. [doi]
• Sharper Guarantees for Learning Neural Network Classifiers with Gradient MethodsHossein Taheri, Christos Thrampoulidis, Arya Mazumdar. [doi]
• OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution FittingXing Hu 0010, Yuan Cheng, Dawei Yang, Zhixuan Chen, Zukang Xu, Jiangyong Yu, Chen Xu, Zhihang Yuan, Zhe Jiang 0004, Sifan Zhou. [doi]
• Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from GeneralizationZixuan Gong, Xiaolin Hu, Huayi Tang, Yong Liu 0020. [doi]
• GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsSeyed-Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar. [doi]
• Perm: A Parametric Representation for Multi-Style 3D Hair ModelingChengan He, Xin Sun 0014, Zhixin Shu, Fujun Luan, Sören Pirk, Jorge Alejandro Amador Herrera, Dominik Ludewig Michels, Tuanfeng Yang Wang, Meng Zhang, Holly E. Rushmeier, Yi Zhou 0023. [doi]
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model EvaluationZhongshen Zeng, Pengguang Chen, Shu Liu 0005, Haiyun Jiang, Jiaya Jia. [doi]
• Advancing Graph Generation through Beta DiffusionXinyang Liu, Yilin He, Bo Chen, Mingyuan Zhou. [doi]
• Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free ControlDevdhar Patel, Hava T. Siegelmann. [doi]
• On the Byzantine-Resilience of Distillation-Based Federated LearningChristophe Roux, Max Zimmer, Sebastian Pokutta. [doi]
• Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context SparsificationWenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin. [doi]
• Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process DataHengyu Fu, Zehao Dou, Jiawei Guo, Mengdi Wang, Minshuo Chen. [doi]
• CEB: Compositional Evaluation Benchmark for Fairness in Large Language ModelsSong Wang, Peng Wang, Tong Zhou, Yushun Dong, Zhen Tan 0001, Jundong Li. [doi]
• Strong Preferences Affect the Robustness of Preference Models and Value AlignmentZiwei Xu 0001, Mohan S. Kankanhalli. [doi]
• Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous TokensLijie Fan, Tianhong Li, Siyang Qin, Yuanzhen Li, Chen Sun 0002, Michael Rubinstein, Deqing Sun, Kaiming He, Yonglong Tian. [doi]
• Preserving Diversity in Supervised Fine-Tuning of Large Language ModelsZiniu Li, Congliang Chen, Tian Xu 0003, Zeyu Qin, Jiancong Xiao, Zhi-Quan Luo, Ruoyu Sun 0001. [doi]
• PFGuard: A Generative Framework with Privacy and Fairness SafeguardsSoyeon Kim, Yuji Roh, Geon Heo, Steven Euijong Whang. [doi]
• NL-Eye: Abductive NLI For ImagesMor Ventura, Michael Toker, Nitay Calderon, Zorik Gekhman, Yonatan Bitton, Roi Reichart. [doi]
• RESuM: A Rare Event Surrogate Model for Physics Detector DesignAnn-Kathrin Schuetz, A. W. P. Poon, Aobo Li. [doi]
• A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile GenerationHuimin Zeng, Xiaojie Wang 0003, Anoop Jain, Zhicheng Dou, Dong Wang. [doi]
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward InferenceQining Zhang, Lei Ying 0001. [doi]
• DistillHGNN: A Knowledge Distillation Approach for High-Speed Hypergraph Neural NetworksSaman Forouzandeh, Parham Moradi, Mahdi Jalili. [doi]
• Error-quantified Conformal Inference for Time SeriesJunxi Wu, Dongjian Hu, Yajie Bao, Shu-Tao Xia, Changliang Zou. [doi]
• Active Task Disambiguation with LLMsKasia Kobalczyk, Nicolás Astorga, Tennison Liu, Mihaela van der Schaar. [doi]
• PRDP: Progressively Refined Differentiable PhysicsKanishk Bhatia, Felix Koehler, Nils Thuerey. [doi]
• High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational AutoencodersSiddharth Ramchandran, Manuel Haussmann, Harri Lähdesmäki. [doi]
• TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningXiangyu Zeng, Kunchang Li 0002, Chenting Wang, Xinhao Li 0004, Tianxiang Jiang, Ziang Yan, Songze Li, Yansong Shi, Zhengrong Yue, Yi Wang 0074, Yali Wang 0001, Yu Qiao 0001, Limin Wang 0002. [doi]
• HaDeMiF: Hallucination Detection and Mitigation in Large Language ModelsXiaoling Zhou, Mingjie Zhang, Zhemg Lee, Wei Ye 0004, Shikun Zhang. [doi]
• Latent Space Chain-of-Embedding Enables Output-free LLM Self-EvaluationYiming Wang 0011, Pei Zhang 0011, Baosong Yang, Derek F. Wong, Rui Wang 0015. [doi]
• Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical SamplingKaiwen Zheng, Yongxin Chen, Hanzi Mao, Ming-Yu Liu 0001, Jun Zhu 0001, Qinsheng Zhang. [doi]
• Towards Unbiased Learning in Semi-Supervised Semantic SegmentationRui Sun, Huayu Mai, Wangkai Li, Tianzhu Zhang. [doi]
• CHAMP: Conformalized 3D Human Multi-Hypothesis Pose EstimatorsHarry Zhang, Luca Carlone. [doi]
• X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving ScenariosYichen Xie 0002, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan. [doi]
• OS-ATLAS: Foundation Action Model for Generalist GUI AgentsZhiyong Wu 0003, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding 0002, Liheng Chen, Paul Pu Liang, Yu Qiao 0001. [doi]
• Aligned Better, Listen Better for Audio-Visual Large Language ModelsYuxin Guo, Shuailei Ma, Shijie Ma, Xiaoyi Bao, Chen-Wei Xie, Kecheng Zheng, Tingyu Weng, Siyang Sun, Yun Zheng, Wei Zou. [doi]
• Scale-Free Graph-Language ModelsJianglin Lu, Yixuan Liu, Yitian Zhang, Yun Fu 0001. [doi]
• Human Simulacra: Benchmarking the Personification of Large Language ModelsQiujie Xie, Qiming Feng, Tianqi Zhang, Qingqiu Li, Linyi Yang, Yuejie Zhang, Rui Feng 0001, Liang He, Shang Gao 0003, Yue Zhang 0004. [doi]
• Does SGD really happen in tiny subspaces?Minhak Song, Kwangjun Ahn, Chulhee Yun. [doi]
• ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuningPengwei Tang, Xiaolin Hu, Yong Liu. [doi]
• Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go BeyondQizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han 0003, Kilian Q. Weinberger. [doi]
• Distilling Reinforcement Learning Algorithms for In-Context Model-Based PlanningJaehyeon Son, Soochan Lee, Gunhee Kim. [doi]
• TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel ConditioningTsiry Mayet, Pourya Shamsolmoali, Simon Bernard 0001, Eric Granger, Romain Hérault, Clément Chatelain 0001. [doi]
• Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGDZe Peng, Jian Zhang 0002, Yisen Wang, Lei Qi 0001, Yinghuan Shi, Yang Gao 0001. [doi]
• Wavelet-based Positional Representation for Long ContextYui Oka, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito. [doi]
• Mechanistic Permutability: Match Features Across LayersNikita Balagansky, Ian Maksimov, Daniil Gavrilov. [doi]
• Improved Techniques for Optimization-Based Jailbreaking on Large Language ModelsXiaojun Jia, Tianyu Pang, Chao Du, Yihao Huang 0001, Jindong Gu, Yang Liu 0003, Xiaochun Cao, Min Lin. [doi]
• Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and AmendmentYuze Zhao, Tianyun Ji, Wenjun Feng, Zhenya Huang, Qi Liu 0003, Zhiding Liu, Yixiao Ma, Kai Zhang 0038, Enhong Chen. [doi]
• MLLM can see? Dynamic Correction Decoding for Hallucination MitigationChenxi Wang, Xiang Chen 0016, Ningyu Zhang 0001, Bozhong Tian, Haoming Xu, Shumin Deng, Huajun Chen. [doi]
• Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information AmountYanbiao Ma, Wei Dai, Jiayi Chen. [doi]
• Generalizable Motion Planning via Operator LearningSharath Matada, Luke Bhan, Yuanyuan Shi, Nikolay Atanasov 0001. [doi]
• An Asynchronous Bundle Method for Distributed Learning ProblemsDaniel Cederberg, Xuyang Wu, Stephen P. Boyd, Mikael Johansson. [doi]
• Data Pruning by Information MaximizationHaoru Tan, Sitong Wu, Wei Huang, Shizhen Zhao, Xiaojuan Qi 0001. [doi]
• Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow SchedulingYifan Yang, Gang Chen, Hui Ma, Cong Zhang, Zhiguang Cao, Mengjie Zhang. [doi]
• In-context Time Series PredictorJiecheng Lu, Yan Sun, Shihao Yang. [doi]
• Learning View-invariant World Models for Visual Robotic ManipulationJing-Cheng Pang, Nan Tang, Kaiyuan Li, Yuting Tang, Xin-Qiang Cai, Zhen-yu Zhang, Gang Niu 0001, Masashi Sugiyama, Yang Yu 0001. [doi]
• uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABsYu Chen 0074, Jiatai Huang, Yan Dai 0002, Longbo Huang. [doi]
• T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular DataHugo Thimonier, José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan. [doi]
• Improved Approximation Algorithms for k-Submodular Maximization via Multilinear ExtensionHuanjian Zhou, Lingxiao Huang, Baoxiang Wang 0001. [doi]
• High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling LawsMuhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli, Samet Oymak. [doi]
• TypedThinker: Diversify Large Language Model Reasoning with Typed ThinkingDanqing Wang, Jianxin Ma, Fei Fang 0001, Lei Li 0005. [doi]
• DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single DemoJunzhe Zhu, Yuanchen Ju, Junyi Zhang, Muhan Wang, Zhecheng Yuan, Kaizhe Hu, Huazhe Xu. [doi]
• Physics-aligned field reconstruction with diffusion bridgeZeYu Li, Hongkun Dou, Shen Fang, Wang Han, Yue Deng, Lijun Yang. [doi]
• EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal ConditioningWei Yu, Songheng Yin, Steve Easterbrook, Animesh Garg. [doi]
• OSCAR: Operating System Control via State-Aware Reasoning and Re-PlanningXiaoqiang Wang, Bang Liu. [doi]
• Spa-Bench: a comprehensive Benchmark for Smartphone Agent EvaluationJingxuan Chen, Derek Yuen, Bin Xie, Yuhao Yang, Gongwei Chen, Zhihao Wu, Li Yixing, Xurui Zhou, Weiwen Liu, Shuai Wang, Kaiwen Zhou, Rui Shao 0001, Liqiang Nie, Yasheng Wang, Jianye Hao, Jun Wang, Kun Shao. [doi]
• InterMask: 3D Human Interaction Generation via Collaborative Masked ModelingMuhammad Gohar Javed, Chuan Guo 0002, Li Cheng 0001, Xingyu Li. [doi]
• Calibrating Expressions of CertaintyPeiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M. Wells III, Tina Kapur, Polina Golland. [doi]
• SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited LabelsXiangyu Dong 0002, Xingyi Zhang 0003, Lei Chen 0031, Mingxuan Yuan, Sibo Wang 0001. [doi]
• Select before Act: Spatially Decoupled Action Repetition for Continuous ControlBuqing Nie, Yangqing Fu, Yue Gao 0005. [doi]
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language ModelsAndy K. Zhang, Neil Perry, Riya Dulepet, Joey Ji, Celeste Menders, Justin W. Lin, Eliot Jones, Gashon Hussein, Samantha Liu, Donovan Julian Jasper, Pura Peetathawatchai, Ari Glenn, Vikram Sivashankar, Daniel Zamoshchin, Leo Glikbarg, Derek Askaryar, Haoxiang Yang, Aolin Zhang, Rishi Alluri, Nathan Tran, et al.. [doi]
• Pareto Low-Rank Adapters: Efficient Multi-Task Learning with PreferencesNikolaos Dimitriadis, Pascal Frossard, François Fleuret. [doi]
• HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion ModelsHayk Manukyan 0001, Andranik Sargsyan, Barsegh Atanyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi. [doi]
• NeRAF: 3D Scene Infused Neural Radiance and Acoustic FieldsAmandine Brunetto, Sascha Hornauer, Fabien Moutarde. [doi]
• SysBench: Can LLMs Follow System Message?Yanzhao Qin, Tao Zhang, Tao Zhang, Yanjun Shen, Wenjing Luo, sunhaoze, Yan Zhang, Yujing Qiao, Weipeng Chen, Zenan Zhou, Wentao Zhang 0001, Bin Cui 0001. [doi]
• Entropy-based Activation Function Optimization: A Method on Searching Better Activation FunctionsHaoyuan Sun, Zihao Wu, Bo Xia, Pu Chang, Zibin Dong, Yifu Yuan, Yongzhe Chang, Xueqian Wang. [doi]
• Benchmarking Agentic Workflow GenerationShuofei Qiao, Runnan Fang, Zhisong Qiu, XiaoBin Wang, Ningyu Zhang 0001, Yong Jiang 0001, Pengjun Xie, Fei Huang 0004, Huajun Chen. [doi]
• ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMsHao Di, Tong He, Haishan Ye, Yinghui Huang, Xiangyu Chang, Guang Dai, Ivor W. Tsang. [doi]
• Decoupling Layout from Glyph in Online Chinese Handwriting GenerationMinsi Ren, Yan-Ming Zhang, Yi Chen. [doi]
• Why Does the Effective Context Length of LLMs Fall Short?Chenxin An, Jun Zhang 0003, Ming Zhong 0005, Lei Li, Shansan Gong, Yao Luo, Jingjing Xu, Lingpeng Kong. [doi]
• GLOMA: Global Video Text Spotting with Morphological AssociationHan Wang, Yanjie Wang, Yang Li, Can Huang. [doi]
• Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory StitchingLei Yuan 0001, Yuqi Bian, Lihe Li, Ziqian Zhang, Cong Guan, Yang Yu 0001. [doi]
• PseDet: Revisiting the Power of Pseudo Label in Incremental Object DetectionQiuchen WANG, Zehui Chen, Chenhongyi Yang, Jiaming Liu, Zhenyu Li, Feng Zhao 0004. [doi]
• Lean-STaR: Learning to Interleave Thinking and ProvingHaohan Lin, Zhiqing Sun, Sean Welleck, Yiming Yang. [doi]
• Animate-X: Universal Character Image Animation with Enhanced Motion RepresentationShuai Tan, Biao Gong, Xiang Wang 0012, Shiwei Zhang 0001, Dandan Zheng, Ruobing Zheng, Kecheng Zheng, Jingdong Chen, Ming Yang 0007. [doi]
• ProtoSnap: Prototype Alignment For Cuneiform SignsRachel Mikulinsky, Morris Alper, Shai Gordin, Enrique Jiménez, Yoram Cohen, Hadar Averbuch-Elor. [doi]
• Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language ModelsOrion Weller, Benjamin Van Durme, Dawn J. Lawrie, Ashwin Paranjape, Yuhao Zhang, Jack Hessel. [doi]
• Dynamic Negative Guidance of Diffusion ModelsFelix Koulischer, Johannes Deleu, Gabriel Raya, Thomas Demeester, Luca Ambrogioni. [doi]
• WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language ModelingShengpeng Ji, Ziyue Jiang 0001, Wen Wang 0001, Yifu Chen, Minghui Fang 0002, Jialong Zuo, Qian Yang 0006, Xize Cheng, Zehan Wang 0001, Ruiqi Li, Ziang Zhang, Xiaoda Yang, Rongjie Huang 0001, Yidi Jiang, Qian Chen 0003, Siqi Zheng, Zhou Zhao 0001. [doi]
• Enhancing Graph Of Thought: Enhancing Prompts with LLM Rationales and Dynamic Temperature ControlSunguk Shin, Youngjoon Kim. [doi]
• Feedback Favors the Generalization of Neural ODEsJindou Jia, Zihan Yang, Meng Wang, Kexin Guo, Jianfei Yang, Xiang Yu 0003, Lei Guo 0003. [doi]
• Temporal Reasoning Transfer from Text to VideoLei Li 0039, Yuanxin Liu, Linli Yao, Peiyuan Zhang, Chenxin An, Lean Wang, Xu Sun 0001, Lingpeng Kong, Qi Liu 0049. [doi]
• EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout EditingKaizhi Zheng, Xiaotong Chen, Xuehai He, Jing Gu, Linjie Li, Zhengyuan Yang, Kevin Lin, Jianfeng Wang, Lijuan Wang, Xin Eric Wang. [doi]
• Structure Language Models for Protein Conformation GenerationJiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Chence Shi, Hongyu Guo, Yoshua Bengio, Jian Tang 0005. [doi]
• Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsHung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu. [doi]
• Sharpness-Aware Minimization: General Analysis and Improved RatesDimitris Oikonomou, Nicolas Loizou. [doi]
• Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization AnalysisHongkang Li, Songtao Lu, Pin-Yu Chen, Xiaodong Cui, Meng Wang. [doi]
• Uni-Sign: Toward Unified Sign Language Understanding at ScaleZecheng Li 0002, Wengang Zhou 0001, Weichao Zhao, Kepeng Wu, Hezhen Hu, Houqiang Li. [doi]
• Frame-Voyager: Learning to Query Frames for Video Large Language ModelsSicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun. [doi]
• Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context RelianceSachin Goyal, Christina Baek, J. Zico Kolter, Aditi Raghunathan. [doi]
• Towards Out-of-Modal Generalization without Instance-level Modal CorrespondenceZhuo Huang, Gang Niu 0001, Bo Han 0003, Masashi Sugiyama, Tongliang Liu. [doi]
• VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement LearningQingtao Liu, Yu Cui, Zhengnan Sun, Gaofeng Li, Jiming Chen 0001, Qi Ye. [doi]
• Towards a Complete Logical Framework for GNN ExpressivenessTuo Xu. [doi]
• GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene SupervisionZihui Zhang, Yafei Yang, Hongtao Wen, Bo Yang 0027. [doi]
• Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy LabelsZhizheng Liu, Joe Lin, Wayne Wu, Bolei Zhou. [doi]
• Periodic Materials Generation using Text-Guided Joint Diffusion ModelKishalay Das, Subhojyoti Khastagir, Pawan Goyal 0002, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly. [doi]
• Multi-Task Dense Predictions via Unleashing the Power of DiffusionYuqi Yang, Peng-Tao Jiang, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li. [doi]
• LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge DistillationFangxun Shu, Yue Liao, Lei Zhang, Le Zhuo, Chenning Xu, Guanghao Zhang, Haonan Shi, Long Chan, Tao Zhong, Zhelun Yu, Wanggui He, Siming FU, Haoyuan Li, Si Liu 0001, Hongsheng Li 0001, Hao Jiang. [doi]
• Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based SamplingYuma Ichikawa, Yamato Arai. [doi]
• Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement LearningXinsong Feng, Zihan Yu, Yanhai Xiong, Haipeng Chen. [doi]
• Causal Identification for Complex Functional Longitudinal StudiesAndrew Ying. [doi]
• Discriminating image representations with principal distortionsJenelle Feather, David Lipshutz, Sarah E. Harvey, Alex H. Williams, Eero P. Simoncelli. [doi]
• RMB: Comprehensively benchmarking reward models in LLM alignmentEnyu Zhou, Guodong Zheng, Binghai Wang, Zhiheng Xi, Shihan Dou, Rong Bao, Wei Shen, Limao Xiong, Jessica Fan, Yurong Mou, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang. [doi]
• TopoNets: High performing vision and language models with brain-like topographyMayukh Deb, Mainak Deb, N. Apurva Ratan Murty. [doi]
• MrT5: Dynamic Token Merging for Efficient Byte-level Language ModelsJulie Kallini, Shikhar Murty, Christopher D. Manning, Christopher Potts, Róbert Csordás. [doi]
• SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus SearchesHiroyuki Deguchi, Go Kamoda, Yusuke Matsushita 0004, Chihiro Taguchi, Kohei Suenaga, Masaki Waga, Sho Yokoi. [doi]
• Nonlinear Sequence Embedding by Monotone Variational InequalityJonathan Yuyang Zhou, Yao Xie. [doi]
• Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and BenchmarksZixuan Xiong, Guangwei Xu, Wenkai Zhang, Yuan Miao, Xuan Wu, LinHai, Ruijie Guo, Hai-Tao Zheng. [doi]
• Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous DrivingKairui Yang, Zihao Guo, Gengjie Lin, Haotian Dong, Zhao Huang, Yipeng Wu, Die Zuo, Jibin Peng, Ziyuan Zhong, Xin Wang 0118, Qing Guo 0005, Xiaosong Jia, Junchi Yan, Di Lin 0002. [doi]
• Is uniform expressivity too restrictive? Towards efficient expressivity of GNNsSammy Khalife, Josué Tonelli-Cueto. [doi]
• Lotus: Diffusion-based Visual Foundation Model for High-quality Dense PredictionJing He, Haodong Li, Wei Yin 0006, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chen. [doi]
• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor ReconstructionZiyu Tang, Weicai Ye, Yifan Wang, Di Huang, Hujun Bao, Tong He 0001, Guofeng Zhang 0001. [doi]
• SGD with memory: fundamental properties and stochastic accelerationDmitry Yarotsky, Maksim Velikanov. [doi]
• Expected Return SymmetriesDarius Muglich, Johannes Forkel, Elise van der Pol, Jakob Nicolaus Foerster. [doi]
• Large Language Models Assume People are More Rational than We Really areRyan Liu, Jiayi Geng, Joshua C. Peterson, Ilia Sucholutsky, Thomas L. Griffiths 0001. [doi]
• Test-Time Ensemble via Linear Mode Connectivity: A Path to Better AdaptationByungjai Kim, Chanho Ahn, Wissam J. Baddar, Kikyung Kim, Huijin Lee, Saehyun Ahn, Seungju Han, Sungjoo Suh, Eunho Yang. [doi]
• To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External ContextsYukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra. [doi]
• HARDMath: A Benchmark Dataset for Challenging Problems in Applied MathematicsJingxuan Fan, Sarah Martinson, Erik Y. Wang, Kaylie Hausknecht, Jonah Brenner, Danxian Liu, Nianli Peng, Corey Wang, Michael P. Brenner. [doi]
• Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential EquationsAbdolmehdi Behroozi, Chaopeng Shen, Daniel Kifer. [doi]
• Gramian Multimodal Representation Learning and AlignmentGiordano Cicchetti, Eleonora Grassucci, Luigi Sigillo, Danilo Comminiello. [doi]
• DocMIA: Document-Level Membership Inference Attacks against DocVQA ModelsKhanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas. [doi]
• AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly DetectionWei Dai, Jicong Fan 0001. [doi]
• Logically Consistent Language Models via Neuro-Symbolic IntegrationDiego Calanzone, Stefano Teso, Antonio Vergari. [doi]
• Improving Equivariant Networks with Probabilistic Symmetry BreakingHannah Lawrence, Vasco Portilheiro, Yan Zhang 0067, Sékou-Oumar Kaba. [doi]
• q-exponential family for policy optimizationLingwei Zhu, Haseeb Shah, Han Wang, Yukie Nagai, Martha White. [doi]
• On Evaluating the Durability of Safeguards for Open-Weight LLMsXiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson 0002. [doi]
• Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?Maxime Méloux, Silviu Maniu, François Portet, Maxime Peyrard. [doi]
• Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion DependencyJianwen Jiang, Chao Liang, Jiaqi Yang, Gaojie Lin, Tianyun Zhong, Yanbo Zheng. [doi]
• MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation ExpertsPeng Jin 0001, Bo Zhu, Li Yuan 0007, Shuicheng Yan. [doi]
• Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention LayersLei Chen 0062, Joan Bruna, Alberto Bietti. [doi]
• Biologically Constrained Barrel Cortex Model Integrates Whisker Inputs and Replicates Key Brain Network DynamicsTianfang Zhu, Dongli Hu, Jiandong Zhou, Kai Du, Anan Li. [doi]
• Composable Interventions for Language ModelsArinbjörn Kolbeinsson, Kyle O'Brien, Tianjin Huang, Shanghua Gao, Shiwei Liu 0003, Jonathan Richard Schwarz, Anurag Jayant Vaidya, Faisal Mahmood 0001, Marinka Zitnik, Tianlong Chen 0001, Thomas Hartvigsen. [doi]
• Truncated Consistency ModelsSangyun Lee, Yilun Xu, Tomas Geffner, Giulia Fanti, Karsten Kreis, Arash Vahdat, Weili Nie. [doi]
• NEAR: A Training-Free Pre-Estimator of Machine Learning Model PerformanceRaphael T. Husistein, Markus Reiher, Marco Eckhoff. [doi]
• Minimax Optimal Reinforcement Learning with Quasi-OptimismHarin Lee, Min-hwan Oh. [doi]
• VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?Xize Cheng, Ruofan Hu, Xiaoda Yang, Jingyu Lu, Dongjie Fu, Zehan Wang 0001, Shengpeng Ji, Rongjie Huang 0001, Boyang Zhang, Tao Jin 0004, Zhou Zhao 0001. [doi]
• Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward PassTong Chen, Hao Fang 0002, Patrick Xia, Xiaodong Liu 0003, Benjamin Van Durme, Luke Zettlemoyer, Jianfeng Gao 0001, Hao Cheng 0002. [doi]
• Efficient Active Imitation Learning with Random Network DistillationEmilien Biré, Anthony Kobanda, Ludovic Denoyer, Rémy Portelas. [doi]
• Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive ExtensionJiahan Li, Tong Chen, Shitong Luo, Chaoran Cheng, Jiaqi Guan, Ruihan Guo, Sheng Wang, Ge Liu, Jian Peng, Jianzhu Ma. [doi]
• Time-to-Event Pretraining for 3D Medical ImagingZepeng Frazier Huo, Jason Alan Fries, Alejandro Lozano, Jeya Maria Jose Valanarasu, Ethan Steinberg, Louis Blankemeier, Akshay S. Chaudhari, Curtis P. Langlotz, Nigam Shah. [doi]
• ST-GCond: Self-supervised and Transferable Graph Dataset CondensationBeining Yang, Qingyun Sun, Cheng Ji 0001, Xingcheng Fu, Jianxin Li 0002. [doi]
• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language ModelsMichael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron C. Courville. [doi]
• Implicit Neural Surface Deformation with Explicit Velocity FieldsLu Sang, Zehranaz Canfes, Dongliang Cao, Florian Bernard, Daniel Cremers. [doi]
• Layout-your-3D: Controllable and Precise 3D Generation with 2D BlueprintJunwei Zhou, Xueting Li, Lu Qi, Ming-Hsuan Yang 0001. [doi]
• LLMs Know More Than They Show: On the Intrinsic Representation of LLM HallucinationsHadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart, Idan Szpektor, Hadas Kotek, Yonatan Belinkov. [doi]
• A Deep Generative Learning Approach for Two-stage Adaptive Robust OptimizationAron Brenner, Rahman Khorramfar, Jennifer Z. Sun, Saurabh Amin. [doi]
• Constructing Confidence Intervals for Average Treatment Effects from Multiple DatasetsYuxin Wang, Maresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Stefan Feuerriegel. [doi]
• MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical ScienceErle Zhu, Yadi Liu, Zhe Zhang, Xujun Li, Jin Zhou, Xinjie Yu, Minlie Huang, Hongning Wang. [doi]
• HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech SynthesisYuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue. [doi]
• Training Free Exponential Context Extension via Cascading KV CacheJeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon, Sung Ju Hwang. [doi]
• Tackling Data Corruption in Offline Reinforcement Learning via Sequence ModelingJiawei Xu, Rui Yang 0010, Shuang Qiu, Feng Luo, Meng Fang, Baoxiang Wang 0001, Lei Han 0001. [doi]
• Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-TuningSomnath Basu Roy Chowdhury, Krzysztof Marcin Choromanski, Arijit Sehanobish, Kumar Avinava Dubey, Snigdha Chaturvedi. [doi]
• FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardwareKorbinian Pöppel, Maximilian Beck, Sepp Hochreiter. [doi]
• BodyGen: Advancing Towards Efficient Embodiment Co-DesignHaofei Lu, Zhe Wu, Junliang Xing, Jianshu Li, Ruoyu Li, Zhe Li, Yuanchun Shi. [doi]
• Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model UtilityMartin Kuo, Jingyang Zhang, Jianyi Zhang, Minxue Tang, Louis DiValentin, Aolin Ding, Jingwei Sun 0002, William Chen, Amin Hass, Tianlong Chen 0001, Yiran Chen 0001, Hai Li 0001. [doi]
• Cross-Embodiment Dexterous Grasping with Reinforcement LearningHaoqi Yuan, Bohan Zhou, Yuhui Fu 0004, Zongqing Lu 0002. [doi]
• VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot ManipulationWei Zhao, Pengxiang Ding, Zhang Min 0031, Zhefei Gong, Shuanghao Bai, Han Zhao 0008, Donglin Wang. [doi]
• Iformer: Integrating ConvNet and Transformer for Mobile ApplicationChuanyang Zheng. [doi]
• SPA: 3D Spatial-Awareness Enables Effective Embodied RepresentationHaoyi Zhu, Honghui Yang, Yating Wang, Jiange Yang, Limin Wang 0002, Tong He 0001. [doi]
• A Statistical Framework for Ranking LLM-based ChatbotsSiavash Ameli, Siyuan Zhuang, Ion Stoica, Michael W. Mahoney. [doi]
• Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space ModelsFusheng Liu, Qianxiao Li. [doi]
• Towards Domain Adaptive Neural Contextual BanditsZiyan Wang, Xiaoming Huo, Hao Wang 0014. [doi]
• Neural Phylogeny: Fine-Tuning Relationship Detection among Neural NetworksRunpeng Yu, Xinchao Wang. [doi]
• Controllable Generation via Locally Constrained ResamplingKareem Ahmed, Kai-Wei Chang, Guy Van den Broeck. [doi]
• CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMsJinpeng Li, Haiping Wang 0004, Jiabin Chen, Yuan Liu 0025, Zhiyang Dou, Yuexin Ma, Sibei Yang, Yuan Li, Wenping Wang, Zhen Dong 0005, Bisheng Yang. [doi]
• Generative Inbetweening: Adapting Image-to-Video Models for Keyframe InterpolationXiaojuan Wang, Boyang Zhou, Brian Curless, Ira Kemelmacher-Shlizerman, Aleksander Holynski, Steven M. Seitz. [doi]
• UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face RecognitionXiao Lin, Yuge Huang, Jianqing Xu, Yuxi Mi, Shuigeng Zhou, Shouhong Ding. [doi]
• What Matters in Learning from Large-Scale Datasets for Robot ManipulationVaibhav Saxena, Matthew Bronars, Nadun Ranawaka Arachchige, Kuancheng Wang, Woo-Chul Shin, Soroush Nasiriany, Ajay Mandlekar, Danfei Xu. [doi]
• SAMRefiner: Taming Segment Anything Model for Universal Mask RefinementYuqi Lin, Hengjia Li, Wenqi Shao, Zheng Yang 0008, Jun Zhao 0009, Xiaofei He 0001, Ping Luo 0002, Kaipeng Zhang. [doi]
• A Common Pitfall of Margin-based Language Model Alignment: Gradient EntanglementHui Yuan 0002, Yifan Zeng, Yue Wu, Huazheng Wang, Mengdi Wang, Liu Leqi. [doi]
• Beyond Random Augmentations: Pretraining with Hard ViewsFabio Ferreira, Ivo Rapant, Jörg K. H. Franke, Frank Hutter. [doi]
• Self-MoE: Towards Compositional Large Language Models with Self-Specialized ExpertsJunmo Kang, Leonid Karlinsky, Hongyin Luo, Zhen Wang 0041, Jacob A. Hansen, James R. Glass, David Daniel Cox, Rameswar Panda, Rogério Feris, Alan Ritter. [doi]
• Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio TestAkinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka. [doi]
• Few for Many: Tchebycheff Set Scalarization for Many-Objective OptimizationXi Lin 0001, Yilu Liu, Xiaoyuan Zhang, Fei Liu 0044, Zhenkun Wang 0001, Qingfu Zhang 0001. [doi]
• Gaussian-Based Instance-Adaptive Intensity Modeling for Point-Supervised Facial Expression SpottingYicheng Deng, Hideaki Hayashi, Hajime Nagahara. [doi]
• Learning stochastic dynamics from snapshots through regularized unbalanced optimal transportZhenyi Zhang, Tiejun Li, Peijie Zhou. [doi]
• PaCA: Partial Connection Adaptation for Efficient Fine-TuningSunghyeon Woo, Sol Namkung, SunWoo Lee, Inho Jeong, BeomSeok Kim, Dongsuk Jeon. [doi]
• TeaserGen: Generating Teasers for Long DocumentariesWeihan Xu, Paul Pu Liang, Haven Kim, Julian J. McAuley, Taylor Berg-Kirkpatrick, Hao-Wen Dong. [doi]
• Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language ModelsJung-Hyun Lee, June Yong Yang, Byeongho Heo, Dongyoon Han, Kyungsu Kim, Eunho Yang, Kang Min Yoo. [doi]
• Palmbench: a comprehensive Benchmark of Compressed Large Language Models on Mobile PlatformsYilong Li, Jingyu Liu, Hao Zhang, M. Badri Narayanan, Utkarsh Sharma, Shuai Zhang, Yijing Zeng, Jayaram Raghuram, Suman Banerjee 0001. [doi]
• Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise ClusteringZiyu Zhao 0001, Tao Shen 0002, Didi Zhu, Zexi Li 0001, Jing Su, Xuwu Wang, Fei Wu 0001. [doi]
• Learning Graph Invariance by Harnessing SpuriosityTianjun Yao, Yongqiang Chen 0002, Kai Hu 0010, Tongliang Liu, Kun Zhang 0001, Zhiqiang Shen. [doi]
• An Auditing Test to Detect Behavioral Shift in Language ModelsLeo Richter, Xuanli He, Pasquale Minervini, Matt J. Kusner. [doi]
• Identifiable Exchangeable Mechanisms for Causal Structure and Representation LearningPatrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel. [doi]
• Graph-based Document Structure AnalysisYufan Chen 0001, Ruiping Liu, Junwei Zheng, Di Wen 0006, Kunyu Peng, Jiaming Zhang 0001, Rainer Stiefelhagen. [doi]
• StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary SpacesKyeongmin Yeo, Jaihoon Kim, Minhyuk Sung. [doi]
• PostEdit: Posterior Sampling for Efficient Zero-Shot Image EditingFeng Tian, Yixuan Li, Yichao Yan, Shanyan Guan, Yanhao Ge, Xiaokang Yang 0001. [doi]
• Beyond Autoregression: Discrete Diffusion for Complex Reasoning and PlanningJiacheng Ye, Jiahui Gao, Shansan Gong, Lin Zheng, Xin Jiang, Zhenguo Li, Lingpeng Kong. [doi]
• Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language ModelsFushuo Huo, Wenchao Xu 0001, Zhong Zhang, Haozhao Wang, Zhicheng Chen, Peilin Zhao. [doi]
• Diffusion Models are Evolutionary AlgorithmsYanbo Zhang, Benedikt Hartl, Hananel Hazan, Michael Levin 0001. [doi]
• KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal ModelsEunice Yiu, Maan Qraitem, Anisa Noor Majhi, Charlie Wong, Yutong Bai, Shiry Ginosar, Alison Gopnik, Kate Saenko. [doi]
• Offline RL with Smooth OOD Generalization in Convex Hull and its NeighborhoodQingmao Yao, Zhichao Lei, Tianyuan Chen, Ziyue Yuan, Xuefan Chen, Jianxiang Liu, Faguo Wu, Xiao Zhang 0004. [doi]
• Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation CompressionSha Guo, Jing Chen, Zixuan Hu, Zhuo Chen 0006, Wenhan Yang, Yu Lin, Xing Jiang, Lingyu Duan. [doi]
• Multi-domain Distribution Learning for De Novo Drug DesignArne Schneuing, Ilia Igashov, Adrian W. Dobbelstein, Thomas Castiglione, Michael M. Bronstein, Bruno Correia. [doi]
• Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function ApproximationChenyu Zhang 0002, Xu Chen, Xuan Di. [doi]
• Self-Supervised Diffusion MRI Denoising via Iterative and Stable RefinementChenxu Wu, Qingpeng Kong, Zihang Jiang, S. Kevin Zhou. [doi]
• Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation LearningZijian Li 0001, Shunxing Fan, Yujia Zheng 0001, Ignavier Ng, Shaoan Xie, Guangyi Chen 0002, Xinshuai Dong, Ruichu Cai, Kun Zhang 0001. [doi]
• DICE: Data Influence Cascade in Decentralized LearningTongtian Zhu, Wenhao Li, Can Wang, Fengxiang He. [doi]
• DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily LifeYu-Ying Chiu, Liwei Jiang, Yejin Choi 0001. [doi]
• Multi-modal brain encoding models for multi-modal stimuliSubba Reddy Oota, Khushbu Pahwa, Mounika Marreddy, Maneesh Kumar Singh 0002, Manish Gupta 0001, Bapi Raju Surampudi. [doi]
• Effective post-training embedding compression via temperature control in contrastive trainingGeorgiana Dinu, Corey D. Barrett, Yi Xiang, Miguel Romero Calvo, Anna Currey, Xing Niu 0001. [doi]
• CausalRivers - Scaling up benchmarking of causal discovery for real-world time-seriesGideon Stein, Maha Shadaydeh, Jan Blunk, Niklas Penzel, Joachim Denzler. [doi]
• AutoG: Towards automatic graph construction from tabular dataZhikai Chen, Han Xie, Jian Zhang, Xiang Song 0003, Jiliang Tang, Huzefa Rangwala, George Karypis. [doi]
• Active Learning for Neural PDE SolversDaniel Musekamp, Marimuthu Kalimuthu, David Holzmüller, Makoto Takamoto, Mathias Niepert. [doi]
• Mufu: Multilingual Fused Learning for Low-Resource Translation with LLMZheng Wei Lim, Nitish Gupta, Honglin Yu, Trevor Cohn. [doi]
• Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave SamplingWei Guo, Molei Tao, Yongxin Chen. [doi]
• ControlAR: Controllable Image Generation with Autoregressive ModelsZongming Li, Tianheng Cheng, Shoufa Chen, Peize Sun, Haocheng Shen, Longjin Ran, Xiaoxin Chen 0001, Wenyu Liu 0001, Xinggang Wang. [doi]
• MTSAM: Multi-Task Fine-Tuning for Segment Anything ModelXuehao Wang, Zhan Zhuang, Feiyang Ye 0001, Yu Zhang 0006. [doi]
• Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI ResponsesDavid Glukhov, Ziwen Han, Ilia Shumailov, Vardan Papyan, Nicolas Papernot. [doi]
• Weak-to-Strong Generalization Through the Data-Centric LensChangho Shin, John Cooper, Frederic Sala. [doi]
• GEVRM: Goal-Expressive Video Generation Model For Robust Visual ManipulationHongyin Zhang, Pengxiang Ding, Shangke Lyu, Ying Peng, Donglin Wang. [doi]
• Identifiability for Gaussian Processes with Holomorphic KernelsAmeer Qaqish, Didong Li. [doi]
• TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric MeshesMinghao Guo, Bohan Wang, Kaiming He, Wojciech Matusik. [doi]
• Combining Induction and Transduction for Abstract ReasoningWen-Ding Li, Keya Hu, Carter Larsen, Yuqing Wu, Simon Alford, Caleb Woo, Spencer M. Dunn, Hao Tang 0008, Wei-Long Zheng, Yewen Pu, Kevin Ellis. [doi]
• ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron PruningRuchika Chavhan, Da Li 0001, Timothy M. Hospedales. [doi]
• Parameter and Memory Efficient Pretraining via Low-rank Riemannian OptimizationZhanfeng Mo, Long-Kai Huang, Sinno Jialin Pan. [doi]
• Matcha: Mitigating Graph Structure Shifts with Test-Time AdaptationWenxuan Bao, Zhichen Zeng 0001, Zhining Liu 0002, Hanghang Tong, Jingrui He. [doi]
• DOPL: Direct Online Preference Learning for Restless Bandits with Preference FeedbackGuojun Xiong, Ujwal Dinesha, Debajoy Mukherjee, Jian Li 0008, Srinivas Shakkottai. [doi]
• Meta Flow Matching: Integrating Vector Fields on the Wasserstein ManifoldLazar Atanackovic, Xi Zhang, Brandon Amos, Mathieu Blanchette, Leo J. Lee, Yoshua Bengio, Alexander Tong 0001, Kirill Neklyudov. [doi]
• PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass EstimationPablo Lemos, Sammy Nasser Sharief, Nikolay Malkin, Salma Salhi, Connor Stone, Laurence Perreault Levasseur, Yashar Hezaveh. [doi]
• Sylber: Syllabic Embedding Representation of Speech from Raw AudioCheol Jun Cho, Nicholas Lee, Akshat Gupta, Dhruv Agarwal 0005, Ethan Chen, Alan W. Black, Gopala Anumanchipalli. [doi]
• Hyper-ConnectionsDefa Zhu, Hongzhi Huang, Zihao Huang, Yutao Zeng, Yunyao Mao, Banggu Wu, Qiyang Min, Xun Zhou. [doi]
• Generalized Consistency Trajectory Models for Image ManipulationBeomsu Kim, Jaemin Kim, Jeongsol Kim, Jong Chul Ye. [doi]
• Mixture Compressor for Mixture-of-Experts LLMs Gains MoreWei Huang, Yue Liao, Jianhui Liu, Ruifei He, Haoru Tan, Shiming Zhang, Hongsheng Li 0001, Si Liu 0001, Xiaojuan Qi 0001. [doi]
• Transformer Encoder Satisfiability: Complexity and Impact on Formal ReasoningMarco Sälzer, Eric Alsmann, Martin Lange. [doi]
• Rethinking Light Decoder-based Solvers for Vehicle Routing ProblemsZiwei Huang, Jianan Zhou 0002, Zhiguang Cao, Yixin Xu. [doi]
• AI Sandbagging: Language Models can Strategically Underperform on EvaluationsTeun van der Weij, Felix Hofstätter, Oliver Jaffe, Samuel F. Brown, Francis Rhys Ward. [doi]
• TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation DataJeremy Andrew Irvin, Emily Ruoyu Liu, Joyce Chuyi Chen, Ines Dormoy, Jinyoung Kim, Samar Khanna, Zhuo Zheng, Stefano Ermon. [doi]
• Grounding by Trying: LLMs with Reinforcement Learning-Enhanced RetrievalSheryl Hsu, Omar Khattab, Chelsea Finn, Archit Sharma. [doi]
• GenXD: Generating Any 3D and 4D ScenesYuyang Zhao, Chung-Ching Lin, Kevin Lin, Zhiwen Yan, Linjie Li, Zhengyuan Yang, Jianfeng Wang, Gim Hee Lee, Lijuan Wang. [doi]
• Deep Compression Autoencoder for Efficient High-Resolution Diffusion ModelsJunyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Song Han 0003. [doi]
• Semantix: An Energy-guided Sampler for Semantic Style TransferHuiang He, Minghui Hu 0001, Chuanxia Zheng, Chaoyue Wang, Tat-Jen Cham. [doi]
• {τ}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World DomainsShunyu Yao, Noah Shinn, Pedram Razavi, Karthik R. Narasimhan. [doi]
• PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training RunsOskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman. [doi]
• Mechanism and Emergence of Stacked Attention Heads in Multi-Layer TransformersTiberiu Musat. [doi]
• Multi-session, multi-task neural decoding from distinct cell-types and brain regionsMehdi Azabou, Krystal Xuejing Pan, Vinam Arora, Ian Jarratt Knight, Eva L. Dyer, Blake Aaron Richards. [doi]
• You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANsYihong Luo, Xiaolong Chen, Xinghua Qu, Tianyang Hu, Jing Tang. [doi]
• Image and Video Tokenization with Binary Spherical QuantizationYue Zhao 0006, Yuanjun Xiong, Philipp Krähenbühl. [doi]
• Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement LearningHaoxin Lin, Yu-Yan Xu, Yihao Sun, Zhilong Zhang, Yi-Chen Li 0001, Chengxing Jia, Junyin Ye, Jiaji Zhang, Yang Yu 0001. [doi]
• Persistent Pre-training Poisoning of LLMsYiming Zhang, Javier Rando, Ivan Evtimov, Jianfeng Chi, Eric Michael Smith, Nicholas Carlini, Florian Tramèr, Daphne Ippolito. [doi]
• Mm-Embed: Universal Multimodal Retrieval with Multimodal LLMSSheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, Wei Ping. [doi]
• Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear ProgrammingQian Li, Minghui Ouyang, Tian Ding, Yuyi Wang, Qingjiang Shi, Ruoyu Sun 0001. [doi]
• Graph Sparsification via Mixture of GraphsGuibin Zhang, Xiangguo Sun, Yanwei Yue, Chonghe Jiang, Kun Wang, Tianlong Chen, Shirui Pan. [doi]
• Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution EstimationRong Tang, Lizhen Lin, Yun Yang. [doi]
• Long-Context Linear System IdentificationOguz Kaan Yüksel, Mathieu Even, Nicolas Flammarion. [doi]
• The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political DiscussionsStefan Sylvius Wagner, Maike Behrendt, Marc Ziegele, Stefan Harmeling. [doi]
• PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural NetworksYoun-Yeol Yu, Jeongwhan Choi 0002, Jaehyeon Park, Kookjin Lee, Noseong Park. [doi]
• Adversarial Mixup UnlearningZhuoyi Peng, Yixuan Tang, Yi Yang 0042. [doi]
• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of ExpertsXiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, Ming Jin. [doi]
• Inverse Rendering using Multi-Bounce Path Tracing and Reservoir SamplingYuxin Dai, Qi Wang, Jingsen Zhu, Dianbing Xi, Yuchi Huo, Chen Qian 0006, Ying He 0001. [doi]
• Learning Spatiotemporal Dynamical Systems from Point Process ObservationsValerii Iakovlev, Harri Lähdesmäki. [doi]
• ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation GroundingIndraneil Paul, Haoyi Yang, Goran Glavas, Kristian Kersting, Iryna Gurevych. [doi]
• Bridging Compressed Image Latents and Multimodal Large Language ModelsChia-Hao Kao, Cheng Chien, Yu-Jen Tseng, Yi-Hsin Chen, Alessandro Gnutti, Shao-Yuan Lo, Wen-Hsiao Peng, Riccardo Leonardi. [doi]
• Contrastive Learning from Synthetic Audio DoppelgängersManuel Cherep, Nikhil Singh 0003. [doi]
• MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuningHaotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang, et al.. [doi]
• Improving Deep Regression with TightnessShihao Zhang, Yuguang Yan, Angela Yao. [doi]
• Optimizing Neural Network Representations of Boolean NetworksJoshua Russell, Ignacio Gavier, Devdhar Patel, Edward A. Rietman, Hava T. Siegelmann. [doi]
• Efficient Cross-Episode Meta-RLGresa Shala, André Biedenkapp, Pierre Krack, Florian Walter, Josif Grabocka. [doi]
• BinaryDM: Accurate Weight Binarization for Efficient Diffusion ModelsXingyu Zheng, Xianglong Liu 0001, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai Wang, Zixiang Zhao, Jinyang Guo, Michele Magno. [doi]
• MMTEB: Massive Multilingual Text Embedding BenchmarkKenneth C. Enevoldsen, Isaac Chung, Imene Kerboua, Márton Kardos, Ashwin Mathur, David Stap, Jay Gala, Wissam Siblini, Dominik Krzeminski, Genta Indra Winata, Saba Sturua, Saiteja Utpala, Mathieu Ciancone, Marion Schaeffer, Diganta Misra, Shreeya Dhakal, Jonathan Rystrøm, Roman Solomatin, Ömer Veysel Çagatan, Akash Kundu, et al.. [doi]
• Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted PhenomenonUSVSN Sai Prashanth, Alvin Deng, Kyle O'Brien, Jyothir S. V, Mohammad Aflah Khan, Jaydeep Borkar, Christopher A. Choquette-Choo, Jacob Ray Fuehne, Stella Biderman, Tracy Ke, Katherine Lee, Naomi Saphra. [doi]
• Subtask-Aware Visual Reward Learning from Segmented DemonstrationsChangyeon Kim, Minho Heo, Doohyun Lee, Honglak Lee, Jinwoo Shin, Joseph J. Lim, Kimin Lee. [doi]
• Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy HessiansIshan Amin, Sanjeev Raja, Aditi S. Krishnapriyan. [doi]
• DreamDistribution: Learning Prompt Distribution for Diverse In-distribution GenerationBrian Nlong Zhao, Yuhang Xiao, Jiashu Xu, Xinyang Jiang, Yifan Yang 0004, Dongsheng Li 0002, Laurent Itti, Vibhav Vineet, Yunhao Ge. [doi]
• Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIsThomas Pethick, Ioannis Mavrothalassitis, Volkan Cevher. [doi]
• Learning Geometric Reasoning Networks For Robot Task And Motion PlanningSmail Ait Bouhsain, Rachid Alami 0001, Thierry Siméon. [doi]
• Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific NeuronYiran Zhao 0006, Wenxuan Zhang 0001, Yuxi Xie, Anirudh Goyal, Kenji Kawaguchi, Michael Shieh. [doi]
• When Selection Meets Intervention: Additional Complexities in Causal DiscoveryHaoyue Dai, Ignavier Ng, Jianle Sun, Zeyu Tang 0002, Gongxu Luo, Xinshuai Dong, Peter Spirtes, Kun Zhang. [doi]
• Group Ligands Docking to Protein PocketsJiaqi Guan, Jiahan Li, Xiangxin Zhou, Xingang Peng, Sheng Wang 0001, Yunan Luo, Jian Peng 0001, Jianzhu Ma. [doi]
• How Does Critical Batch Size Scale in Pre-training?Hanlin Zhang, Depen Morwani, Nikhil Vyas 0001, Jingfeng Wu, Difan Zou, Udaya Ghai, Dean P. Foster, Sham M. Kakade. [doi]
• MamBEV: Enabling State Space Models to Learn Birds-Eye-View RepresentationsHongyu Ke, Jack Morris, Kentaro Oguchi 0001, Xiaofei Cao, Yongkang Liu 0005, Haoxin Wang, Yi Ding. [doi]
• Small-to-Large Generalization: Training Data Influences Models Consistently Across ScaleAlaa Khaddaj, Logan Engstrom, Aleksander Madry. [doi]
• High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian RepresentationZiye Wang, Yiran Qin, Lin Zeng, Ruimao Zhang. [doi]
• Delta: Dense Efficient Long-Range 3D tracking for any videoTuan Duc Ngo, Peiye Zhuang, Evangelos Kalogerakis, Chuang Gan, Sergey Tulyakov, Hsin-Ying Lee 0001, Chaoyang Wang 0001. [doi]
• Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume MinimizationYuChen Sun, Kejun Huang. [doi]
• Synthetic continued pretrainingZitong Yang, Neil Band, Shuangping Li, Emmanuel J. Candès, Tatsunori Hashimoto. [doi]
• The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language ModelJiawei Chen 0011, Wentao Chen, Jing Su, Jingjing Xu, Hongyu Lin, Mengjie Ren, Yaojie Lu 0001, Xianpei Han, Le Sun 0001. [doi]
• Bayesian Optimization via Continual Variational Last Layer TrainingPaul Brunzema, Mikkel Jordahn, John Willes, Sebastian Trimpe, Jasper Snoek, James Harrison. [doi]
• Boosting Methods for Interval-censored Data with Regression and ClassificationYuan Bian 0005, Grace Y. Yi, Wenqing He. [doi]
• Action Sequence Augmentation for Action AnticipationYihui Qiu, Deepu Rajan. [doi]
• Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial DecodersQichao Shentu, Beibu Li, Kai Zhao 0009, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang 0002, Chenjuan Guo. [doi]
• DeeperForward: Enhanced Forward-Forward Training for Deeper and Better PerformanceLiang Sun, Yang Zhang 0012, Weizhao He, Jiajun Wen 0001, LinLin Shen, Weicheng Xie 0001. [doi]
• Multimodality Helps Few-shot 3D Point Cloud Semantic SegmentationZhaochong An, Guolei Sun, Yun Liu 0011, Runjia Li, Min Wu 0008, Ming-Ming Cheng, Ender Konukoglu, Serge J. Belongie. [doi]
• Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed GraphsLevi Rauchwerger, Stefanie Jegelka, Ron Levie. [doi]
• UniGS: Unified Language-Image-3D Pretraining with Gaussian SplattingHaoyuan Li, Yanpeng Zhou, Tao Tang, Jifei Song, Yihan Zeng, Michael Kampffmeyer, Hang Xu 0004, Xiaodan Liang. [doi]
• Neural Wave Equation for Irregularly Sampled Sequence DataArkaprava Majumdar, M. Anand Krishna, P. K. Srijith. [doi]
• Chain-of-Action: Faithful and Multimodal Question Answering through Large Language ModelsZhenyu Pan, Haozheng Luo, Manling Li, Han Liu 0001. [doi]
• ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger BridgeEslam Mohamed Bakr, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord, Patrick Pérez, Mohamed Elhoseiny. [doi]
• FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence InferenceXunhao Lai, Jianqiao Lu, Yao Luo, Yiyuan Ma, Xun Zhou. [doi]
• Adversarial Search Engine Optimization for Large Language ModelsFredrik Nestaas, Edoardo Debenedetti, Florian Tramèr. [doi]
• Scaling Wearable Foundation ModelsGirish Narayanswamy, Xin Liu 0034, Kumar Ayush, Yuzhe Yang 0003, Xuhai Xu, Shun Liao, Jake Garrison, Shyam A. Tailor, Jacob E. Sunshine, Yun Liu 0013, Tim Althoff, Shrikanth Narayanan, Pushmeet Kohli, Jiening Zhan, Mark Malhotra, Shwetak N. Patel, Samy Abdel-Ghaffar, Daniel McDuff. [doi]
• Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across DomainsRazmik Arman Khosrovian, Takaharu Yaguchi, Hiroaki Yoshimura, Takashi Matsubara 0001. [doi]
• Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation CorrentropyMingyang Zhao 0001, Gaofeng Meng, Dong-Ming Yan 0001. [doi]
• MuPT: A Generative Symbolic Music Pretrained TransformerXingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, Xeron Du, Shuyue Guo, Yiming Liang, Yizhi Li, Shangda Wu, Junting Zhou, Tianyu Zheng, Ziyang Ma, Fengze Han, Wei Xue, et al.. [doi]
• When does compositional structure yield compositional generalization? A kernel theorySamuel Lippl, Kim Stachenfeld. [doi]
• Exact Computation of Any-Order Shapley Interactions for Graph Neural NetworksMaximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto, Janine Strotherm, Luca Hermes, Alessandro Sperduti, Eyke Hüllermeier, Barbara Hammer. [doi]
• Temporal Heterogeneous Graph Generation with Privacy, Utility, and EfficiencyXinyu He 0003, Dongqi Fu, Hanghang Tong, Ross Maciejewski, Jingrui He. [doi]
• SCBench: A KV Cache-Centric Analysis of Long-Context MethodsYucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao 0001, Yuqing Yang 0001, Lili Qiu. [doi]
• RankSHAP: Shapley Value Based Feature Attributions for Learning to RankTanya Chowdhury, Yair Zick, James Allan. [doi]
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive RetrievalHongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-Yu Wang, Haisu Liu, Quan Shi, Zachary S. Siegel, Michael Tang, Ruoxi Sun 0002, Jinsung Yoon, Sercan Ö. Arik, Danqi Chen 0001, Tao Yu 0009. [doi]
• MMEgo: Towards Building Egocentric Multimodal LLMs for Video QAHanrong Ye, Haotian Zhang, Erik A. Daxberger, Lin Chen 0010, Zongyu Lin, Yanghao Li, Bowen Zhang 0002, Haoxuan You, Dan Xu 0002, Zhe Gan, Jiasen Lu, Yinfei Yang. [doi]
• Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language ModelsJun Luo 0010, Chen Chen 0001, Shandong Wu. [doi]
• Enhancing Language Model Agents using Diversity of ThoughtsVijay Lingam, Behrooz Omidvar Tehrani, Sujay Sanghavi, Gaurav Gupta, Sayan Ghosh, Linbo Liu, Jun Huan, Anoop Deoras. [doi]
• Bridging Jensen Gap for Max-Min Group Fairness Optimization in RecommendationChen Xu 0010, Yuxin Li, Wenjie Wang 0007, Liang Pang, Jun Xu 0001, Tat-Seng Chua. [doi]
• Generalized Behavior Learning from Diverse DemonstrationsVarshith Sreeramdass, Rohan R. Paleja, Letian Chen, Sanne van Waveren, Matthew C. Gombolay. [doi]
• Simplifying, Stabilizing and Scaling Continuous-time Consistency ModelsCheng Lu, Yang Song. [doi]
• LICO: Large Language Models for In-Context Molecular OptimizationTung Nguyen, Aditya Grover. [doi]
• A Watermark for Order-Agnostic Language ModelsRuibo Chen, Yihan Wu, Yanshuo Chen, Chenxi Liu, Junfeng Guo, Heng Huang. [doi]
• NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule GenerationZhiyuan Liu 0001, Yanchen Luo, Han Huang, Enzhi Zhang, Sihang Li 0002, Junfeng Fang, Yaorui Shi, Xiang Wang 0010, Kenji Kawaguchi, Tat-Seng Chua. [doi]
• WardropNet: Traffic Flow Predictions via Equilibrium-Augmented LearningKai Jungel, Dario Paccagnan, Axel Parmentier, Maximilian Schiffer. [doi]
• CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired TransformerYang Liu, Zinan Zheng, Jiashun Cheng, Fugee Tsung, Deli Zhao, Yu Rong 0001, Jia Li. [doi]
• Instructional Segment Embedding: Improving LLM Safety with Instruction HierarchyTong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang 0001, Prateek Mittal, Wenxuan Zhou. [doi]
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed ImagesBotao Ye, Sifei Liu, Haofei Xu, Xueting Li, Marc Pollefeys, Ming-Hsuan Yang 0001, Songyou Peng. [doi]
• Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and ModalitiesYichen Wang, Yiyi Zhang, Xinhao Hu, Li Niu 0002, Jianfu Zhang 0003, Yasushi Makihara, Yasushi Yagi, Pai Peng, Wenlong Liao, Tao He, Junchi Yan, Liqing Zhang 0001. [doi]
• Quantum (Inspired) D2-sampling with ApplicationsPoojan Chetan Shah, Ragesh Jaiswal. [doi]
• Neural Causal Graph for Interpretable and Intervenable ClassificationJiawei Wang 0025, Shaofei Lu, Da Cao, Dongyu Wang, Yuquan Le, Zhe Quan, Tat-Seng Chua. [doi]
• ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene ImaginationXinxin Zhao, Wenzhe Cai, Likun Tang, Teng Wang. [doi]
• Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image UnderstandingZhongyi Shui, Jianpeng Zhang, Weiwei Cao, Sinuo Wang, Ruizhe Guo, Le Lu 0001, Lin Yang, Xianghua Ye, Tingbo Liang, Qi Zhang, Ling Zhang. [doi]
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex InstructionsTerry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu 0002, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen Gong 0005, James Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Zhihan Zhang 0001, Prateek Yadav, et al.. [doi]
• Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inferenceKe Yi 0003, Zengke Liu, Jianwei Zhang 0012, Chengyuan Li, Tong Zhang 0015, Junyang Lin, Jingren Zhou 0001. [doi]
• Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsAndrea Tirinzoni, Ahmed Touati, Jesse Farebrother, Mateusz Guzek, Anssi Kanervisto, Yingchen Xu, Alessandro Lazaric, Matteo Pirotta. [doi]
• Node-Time Conditional Prompt Learning in Dynamic GraphsXingtong Yu, Zhenghao Liu, Xinming Zhang, Yuan Fang. [doi]
• Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL AssortmentAadirupa Saha, Pierre Gaillard. [doi]
• CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmarkJian Wu, Linyi Yang, Zhen Wang, Manabu Okumura, Yue Zhang. [doi]
• Dreamweaver: Learning Compositional World Models from PixelsJunyeob Baek, Yi-Fu Wu, Gautam Singh, Sungjin Ahn. [doi]
• CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback DisentanglementAming Wu, Cheng Deng. [doi]
• Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation DynamicsAlexander Tyurin. [doi]
• DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human ReferencesXueyi Liu, Jianibieke Adalibieke, Qianwei Han, Yuzhe Qin, Li Yi 0001. [doi]
• Enhancing Pre-trained Representation Classifiability can Boost its InterpretabilityShufan Shen, Zhaobo Qi, Junshu Sun, Qingming Huang, Qi Tian 0001, Shuhui Wang. [doi]
• Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningChongyi Zheng, Jens Tuyls, Joanne Peng, Benjamin Eysenbach. [doi]
• Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a PosteriorTongda Xu, Xiyan Cai, Xinjie Zhang, Xingtong Ge, Dailan He, Ming Sun, Jingjing Liu, Ya-Qin Zhang, Jian Li, Yan Wang. [doi]
• CBMA: Improving Conformal Prediction through Bayesian Model AveragingPankaj Bhagwat, Linglong Kong, Bei Jiang. [doi]
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language ModelsJiale Cheng, Xiao Liu, Cunxiang Wang, Xiaotao Gu, Yida Lu, Dan Zhang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang. [doi]
• Robustness Auditing for Linear Regression: To Singularity and BeyondIttai Rubinstein, Samuel B. Hopkins. [doi]
• Counterfactual Generative Modeling with Variational Causal InferenceYulun Wu, Louie McConnell, Claudia Iriondo. [doi]
• Differentiable and Learnable Wireless Simulation with Geometric TransformersThomas Hehn 0001, Markus Peschl, Tribhuvanesh Orekondy, Arash Behboodi, Johann Brehmer. [doi]
• Personality Alignment of Large Language ModelsMinjun Zhu, Yixuan Weng, Linyi Yang, Yue Zhang 0004. [doi]
• An Empirical Analysis of Uncertainty in Large Language Model EvaluationsQiujie Xie, Qingqiu Li, Zhuohao Yu, Yuejie Zhang, Yue Zhang 0004, Linyi Yang. [doi]
• LoLCATs: On Low-Rank Linearizing of Large Language ModelsMichael Zhang, Simran Arora, Rahul Chalamala, Benjamin Frederick Spector, Alan Wu, Krithik Ramesh, Aaryan Singhal, Christopher Ré. [doi]
• Navigation-Guided Sparse Scene Representation for End-to-End Autonomous DrivingPeidong Li, Dixiao Cui. [doi]
• Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt TuningYilun Li, MiaoMiao Cheng, Xu Han, Wei Song. [doi]
• SmartRAG: Jointly Learn RAG-Related Tasks From the Environment FeedbackJingsheng Gao, Linxu Li, Ke-ji, Weiyuan Li, Yixin Lian, Yuzhuo Fu, Bin Dai. [doi]
• Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-TrainingMaximillian Chen, Ruoxi Sun 0002, Tomas Pfister, Sercan Ö. Arik. [doi]
• Studying the Interplay Between the Actor and Critic Representations in Reinforcement LearningSamuel Garcin, Trevor McInroe, Pablo Samuel Castro, Christopher G. Lucas, David Abel, Prakash Panangaden, Stefano V. Albrecht. [doi]
• Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient ClippingZijian Liu, Zhengyuan Zhou. [doi]
• Revisit the Open Nature of Open Vocabulary Semantic SegmentationQiming Huang, Han Hu, Jianbo Jiao. [doi]
• Provable Convergence and Limitations of Geometric Tempering for Langevin DynamicsOmar Chehab, Anna Korba, Austin J. Stromme, Adrien Vacher. [doi]
• Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated LearningMingyuan Fan 0003, Zhanyi Hu, Fuyi Wang, Cen Chen 0001. [doi]
• Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision ProcessesJongmin Lee, Ernest K. Ryu. [doi]
• Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance SegmentationMohamed El Amine Boudjoghra, Angela Dai, Jean Lahoud, Hisham Cholakkal, Rao Muhammad Anwer, Salman H. Khan 0001, Fahad Shahbaz Khan. [doi]
• On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking FunctionsOmer Madmon, Idan Pipano, Itamar Reinman, Moshe Tennenholtz. [doi]
• Representative Guidance: Diffusion Model Sampling with CoherenceAnh-Dung Dinh, Daochang Liu, Chang Xu 0002. [doi]
• Post-hoc Reward Calibration: A Case Study on Length BiasZeyu Huang, Zihan Qiu, Zili Wang, Edoardo M. Ponti, Ivan Titov. [doi]
• Physics-informed Temporal Difference Metric Learning for Robot Motion PlanningRuiqi Ni, Zherong Pan, Ahmed H. Qureshi. [doi]
• Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised LearningRuikun Li 0002, Huandong Wang, Qingmin Liao, Yong Li 0008. [doi]
• Improving Graph Neural Networks by Learning Continuous Edge DirectionsSeong Ho Pahng, Sahand Hormoz. [doi]
• Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMsAldo Pareja, Nikhil Shivakumar Nayak, Hao Wang, KrishnaTeja Killamsetty, Shivchander Sudalairaj, Wenlong Zhao 0001, Seungwook Han, Abhishek Bhandwaldar, Guangxuan Xu, Kai Xu 0016, Ligong Han, Luke Inglis, Akash Srivastava. [doi]
• Diffusion-Based Planning for Autonomous Driving with Flexible GuidanceYinan Zheng, Ruiming Liang, Kexin Zheng, Jinliang Zheng, Liyuan Mao, Jianxiong Li, Weihao Gu, Rui Ai 0001, Shengbo Eben Li, Xianyuan Zhan, Jingjing Liu. [doi]
• Revisiting In-context Learning Inference Circuit in Large Language ModelsHakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue. [doi]
• HOPE for a Robust Parameterization of Long-memory State Space ModelsAnnan Yu, Michael W. Mahoney, N. Benjamin Erichson. [doi]
• Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution DetectionYingwen Wu, Ruiji Yu, Xinwen Cheng, Zhengbao He, Xiaolin Huang. [doi]
• How many samples are needed to train a deep neural network?Pegah Golestaneh, Mahsa Taheri, Johannes Lederer. [doi]
• Vector-ICL: In-context Learning with Continuous Vector RepresentationsYufan Zhuang, Chandan Singh, Liyuan Liu, Jingbo Shang, Jianfeng Gao 0001. [doi]
• JudgeBench: A Benchmark for Evaluating LLM-Based JudgesSijun Tan, Siyuan Zhuang, Kyle Montgomery, William Yuan Tang, Alejandro Cuadron, Chenguang Wang 0001, Raluca A. Popa, Ion Stoica. [doi]
• Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain TrajectoriesVasiliki Tassopoulou, Haochang Shou, Christos Davatzikos. [doi]
• Logical Consistency of Large Language Models in Fact-CheckingBishwamittra Ghosh, Sarah Hasan, Naheed Anjum Arafat, Arijit Khan 0001. [doi]
• Training-free Camera Control for Video GenerationChen Hou, Zhibo Chen 0001. [doi]
• OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in CodeMaxence Faldor, Jenny Zhang, Antoine Cully, Jeff Clune. [doi]
• Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask LearningMoritz Reuss, Jyothish Pari, Pulkit Agrawal 0001, Rudolf Lioutikov. [doi]
• Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language ModelsQiong Wu 0012, Zhaoxi Ke, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji. [doi]
• Can We Ignore Labels in Out of Distribution Detection?Hong Yang, Qi Yu 0001, Travis Desell. [doi]
• Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret LearningYuheng Zhang, Dian Yu 0001, Baolin Peng, Linfeng Song, Ye Tian, Mingyue Huo, Nan Jiang 0008, Haitao Mi, Dong Yu 0001. [doi]
• Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity DocumentsHaoyu Wang, Sunhao Dai, Haiyuan Zhao, Liang Pang, Xiao Zhang 0034, Gang Wang, Zhenhua Dong, Jun Xu 0001, Ji-Rong Wen. [doi]
• NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model InternalsJaden Fried Fiotto-Kaufman, Alexander Russell Loftus, Eric Todd, Jannik Brinkmann, Koyena Pal, Dmitrii Troitskii, Michael Ripa, Adam Belfki, Can Rager, Caden Juang, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Nikhil Prakash, Carla E. Brodley, Arjun Guha, Jonathan Bell 0001, Byron C. Wallace, David Bau. [doi]
• Bootstrapping Language Models with DPO Implicit RewardsChangyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu 0012, Arunesh Sinha, Pradeep Varakantham, Min Lin. [doi]
• Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model EnsemblesBuu Phan, Brandon Amos, Itai Gat, Marton Havasi, Matthew J. Muckley, Karen Ullrich. [doi]
• Chain-of-region: Visual Language Models Need Details for Diagram AnalysisXue Li, Yiyou Sun, Wei Cheng 0002, Yinglun Zhu, Haifeng Chen. [doi]
• Jamba: Hybrid Transformer-Mamba Language ModelsBarak Lenz, Opher Lieber, Alan Arazi, Amir Bergman, Avshalom Manevich, Barak Peleg, Ben Aviram, Chen Almagor, Clara Fridman, Dan Padnos, Daniel Gissin, Daniel Jannai, Dor Muhlgay, Dor Zimberg, Edden M. Gerber, Elad Dolev, Eran Krakovsky, Erez Safahi, Erez Schwartz, Gal Cohen, et al.. [doi]
• MUSE: Machine Unlearning Six-Way Evaluation for Language ModelsWeijia Shi, Jaechan Lee, Yangsibo Huang, Sadhika Malladi, Jieyu Zhao 0001, Ari Holtzman, Daogao Liu, Luke Zettlemoyer, Noah A. Smith, Chiyuan Zhang. [doi]
• P-Spikessm: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency TasksMalyaban Bal, Abhronil Sengupta. [doi]
• HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual AdaptersYujie Mo, Runpeng Yu, Xiaofeng Zhu 0001, Xinchao Wang. [doi]
• Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-offFuta Kai Waseda, Ching-Chun Chang, Isao Echizen. [doi]
• SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View ConsistencyYiming Xie, Chun-Han Yao, Vikram Voleti, Huaizu Jiang, Varun Jampani. [doi]
• Self-Play Preference Optimization for Language Model AlignmentYue Wu, Zhiqing Sun, Huizhuo Yuan, Kaixuan Ji, Yiming Yang, Quanquan Gu. [doi]
• Token Statistics Transformer: Linear-Time Attention via Variational Rate ReductionZiyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong Yu, Yi Ma 0001, Benjamin David Haeffele. [doi]
• Towards Interpreting Visual Information Processing in Vision-Language ModelsClement Neo, Luke Ong, Philip Torr 0001, Mor Geva, David Krueger 0001, Fazl Barez. [doi]
• MiniPLM: Knowledge Distillation for Pre-training Language ModelsYuxian Gu, Hao Zhou, Fandong Meng, Jie Zhou, Minlie Huang. [doi]
• Context-Alignment: Activating and Enhancing LLMs Capabilities in Time SeriesYuxiao Hu 0003, Qian Li, Dongxiao Zhang, Jinyue Yan, Yuntian Chen. [doi]
• An Engorgio Prompt Makes Large Language Model Babble onJianshuo Dong, Ziyuan Zhang, Qingjie Zhang, Tianwei Zhang 0004, Hao Wang 0003, Hewu Li, Qi Li 0002, Chao Zhang 0008, Ke Xu 0002, Han Qiu 0001. [doi]
• Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural NetworksOuns El Harzli, Bernardo Cuenca Grau. [doi]
• What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian AnalysisWeronika Ormaniec, Felix Dangel, Sidak Pal Singh. [doi]
• Model merging with SVD to tie the KnotsGeorge Stoica, Pratik Ramesh, Boglarka Ecsedi, Leshem Choshen, Judy Hoffman. [doi]
• SpinQuant: LLM Quantization with Learned RotationsZechun Liu, Changsheng Zhao 0002, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort. [doi]
• Conformal Language Model Reasoning with Coherent FactualityMaxon Rubin-Toles, Maya Gambhir, Keshav Ramji, Aaron Roth 0001, Surbhi Goel. [doi]
• Montessori-Instruct: Generate Influential Training Data Tailored for Student LearningXiaochuan Li, Zichun Yu, Chenyan Xiong. [doi]
• Breaking Free from MMI: A New Frontier in Rationalization by Probing Input UtilizationWei Liu, Zhiying Deng, Zhongyu Niu, Jun Wang, Haozhao Wang, Zhigang Zeng, Ruixuan Li 0001. [doi]
• Improving Pretraining Data Using Perplexity CorrelationsTristan Thrush, Christopher Potts, Tatsunori Hashimoto. [doi]
• NextBestPath: Efficient 3D Mapping of Unseen EnvironmentsShiyao Li, Antoine Guédon, Clémentin Boittiaux, Shizhe Chen, Vincent Lepetit. [doi]
• PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative ModelsKyeongkook Seo, Dong-Jun Han, Jaejun Yoo. [doi]
• Locally Connected Echo State Networks for Time Series ForecastingFilip Matzner, Frantisek Mráz. [doi]
• FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMsZhiting Fan, Ruizhe Chen, Tianxiang Hu, Zuozhu Liu. [doi]
• Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete GeneratorsAriel Elnekave, Yair Weiss. [doi]
• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingWenda Xu, Rujun Han, Zifeng Wang 0002, Long T. Le, Dhruv Madeka, Lei Li 0005, William Yang Wang, Rishabh Agarwal, Chen-Yu Lee, Tomas Pfister. [doi]
• Can Transformers Do Enumerative Geometry?Baran Hashemi, Roderic Guigo Corominas, Alessandro Giacchetto. [doi]
• Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain ModelYaxuan Huang, Xili Dai, Jianan Wang, Xianbiao Qi, Yixing Yuan, Xiangyu Yue 0001. [doi]
• Beyond Random Masking: When Dropout meets Graph Convolutional NetworksYuankai Luo, Xiao-Ming Wu 0003, Hao Zhu. [doi]
• Prompting Fairness: Integrating Causality to Debias Large Language ModelsJingling Li, Zeyu Tang 0002, Xiaoyu Liu, Peter Spirtes, Kun Zhang, Liu Leqi, Yang Liu. [doi]
• TopoLM: brain-like spatio-functional organization in a topographic language modelNeil Rathi, Johannes Mehrer, Badr AlKhamissi, Taha Osama A Binhuraib, Nicholas M. Blauch, Martin Schrimpf. [doi]
• Inverse decision-making using neural amortized Bayesian actorsDominik Straub, Tobias F. Niehues, Jan Peters 0001, Constantin A. Rothkopf. [doi]
• CG-Bench: Clue-grounded Question Answering Benchmark for Long Video UnderstandingGuo Chen 0006, Yicheng Liu, Yifei Huang 0002, Baoqi Pei, Jilan Xu, Yuping He, Tong Lu, Yali Wang 0001, Limin Wang 0002. [doi]
• One for all and all for one: Efficient computation of partial Wasserstein distances on the lineLaetitia Chapel, Romain Tavenard. [doi]
• Interference Among First-Price Pacing Equilibria: A Bias and Variance AnalysisLuofeng Liao, Christian Kroer, Sergei Leonenkov, Okke Schrijvers, Liang Shi, Nicolás Stier Moses, Congshan Zhang. [doi]
• InstaRevive: One-Step Image Enhancement via Dynamic Score MatchingYixuan Zhu, Haolin Wang, Ao Li, Wenliang Zhao, Yansong Tang, Jingxuan Niu, Lei Chen 0069, Jie Zhou 0001, Jiwen Lu. [doi]
• An Efficient Framework for Crediting Data Contributors of Diffusion ModelsMingyu Lu, Chris Lin, Chanwoo Kim, Su-In Lee. [doi]
• ReMatching Dynamic Reconstruction FlowSara Oblak, Despoina Paschalidou, Sanja Fidler, Matan Atzmon. [doi]
• A Second-Order Perspective on Model Compositionality and Incremental LearningAngelo Porrello, Lorenzo Bonicelli, Pietro Buzzega, Monica Millunzi, Simone Calderara, Rita Cucchiara. [doi]
• Sensitivity Verification for Additive Decision Tree EnsemblesArhaan Ahmad, Tanay Vineet Tayal, Ashutosh Gupta, S. Akshay. [doi]
• OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video GenerationKepan Nan, Rui Xie, Penghao Zhou, Tiehan Fan, Zhenheng Yang, Zhijie Chen, Xiang Li 0041, Jian Yang 0003, Ying Tai. [doi]
• Regret Bounds for Episodic Risk-Sensitive Linear Quadratic RegulatorWenhao Xu, Xuefeng Gao, Xuedong He. [doi]
• Identifying latent state transitions in non-linear dynamical systemsÇaglar Hizli, Çagatay Yildiz, Matthias Bethge, S. T. John, Pekka Marttinen. [doi]
• DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language ModelsChengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, Huan Zhang. [doi]
• SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box OptimizationHong Qian, Yiyi Zhu, Xiang Shu, Shuo Liu, Yaolin Wen, Xin An, Huakang Lu, Aimin Zhou, Ke Tang 0001, Yang Yu. [doi]
• AutoBencher: Towards Declarative Benchmark ConstructionXiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu, Yifan Mai, Percy Liang, Tatsunori Hashimoto. [doi]
• Information Theoretic Text-to-Image AlignmentChao Wang 0103, Giulio Franzese, Alessandro Finamore, Massimo Gallo, Pietro Michiardi. [doi]
• Repetition Improves Language Model EmbeddingsJacob Mitchell Springer, Suhas Kotha, Daniel Fried, Graham Neubig, Aditi Raghunathan. [doi]
• MetaOOD: Automatic Selection of OOD Detection ModelsYuehan Qin, Yichi Zhang, Yi Nian, Xueying Ding, Yue Zhao 0016. [doi]
• Self-Updatable Large Language Models by Integrating Context into Model ParametersYu Wang 0170, Xinshuang Liu, Xiusi Chen, Sean O'Brien, Junda Wu, Julian J. McAuley. [doi]
• Generalizing Reasoning Problems to Longer LengthsChangnan Xiao, Bing Liu 0001. [doi]
• MAI: A Multi-turn Aggregation-Iteration Model for Composed Image RetrievalYanzhe Chen, Zhiwen Yang, Jinglin Xu, Yuxin Peng. [doi]
• Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking DynamicsSiddhant Arora, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Shinji Watanabe 0001. [doi]
• Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum MechanismTehila Dahan, Kfir Yehuda Levy. [doi]
• Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer ModelsJerry Yao-Chieh Hu, Maojiang Su, En-Jui Kuo, Zhao Song 0002, Han Liu 0001. [doi]
• Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented GenerationMufei Li, Siqi Miao 0001, Pan Li 0005. [doi]
• Tuning Frequency Bias of State Space ModelsAnnan Yu, Dongwei Lyu, Soon Hoe Lim, Michael W. Mahoney, N. Benjamin Erichson. [doi]
• Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMsYuzhe Gu, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen 0026. [doi]
• Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement LearningPrajwal Koirala, Zhanhong Jiang, Soumik Sarkar, Cody H. Fleming. [doi]
• Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor AttacksBowei He, Lihao Yin, Hui-Ling Zhen, Jianping Zhang 0002, Lanqing Hong, Mingxuan Yuan, Chen Ma 0001. [doi]
• Difference-of-submodular Bregman DivergenceMasanari Kimura, Takahiro Kawashima, Tasuku Soma, Hideitsu Hino. [doi]
• Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded BoundaryYuena Lin, Yiyuan Wang, Gengyu Lyu, Yongjian Deng, Haichun Cai, Huibin Lin, Haobo Wang, Zhen Yang. [doi]
• Towards Calibrated Deep Clustering NetworkYuheng Jia, Jianhong Cheng, Hui Liu 0032, Junhui Hou. [doi]
• AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context AttributionFengyuan Liu, Nikhil Kandpal, Colin Raffel. [doi]
• Spectro-Riemannian Graph Neural NetworksKarish Grover, Haiyang Yu, Xiang Song 0003, Qi Zhu 0008, Han Xie, Vassilis N. Ioannidis, Christos Faloutsos. [doi]
• Measuring And Improving Persuasiveness Of Large Language ModelsSomesh Kumar Singh, Yaman Kumar Singla, Harini S. I, Balaji Krishnamurthy. [doi]
• Metric-Driven Attributions for Vision TransformersChase Walker, Sumit Kumar Jha 0001, Rickard Ewetz. [doi]
• Disentangling Representations through Multi-task LearningPantelis Vafidis, Aman Bhargava, Antonio Rangel. [doi]
• MMAU: A Massive Multi-Task Audio Understanding and Reasoning BenchmarkS. Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, Dinesh Manocha. [doi]
• On the Optimization Landscape of Low Rank Adaptation Methods for Large Language ModelsXu-Hui Liu, Yali Du 0001, Jun Wang 0012, Yang Yu 0001. [doi]
• Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive ImagesCanfer Akbulut, Kevin Robinson, Maribeth Rauh, Isabela Albuquerque, Olivia Wiles, Laura Weidinger, Verena Rieser, Yana Hasson, Nahema Marchal, Iason Gabriel, William Isaac 0001, Lisa Anne Hendricks. [doi]
• Procedural Synthesis of Synthesizable MoleculesMichael Sun, Alston Lo, Minghao Guo, Jie Chen 0007, Connor W. Coley, Wojciech Matusik. [doi]
• What's the Move? Hybrid Imitation Learning via Salient PointsPriya Sundaresan, Hengyuan Hu, Quan Vuong, Jeannette Bohg, Dorsa Sadigh. [doi]
• Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global ForgettingMilad Khademi Nori, Il-Min Kim 0001, Guanghui Wang. [doi]
• Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface RepresentationSlava Elizarov, Ciara Rowles, Simon Donné. [doi]
• Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernelsDaning Huang, Hanyang He, John Harlim, Yan Li. [doi]
• Have the VLMs Lost Confidence? A Study of Sycophancy in VLMsShuo Li, Tao Ji, Xiaoran Fan, Linsheng Lu, Leyi Yang, Yuming Yang, Zhiheng Xi, Rui Zheng, Yuran Wang, xh. zhao, Tao Gui, Qi Zhang, Xuanjing Huang 0001. [doi]
• Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networksSabrina Herbst, Sandeep Suresh Cranganore, Vincenzo De Maio, Ivona Brandic. [doi]
• Compute-Optimal LLMs Provably Generalize Better with ScaleMarc Anton Finzi, Sanyam Kapoor, Diego Granziol, Anming Gu, Christopher De Sa, J. Zico Kolter, Andrew Gordon Wilson. [doi]
• MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex QuestionsJian Wu, Linyi Yang, Dongyuan Li, Yuliang Ji, Manabu Okumura, Yue Zhang. [doi]
• Measuring memorization in RLHF for code completionJamie Hayes, Ilia Shumailov, William P. Porter, Aneesh Pappu. [doi]
• DaWin: Training-free Dynamic Weight Interpolation for Robust AdaptationChangdae Oh, Yixuan Li, Kyungwoo Song, Sangdoo Yun, Dongyoon Han. [doi]
• Generator Matching: Generative modeling with arbitrary Markov processesPeter Holderrieth, Marton Havasi, Jason Yim, Neta Shaul, Itai Gat, Tommi S. Jaakkola, Brian Karrer, Ricky T. Q. Chen, Yaron Lipman. [doi]
• Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity AssumptionsPiotr Indyk, Michael Kapralov, Kshiteej Sheth, Tal Wagner. [doi]
• Exploring a Principled Framework for Deep Subspace ClusteringXianghan Meng, Zhiyuan Huang, Wei He, Xianbiao Qi, Rong Xiao 0003, Chun-Guang Li. [doi]
• SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward MarginsJongwoo Ko, Saket Dingliwal, Bhavana Ganesh, Sailik Sengupta, Sravan Babu Bodapati, Aram Galstyan. [doi]
• Not-So-Optimal Transport Flows for 3D Point Cloud GenerationKa-Hei Hui, Chao Liu, Xiaohui Zeng, Chi-Wing Fu, Arash Vahdat. [doi]
• For Better or For Worse? Learning Minimum Variance Features With Label AugmentationMuthu Chidambaram, Rong Ge 0001. [doi]
• Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluationChenbin Zhang, Zhiqiang Hu, Chuchu Jiang, Wen Chen 0022, Jie Xu, Shaoting Zhang 0001. [doi]
• Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language ModelsFushuo Huo, Wenchao Xu 0001, Zhong Zhang, Haozhao Wang, Zhicheng Chen, Peilin Zhao. [doi]
• Deep Kernel Relative Test for Machine-generated Text DetectionYiliao Song, Zhenqiao Yuan, Shuhai Zhang, Zhen Fang 0001, Jun Yu, Feng Liu 0003. [doi]
• Efficient Model-Based Reinforcement Learning Through Optimistic Thompson SamplingJasmine Bayrooti, Carl Henrik Ek, Amanda Prorok. [doi]
• Selective Task Group Updates for Multi-Task OptimizationWooseong Jeong, Kuk-Jin Yoon. [doi]
• To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-DimensionsNoah Marshall, Ke Liang Xiao, Atish Agarwala, Elliot Paquette. [doi]
• Self-Evolved Reward Learning for LLMSChenghua Huang, Zhizhen Fan, Lu Wang 0029, Fangkai Yang, Pu Zhao 0004, Zeqi Lin, Qingwei Lin, Dongmei Zhang 0001, Saravan Rajmohan, Qi Zhang 0066. [doi]
• Singular Subspace Perturbation Bounds via Rectangular Random Matrix DiffusionsPeiyao Lai, Oren Mangoubi. [doi]
• Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction TuningMingyang Chen, sunhaoze, Tianpeng Li, Fan Yang, Hao Liang, Keer Lu, Bin Cui 0001, Wentao Zhang 0001, Zenan Zhou, Weipeng Chen. [doi]
• What is Wrong with Perplexity for Long-context Language Modeling?Lizhe Fang, Yifei Wang, Zhaoyang Liu, Chenheng Zhang, Stefanie Jegelka, Jinyang Gao, Bolin Ding, Yisen Wang 0001. [doi]
• TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech SeparationMohan Xu, Kai Li, Guo Chen, Xiaolin Hu. [doi]
• PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational AutoencodersTianyu Xie 0001, Harry Richman, Jiansi Gao, Frederick A. Matsen IV, Cheng Zhang. [doi]
• Depth Any Video with Scalable Synthetic DataHonghui Yang, Di Huang, Wei Yin 0006, Chunhua Shen, Haifeng Liu 0001, Xiaofei He 0001, Binbin Lin, Wanli Ouyang, Tong He 0001. [doi]
• Towards Effective Evaluations and Comparisons for LLM Unlearning MethodsQizhou Wang, Bo Han 0003, Puning Yang, Jianing Zhu, Tongliang Liu, Masashi Sugiyama. [doi]
• Denoising Task Difficulty-based Curriculum for Training Diffusion ModelsJin Young Kim, Hyojun Go, Soonwoo Kwon, Hyun-Gyoon Kim. [doi]
• LiveXiv - A Multi-Modal live benchmark based on Arxiv papers contentNimrod Shabtay, Felipe Maia Polo, Sivan Doveh, Wei Lin 0019, Muhammad Jehanzeb Mirza, Leshem Choshen, Mikhail Yurochkin, Yuekai Sun, Assaf Arbelle, Leonid Karlinsky, Raja Giryes. [doi]
• Episodic Memories Generation and Evaluation Benchmark for Large Language ModelsAlexis Huet, Zied Ben-Houidi, Dario Rossi 0001. [doi]
• Safety Layers in Aligned Large Language Models: The Key to LLM SecurityShen Li, Liuyi Yao, Lan Zhang 0002, Yaliang Li. [doi]
• Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsJianqun Zhou, Yuanlei Zheng, Wei Chen, Qianqian Zheng, Zeyuan Shang, Wei Zhang 0185, Rui Meng, Xiaoyu Shen 0001. [doi]
• Doubly robust identification of treatment effects from multiple environmentsPiersilvio De Bartolomeis, Julia Kostin, Javier Abad, Yixin Wang, Fanny Yang. [doi]
• Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics SimulationsNils Wandel, Stefan Schulz, Reinhard Klein. [doi]
• FreDF: Learning to Forecast in the Frequency DomainHao Wang 0049, Lichen Pan, Yuan Shen, Zhichao Chen 0001, Degui Yang, Yifei Yang, Sen Zhang 0006, Xinggao Liu, Haoxuan Li 0001, Dacheng Tao. [doi]
• Representational Similarity via Interpretable Visual ConceptsNeehar Kondapaneni, Oisin Mac Aodha, Pietro Perona. [doi]
• Scaling Speech-Text Pre-training with Synthetic Interleaved DataAohan Zeng, Zhengxiao Du, Mingdao Liu, Lei Zhang, Shengmin Jiang, Yuxiao Dong, Jie Tang 0001. [doi]
• DCT-CryptoNets: Scaling Private Inference in the Frequency DomainArjun Roy, Kaushik Roy 0001. [doi]
• PivotMesh: Generic 3D Mesh Generation via Pivot Vertices GuidanceHaohan Weng, Yikai Wang, Tong Zhang 0015, C. L. Philip Chen, Jun Zhu. [doi]
• Utilitarian Algorithm Configuration for Infinite Parameter SpacesDevon R. Graham, Kevin Leyton-Brown. [doi]
• Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?HyoJung Han, Akiko Eriguchi, Haoran Xu, Hieu Hoang, Marine Carpuat, Huda Khayrallah. [doi]
• ALBAR: Adversarial Learning approach to mitigate Biases in Action RecognitionJoseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah. [doi]
• Better autoregressive regression with LLMs via regression-aware fine-tuningMichal Lukasik, Zhao Meng, Harikrishna Narasimhan, Yin-Wen Chang, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar. [doi]
• Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba ModelsNguyen Hoang Khoi Do, Truc Nguyen, Malik Hassanaly, Raed Alharbi, Jung-Taek Seo, My T. Thai. [doi]
• FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded SamplingZhengqiang Zhang, Ruihuang Li, Lei Zhang 0006. [doi]
• NovelQA: Benchmarking Question Answering on Documents Exceeding 200K TokensCunxiang Wang, Ruoxi Ning, Boqi Pan, Tonghui Wu, Qipeng Guo, Cheng Deng, Guangsheng Bao, Xiangkun Hu, Zheng Zhang 0001, Qian Wang, Yue Zhang. [doi]
• Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained ControlHejia Chen, Haoxian Zhang, Shoulong Zhang, Xiaoqiang Liu, Sisi Zhuang, Yuan Zhang, Pengfei Wan 0001, Di Zhang, Shuai Li 0001. [doi]
• Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive DiffusionXingqun Qi, Yatian Wang, Hengyuan Zhang, Jiahao Pan, Wei Xue, Shanghang Zhang, Wenhan Luo, Qifeng Liu, Yike Guo. [doi]
• On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position EmbeddingDehong Xu, RuiQi Gao, Wenhao Zhang 0002, Xue-Xin Wei, Ying Nian Wu. [doi]
• Topological Schrödinger Bridge MatchingMaosheng Yang. [doi]
• Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index ModelSiyu Chen 0001, Beining Wu, Miao Lu, Zhuoran Yang, Tianhao Wang 0002. [doi]
• Oracle efficient truncated statisticsKonstantinos Karatapanis, Vasilis Kontonis, Christos Tzamos. [doi]
• DeLLMa: Decision Making Under Uncertainty with Large Language ModelsOllie Liu, Deqing Fu, Dani Yogatama, Willie Neiswanger. [doi]
• Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow MatchingEnshu Liu, Xuefei Ning, Yu Wang 0002, Zinan Lin 0001. [doi]
• ConMix: Contrastive Mixup at Representation Level for Long-tailed Deep ClusteringZhixin Li, Yuheng Jia. [doi]
• Learning mirror maps in policy mirror descentCarlo Alfano, Sebastian Rene Towers, Silvia Sapora, Chris Lu 0001, Patrick Rebeschini. [doi]
• The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGDMilad Nasr, Thomas Steinke 0002, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam D. Smith 0001, Andreas Terzis. [doi]
• Long-time asymptotics of noisy SVGD outside the population limitVictor Priser, Pascal Bianchi, Adil Salim. [doi]
• Consistency Checks for Language Model ForecastersDaniel Paleka, Abhimanyu Pallavi Sudhir, Alejandro Alvarez, Vineeth Bhat, Adam Shen, Evan Wang, Florian Tramèr. [doi]
• Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among PromptsMinh Le, Chau Nguyen, Huy Nguyen, Quyen Tran, Trung Le 0001, Nhat Ho. [doi]
• Regulatory DNA Sequence Design with Reinforcement LearningZhao Yang 0006, Bing Su 0001, Chuan Cao, Ji-Rong Wen. [doi]
• Credal Wrapper of Model Averaging for Uncertainty Estimation in ClassificationKaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez. [doi]
• MVTokenFlow: High-quality 4D Content Generation using Multiview Token FlowHanzhuo Huang, Yuan Liu 0025, Ge Zheng, Jiepeng Wang 0001, Zhiyang Dou, Sibei Yang. [doi]
• Polynomial Composition Activations: Unleashing the Dynamics of Large Language ModelsZhijian Zhuo, Ya Wang, Yutao Zeng, Xiaoqing Li, Xun Zhou, Jinwen Ma. [doi]
• Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLGhada Sokar, Johan Samir Obando-Ceron, Aaron C. Courville, Hugo Larochelle, Pablo Samuel Castro. [doi]
• Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic PriorsPeiran Xu 0001, Yadong Mu. [doi]
• Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMsYuxiao Lu, Arunesh Sinha, Pradeep Varakantham. [doi]
• ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMsYi-Kai Zhang, Shiyin Lu, Qing-Guo Chen, De-Chuan Zhan, Han-Jia Ye. [doi]
• Policy Design in Long-run Welfare DynamicsJiduan Wu, Rediet Abebe, Moritz Hardt, Ana-Andreea Stoica. [doi]
• Lasso Bandit with Compatibility Condition on Optimal ArmHarin Lee, TaeHyun Hwang, Min-hwan Oh. [doi]
• Fourier Sliced-Wasserstein Embedding for Multisets and MeasuresTal Amir, Nadav Dym. [doi]
• Cross-Domain Off-Policy Evaluation and Learning for Contextual BanditsYuta Natsubori, Masataka Ushiku, Yuta Saito. [doi]
• GraphEval: A Lightweight Graph-Based LLM Framework for Idea EvaluationTao Feng, Yihang Sun, Jiaxuan You. [doi]
• TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series ForecastingSongtao Huang, Zhen Zhao, Can Li, Lei Bai 0001. [doi]
• PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph MatchingDaniel Rose, Oliver Wieder, Thomas Seidel, Thierry Langer. [doi]
• CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic ScreeningGen Zhou, Sugitha Janarthanan, Yutong Lu, Pingzhao Hu. [doi]
• Robustness Reprogramming for Representation LearningZhichao Hou, MohamadAli Torkamani, Hamid Krim, Xiaorui Liu. [doi]
• Advancing LLM Reasoning Generalists with Preference TreesLifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding 0002, Xingyao Wang 0002, Boji Shan, Zeyuan Liu, Jia Deng, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou 0002, Hao Peng 0015, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Towards Universality: Studying Mechanistic Similarity Across Language Model ArchitecturesJunxuan Wang, Xuyang Ge, Wentao Shu, Qiong Tang, Yunhua Zhou, Zhengfu He, Xipeng Qiu. [doi]
• Improving Semantic Understanding in Speech Language Models via Brain-tuningOmer Moussa, Dietrich Klakow, Mariya Toneva. [doi]
• GMValuator: Similarity-based Data Valuation for Generative ModelsJiaxi Yang, Wenlong Deng, Benlin Liu, Yangsibo Huang, James Zou, Xiaoxiao Li. [doi]
• A Truncated Newton Method for Optimal TransportMete Kemertas, Amir Massoud Farahmand, Allan Douglas Jepson. [doi]
• O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal AssumptionsGen Li 0005, Yuling Yan. [doi]
• Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit AlgorithmsParham Rezaei, Farzan Farnia, Cheuk Ting Li. [doi]
• Uncertainty Herding: One Active Learning Method for All Label BudgetsWonho Bae, Danica J. Sutherland, Gabriel L. Oliveira. [doi]
• Coreset Selection via Reducible Loss in Continual LearningRuilin Tong, Yuhang Liu 0002, Javen Qinfeng Shi, Dong Gong. [doi]
• Uncertainty modeling for fine-tuned implicit functionsAnna Susmelj, Mael Macuglia, Natasa Tagasovska, Reto Sutter, Sebastiano Caprara, Jean-Philippe Thiran, Ender Konukoglu. [doi]
• Rectified Diffusion: Straightness Is Not Your Need in Rectified FlowFu-Yun Wang, Ling Yang 0006, Zhaoyang Huang, Mengdi Wang, Hongsheng Li 0001. [doi]
• Toward Guidance-Free AR Visual Generation via Condition Contrastive AlignmentHuayu Chen, Hang Su, Peize Sun, Jun Zhu. [doi]
• MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable EvaluationsShaochen Zhong, Yifan Lu, Lize Shao, Bhargav Bhushanam, Xiaocong Du, Yixin Wan, Yucheng Shi, Daochen Zha, Yiwei Wang, Ninghao Liu, Kaixiong Zhou, Shuai Xu, Kai-Wei Chang, Louis Feng, Vipin Chaudhary, Xia Hu. [doi]
• Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution DetectionHengzhuang Li, Teng Zhang. [doi]
• Learning Hierarchical Polynomials of Multiple Nonlinear FeaturesHengyu Fu, Zihao Wang, Eshaan Nichani, Jason D. Lee. [doi]
• Generative Representational Instruction TuningNiklas Muennighoff, Hongjin Su, Liang Wang 0046, Nan Yang 0002, Furu Wei, Tao Yu 0009, Amanpreet Singh, Douwe Kiela. [doi]
• Finding Shared Decodable Concepts and their Negations in the BrainCory Daniel Efird, Alex Murphy, Joel Zylberberg, Alona Fyshe. [doi]
• DPaI: Differentiable Pruning at Initialization with Node-Path Balance PrincipleLichuan Xiang, Quan Nguyen-Tri, Lan-Cuong Nguyen, Hoang Pham, Khoat Than, Long Tran-Thanh, Hongkai Wen 0001. [doi]
• SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent ExplanationsZhaorun Chen, Francesco Pinto, Minzhou Pan, Bo Li. [doi]
• Causal Effect Estimation with Mixed Latent Confounders and Post-treatment VariablesYaochen Zhu, Jing Ma 0002, Liang Wu 0006, Qi Guo, Liangjie Hong, Jundong Li. [doi]
• Graph Neural Networks Can (Often) Count SubstructuresPaolo Pellizzoni, Till Hendrik Schulz, Karsten M. Borgwardt. [doi]
• Immunogenicity Prediction with Dual Attention Enables Vaccine Target SelectionSong Li, Yang Tan, Song Ke, Liang Hong, Bingxin Zhou. [doi]
• Ward: Provable RAG Dataset Inference via LLM WatermarksNikola Jovanovic 0001, Robin Staab, Maximilian Baader, Martin T. Vechev. [doi]
• Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality GapChristopher Liao, Christian So, Theodoros Tsiligkaridis, Brian Kulis. [doi]
• Variance-Reducing Couplings for Random FeaturesIsaac Reid, Stratis Markou, Krzysztof Marcin Choromanski, Richard E. Turner, Adrian Weller. [doi]
• Gaussian Differentially Private Human Faces Under a Face Radial Curve RepresentationCarlos J. Soto, Matthew Reimherr, Aleksandra B. Slavkovic, Mark Shriver. [doi]
• Interpreting and Editing Vision-Language Representations to Mitigate HallucinationsNick Jiang, Anish Kachinthaya, Suzanne Petryk, Yossi Gandelsman. [doi]
• CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScaleZeMing Gong, Austin T. Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott C. Lowe, Graham W. Taylor, Angel X. Chang. [doi]
• Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning AgentYangning Li, Yinghui Li, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinran Zheng, Hui Wang, Hai-Tao Zheng, Fei Huang, Jingren Zhou 0001, Philip S. Yu. [doi]
• MetaUrban: An Embodied AI Simulation Platform for Urban MicromobilityWayne Wu, Honglin He, Jack He, Yiran Wang, Chenda Duan, Zhizheng Liu, Quanyi Li, Bolei Zhou. [doi]
• Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with ImaginationLeonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves. [doi]
• FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language ModelsZhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang 0018. [doi]
• Provable Convergence Bounds for Hybrid Dynamical Sampling and OptimizationMatthew X. Burns, Qingyuan Hou, Michael C. Huang 0001. [doi]
• The Hidden Cost of Waiting for Accurate PredictionsAli Shirali, Ariel D. Procaccia, Rediet Abebe. [doi]
• Joint Graph Rewiring and Feature Denoising via Spectral ResonanceJonas Linkerhägner, Cheng Shi, Ivan Dokmanic. [doi]
• Eia: Environmental Injection Attack on Generalist Web Agents for Privacy LeakageZeyi Liao, Lingbo Mo, Chejian Xu, Mintong Kang, Jiawei Zhang 0002, Chaowei Xiao, Yuan Tian, Bo Li 0026, Huan Sun 0001. [doi]
• Generalized Principal-Agent Problem with a Learning AgentTao Lin, Yiling Chen. [doi]
• MIND over Body: Adaptive Thinking using Dynamic ComputationMrinal Mathur, Barak A. Pearlmutter, Sergey M. Plis. [doi]
• Rethinking Reward Modeling in Preference-based Large Language Model AlignmentHao Sun 0017, Yunyi Shen, Jean-Francois Ton. [doi]
• Data Scaling Laws in Imitation Learning for Robotic ManipulationFanqi Lin, Yingdong Hu, Pingyue Sheng, Chuan Wen, Jiacheng You, Yang Gao 0029. [doi]
• Indirect Gradient Matching for Adversarial Robust DistillationHongsin Lee, Seungju Cho, Changick Kim. [doi]
• Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEsXin Gao, Jian Pu. [doi]
• MELODI: Exploring Memory Compression for Long ContextsYinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov, David Racz, Jesper Sparre Andersen. [doi]
• K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language ModelsJaehyung Seo, HeuiSeok Lim. [doi]
• Robotouille: An Asynchronous Planning Benchmark for LLM AgentsGonzalo Gonzalez-Pumariega, Leong Su Yean, Neha Sunkara, Sanjiban Choudhury. [doi]
• Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech RepresentationSungnyun Kim, Sungwoo Cho, Sangmin Bae, Kangwook Jang, Se-Young Yun. [doi]
• RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and StyleYantao Liu, Zijun Yao 0002, Rui Min, Yixin Cao 0002, Lei Hou 0001, Juanzi Li. [doi]
• Many-Objective Multi-Solution TransportZiyue Li, Tian Li, Virginia Smith, Jeff Bilmes, Tianyi Zhou 0001. [doi]
• Elliptic Loss RegularizationAli-Hasan, Haoming Yang, Yuting Ng, Vahid Tarokh. [doi]
• Fair Clustering in the Sliding Window ModelVincent Cohen-Addad, Shaofeng H.-C. Jiang, Qiaoyuan Yang, Yubo Zhang, Samson Zhou. [doi]
• UniMatch: Universal Matching from Atom to Task for Few-Shot Drug DiscoveryRuifeng Li, Mingqian Li, Wei Liu, Yuhua Zhou, Xiangxin Zhou, Yuan Yao, Qiang Zhang, Hongyang Chen. [doi]
• A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial ContextsSuyu Ge, Xihui Lin, Yunan Zhang 0001, Jiawei Han 0001, Hao Peng 0009. [doi]
• Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement LearningCaleb Chuck, Fan Feng, Carl Qi, Chang Shi, Siddhant Agarwal, Amy Zhang 0001, Scott Niekum. [doi]
• Noise Separation guided Candidate Label Reconstruction for Noisy Partial Label LearningXiaorui Peng, Yuheng Jia, Fuchao Yang, Ran Wang 0001, Min-Ling Zhang. [doi]
• Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot VideosMingfei Han 0002, Linjie Yang, Xiaojun Chang, Lina Yao 0001, Heng Wang. [doi]
• Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and DebiasingElad Romanov, Fangzhao Zhang, Mert Pilanci. [doi]
• Self-Boosting Large Language Models with Synthetic Preference DataQingxiu Dong, Li Dong 0004, Xingxing Zhang 0002, Zhifang Sui, Furu Wei. [doi]
• Process Reward Model with Q-value RankingsWendi Li, Yixuan Li. [doi]
• Robust Representation Consistency Model via Contrastive DenoisingJiachen Lei, Julius Berner, Jiongxiao Wang, Zhongzhu Chen, Chaowei Xiao, Zhongjie Ba, Kui Ren 0001, Jun Zhu 0001, Anima Anandkumar. [doi]
• KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language ModelsFan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang 0004. [doi]
• RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataMaxwell A. Xu, Jaya Narain, Gregory Darnell, Haraldur Tómas Hallgrimsson, Hyewon Jeong, Darren Forde, Richard Andres Fineman, Karthik Jayaraman Raghuram, James Matthew Rehg, Shirley You Ren. [doi]
• Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?Charles Dawson 0001, Van Tran, Max Z. Li, Chuchu Fan. [doi]
• CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS CompressionYu-Ting Zhan, Cheng-Yuan Ho, Hebi Yang, Yi-Hsin Chen, Jui-Chiu Chiang, Yu-Lun Liu 0001, Wen-Hsiao Peng. [doi]
• MaestroMotif: Skill Design from Artificial Intelligence FeedbackMartin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang 0001, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro. [doi]
• Dissecting Adversarial Robustness of Multimodal LM AgentsChen Henry Wu, Rishi Rajesh Shah, Jing Yu Koh, Russ Salakhutdinov, Daniel Fried, Aditi Raghunathan. [doi]
• Think Then React: Towards Unconstrained Action-to-Reaction Motion GenerationWenhui Tan, Boyuan Li, Chuhao Jin, Wenbing Huang 0001, Xiting Wang, Ruihua Song. [doi]
• DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max OptimizationYi Zhang, Siwei Wang, Jiyuan Liu, Shengju Yu, Zhibin Dong, Suyuan Liu, Xinwang Liu 0002, En Zhu. [doi]
• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity DatasetYingzi Ma, Jiongxiao Wang, Fei Wang, Siyuan Ma, Jiazhao Li, Jinsheng Pan, Xiujun Li, Furong Huang, Lichao Sun, Bo Li, Yejin Choi, Muhao Chen, Chaowei Xiao. [doi]
• Text2PDE: Latent Diffusion Models for Accessible Physics SimulationAnthony Y. Zhou, Zijie Li, Michael Schneier, John R. Buchanan Jr., Amir Barati Farimani. [doi]
• Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction TuningGangwei Jiang, Caigao Jiang, Zhaoyi Li, Siqiao Xue, Jun Zhou 0011, Linqi Song, Defu Lian, Ying Wei 0001. [doi]
• Zero-shot Model-based Reinforcement Learning using Large Language ModelsAbdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat, Oussama Zekri, Albert Thomas 0001, Giuseppe Paolo, Maurizio Filippone, Ievgen Redko, Balázs Kégl. [doi]
• Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find ThemAnh Tuan Bui, Thuy-Trang Vu, Long Tung Vuong, Trung Le 0001, Paul Montague, Tamas Abraham, Junae Kim, Dinh Phung 0001. [doi]
• Diffusion-based Neural Network Weights GenerationBedionita Soro, Bruno Andreis, Hayeon Lee, Wonyong Jeong, Song Chong, Frank Hutter, Sung Ju Hwang. [doi]
• FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian NoiseYunlong Yuan, Yuanfan Guo, Chunwei Wang, Wei Zhang, Hang Xu, Li Zhang. [doi]
• Radar: Fast Long-Context Decoding for Any TransformerYongchang Hao, Mengyao Zhai, Hossein Hajimirsadeghi, Sepidehsadat Hosseini, Frederick Tung. [doi]
• The Value of Sensory Information to a RobotArjun Krishna, Edward S. Hu, Dinesh Jayaraman. [doi]
• PolaFormer: Polarity-aware Linear Attention for Vision TransformersWeikang Meng, Yadan Luo, Xin Li 0003, Dongmei Jiang, Zheng Zhang 0006. [doi]
• Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption RobustnessBoqian Wu, Qiao Xiao, Shunxin Wang, Nicola Strisciuglio, Mykola Pechenizkiy, Maurice van Keulen, Decebal Constantin Mocanu, Elena Mocanu. [doi]
• Centrality-guided Pre-training for GraphBin Liang 0004, Shiwei Chen, Lin Gui 0003, Hui Wang 0030, Yue Yu 0001, Ruifeng Xu 0001, Kam-Fai Wong. [doi]
• Neural Context Flows for Meta-Learning of Dynamical SystemsRoussel Desmond Nzoyem, David A. W. Barton, Tom Deakin. [doi]
• Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction DefenseSiyu Luan, Zhenyi Wang 0001, Li Shen 0008, Zonghua Gu 0001, Chao Wu, Dacheng Tao. [doi]
• Artificial Kuramoto Oscillatory NeuronsTakeru Miyato, Sindy Löwe, Andreas Geiger 0001, Max Welling. [doi]
• Mind Control through Causal Inference: Predicting Clean Images from Poisoned DataMengxuan Hu, Zihan Guan 0001, Yi Zeng 0005, Junfeng Guo, Zhongliang Zhou, Jielu Zhang, Ruoxi Jia 0001, Anil Kumar S. Vullikanti, Sheng Li 0001. [doi]
• Bridging the Data Provenance Gap Across Text, Speech, and VideoShayne Longpre, Nikhil Singh 0003, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Naana Obeng-Marnu, Manan Dey, Mohammed Hamdy, Nayan Saxena, Ahmad Mustafa Anis, Emad A. Alghamdi, Vu Minh Chien, Da Yin, Kun Qian, Yizhi Li, Minnie Liang, An Dinh, Shrestha Mohanty, et al.. [doi]
• CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationMatan Rusanovsky, Or Hirschorn, Shai Avidan. [doi]
• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang 0009, Xinya Du, Dong Yu 0001. [doi]
• SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIPYusuke Hirota, Min-Hung Chen, Chien-Yi Wang, Yuta Nakashima, Yu-Chiang Frank Wang, Ryo Hachiuma. [doi]
• A Simple Approach to Unifying Diffusion-based Conditional GenerationXirui Li, Charles Herrmann, Kelvin C. K. Chan, Yinxiao Li, Deqing Sun, Chao Ma 0004, Ming-Hsuan Yang 0001. [doi]
• Exploring The Loss Landscape Of Regularized Neural Networks Via Convex DualitySungyoon Kim, Aaron Mishkin, Mert Pilanci. [doi]
• Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety TuningSeanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee 0001, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Moksh Jain. [doi]
• Progress or Regress? Self-Improvement Reversal in Post-trainingTing Wu, Xuefeng Li 0003, Pengfei Liu 0003. [doi]
• Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared AutonomyZhenghai Xue, Bo An 0001, Shuicheng Yan. [doi]
• The Unreasonable Ineffectiveness of the Deeper LayersAndrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Daniel A. Roberts. [doi]
• Unsupervised Disentanglement of Content and Style via Variance-Invariance ConstraintsYuxuan Wu, Ziyu Wang 0008, Bhiksha Raj, Gus Xia. [doi]
• GeSubNet: Gene Interaction Inference for Disease Subtype Network GenerationZiwei Yang 0002, Zheng Chen 0012, Xin Liu, Rikuto Kotoge, Peng Chen, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun 0001. [doi]
• Generalization through variance: how noise shapes inductive biases in diffusion modelsJohn J. Vastola. [doi]
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language AlignmentChenhang Cui, An Zhang 0003, Yiyang Zhou, Zhaorun Chen, Gelei Deng, Huaxiu Yao, Tat-Seng Chua. [doi]
• Learning from Imperfect Human Feedback: A Tale from Corruption-Robust DuelingYuwei Cheng, Fan Yao, Xuefeng Liu, Haifeng Xu. [doi]
• Mixture of Parrots: Experts improve memorization more than reasoningSamy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas 0001, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach. [doi]
• TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential DynamicsLu Yi 0002, Jie Peng 0005, Yanping Zheng, Fengran Mo, Zhewei Wei, Yuhang Ye 0002, Yue Zixuan, Zengfeng Huang. [doi]
• Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetsZhen Liu 0019, Tim Z. Xiao, Weiyang Liu, Yoshua Bengio, Dinghuai Zhang. [doi]
• DECO: Unleashing the Potential of ConvNets for Query-based Detection and SegmentationXinghao Chen 0001, Siwei Li, Yijing Yang, Yunhe Wang 0001. [doi]
• SOREL: A Stochastic Algorithm for Spectral Risks MinimizationYuze Ge, Rujun Jiang. [doi]
• Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language ModelsAli Khajegili Mirabadi, Katherine Rich, Hossein Farahani, Ali Bashashati. [doi]
• Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion ModelsLin Zhu, Xinbing Wang, Chenghu Zhou, Qinying Gu, Nanyang Ye 0001. [doi]
• ThunderKittens: Simple, Fast, and Adorable KernelsBenjamin Frederick Spector, Simran Arora, Aaryan Singhal, Arjun Parthasarathy, Daniel Y. Fu, Christopher Ré. [doi]
• Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View PredictionJunyi Chen, Di Huang, Weicai Ye, Wanli Ouyang, Tong He 0001. [doi]
• Reinforcement Learning for Control of Non-Markovian Cellular Population DynamicsJosiah C. Kratz, Jacob Adamczyk. [doi]
• Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based SamplingMinhyuk Seo, Hyunseo Koh, Jonghyun Choi. [doi]
• Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades LaterHan-Jia Ye, Huai-Hong Yin, De-Chuan Zhan, Wei-Lun Chao. [doi]
• Gradient-Free Generation for Hard-Constrained SystemsChaoran Cheng, Boran Han, Danielle C. Maddix, Abdul Fatir Ansari, Andrew Stuart, Michael W. Mahoney, Bernie Wang 0001. [doi]
• Aligning Visual Contrastive learning models via Preference OptimizationAmirabbas Afzali, Borna Khodabandeh, Ali Rasekh, Mahyar JafariNodeh, Sepehr Kazemi Ranjbar, Simon Gottschalk 0001. [doi]
• Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute AlignmentYankai Jiang 0003, Wenhui Lei, Xiaofan Zhang 0002, Shaoting Zhang 0001. [doi]
• Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual BanditsZihan Zhang, Xiangyang Ji, Yuan Zhou 0007. [doi]
• Mixture-of-Agents Enhances Large Language Model CapabilitiesJunlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, James Zou. [doi]
• Controllable Unlearning for Image-to-Image Generative Models via ϵ-Constrained OptimizationXiaohua Feng, Yuyuan Li, Chaochao Chen 0001, Li Zhang, Longfei Li, Jun Zhou 0011, Xiaolin Zheng. [doi]
• Block Verification Accelerates Speculative DecodingZiteng Sun, Uri Mendlovic, Yaniv Leviathan, Asaf Aharoni, Jae Hun Ro, Ahmad Beirami, Ananda Theertha Suresh. [doi]
• Higher-Order Graphon Neural Networks: Approximation and Cut DistanceDaniel Herbst, Stefanie Jegelka. [doi]
• Encryption-Friendly LLM ArchitectureDonghwan Rho, Taeseong Kim, Minje Park, Jung-Woo Kim, Hyunsik Chae, Ernest K. Ryu, Jung Hee Cheon. [doi]
• Attention layers provably solve single-location regressionPierre Marion, Raphaël Berthier, Gérard Biau, Claire Boyer. [doi]
• Event-Driven Online Vertical Federated LearningGanyu Wang, Boyu Wang 0004, Bin Gu 0001, Charles Ling 0001. [doi]
• Bringing NeRFs to the Latent Space: Inverse Graphics AutoencoderAntoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jérémie Mary, Andrew I. Comport, Valérie Gouet-Brunet. [doi]
• Multilevel Generative Samplers for Investigating Critical PhenomenaAnkur Singha, Elia Cellini, Kim Andrea Nicoli, Karl Jansen, Stefan Kühn, Shinichi Nakajima. [doi]
• Diffusion State-Guided Projected Gradient for Inverse ProblemsRayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar. [doi]
• CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code RepairMingjie Liu, Yun-Da Tsai, Wenfei Zhou, Haoxing Ren. [doi]
• ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug designKeir Adams, Kento Abeywardane, Jenna C. Fromer, Connor W. Coley. [doi]
• Knowledge Localization: Mission Not Accomplished? Enter Query Localization!Yuheng Chen, Pengfei Cao, Yubo Chen 0001, Kang Liu 0001, Jun Zhao 0001. [doi]
• Structural-Entropy-Based Sample Selection for Efficient and Effective LearningTianchi Xie, Jiangning Zhu, Guozu Ma, Minzhi Lin, Wei Chen 0001, Weikai Yang, Shixia Liu. [doi]
• Universal Image Restoration Pre-training via Degradation ClassificationJiakui Hu, Lujia Jin, Zhengjian Yao, Yanye Lu. [doi]
• SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMsMohammad Mozaffari, Amir Yazdanbakhsh, Zhao Zhang, Maryam Mehri Dehnavi. [doi]
• TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated WeightsAiwei Liu, Haoping Bai, Zhiyun Lu, Yanchao Sun, Xiang Kong, Xiaoming Simon Wang, Jiulong Shan, Albin Madappally Jose, Xiaojiang Liu, Lijie Wen 0001, Philip S. Yu, Meng Cao. [doi]
• W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language ModelsShang Wang. [doi]
• 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D EditingJiahua Dong 0002, Yu-Xiong Wang. [doi]
• Vec2Face: Scaling Face Dataset Generation with Loosely Constrained VectorsHaiyu Wu, Jaskirat Singh, Sicong Tian, Liang Zheng 0001, Kevin W. Bowyer. [doi]
• Specialized Foundation Models Struggle to Beat Supervised BaselinesZongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen 0003, Junhong Shen, Ameet Talwalkar, Mikhail Khodak. [doi]
• Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like ArchitecturesYuchen Duan, Weiyun Wang, Zhe Chen, Xizhou Zhu, Lewei Lu, Tong Lu, Yu Qiao, Hongsheng Li 0001, Jifeng Dai, Wenhai Wang. [doi]
• Learning from weak labelers as constraintsVishwajeet Agrawal, Rattana Pukdee, Maria-Florina Balcan, Pradeep Kumar Ravikumar. [doi]
• Denoising with a Joint-Embedding Predictive ArchitectureDengsheng Chen, Jie Hu 0019, Xiaoming Wei, Enhua Wu. [doi]
• MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning SegmentationDonggon Jang, Yucheol Cho, Suin Lee, Taehyeon Kim, Daeshik Kim. [doi]
• Hierarchical Uncertainty Estimation for Learning-based Registration in NeuroimagingXiaoling Hu 0002, Karthik Gopinath, Peirong Liu, Malte Hoffmann, Koen Van Leemput, Oula Puonti, Juan Eugenio Iglesias. [doi]
• Redefining the task of Bioactivity PredictionYanwen Huang, Bowen Gao, Yinjun Jia, Hongbo Ma, Wei-Ying Ma, Ya-Qin Zhang, Yanyan Lan. [doi]
• General Scene Adaptation for Vision-and-Language NavigationHaodong Hong, Yanyuan Qiao, Sen Wang, Jiajun Liu, Qi Wu. [doi]
• Learning Graph Quantized TokenizersLimei Wang, Kaveh Hassani, Si Zhang, Dongqi Fu, Baichuan Yuan, Weilin Cong, Zhigang Hua, Hao Wu, Ning Yao, Bo Long. [doi]
• MeteoRA: Multiple-tasks Embedded LoRA for Large Language ModelsJingwei Xu 0001, Junyu Lai, Yunpeng Huang. [doi]
• Can LLMs Understand Time Series Anomalies?Zihao Zhou, Rose Yu. [doi]
• Steering Large Language Models between Code Execution and Textual ReasoningYongchao Chen, Harsh Jhamtani, Srinagesh Sharma, Chuchu Fan, Chi Wang. [doi]
• Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error BarrierLu Yi 0002, Zhewei Wei. [doi]
• Contextual Document EmbeddingsJohn Xavier Morris, Alexander M. Rush. [doi]
• Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow NetworksRui Hu, Yifan Zhang, Zhuoran Li, Longbo Huang. [doi]
• On the Feature Learning in Diffusion ModelsAndi Han, Wei Huang 0034, Yuan Cao 0006, Difan Zou. [doi]
• Fast and Accurate Blind Flexible DockingZizhuo Zhang, Lijun Wu, Kaiyuan Gao, Jiangchao Yao, Tao Qin, Bo Han 0003. [doi]
• Targeted Attack Improves Protection against Unauthorized Diffusion CustomizationBoyang Zheng, Chumeng Liang, Xiaoyu Wu. [doi]
• Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy SamplesYangming Li, Max Ruiz Luyten, Mihaela van der Schaar. [doi]
• Measuring Non-Adversarial Reproduction of Training Data in Large Language ModelsMichael Aerni, Javier Rando, Edoardo Debenedetti, Nicholas Carlini, Daphne Ippolito, Florian Tramèr. [doi]
• ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLYang Qin, Chao Chen 0026, Zhihang Fu, Ze Chen 0001, Dezhong Peng, Peng Hu 0002, Jieping Ye. [doi]
• Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation ModelsAmir Mohammad Karimi-Mamaghan, Samuele Papa, Karl Henrik Johansson, Stefan Bauer, Andrea Dittadi. [doi]
• Descent with Misaligned Gradients and Applications to Hidden ConvexityAditya Bhaskara, Ashok Cutkosky, Ravi Kumar 0001, Manish Purohit. [doi]
• Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language ModelsRui Ye, Jingyi Chai, Xiangrui Liu, Yaodong Yang, Yanfeng Wang, Siheng Chen. [doi]
• OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?Zijian Chen 0001, Tingzhu Chen, Wenjun Zhang 0001, Guangtao Zhai. [doi]
• On Scaling Up 3D Gaussian Splatting TrainingHexu Zhao, Haoyang Weng, Daohan Lu, Ang Li 0006, Jinyang Li 0001, Aurojit Panda, Saining Xie. [doi]
• Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human ratingOlivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kajic, Su Wang 0001, Emanuele Bugliarello, Yasumasa Onoe, Pinelopi Papalampidi, Ira Ktena, Christopher Knutsen, Cyrus Rashtchian, Anant Nawalgaria, Jordi Pont-Tuset, Aida Nematzadeh. [doi]
• CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot ClassificationMingkun Zhang, Keping Bi, Wei Chen 0034, Jiafeng Guo, Xueqi Cheng. [doi]
• CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMsJinpeng Li, Haiping Wang 0004, Jiabin Chen, Yuan Liu 0025, Zhiyang Dou, Yuexin Ma, Sibei Yang, Yuan Li, Wenping Wang, Zhen Dong 0005, Bisheng Yang. [doi]
• R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical ReasoningMintong Kang, Bo Li. [doi]
• Learning Diagrams: A Graphical Language for Compositional Training RegimesMason Lary, Richard Samuelson, Alexander Wilentz, Alina Zare, Matthew Klawonn, James P. Fairbanks. [doi]
• Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of ExpressivityYam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael M. Bronstein, Haggai Maron. [doi]
• Learning Color Equivariant RepresentationsYulong Yang 0003, Felix O'Mahony, Christine Allen-Blanchette. [doi]
• How Gradient descent balances features: A dynamical analysis for two-layer neural networksZhenyu Zhu, Fanghui Liu 0001, Volkan Cevher. [doi]
• Interpreting Emergent Planning in Model-Free Reinforcement LearningThomas Bush, Stephen Chung, Usman Anwar, Adrià Garriga-Alonso, David Krueger 0001. [doi]
• Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question AnsweringXingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan L. Yuille. [doi]
• Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear BanditsYuwei Luo, Mohsen Bayati. [doi]
• Geometry-aware RL for Manipulation of Varying Shapes and Deformable ObjectsTai Hoang, Huy Le, Philipp Becker, Ngo Anh Vien, Gerhard Neumann. [doi]
• Offline Hierarchical Reinforcement Learning via Inverse OptimizationCarolin Schmidt, Daniele Gammelli, James Harrison, Marco Pavone 0001, Filipe Rodrigues 0001. [doi]
• COME: Test-time Adaption by Conservatively Minimizing EntropyQingyang Zhang, Yatao Bian, Xinke Kong, Peilin Zhao, Changqing Zhang. [doi]
• Near-optimal Active Regression of Single-Index ModelsYi Li, Wai Ming Tai. [doi]
• G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language ModelJiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang 0005, Lanqing Hong, Jianhua Han, Hang Xu 0004, Zhenguo Li, Lingpeng Kong. [doi]
• Exposure Bracketing Is All You Need For A High-Quality ImageZhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, Wangmeng Zuo. [doi]
• Fine-tuning with Reserved Majority for Noise ReductionShuyang Jiang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang 0027. [doi]
• Predicate Hierarchies Improve Few-Shot State ClassificationEmily Jin, Joy Hsu, Jiajun Wu 0001. [doi]
• Progressive Compression with Universally Quantized Diffusion ModelsYibo Yang, Justus C. Will, Stephan Mandt. [doi]
• SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature EmbeddingsBarbora Barancikova, Zhuoyue Huang, Cristopher Salvi. [doi]
• Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary ResolutionZuyan Liu, Yuhao Dong, Ziwei Liu 0002, Winston Hu, Jiwen Lu, Yongming Rao. [doi]
• Risk-Sensitive Variational Actor-Critic: A Model-Based ApproachAlonso Granados Baca, Reza Ebrahimi, Jason Pacheco. [doi]
• SelKD: Selective Knowledge Distillation via Optimal Transport PerspectiveLiangliang Shi, Zhengyan Shi, Junchi Yan. [doi]
• Schur's Positive-Definite Network: Deep Learning in the SPD cone with structureCan Pouliquen, Mathurin Massias, Titouan Vayer. [doi]
• Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi DecodingYao Teng, Han Shi, Xian Liu, Xuefei Ning, Guohao Dai, Yu Wang 0002, Zhenguo Li, Xihui Liu. [doi]
• Cached Multi-Lora Composition for Multi-Concept Image GenerationXiandong Zou, Mingzhu Shen, Christos-Savvas Bouganis, Yiren Zhao. [doi]
• Empowering Users in Digital Privacy Management through Interactive LLM-Based AgentsBolun Sun, Yifan Zhou, Haiyun Jiang. [doi]
• AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-TuningYehonathan Refael, Jonathan Svirsky, Boris Shustin, Wasim Huleihel, Ofir Lindenbaum. [doi]
• EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice RoutingHaotian Sun, Tao Lei, Bowen Zhang, Yanghao Li, Haoshuo Huang, Ruoming Pang, Bo Dai 0001, Nan Du. [doi]
• Approximation algorithms for combinatorial optimization with predictionsAntonios Antoniadis 0001, Marek Eliás 0001, Adam Polak 0001, Moritz Venzin. [doi]
• From Tokens to Lattices: Emergent Lattice Structures in Language ModelsBo Xiong, Steffen Staab. [doi]
• SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-CorrectionLing Yang 0006, Zhaochen Yu, Tianjun Zhang, Minkai Xu, Joseph E. Gonzalez, Bin Cui 0001, Shuicheng Yan. [doi]
• Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov EquationZhanfeng Mo, Haosen Shi 0003, Sinno Jialin Pan. [doi]
• Exact Certification of (Graph) Neural Networks Against Label PoisoningMahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar. [doi]
• DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity PreservationJiwook Kim, Seonho Lee, Jaeyo Shin, Jiho Choi, Hyunjung Shim. [doi]
• LDAdam: Adaptive Optimization from Low-Dimensional Gradient StatisticsThomas Robert 0007, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh. [doi]
• Linear Transformer Topological Masking with Graph Random FeaturesIsaac Reid, Kumar Avinava Dubey, Deepali Jain, William F. Whitney, Amr Ahmed 0001, Joshua Ainslie, Alex Bewley, Mithun George Jacob, Aranyak Mehta, David Rendleman,