Table of Contents

• CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement PredictionShuqi Li, Yuebo Sun, Yuxin Lin, Xin Gao 0001, Shuo Shang, Rui Yan 0001. [doi]
• Wide Two-Layer Networks can Learn from Adversarial PerturbationsSoichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki. [doi]
• Derandomizing Multi-Distribution LearningKasper Green Larsen, Omar Montasser, Nikita Zhivotovskiy. [doi]
• Federated Ensemble-Directed Offline Reinforcement LearningDesik Rengarajan, Nitin Ragothaman, Dileep Kalathil, Srinivas Shakkottai. [doi]
• Why Warmup the Learning Rate? Underlying Mechanisms and ImprovementsDayal Singh Kalra, Maissam Barkeshli. [doi]
• SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation LearningJiying Zhang, Zijing Liu, Yu Wang, Bin Feng, Yu Li. [doi]
• Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure ElucidationKehan Guo, Bozhao Nan, Yujun Zhou 0002, Taicheng Guo, Zhichun Guo, Mihir Surve, Zhenwen Liang, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang 0001. [doi]
• ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less ReparameterizationHaoran You, Yipin Guo, Yichao Fu, Wei Zhou, Huihong Shi, Xiaofan Zhang 0001, Souvik Kundu 0009, Amir Yazdanbakhsh, Yingyan (Celine) Lin. [doi]
• OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and UnderstandingTao Zhang, Xiangtai Li, Hao Fei 0001, Haobo Yuan, Shengqiong Wu, Shunping Ji, Chen Change Loy, Shuicheng Yan. [doi]
• Explanations that reveal all through the definition of encodingAahlad Manas Puli, Nhi Nguyen, Rajesh Ranganath. [doi]
• A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive DelaysSaeed Masoudian, Julian Zimmert, Yevgeny Seldin. [doi]
• HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data PruningYancheng Zhang, Mengxin Zheng, Yuzhang Shang, Xun Chen, Qian Lou. [doi]
• DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular DockingJiaxian Yan, Zaixi Zhang, JinTao Zhu, Kai Zhang, Jianfeng Pei, Qi Liu. [doi]
• Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning ScenariosShantanu Jaiswal, Debaditya Roy, Basura Fernando, Cheston Tan. [doi]
• DeepDRK: Deep Dependency Regularized Knockoff for Feature SelectionHongyu Shen, Yici Yan, Zhizhen Jane Zhao. [doi]
• Collaborative Video Diffusion: Consistent Multi-video Generation with Camera ControlZhengfei Kuang, Shengqu Cai, Hao He, Yinghao Xu, Hongsheng Li, Leonidas J. Guibas, Gordon Wetzstein. [doi]
• Energy-Guided Continuous Entropic Barycenter Estimation for General CostsAlexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Anastasis Kratsios, Evgeny Burnaev, Aleksandr Korotin. [doi]
• Improved Algorithms for Contextual Dynamic PricingMatilde Tullii, Solenne Gaucher, Nadav Merlis, Vianney Perchet. [doi]
• The Limits of Transfer Reinforcement Learning with Latent Low-rank StructureTyler Sam, Yudong Chen 0001, Christina Lee Yu. [doi]
• Exploring Fixed Point in Image Editing: Theoretical Support and Convergence OptimizationChen Hang, Zhe Ma, Haoming Chen, Xuwei Fang, Vincent Xie, Faming Fang, Guixu Zhang, Hongbin Wang. [doi]
• Instance-Optimal Private Density Estimation in the Wasserstein DistanceVitaly Feldman, Audra McMillan, Satchit Sivakumar, Kunal Talwar. [doi]
• SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel OptimizationShuchen Zhu, Boao Kong, Songtao Lu, Xinmeng Huang, Kun Yuan. [doi]
• A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-WorldsTaira Tsuchiya, Shinji Ito. [doi]
• 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional RecognitionMahmoud Ahmed, Xiang Li, Arpit Prajapati, Mohamed Elhoseiny. [doi]
• MoVA: Adapting Mixture of Vision Experts to Multimodal ContextZhuofan Zong, Bingqi Ma, Dazhong Shen, Guanglu Song, Hao Shao, Dongzhi Jiang, Hongsheng Li, Yu Liu 0015. [doi]
• Visual Perception by Large Language Model's WeightsFeipeng Ma, Hongwei Xue, Yizhou Zhou, Guangting Wang, Fengyun Rao, Shilin Yan, Yueyi Zhang, Siying Wu, Mike Zheng Shou, Xiaoyan Sun 0001. [doi]
• Interpolating Item and User Fairness in Multi-Sided RecommendationsQinyi Chen, Jason Cheuk Nam Liang, Negin Golrezaei, Djallel Bouneffouf 0001. [doi]
• 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion PriorsXi Liu, Chaoyi Zhou, Siyu Huang. [doi]
• Theoretical Foundations of Deep Selective State-Space ModelsNicola Muca Cirone, Antonio Orvieto, Benjamin Walker 0001, Cristopher Salvi, Terry J. Lyons. [doi]
• RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion ModelsXinchen Zhang, Ling Yang, Yaqi Cai, Zhaochen Yu, Kai-Ni Wang, Jiake Xie, Ye Tian, Minkai Xu, Yong Tang, Yujiu Yang, Bin Cui 0001. [doi]
• Weight decay induces low-rank attention layersSeijin Kobayashi, Yassir Akram, Johannes von Oswald. [doi]
• Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data DomainsLei Wang 0108, Jieming Bian, Letian Zhang, Chen Chen 0001, Jie Xu 0001. [doi]
• Image Textualization: An Automatic Framework for Generating Rich and Detailed Image DescriptionsRenjie Pi, Jianshu Zhang, Jipeng Zhang, Rui Pan, Zhekai Chen, Tong Zhang 0001. [doi]
• Stress-Testing Capability Elicitation With Password-Locked ModelsRyan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David Krueger 0001. [doi]
• A Simple Image Segmentation Framework via In-Context ExamplesYang Liu, Chenchen Jing, Hengtao Li, Muzhi Zhu, Hao Chen 0041, Xinlong Wang, Chunhua Shen. [doi]
• Generating Highly Designable Proteins with Geometric Algebra Flow MatchingSimon Wagner, Leif Seute, Vsevolod Viliuga, Nicolas Wolf, Frauke Gräter, Jan Stühmer. [doi]
• MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activityLynn Le, Paolo Papale, Katja Seeliger, Antonio Lozano, Thirza Dado, Feng Wang, Pieter R. Roelfsema, Marcel A. J. van Gerven, Yagmur Güçlütürk, Umut Güçlü. [doi]
• MmCows: A Multimodal Dataset for Dairy Cattle MonitoringHien Vu, Omkar Prabhune, Unmesh Raskar, Dimuth Panditharatne, Hanwook Chung, Christopher Y. Choi, Younghyun Kim 0001. [doi]
• EEVR: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation LearningPragya Singh, Ritvik Budhiraja, Ankush Gupta, Anshul Goswami, Mohan Kumar, Pushpendra Singh 0001. [doi]
• EffiBench: Benchmarking the Efficiency of Automatically Generated CodeDong Huang 0005, Yuhao Qing, Weiyi Shang, Heming Cui, Jie Zhang 0050. [doi]
• Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series ForecastingRomain Ilbert, Malik Tiomoko, Cosme Louart, Ambroise Odonnat, Vasilii Feofanov, Themis Palpanas, Ievgen Redko. [doi]
• Leveraging partial stragglers within gradient codingAditya Ramamoorthy, Ruoyu Meng, Vrinda S. Girimaji. [doi]
• Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single ImagesBahri Batuhan Bilecen, Ahmet Berke Gökmen, Aysegul Dundar. [doi]
• Scribbles for All: Benchmarking Scribble Supervised Segmentation Across DatasetsWolfgang Boettcher, Lukas Hoyer, Ozan Unal, Jan Eric Lenssen, Bernt Schiele. [doi]
• Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data CorruptionsRui Yang, Jie Wang, Guoping Wu, Bin Li. [doi]
• Truthful High Dimensional Sparse Linear RegressionLiyang Zhu, Amina Manseur, Meng Ding, Jinyan Liu, Jinhui Xu 0001, Di Wang 0015. [doi]
• Transductive Active Learning: Theory and ApplicationsJonas Hübotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause 0001. [doi]
• How Diffusion Models Learn to Factorize and ComposeQiyao Liang, Ziming Liu, Mitchell Ostrow, Ila Fiete. [doi]
• RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging RadarFangqiang Ding, Xiangyu Wen, Yunzhou Zhu, Yiming Li 0003, Chris Xiaoxuan Lu. [doi]
• Learning Action and Reasoning-Centric Image Editing from Videos and SimulationBenno Krojer, Dheeraj Vattikonda, Luis Lara, Varun Jampani, Eva Portelance, Chris Pal, Siva Reddy. [doi]
• Attack-Aware Noise Calibration for Differential PrivacyBogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Flávio P. Calmon, Carmela Troncoso. [doi]
• Universal Exact Compression of Differentially Private MechanismsYanxiao Liu 0003, Wei-Ning Chen, Ayfer Özgür, Cheuk Ting Li. [doi]
• Not so griddy: Internal representations of RNNs path integrating more than one agentWilliam Redman, Francisco Acosta, Santiago Acosta-Mendoza, Nina Miolane. [doi]
• Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned PoliciesFrédéric Berdoz, Roger Wattenhofer. [doi]
• Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement LearningGaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne Collins. [doi]
• GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationAnindya Sarkar, Srikumar Sastry, Aleksis Pirinen, Chongjie Zhang, Nathan Jacobs, Yevgeniy Vorobeychik. [doi]
• Graph Neural Networks and Arithmetic CircuitsTimon Barlag, Vivian Holzapfel, Laura Strieker, Jonni Virtema, Heribert Vollmer. [doi]
• Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and MetricsLukas Klein, Carsten T. Lüth, Udo Schlegel, Till J. Bungert, Mennatallah El-Assady, Paul F. Jaeger. [doi]
• Metric Space Magnitude for Evaluating the Diversity of Latent RepresentationsKatharina Limbeck, Rayna Andreeva, Rik Sarkar, Bastian Rieck. [doi]
• What Makes and Breaks Safety Fine-tuning? A Mechanistic StudySamyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr 0001, Amartya Sanyal, Puneet K. Dokania. [doi]
• UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-TrainingBiao Gong, Shuai Tan, Yutong Feng, Xiaoying Xie, Yuyuan Li, Chaochao Chen 0001, Kecheng Zheng, Yujun Shen, Deli Zhao. [doi]
• Non-asymptotic Approximation Error Bounds of Parameterized Quantum CircuitsZhan Yu, Qiuhao Chen, Yuling Jiao, Yinan Li, Xiliang Lu, Xin Wang, Jerry Zhijian Yang. [doi]
• Boosting Vision-Language Models with TransductionMaxime Zanella, Benoît Gérin, Ismail Ben Ayed. [doi]
• AutoSurvey: Large Language Models Can Automatically Write SurveysYidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu 0002, Meishan Zhang, Xinyu Dai, Min Zhang 0005, Qingsong Wen, Wei Ye 0004, Shikun Zhang, Yue Zhang 0004. [doi]
• GraphCroc: Cross-Correlation Autoencoder for Graph Structural ReconstructionShijin Duan, Ruyi Ding, Jiaxing He, Aidong Adam Ding, Yunsi Fei, Xiaolin Xu 0001. [doi]
• Inference via Interpolation: Contrastive Representations Provably Enable Planning and InferenceBenjamin Eysenbach, Vivek Myers, Ruslan Salakhutdinov, Sergey Levine. [doi]
• Quadratic Quantum Variational Monte CarloBaiyu Su, Qiang Liu. [doi]
• DePLM: Denoising Protein Language Models for Property OptimizationZeyuan Wang, Keyan Ding, Ming Qin, Xiaotong Li, Xiang Zhuang, Yu Zhao 0009, Jianhua Yao 0001, Qiang Zhang 0026, Huajun Chen. [doi]
• RL-GPT: Integrating Reinforcement Learning and Code-as-policyShaoteng Liu, Haoqi Yuan, Minda Hu, Yanwei Li, Yukang Chen, Shu Liu 0005, Zongqing Lu, Jiaya Jia. [doi]
• Exactly Minimax-Optimal Locally Differentially Private SamplingHyun Young Park, Shahab Asoodeh, Si-Hyeon Lee. [doi]
• FedLPA: One-shot Federated Learning with Layer-Wise Posterior AggregationXiang Liu, Liangxi Liu, Feiyang Ye 0004, Yunheng Shen, Xia Li, Linshan Jiang, Jialin Li. [doi]
• Nesterov acceleration despite very noisy gradientsKanan Gupta, Jonathan W. Siegel, Stephan Wojtowytsch. [doi]
• AdaptiveISP: Learning an Adaptive Image Signal Processor for Object DetectionYujin Wang, Tianyi Xu, Zhang Fan, Tianfan Xue, Jinwei Gu. [doi]
• ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object ConceptualizationJianhua Sun 0003, Yuxuan Li, Longfei Xu, Nange Wang, Jiude Wei, Yining Zhang, Cewu Lu. [doi]
• Exploring Token Pruning in Vision State Space ModelsZheng Zhan 0001, Zhenglun Kong, Yifan Gong 0004, Yushu Wu, Zichong Meng, Hangyu Zheng, Xuan Shen, Stratis Ioannidis, Wei Niu 0002, Pu Zhao 0001, Yanzhi Wang. [doi]
• CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor SegmentationZhongzhen Huang, Yankai Jiang 0003, Rongzhao Zhang, Shaoting Zhang 0001, Xiaofan Zhang 0002. [doi]
• Query-Based Adversarial Prompt GenerationJonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr. [doi]
• Learning Goal-Conditioned Representations for Language Reward ModelsVaskar Nath, Dylan Slack, Jeff Da, Yuntao Ma, Hugh Zhang, Spencer Whitehead, Sean Hendryx. [doi]
• EGODE: An Event-attended Graph ODE Framework for Modeling Rigid DynamicsJingyang Yuan, Gongbo Sun, Zhiping Xiao 0001, Hang Zhou 0008, Xiao Luo 0001, Junyu Luo 0002, Yusheng Zhao, Wei Ju, Ming Zhang 0004. [doi]
• Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction EfficiencyYuan Deng, Jieming Mao, Vahab Mirrokni, Hanrui Zhang 0001, Song Zuo. [doi]
• MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical ProblemsBin Lei, Yi Zhang, Shan Zuo, Ali Payani, Caiwen Ding. [doi]
• Simple and Effective Masked Diffusion Language ModelsSubham S. Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan, Edgar Marroquin, Justin T. Chiu, Alexander Rush, Volodymyr Kuleshov. [doi]
• Fearless Stochasticity in Expectation PropagationJonathan So, Richard E. Turner. [doi]
• HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical HumanoidXinyu Xu, Yizheng Zhang, Yonglu Li 0001, Lei Han 0001, Cewu Lu. [doi]
• Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectorsAnisha Pal, Julia Kruk, Mansi Phute, Manognya Bhattaram, Diyi Yang, Duen Horng Chau, Judy Hoffman. [doi]
• Neglected Hessian component explains mysteries in sharpness regularizationYann N. Dauphin, Atish Agarwala, Hossein Mobahi. [doi]
• A distributional simplicity bias in the learning dynamics of transformersRiccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt. [doi]
• Linear Causal Bandits: Unknown Graph and Soft InterventionsZirui Yan, Ali Tajer. [doi]
• Model Collapse Demystified: The Case of RegressionElvis Dohmatob, Yunzhen Feng, Julia Kempe. [doi]
• INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and HelpfulnessHung Le, Doyen Sahoo, Yingbo Zhou, Caiming Xiong, Silvio Savarese. [doi]
• The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value FactorizationHaoyuan Qin, Chennan Ma, Mian Deng, Zhengzhu Liu, Songzhu Mei, Xinwang Liu, Cheng Wang, Siqi Shen. [doi]
• Do's and Don'ts: Learning Desirable Skills with Instruction VideosHyunseung Kim, ByungKun Lee, HoJoon Lee, Dongyoon Hwang, Donghu Kim, Jaegul Choo. [doi]
• Achieving Tractable Minimax Optimal Regret in Average Reward MDPsVictor Boone, Zihan Zhang. [doi]
• Conditional Generative Models are Sufficient to Sample from Any Causal Effect EstimandMd. Musfiqur Rahman, Matt Jordan, Murat Kocaoglu. [doi]
• A teacher-teacher framework for clinical language representation learningFeiqing Huang, Shenghan Zhang, Sara Morini Sweet, Tianxi Cai. [doi]
• Toward Efficient Inference for Mixture of ExpertsHaiyang Huang 0003, Newsha Ardalani, Anna Y. Sun, Liu Ke 0001, Shruti Bhosale, Hsien-Hsin S. Lee, Carole-Jean Wu, Benjamin Lee. [doi]
• Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuliChristopher Wang, Adam Uri Yaari, Aaditya Singh, Vighnesh Subramaniam, Dana Rosenfarb, Jan DeWitt, Pranav Misra, Joseph R. Madsen, Scellig Stone, Gabriel Kreiman, Boris Katz, Ignacio Cases, Andrei Barbu. [doi]
• Fast Best-of-N Decoding via Speculative RejectionHanshi Sun, Momin Haider, Ruiqi Zhang, Huitao Yang, Jiahao Qiu, Ming Yin, Mengdi Wang, Peter L. Bartlett, Andrea Zanette. [doi]
• Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit AlgorithmsJiechao Guan, Hui Xiong 0001. [doi]
• RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient BoostingHsiang Hsu, Ivan Brugere, Shubham Sharma, Freddy Lécué, Richard Chen. [doi]
• HaloScope: Harnessing Unlabeled LLM Generations for Hallucination DetectionXuefeng Du, Chaowei Xiao, Sharon Li 0001. [doi]
• Weak-to-Strong Search: Align Large Language Models via Searching over Small Language ModelsZhanhui Zhou, Zhixuan Liu, Jie Liu, Zhichen Dong, Chao Yang, Yu Qiao. [doi]
• WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language ModelsJinghan Jia, Jiancheng Liu, Yihua Zhang, Parikshit Ram, Nathalie Baracaldo, Sijia Liu 0001. [doi]
• Better by default: Strong pre-tuned MLPs and boosted trees on tabular dataDavid Holzmüller, Léo Grinsztajn, Ingo Steinwart. [doi]
• From an Image to a Scene: Learning to Imagine the World from a Million 360° VideosMatthew Wallingford, Anand Bhattad, Aditya Kusupati, Vivek Ramanujan, Matt Deitke, Aniruddha Kembhavi, Roozbeh Mottaghi, Wei-Chiu Ma, Ali Farhadi. [doi]
• MoGenTS: Motion Generation based on Spatial-Temporal Joint ModelingWeihao Yuan 0001, Yisheng He, Weichao Shen, Yuan Dong, Xiaodong Gu 0004, Zilong Dong, Liefeng Bo, Qixing Huang. [doi]
• PromptFix: You Prompt and We Fix the PhotoYongsheng Yu, Ziyun Zeng, Hang Hua, Jianlong Fu, Jiebo Luo 0001. [doi]
• Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information MinimizationZiyu Shan, Yujie Zhang, Yipeng Liu 0003, Yiling Xu. [doi]
• Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image StructureSimone Rossetti, Fiora Pirri. [doi]
• Unleashing the Potential of the Diffusion Model in Few-shot Semantic SegmentationMuzhi Zhu, Yang Liu, Zekai Luo, Chenchen Jing, Hao Chen 0041, Guangkai Xu, Xinlong Wang, Chunhua Shen. [doi]
• Memory-Efficient Gradient Unrolling for Large-Scale Bi-level OptimizationQianli Shen, Yezhen Wang, Zhouhao Yang, Xiang Li, Haonan Wang, Yang Zhang, Jonathan Scarlett, Zhanxing Zhu, Kenji Kawaguchi. [doi]
• Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex OptimizationIpsita Ghosh, Abiy Tasissa, Christian Kümmerle. [doi]
• Computing the Bias of Constant-step Stochastic Approximation with Markovian NoiseSebastian Allmeier, Nicolas Gast. [doi]
• Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementZhi Wang, Li Zhang, Wenhao Wu, Yuanheng Zhu, Dongbin Zhao, Chunlin Chen. [doi]
• Time-MMD: Multi-Domain Multimodal Dataset for Time Series AnalysisHaoxin Liu 0001, Shangqing Xu, Zhiyuan Zhao 0002, Lingkai Kong, Harshavardhan Kamarthi, Aditya B. Sasanur, Megha Sharma, Jiaming Cui, Qingsong Wen, Chao Zhang 0014, B. Aditya Prakash. [doi]
• Causal discovery with endogenous context variablesWiebke Günther, Oana-Iuliana Popescu, Martin Rabel, Urmi Ninad, Andreas Gerhardus, Jakob Runge. [doi]
• The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspectivePascal Bergsträßer, Chris Köcher, Anthony Widjaja Lin, Georg Zetzsche. [doi]
• Analyzing & Reducing the Need for Learning Rate Warmup in GPT TrainingAtli Kosson, Bettina Messmer, Martin Jaggi. [doi]
• Unraveling the Gradient Descent Dynamics of TransformersBingqing Song, Boran Han, Shuai Zhang, Jie Ding 0002, Mingyi Hong 0001. [doi]
• Learning to be Smooth: An End-to-End Differentiable Particle SmootherAli Younis, Erik B. Sudderth. [doi]
• Elucidating the Design Space of Dataset CondensationShitong Shao, Zikai Zhou, Huanran Chen, Zhiqiang Shen. [doi]
• DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-SolvingYuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, Junxian He. [doi]
• Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RLQin-Wen Luo, Ming-Kun Xie, Ye-Wen Wang, Sheng-Jun Huang. [doi]
• QKFormer: Hierarchical Spiking Transformer using Q-K AttentionChenlin Zhou, Han Zhang, Zhaokun Zhou, Liutao Yu, Liwei Huang, Xiaopeng Fan, Li Yuan 0007, Zhengyu Ma, Huihui Zhou, Yonghong Tian 0001. [doi]
• Learning Noisy Halfspaces with a Margin: Massart is No Harder than RandomGautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos, Kevin Tian. [doi]
• FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample SettingsXiao Tan 0005, Yiqin Wang, Yangyang Shen, Dian Shen, Meng Wang 0009, Peibo Duan, Beilun Wang. [doi]
• Bridging the Divide: Reconsidering Softmax and Linear AttentionDongchen Han, Yifan Pu, Zhuofan Xia, Yizeng Han, Xuran Pan, Xiu Li 0001, Jiwen Lu, Shiji Song, Gao Huang 0001. [doi]
• Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and FabricationYunuo Chen, Tianyi Xie, Zeshun Zong, Xuan Li, Feng Gao, Yin Yang 0002, Ying Nian Wu, Chenfanfu Jiang. [doi]
• Policy Optimization for Robust Average Reward MDPsZhongchang Sun, Sihong He, Fei Miao, Shaofeng Zou. [doi]
• SyncTweedies: A General Generative Framework Based on Synchronized DiffusionsJaihoon Kim, Juil Koo, Kyeongmin Yeo, Minhyuk Sung. [doi]
• UniGAD: Unifying Multi-level Graph Anomaly DetectionYiqing Lin, Jianheng Tang, Chenyi Zi, H. Vicky Zhao, Yuan Yao, Jia Li. [doi]
• Action Gaps and Advantages in Continuous-Time Distributional Reinforcement LearningHarley Wiltzer, Marc G. Bellemare, David Meger, Patrick Shafto, Yash Jhaveri. [doi]
• No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen RepresentationsWalter Simoncini, Andrei Bursuc, Spyridon Gidaris, Yuki M. Asano. [doi]
• CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial VideosTrong Thuan Nguyen, Pha A. Nguyen, Xin Li 0005, Jackson David Cothren, Alper Yilmaz, Khoa Luu. [doi]
• Approximation-Aware Bayesian OptimizationNatalie Maus, Kyurae Kim, David Eriksson, Geoff Pleiss, John P. Cunningham, Jacob R. Gardner. [doi]
• A Method for Evaluating Hyperparameter Sensitivity in Reinforcement LearningJacob Adkins, Michael Bowling, Adam White 0001. [doi]
• Exploring DCN-like architecture for fast image generation with arbitrary resolutionShuai Wang, Zexian Li, Tianhui Song, Xubin Li, Tiezheng Ge, Bo Zheng 0007, Limin Wang 0002. [doi]
• Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuliMatthias Tangemann, Matthias Kümmerer, Matthias Bethge. [doi]
• The Sample Complexity of Gradient Descent in Stochastic Convex OptimizationRoi Livni. [doi]
• Toxicity Detection for FreeZhanhao Hu, Julien Piet, Geng Zhao, Jiantao Jiao, David A. Wagner 0001. [doi]
• Regression under demographic parity constraints via unlabeled post-processingGayane Taturyan, Evgenii Chzhen, Mohamed Hebiri. [doi]
• Consensus Learning with Deep Sets for Essential Matrix EstimationDror Moran, Yuval Margalit, Guy Trostianetsky, Fadi Khatib, Meirav Galun, Ronen Basri. [doi]
• Semi-supervised Knowledge Transfer Across Multi-omic Single-cell DataFan Zhang, Tianyu Liu, Zihao Chen, Xiaojiang Peng, Chong Chen 0002, Xian-Sheng Hua 0001, Xiao Luo 0001, Hongyu Zhao. [doi]
• Segment Any ChangeZhuo Zheng, Yanfei Zhong, Liangpei Zhang 0001, Stefano Ermon. [doi]
• A theoretical design of concept sets: improving the predictability of concept bottleneck modelsMax Ruiz Luyten, Mihaela van der Schaar. [doi]
• Implicit Regularization Paths of Weighted Neural RepresentationsJin-Hong Du, Pratik Patil. [doi]
• A Modular Conditional Diffusion Framework for Image ReconstructionMagauiya Zhussip, Iaroslav Koshelev, Stamatios Lefkimmiatis. [doi]
• In Pursuit of Causal Label Correlations for Multi-label Image RecognitionZhao-Min Chen, Xin Jin, Yisu Ge, Sixian Chan. [doi]
• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement LearningHao Bai, Yifei Zhou, Jiayi Pan, Mert Cemri, Alane Suhr, Sergey Levine, Aviral Kumar. [doi]
• FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?Marco Bornstein, Amrit Singh Bedi, Abdirisak Mohamed, Furong Huang. [doi]
• Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm VarianceYiting Chen 0003, Jiazi Bu, Junchi Yan. [doi]
• Smoke and Mirrors in Causal Downstream TasksRiccardo Cadei, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, Francesco Locatello. [doi]
• Entity Alignment with Noisy Annotations from Large Language ModelsShengyuan Chen, Qinggang Zhang, Junnan Dong, Wen-hua, Qing Li 0001, Xiao Huang 0001. [doi]
• LoRA-GA: Low-Rank Adaptation with Gradient ApproximationShaowen Wang, Linxi Yu, Jian Li. [doi]
• Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language ModelsYilun Jin, Zheng Li 0018, Chenwei Zhang, Tianyu Cao 0001, Yifan Gao 0001, Pratik Jayarao, Mao Li, Xin Liu 0039, Ritesh Sarkhel, Xianfeng Tang, Haodong Wang, Zhengyang Wang, Wenju Xu, Jingfeng Yang 0001, Qingyu Yin, Xian Li, Priyanka Nigam, Yi Xu, Kai Chen 0005, Qiang Yang 0001, Meng Jiang 0001, Bing Yin. [doi]
• ChatQA: Surpassing GPT-4 on Conversational QA and RAGZihan Liu 0001, Wei Ping, Rajarshi Roy 0003, Peng Xu 0008, Chankyu Lee, Mohammad Shoeybi, Bryan Catanzaro. [doi]
• FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent SpaceYiyang Guo, Ruizhe Li, Mude Hui, Hanzhong Guo, Chen Zhang, Chuangjian Cai, Le Wan, Shangfei Wang. [doi]
• Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory MatchingYasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao 0013, Ying Nian Wu, Oscar Leong. [doi]
• Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural NetworkZih-Syuan Huang, Ching-Pei Lee. [doi]
• Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie StimuliLiwei Huang, Zhengyu Ma, Liutao Yu, Huihui Zhou, Yonghong Tian 0001. [doi]
• Chain of Agents: Large Language Models Collaborating on Long-Context TasksYusen Zhang, Ruoxi Sun 0002, Yanfei Chen, Tomas Pfister, Rui Zhang, Sercan Ö. Arik. [doi]
• MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State SpaceJiangwei Weng, Zhiqiang Yan, Ying Tai, Jianjun Qian, Jian Yang, Jun Li. [doi]
• Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement LearningStefan Pranger, Hana Chockler, Martin Tappler, Bettina Könighofer. [doi]
• End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student LearningXin Yang, Wending Yan, Michael Bi Mi, Yuan Yuan, Robby T. Tan. [doi]
• KFNN: K-Free Nearest Neighbor For CrowdsourcingWenjun Zhang 0012, Liangxiao Jiang, Chaoqun Li 0001. [doi]
• Semi-supervised Multi-label Learning with Balanced Binary Angular Margin LossXiming Li 0002, Silong Liang, Changchun Li, Pengfei Wang, Fangming Gu. [doi]
• Instance-Specific Asymmetric Sensitivity in Differential PrivacyDavid Durfee. [doi]
• Recognize Any RegionsHaosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu. [doi]
• SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference DatasetJuntao Dai, Tianle Chen, Xuyao Wang, Ziran Yang, Taiye Chen, Jiaming Ji, Yaodong Yang 0001. [doi]
• Online Weighted Paging with Unknown WeightsOrin Levy, Noam Touitou, Aviv Rosenberg. [doi]
• A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative MissingnessJiangyuan Li, Jiayi Wang, Raymond K. W. Wong, Kwun Chuen Gary Chan. [doi]
• Online Iterative Reinforcement Learning from Human Feedback with General Preference ModelChenlu Ye, Wei Xiong 0015, Yuheng Zhang, Hanze Dong, Nan Jiang 0008, Tong Zhang 0001. [doi]
• UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial VehiclesHui Ye, Rajshekhar Sunderraman, Jonathan Shihao Ji. [doi]
• ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion ForecastingSharmita Dey, Sarath Ravindran Nair. [doi]
• Relationship Prompt Learning is Enough for Open-Vocabulary Semantic SegmentationJiahao Li, Yang Lu 0009, Yuan Xie 0006, Yanyun Qu. [doi]
• On the Use of Anchoring for Training Vision ModelsVivek Sivaraman Narayanaswamy, Kowshik Thopalli, Rushil Anirudh, Yamen Mubarka, Wesam Sakla, Jayaraman J. Thiagarajan. [doi]
• UniMTS: Unified Pre-training for Motion Time SeriesXiyuan Zhang 0001, Diyan Teng, Ranak Roy Chowdhury, Shuheng Li, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang. [doi]
• Mixture of Tokens: Continuous MoE through Cross-Example AggregationSzymon Antoniak, Michal Krutul, Maciej Pióro, Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Król, Tomasz Odrzygózdz, Marek Cygan, Sebastian Jaszczur. [doi]
• On Feature Learning in Structured State Space ModelsLeena Chennuru Vankadara, Jin Xu, Moritz Haas, Volkan Cevher. [doi]
• ReFT: Representation Finetuning for Language ModelsZhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning, Christopher Potts. [doi]
• Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion PerceptionShuangpeng Han, Ziyu Wang, Mengmi Zhang. [doi]
• Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural NetworksXuyuan Liu, Yinghao Cai, Qihui Yang, Yujun Yan. [doi]
• DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency DomainFengpeng Li, Kemou Li, Haiwei Wu, Jinyu Tian 0001, Jiantao Zhou 0001. [doi]
• VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface ReconstructionHanlin Chen, Fangyin Wei, Chen Li 0038, Tianxin Huang, Yunsong Wang, Gim Hee Lee. [doi]
• ChatCam: Empowering Camera Control through Conversational AIXinhang Liu, Yu-Wing Tai, Chi-Keung Tang. [doi]
• Token Merging for Training-Free Semantic Binding in Text-to-Image SynthesisTaihang Hu, Linxuan Li, Joost van de Weijer 0001, Hongcheng Gao, Fahad Shahbaz Khan, Jian Yang, Ming-Ming Cheng, Kai Wang, Yaxing Wang. [doi]
• InstructG2I: Synthesizing Images from Multimodal Attributed GraphsBowen Jin, Ziqi Pang, Bingjun Guo, Yu-Xiong Wang, Jiaxuan You, Jiawei Han 0001. [doi]
• Evaluating the World Model Implicit in a Generative ModelKeyon Vafa, Justin Y. Chen, Ashesh Rambachan, Jon M. Kleinberg, Sendhil Mullainathan. [doi]
• Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential PrivacyZeki Kazan, Jerome P. Reiter. [doi]
• A scalable generative model for dynamical system reconstruction from neuroimaging dataEric Volkmann, Alena Brändle, Daniel Durstewitz, Georgia Koppe. [doi]
• On the Impact of Feature Heterophily on Link Prediction with Graph Neural NetworksJiong Zhu, Gaotang Li, Yao-An Yang, Jing Zhu 0005, Xuehao Cui, Danai Koutra. [doi]
• Off-policy estimation with adaptively collected data: the power of online learningJeonghwan Lee, Cong Ma 0001. [doi]
• Practical Bayesian Algorithm Execution via Posterior SamplingChu Xin Cheng, Raul Astudillo, Thomas A. Desautels, Yisong Yue. [doi]
• FNP: Fourier Neural Processes for Arbitrary-Resolution Data AssimilationKun Chen, Peng Ye, Hao Chen 0045, Kang Chen, Tao Han 0002, Wanli Ouyang, Tao Chen 0003, Lei Bai 0001. [doi]
• Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay BuffersGautham Vasan, Mohamed Elsayed 0003, Seyed Alireza Azimi, Jiamin He, Fahim Shahriar, Colin Bellinger, Martha White, Rupam Mahmood. [doi]
• Dual Lagrangian Learning for Conic OptimizationMathieu Tanneau, Pascal Van Hentenryck. [doi]
• ENAT: Rethinking Spatial-temporal Interactions in Token-based Image SynthesisZanlin Ni, Yulin Wang, Renping Zhou, Yizeng Han, Jiayi Guo, Zhiyuan Liu 0001, Yuan Yao 0013, Gao Huang 0001. [doi]
• Everyday Object Meets Vision-and-Language Navigation Agent via BackdoorKeji He, Kehan Chen, Jiawang Bai, Yan Huang 0008, Qi Wu 0001, Shu-Tao Xia, Liang Wang 0001. [doi]
• Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh RecoveryYongwei Nie, Mingxian Fan, Chengjiang Long, Qing Zhang 0006, Jian Zhu 0001, Xuemiao Xu. [doi]
• PrefPaint: Aligning Image Inpainting Diffusion Model with Human PreferenceKendong Liu, Zhiyu Zhu, Chuanhao Li, Hui Liu 0032, Huanqiang Zeng, Junhui Hou. [doi]
• Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth ActivationKaibo Zhang, Yunjuan Wang, Raman Arora. [doi]
• DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable DiffusionKe Sun 0016, Shen Chen, Taiping Yao, Hong Liu 0009, Xiaoshuai Sun, Shouhong Ding, Rongrong Ji. [doi]
• A Universal Growth Rate for Learning with Smooth Surrogate LossesAnqi Mao, Mehryar Mohri, Yutao Zhong 0002. [doi]
• Localized Adaptive Risk ControlMatteo Zecchin, Osvaldo Simeone. [doi]
• Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor DefenseRui Min, Zeyu Qin, Nevin L. Zhang, Li Shen 0008, Minhao Cheng. [doi]
• ClevrSkills: Compositional Language And Visual Reasoning in RoboticsSanjay Haresh, Daniel Dijkman, Apratim Bhattacharyya, Roland Memisevic. [doi]
• Real-Time Selection Under General Constraints via Predictive InferenceYuyang Huo, Lin Lu, Haojie Ren, Changliang Zou. [doi]
• SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier FunctionsHongchao Zhang, Zhizhen Qin, Sicun Gao, Andrew Clark 0001. [doi]
• Towards Multi-Domain Learning for Generalizable Video Anomaly DetectionMyeongAh Cho, Taeoh Kim, Minho Shim, Dongyoon Wee, Sangyoun Lee. [doi]
• EffiLearner: Enhancing Efficiency of Generated Code via Self-OptimizationDong Huang 0005, Jianbo Dai, Han Weng, Puzhen Wu, Yuhao Qing, Heming Cui, Zhijiang Guo, Jie Zhang 0050. [doi]
• Video Diffusion Models are Training-free Motion Interpreter and ControllerZeqi Xiao, Yifan Zhou, Shuai Yang, Xingang Pan. [doi]
• TuneTables: Context Optimization for Scalable Prior-Data Fitted NetworksBenjamin Feuer, Robin Schirrmeister, Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum, Niv Cohen, Colin White. [doi]
• EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for ElectromyographyJehan Yang, Maxwell Soh, Vivianna Lieu, Douglas J. Weber, Zackory Erickson. [doi]
• Differentiable Quantum Computing for Large-scale Linear ControlConnor Clayton, Jiaqi Leng, Gengzhi Yang, Yi-Ling Qiao, Ming C. Lin, Xiaodi Wu 0001. [doi]
• Déjà Vu Memorization in Vision-Language ModelsBargav Jayaraman, Chuan Guo 0001, Kamalika Chaudhuri. [doi]
• Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for ControlGunshi Gupta, Karmesh Yadav, Yarin Gal, Dhruv Batra, Zsolt Kira, Cong Lu, Tim G. J. Rudner. [doi]
• Pre-trained Large Language Models Use Fourier Features to Compute AdditionTianyi Zhou, Deqing Fu, Vatsal Sharan, Robin Jia. [doi]
• Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel CollaborationYichong Huang, Xiaocheng Feng, Baohang Li, Yang Xiang, Hui Wang, Ting Liu, Bing Qin 0001. [doi]
• Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight FrameEvan Markou, Thalaiyasingam Ajanthan, Stephen Gould. [doi]
• IllumiNeRF: 3D Relighting Without Inverse RenderingXiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin-Brualla, Philipp Henzler. [doi]
• Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion ModelsYuxuan Xue, Xianghui Xie, Riccardo Marin, Gerard Pons-Moll. [doi]
• Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View SynthesisDiwen Wan, Yuxiang Wang, Ruijie Lu, Gang Zeng. [doi]
• Revisiting Differentially Private ReLU RegressionMeng Ding, Mingxi Lei, Liyang Zhu, Shaowei Wang 0003, Di Wang 0015, Jinhui Xu 0001. [doi]
• Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time SeriesVijay Ekambaram, Arindam Jati, Pankaj Dayama 0001, Sumanta Mukherjee, Nam Nguyen, Wesley M. Gifford, Chandra Reddy, Jayant Kalagnanam. [doi]
• Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksJiacong Hu, Jing Gao, Jingwen Ye, Yang Gao, Xingen Wang, Zunlei Feng, Mingli Song. [doi]
• ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction HorizonsJiawen Zhang, Xumeng Wen, Zhenwei Zhang, Shun Zheng, Jia Li 0009, Jiang Bian 0002. [doi]
• Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, EditingHao Fei 0001, Shengqiong Wu, Hanwang Zhang, Tat-Seng Chua, Shuicheng Yan. [doi]
• Automating Data Annotation under Strategic Human Agents: Risks and Potential SolutionsTian Xie, Xueru Zhang. [doi]
• Generalization of Hamiltonian algorithmsAndreas Maurer. [doi]
• Rethinking Score Distillation as a Bridge Between Image DistributionsDavid McAllister, Songwei Ge, Jia-Bin Huang 0001, David Jacobs 0001, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa. [doi]
• MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language ModelsLeyang Shen, Gongwei Chen, Rui Shao, Weili Guan, Liqiang Nie. [doi]
• FERERO: A Flexible Framework for Preference-Guided Multi-Objective LearningLisha Chen, A. F. M. Saif, Yanning Shen, Tianyi Chen. [doi]
• Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation ModelsAthanasios Tragakis, Marco Aversa, Chaitanya Kaul, Roderick Murray-Smith, Daniele Faccio. [doi]
• Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPsMatthew Zurek, Yudong Chen. [doi]
• Can Models Learn Skill Composition from Examples?Haoyu Zhao, Simran Kaur 0001, Dingli Yu, Anirudh Goyal, Sanjeev Arora. [doi]
• Bayesian Online Natural Gradient (BONG)Matt Jones 0002, Peter G. Chang, Kevin P. Murphy. [doi]
• UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA LabelsJacob Silberg, Kyle Swanson, Elana Simon, Angela Zhang, Zaniar Ghazizadeh, Scott Ogden, Hisham Hamadeh, James Y. Zou. [doi]
• Amortized Planning with Large-Scale Transformers: A Case Study on ChessAnian Ruoss, Grégoire Delétang, Sourabh Medapati, Jordi Grau-Moya, Kevin Li, Elliot Catt, John Reid, Cannada Lewis, Joel Veness, Tim Genewein. [doi]
• CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object DetectionJisong Kim, Minjae Seong, Jun Won Choi. [doi]
• Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence ImaginationRuochen Liu, Hao Chen, Yuanchen Bei, Qijie Shen, Fangwei Zhong, Senzhang Wang, Jianxin Wang. [doi]
• Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly DetectionYu Zhang, Ruoyu Li, Nengwu Wu, Qing Li, Xinhan Lin, Yang Hu, Tao Li, Yong Jiang. [doi]
• Online Consistency of the Nearest Neighbor RuleGeelon So, Sanjoy Dasgupta. [doi]
• Constrained Synthesis with Projected Diffusion ModelsJacob K. Christopher, Stephen Baek, Ferdinando Fioretto. [doi]
• Universal Neural FunctionalsAllan Zhou, Chelsea Finn, James Harrison. [doi]
• Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic SegmentationRuihao Xia, Yu Liang, Peng-Tao Jiang, Hao Zhang, Bo Li, Yang Tang, Pan Zhou 0002. [doi]
• Regularized Conditional Diffusion Model for Multi-Task Preference AlignmentXudong Yu, Chenjia Bai, Haoran He, Changhong Wang, Xuelong Li 0001. [doi]
• Mean-Field Langevin Dynamics for Signed Measures via a Bilevel ApproachGuillaume Wang, Alireza Mousavi Hosseini, Lénaïc Chizat. [doi]
• Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance RepresentationXinhao Zheng, Yang Li, Cunxin Fan, Huaijin Wu, Xinhao Song, Junchi Yan. [doi]
• Generative Semi-supervised Graph Anomaly DetectionHezhe Qiao, Qingsong Wen, Xiaoli Li 0001, Ee-Peng Lim, Guansong Pang. [doi]
• GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell GenomicsDominik Klein, Théo Uscidda, Fabian J. Theis, Marco Cuturi. [doi]
• Ex Uno Pluria: Insights on Ensembling in Low Precision Number SystemsGiung Nam, Juho Lee 0001. [doi]
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSZhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang. [doi]
• TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance ControlWeichao Zeng, Yan Shu, Zhenhang Li, Dongbao Yang, Yu Zhou. [doi]
• An Analysis of Tokenization: Transformers under Markov DataNived Rajaraman, Jiantao Jiao, Kannan Ramchandran. [doi]
• PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant PerturbationsJiatong Li 0002, Renjun Hu, Kunzhe Huang, Yan Zhuang, Qi Liu 0003, Mengxiao Zhu 0001, Xing Shi, Wei Lin 0016. [doi]
• On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)Jerry Yao-Chieh Hu, Weimin Wu, Zhuoru Li, Sophia Pi, Zhao Song 0002, Han Liu 0001. [doi]
• On the cohesion and separability of average-link for hierarchical agglomerative clusteringEduardo Laber, Miguel Batista. [doi]
• CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMsZirui Wang, Mengzhou Xia, Luxi He, Howard Chen 0003, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, Alexis Chevalier, Sanjeev Arora, Danqi Chen 0001. [doi]
• Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical SystemsKurt Butler, Daniel Waxman 0002, Petar M. Djuric. [doi]
• Training Data Attribution via Approximate UnrollingJuhan Bae, Wu Lin, Jonathan Lorraine, Roger B. Grosse. [doi]
• BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement LearningHaohong Lin, Wenhao Ding, Jian Chen, Laixi Shi, Jiacheng Zhu, Bo Li, Ding Zhao. [doi]
• Sample-Efficient Agnostic BoostingUdaya Ghai, Karan Singh. [doi]
• FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion ModelsTong Wu, Yinghao Xu, Ryan Po, Mengchen Zhang 0001, Guandao Yang, Jiaqi Wang 0003, Ziwei Liu 0002, Dahua Lin, Gordon Wetzstein. [doi]
• Confidence Calibration of Classifiers with Many ClassesAdrien Le-Coz, Stéphane Herbin, Faouzi Adjed. [doi]
• On the Necessity of Collaboration for Online Model Selection with Decentralized DataJunfan Li, Zheshun Wu, Zenglin Xu, Irwin King. [doi]
• SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer DevicesRuslan Svirschevski, Avner May, Zhuoming Chen, Beidi Chen, Zhihao Jia, Max Ryabinin. [doi]
• Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement LearningLanqing Li, Hai Zhang, Xinyu Zhang, Shatong Zhu, Yang Yu, Junqiao Zhao, Pheng-Ann Heng. [doi]
• Learning the Expected Core of Strictly Convex Stochastic Cooperative GamesNam Phuong Tran, The-Anh Ta, Shuqing Shi, Debmalya Mandal, Yali Du 0001, Long Tran-Thanh. [doi]
• Rethinking Out-of-Distribution Detection on Imbalanced Data DistributionKai Liu, Zhihang Fu, Sheng Jin 0002, Chao Chen, Ze Chen, Rongxin Jiang 0001, Fan Zhou 0007, Yaowu Chen, Jieping Ye. [doi]
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM AgentsEdoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer 0002, Florian Tramèr. [doi]
• Learning 3D Garment Animation from Trajectories of A Piece of ClothYidi Shao, Chen Change Loy, Bo Dai 0002. [doi]
• Fight Back Against Jailbreaking via Prompt Adversarial TuningYichuan Mo, Yuji Wang, Zeming Wei, Yisen Wang 0001. [doi]
• A General Protocol to Probe Large Vision Models for 3D Physical UnderstandingGuanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman. [doi]
• Improved Particle Approximation Error for Mean Field Neural NetworksAtsushi Nitanda. [doi]
• Speaking Your Language: Spatial Relationships in Interpretable Emergent CommunicationOlaf Lipinski, Adam J. Sobey, Federico Cerutti 0001, Timothy J. Norman. [doi]
• Is Programming by Example Solved by LLMs?Wen-Ding Li, Kevin Ellis. [doi]
• Why Go Full? Elevating Federated Learning Through Partial Network UpdatesHaolin Wang, Xuefeng Liu 0001, Jianwei Niu 0002, Wenkai Guo, Shaojie Tang 0001. [doi]
• Self-Labeling the Job Shop Scheduling ProblemAndrea Corsini, Angelo Porrello, Simone Calderara, Mauro Dell'Amico. [doi]
• ReFIR: Grounding Large Restoration Models with Retrieval AugmentationHang Guo, Tao Dai 0001, Zhihao Ouyang, Taolin Zhang 0003, Yaohua Zha, Bin Chen 0011, Shu-Tao Xia. [doi]
• Motion Graph Unleashed: A Novel Approach to Video PredictionYiqi Zhong, Luming Liang, Bohan Tang, Ilya Zharkov, Ulrich Neumann. [doi]
• A Theoretical Perspective for Speculative Decoding AlgorithmMing Yin 0003, Minshuo Chen, Kaixuan Huang, Mengdi Wang. [doi]
• ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep GenerationYizhuo Ma, Shanmin Pang, Qi Guo, Tianyu Wei, Qing Guo 0005. [doi]
• Humanoid Locomotion as Next Token PredictionIlija Radosavovic, Bike Zhang, Baifeng Shi, Jathushan Rajasegaran, Sarthak Kamat, Trevor Darrell, Koushil Sreenath, Jitendra Malik. [doi]
• Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential ChoiceSebastiaan De Peuter, Shibei Zhu, Yujia Guo, Andrew Howes, Samuel Kaski. [doi]
• MeMo: Meaningful, Modular Controllers via Noise InjectionMegan Tjandrasuwita, Jie Xu 0028, Armando Solar-Lezama, Wojciech Matusik. [doi]
• MALT Powers Up Adversarial AttacksOdelia Melamed, Gilad Yehudai, Adi Shamir. [doi]
• Transformer Doctor: Diagnosing and Treating Vision TransformersJiacong Hu, Hao Chen 0041, Kejia Chen 0007, Yang Gao 0001, Jingwen Ye, Xingen Wang, Mingli Song, Zunlei Feng. [doi]
• Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer NormalizationQihao Liu, Zhanpeng Zeng, Ju He, Qihang Yu, Xiaohui Shen, Liang-Chieh Chen. [doi]
• Interventional Causal Discovery in a Mixture of DAGsBurak Varici, Dmitriy Katz, Dennis Wei, Prasanna Sattigeri, Ali Tajer. [doi]
• SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD LearningPaul Mangold, Sergey Samsonov, Safwan Labbi, Ilya Levin, Réda Alami, Alexey Naumov, Eric Moulines. [doi]
• Mixture of Experts Meets Prompt-Based Continual LearningMinh Le, An Nguyen The, Huy Nguyen, Trang Nguyen, Trang Pham, Linh Ngo, Nhat Ho. [doi]
• SparseLLM: Towards Global Pruning of Pre-trained Language ModelsGuangji Bai, Yijiang Li, Chen Ling 0003, Kibaek Kim, Liang Zhao 0002. [doi]
• Rethinking The Training And Evaluation of Rich-Context Layout-to-Image GenerationJiaxin Cheng, Zixu Zhao, Tong He 0002, Tianjun Xiao, Zheng Zhang 0001, Yicong Zhou. [doi]
• On the Complexity of Learning Sparse Functions with Statistical and Gradient QueriesNirmit Joshi, Theodor Misiakiewicz, Nati Srebro. [doi]
• EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free ProbingQibo Qiu, Shun Zhang, Haiming Gao, Honghui Yang, Haochao Ying, Wenxiao Wang 0001, Xiaofei He 0001. [doi]
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?Jiahua Dong 0001, Wenqi Liang, Hongliu Li, Duzhen Zhang, Meng Cao, Henghui Ding, Salman H. Khan 0001, Fahad Shahbaz Khan. [doi]
• FUGAL: Feature-fortified Unrestricted Graph AlignmentAditya Bommakanti, Harshith Reddy Vonteri, Konstantinos Skitsas, Sayan Ranu, Davide Mottin, Panagiotis Karras. [doi]
• Conformal Alignment: Knowing When to Trust Foundation Models with GuaranteesYu Gui, Ying Jin, Zhimei Ren. [doi]
• Maximum Entropy Reinforcement Learning via Energy-Based Normalizing FlowChen-Hao Chao, Chien Feng, Wei-Fang Sun, Cheng-Kuang Lee, Simon See, Chun-Yi Lee. [doi]
• Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable SegmentationJian Hu 0002, Jiayi Lin 0002, Junchi Yan, Shaogang Gong. [doi]
• Mitigating Biases in Blackbox Feature Extractors for Image Classification TasksAbhipsa Basu, Saswat Subhajyoti Mallick, R. Venkatesh Babu. [doi]
• Weak Supervision Performance Evaluation via Partial IdentificationFelipe Maia Polo, Subha Maity, Mikhail Yurochkin, Moulinath Banerjee, Yuekai Sun. [doi]
• Opponent Modeling based on Subgoal InferenceXiaopeng Yu, Jiechuan Jiang, Zongqing Lu. [doi]
• LG-VQ: Language-Guided Codebook LearningGuotao Liang, Baoquan Zhang, Yaowei Wang 0001, Yunming Ye, Xutao Li, Huaibin Wang, Chuyao Luo, Kola Ye, Linfeng Luo. [doi]
• Axioms for AI Alignment from Human FeedbackLuise Ge, Daniel Halpern 0002, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu 0001. [doi]
• Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured trainingYanlai Yang, Matt Jones 0001, Michael C. Mozer, Mengye Ren. [doi]
• Learning to Understand: Identifying Interactions via the Möbius TransformJustin Singh Kang, Yigit Efe Erginbas, Landon Butler, Ramtin Pedarsani, Kannan Ramchandran. [doi]
• Improving Temporal Link Prediction via Temporal Walk Matrix ProjectionXiaodong Lu, Leilei Sun, Tongyu Zhu, Weifeng Lv. [doi]
• Benchmarking Counterfactual Image GenerationThomas Melistas, Nikos Spyrou, Nefeli Gkouti, Pedro Sanchez, Athanasios Vlontzos, Yannis Panagakis, Giorgos Papanastasiou, Sotirios A. Tsaftaris. [doi]
• Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label ConfigurationsHao Chen 0102, Ankit Shah 0001, Jindong Wang 0001, Ran Tao 0013, Yidong Wang, Xiang Li 0106, Xing Xie 0001, Masashi Sugiyama, Rita Singh, Bhiksha Raj. [doi]
• An End-To-End Graph Attention Network Hashing for Cross-Modal RetrievalHuilong Jin, Yingxue Zhang, Lei Shi 0030, Shuang Zhang 0009, Feifei Kou, Jiapeng Yang, Chuangying zhu, Jia Luo 0001. [doi]
• Distributed Least Squares in Small Space via Sketching and Bias ReductionSachin Garg, Kevin Tan, Michal Derezinski. [doi]
• Optimal Classification under Performative Distribution ShiftEdwige Cyffers, Muni Sreenivas Pydi, Jamal Atif, Olivier Cappé. [doi]
• Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial ShiftsAndong Wang, Yuning Qiu, Mingyuan Bai, Zhong Jin, GuoXu Zhou, Qibin Zhao. [doi]
• Benchmarking LLMs via Uncertainty QuantificationFanghua Ye 0001, Mingming Yang, Jianhui Pang, Longyue Wang, Derek F. Wong, Emine Yilmaz, Shuming Shi 0001, Zhaopeng Tu. [doi]
• Improving Robustness of 3D Point Cloud Recognition from a Fourier PerspectiveYibo Miao, Yinpeng Dong, Jinlai Zhang, Lijia Yu, Xiao Yang, Xiao-Shan Gao. [doi]
• Calibrated Self-Rewarding Vision Language ModelsYiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang, Zhaorun Chen, Chenhang Cui, Xiyao Wang, Yun Li, Linjun Zhang, Huaxiu Yao. [doi]
• SpeechAlign: Aligning Speech Generation to Human PreferencesDong Zhang, Zhaowei Li, Shimin Li, Xin Zhang, Pengyu Wang, Yaqian Zhou, Xipeng Qiu. [doi]
• Oracle-Efficient Differentially Private Learning with Public DataAdam Block, Mark Bun, Rathin Desai, Abhishek Shetty, Zhiwei Steven Wu. [doi]
• Learning World Models for Unconstrained Goal NavigationYuanlin Duan, Wensen Mao, He Zhu 0001. [doi]
• SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational OverheadMinsu Kim 0003, Walid Saad, Mérouane Debbah, Choong Seon Hong. [doi]
• Tighter Convergence Bounds for Shuffled SGD via Primal-Dual PerspectiveXufeng Cai, Cheuk Yin Lin, Jelena Diakonikolas. [doi]
• Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed AnalysisIoannis Anagnostides, Tuomas Sandholm. [doi]
• BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n SamplingLin Gui, Cristina Garbacea, Victor Veitch. [doi]
• BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language ModelsYibin Wang 0005, Haizhou Shi, Ligong Han, Dimitris N. Metaxas, Hao Wang 0014. [doi]
• Revisiting K-mer Profile for Effective and Scalable Genome Representation LearningAbdulkadir Çelikkanat, Andrés R. Masegosa, Thomas Nielsen. [doi]
• Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite ProgrammingLorenzo Orecchia, Jiawei Hu, Xue He, Wang Mark, XuLei Yang, Min Wu 0008, Xue Geng. [doi]
• APEBench: A Benchmark for Autoregressive Neural Emulators of PDEsFelix Koehler, Simon Niedermayr, Rüdiger Westermann, Nils Thuerey. [doi]
• AUC Maximization under Positive Distribution ShiftAtsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Yasuhiro Fujiwara. [doi]
• Learning Diffusion Priors from Observations by Expectation MaximizationFrançois Rozet, Gérôme Andry, François Lanusse, Gilles Louppe. [doi]
• Understanding Emergent Abilities of Language Models from the Loss PerspectiveZhengxiao Du, Aohan Zeng, Yuxiao Dong, Jie Tang 0001. [doi]
• ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot CoordinationXihuai Wang, Shao Zhang, Wenhao Zhang, Wentao Dong, Jingxiao Chen, Ying Wen 0001, Weinan Zhang 0001. [doi]
• MetaLA: Unified Optimal Linear Approximation to Softmax Attention MapYuhong Chou, Man Yao, Kexin Wang, Yuqi Pan, Rui-Jie Zhu 0003, Jibin Wu, Yiran Zhong, Yu Qiao, Bo Xu 0002, Guoqi Li. [doi]
• SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image ClassificationBenjamin Feuer, Jiawei Xu, Niv Cohen, Patrick Yubeaton, Govind Mittal, Chinmay Hegde. [doi]
• Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled DataZhilin Zhao 0001, Longbing Cao, Xuhui Fan 0001, Wei-Shi Zheng 0001. [doi]
• Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RLYangru Huang, Peixi Peng, Yifan Zhao 0002, Guangyao Chen, Yonghong Tian 0001. [doi]
• Sequential Decision Making with Expert Demonstrations under Unobserved HeterogeneityVahid Balazadeh Meresht, Keertana Chidambaram, Viet Nguyen, Rahul G. Krishnan, Vasilis Syrgkanis. [doi]
• No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language ModelsAngéline Pouget, Lucas Beyer, Emanuele Bugliarello, Xiao Wang 0038, Andreas Steiner, Xiaohua Zhai, Ibrahim M. Alabdulmohsin. [doi]
• LocCa: Visual Pretraining with Location-aware CaptionersBo Wan, Michael Tschannen, Yongqin Xian, Filip Pavetic, Ibrahim M. Alabdulmohsin, Xiao Wang 0038, André Susano Pinto, Andreas Steiner, Lucas Beyer, Xiaohua Zhai. [doi]
• Gradient-based Discrete Sampling with Automatic Cyclical SchedulingPatrick Pynadath, Riddhiman Bhattacharya, Arun Hariharan, Ruqi Zhang. [doi]
• ProTransformer: Robustify Transformers via Plug-and-Play ParadigmZhichao Hou, Weizhi Gao, Yuchen Shen, Feiyi Wang, Xiaorui Liu. [doi]
• Can Large Language Model Agents Simulate Human Trust Behavior?Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Shiyang Lai, Kai Shu, Jindong Gu, Adel Bibi, Ziniu Hu, David Jurgens, James Evans, Philip Torr 0001, Bernard Ghanem, Guohao Li 0001. [doi]
• RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from ScriptsJiaheng Liu, Zehao Ni, Haoran Que, Tao Sun, Noah Wang, Jian Yang 0030, Jiakai Wang, Hongcheng Guo, Zhongyuan Peng, Ge Zhang, Jiayi Tian, Xingyuan Bu, Ke Xu 0001, Wenge Rong, Junran Peng, Zhaoxiang Zhang 0001. [doi]
• ProgressGym: Alignment with a Millennium of Moral ProgressTianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang 0001. [doi]
• If You Want to Be Robust, Be Wary of InitializationSofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, El Houcine Bergou. [doi]
• Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?Haoang Chi, He Li, Wenjing Yang 0002, Feng Liu 0003, Long Lan, Xiaoguang Ren, Tongliang Liu, Bo Han 0003. [doi]
• Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational DataSofia Ek, Dave Zachariah. [doi]
• Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image CompressionXi Zhang, Xiaolin Wu. [doi]
• PUZZLES: A Benchmark for Neural Algorithmic ReasoningBenjamin Estermann, Luca A. Lanzendörfer, Yannick Niedermayr, Roger Wattenhofer. [doi]
• Statistical Multicriteria Benchmarking via the GSD-FrontChristoph Jansen, Georg Schollmeyer, Julian Rodemann, Hannah Blocher, Thomas Augustin 0001. [doi]
• Understanding and Improving Adversarial Collaborative Filtering for Robust RecommendationKaike Zhang, Qi Cao, Yunfan Wu, Fei Sun 0001, Huawei Shen, Xueqi Cheng. [doi]
• Mission Impossible: A Statistical Perspective on Jailbreaking LLMsJingtong Su, Julia Kempe, Karen Ullrich. [doi]
• Identifiability Guarantees for Causal Disentanglement from Purely Observational DataRyan Welch, Jiaqi Zhang, Caroline Uhler. [doi]
• Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State SegmentationSagi Eppel, Jolina Li, Manuel S. Drehwald, Alán Aspuru-Guzik. [doi]
• Online Adaptation of Language Models with a Memory of Amortized ContextsJihoon Tack, Jaehyung Kim 0001, Eric Mitchell, Jinwoo Shin, Yee Whye Teh, Jonathan Richard Schwarz. [doi]
• Policy-shaped prediction: avoiding distractions in model-based reinforcement learningMiles Hutson, Isaac Kauvar, Nick Haber. [doi]
• Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse ProblemsJiawei Zhang, Jiaxin Zhuang, Cheng Jin, Gen Li, Yuantao Gu. [doi]
• Classification Diffusion Models: Revitalizing Density Ratio EstimationShahar Yadin, Noam Elata, Tomer Michaeli. [doi]
• A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language ModelsHirofumi Tsuruta, Hiroyuki Yamazaki, Ryota Maeda, Ryotaro Tamura, Akihiro Imura. [doi]
• Sourcerer: Sample-based Maximum Entropy Source Distribution EstimationJulius Vetter, Guy Moss, Cornelius Schröder, Richard Gao, Jakob H. Macke. [doi]
• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model FeaturesLetian Wang, Seung Wook Kim 0001, Jiawei Yang, Cunjun Yu, Boris Ivanovic, Steven L. Waslander, Yue Wang 0036, Sanja Fidler, Marco Pavone 0001, Péter Karkus. [doi]
• Iteration Head: A Mechanistic Study of Chain-of-ThoughtVivien Cabannes, Charles Arnal, Wassim Bouaziz, Xingyu Yang, François Charton, Julia Kempe. [doi]
• VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video UnderstandingHoulun Chen, Xin Wang 0019, Hong Chen, Zeyang Zhang, Wei Feng, Bin Huang, Jia Jia 0001, Wenwu Zhu 0001. [doi]
• On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion ModelsTariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall, Reyhane Askari Hemmat, Yohann Benchetrit, Marton Havasi, Matthew J. Muckley, Karteek Alahari, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal. [doi]
• Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear FormsChengyuan Deng, Jie Gao, Kevin Lu, Feng Luo, Hongbin Sun, Cheng Xin. [doi]
• Spiking Neural Network as Adaptive Event Stream SlicerJiahang Cao, Mingyuan Sun, Ziqing Wang, Hao Cheng, Qiang Zhang 0029, Shibo Zhou, Renjing Xu. [doi]
• Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain SegmentersDong Zhao, Qi Zang, Shuang Wang 0001, Nicu Sebe, Zhun Zhong. [doi]
• Fast Last-Iterate Convergence of Learning in Games Requires Forgetful AlgorithmsYang Cai 0001, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-wei Lee, Haipeng Luo, Weiqiang Zheng. [doi]
• FinBen: A Holistic Financial Benchmark for Large Language ModelsQianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu 0001, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Yangyang Yu, Gang Hu 0003, Jiajia Huang, Xiao-Yang Liu, Alejandro Lopez-Lira, Benyou Wang, Yanzhao Lai, Hao Wang, Min Peng 0002, Sophia Ananiadou, Jimin Huang. [doi]
• QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-PenalizationQi Song, Tianxiang Gong, Shiqi Gao, Haoyi Zhou, Jianxin Li 0002. [doi]
• VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological ImagesM. Maruf, Arka Daw, Kazi Sajeed Mehrab, Harish Babu Manogaran, Abhilash Neog, Medha Sawhney, Mridul Khurana, James P. Balhoff, Yasin Bakis, Bahadir Altintas, Matthew J. Thompson, Elizabeth G. Campolongo, Josef C. Uyeda, Hilmar Lapp, Henry L. Bart Jr., Paula M. Mabee, Yu Su 0001, Wei-Lun Chao, Charles V. Stewart, Tanya Y. Berger-Wolf, Wasila M. Dahdul, Anuj Karpatne. [doi]
• Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spacesAngeliki Kamoutsi, Peter Schmitt-Förster, Tobias Sutter, Volkan Cevher, John Lygeros. [doi]
• Learning Distributions on Manifolds with Free-Form FlowsPeter Sorrenson, Felix Draxler, Armand Rousselot, Sander Hummerich, Ullrich Köthe. [doi]
• A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled ConstraintsLiuyuan Jiang, Quan Xiao, Victor Tenorio, Fernando Real-Rojas, Antonio G. Marques, Tianyi Chen. [doi]
• Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object PosesSeungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung. [doi]
• Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation MismatchMalek Mechergui, Sarath Sreedharan. [doi]
• NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage RegimesHao-Lun Sun, Lei Hsiung, Nandhini Chandramoorthy, Pin-Yu Chen, Tsung-Yi Ho. [doi]
• OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map ConstructionHongbo Zhao 0006, Lue Fan, YunTao Chen, Haochen Wang, Yuran Yang, Xiaojuan Jin, Yixin Zhang, Gaofeng Meng, Zhao-Xiang Zhang. [doi]
• Self-Consuming Generative Models with Curated Data Provably Optimize Human PreferencesDamien Ferbach, Quentin Bertrand, Avishek Joey Bose, Gauthier Gidel. [doi]
• Renovating Names in Open-Vocabulary Segmentation BenchmarksHaiwen Huang, Songyou Peng, Dan Zhang, Andreas Geiger 0001. [doi]
• DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data ReleaseFarzaneh Askari, Lingjuan Lyu, Vivek Sharma 0001. [doi]
• LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality AssessmentLinfeng Dong, Wei Wang, Yu Qiao, Xiao Sun. [doi]
• Fast Iterative Hard Thresholding Methods with Pruning Gradient ComputationsYasutoshi Ida, Sekitoshi Kanai, Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara. [doi]
• Bias Detection via SignalingYiling Chen, Tao Lin 0013, Ariel D. Procaccia, Aaditya Ramdas, Itai Shapira. [doi]
• Imitating Language via Scalable Inverse Reinforcement LearningMarkus Wulfmeier, Michael Bloesch, Nino Vieillard, Arun Ahuja, Jorg Bornschein, Sandy H. Huang, Artem Sokolov, Matt Barnes 0001, Guillaume Desjardins, Alex Bewley, Sarah Bechtle, Jost Tobias Springenberg, Nikola Momchev, Olivier Bachem, Matthieu Geist, Martin A. Riedmiller. [doi]
• SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language ModelsDan Zhang, Ziniu Hu, Sining Zhoubian, Zhengxiao Du, Kaiyu Yang, Zihan Wang, Yisong Yue, Yuxiao Dong, Jie Tang 0001. [doi]
• Tell What You Hear From What You See - Video to Audio Generation Through TextXiulong Liu, Kun Su, Eli Shlizerman. [doi]
• Recursive Introspection: Teaching Language Model Agents How to Self-ImproveYuxiao Qu, Tianjun Zhang, Naman Garg, Aviral Kumar. [doi]
• MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language ModelsTianle Gu, Zeyang Zhou, Kexin Huang, Dandan Liang, Yixu Wang, Haiquan Zhao, Yuanqi Yao, Xingge Qiao, Keqing Wang, Yujiu Yang, Yan Teng, Yu Qiao, Yingchun Wang. [doi]
• HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation PredictionQianyue Hao, Jingyang Fan, Fengli Xu, Jian Yuan, Yong Li 0008. [doi]
• What is my quantum computer good for? Quantum capability learning with physics-aware neural networksDaniel Hothem, Ashe Miller, Timothy Proctor. [doi]
• Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path SamplingYuanqi Du, Michael Plainer, Rob Brekelmans, Chenru Duan, Frank Noé, Carla P. Gomes, Alán Aspuru-Guzik, Kirill Neklyudov. [doi]
• Structured flexibility in recurrent neural networks via neuromodulationJulia Costacurta, Shaunak Bhandarkar, David M. Zoltowski, Scott W. Linderman. [doi]
• Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language ModelsJiahao Ying, Yixin Cao 0002, Yushi Bai, Qianru Sun, Bo Wang, Wei Tang 0015, Zhaojun Ding, Yizhe Yang, Xuanjing Huang 0001, Shuicheng Yan. [doi]
• 2: Overcoming Few Labels in Federated Semi-Supervised LearningSeungjoo Lee, Thanh-Long V. Le, Jaemin Shin 0005, Sung-Ju Lee. [doi]
• Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component AnalysisJiayu Su, David A. Knowles, Raúl Rabadán. [doi]
• Scaling White-Box Transformers for VisionJinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma 0001, Yaodong Yu, Cihang Xie. [doi]
• PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication DecisionYutao Dou, Huimin Yu, Wei Li, Jingyang Li, Fei Xia, Jian Xiao. [doi]
• Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum LikelihoodZiyi Liu, Idan Attias, Dan Roy. [doi]
• The Group Robustness is in the Details: Revisiting Finetuning under Spurious CorrelationsTyler Labonte, John C. Hill, Xinchen Zhang, Vidya Muthukumar, Abhishek Kumar 0001. [doi]
• On Differentially Private U StatisticsKamalika Chaudhuri, Po-Ling Loh, Shourya Pandey, Purnamrita Sarkar. [doi]
• Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View SynthesisZhiyuan Min, Yawei Luo, Jianwen Sun, Yi Yang 0001. [doi]
• Label Noise: Ignorance Is BlissYilun Zhu, Jianxin Zhang, Aditya Gangrade, Clayton Scott. [doi]
• An Image is Worth 32 Tokens for Reconstruction and GenerationQihang Yu, Mark Weber, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen. [doi]
• Average gradient outer product as a mechanism for deep neural collapseDaniel Beaglehole, Peter Súkeník, Marco Mondelli, Misha Belkin. [doi]
• Dueling over Dessert, Mastering the Art of Repeated Cake CuttingSimina Brânzei, MohammadTaghi Hajiaghayi, Reed Phillips, Suho Shin, Kun Wang. [doi]
• Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced OptimizationXinyu Lyu, Beitao Chen, Lianli Gao, Hengtao Shen, Jingkuan Song. [doi]
• Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt OptimizationXingchen Wan, Ruoxi Sun 0002, Hootan Nakhost, Sercan Ö. Arik. [doi]
• Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time AdaptationYizhou Zhao, Hengwei Bian, Kaihua Chen, Pengliang Ji, Liao Qu, Shao-yu Lin, Weichen Yu, Haoran Li, Hao Chen, Jun Shen 0001, Bhiksha Raj, Min Xu. [doi]
• Uncertainty-aware Fine-tuning of Segmentation Foundation ModelsKangning Liu, Brian L. Price, Jason Kuen, Yifei Fan, Zijun Wei, Luis Figueroa, Krzysztof J. Geras, Carlos Fernandez-Granda. [doi]
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-DesignRuisi Cai, Yeonju Ro, Geon Woo Kim, Peihao Wang, Babak Ehteshami Bejnordi, Aditya Akella, Zhangyang Wang. [doi]
• MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical JourneyXian Wu 0001, Yutian Zhao, Yunyan Zhang, Jiageng Wu, Zhihong Zhu, Yingying Zhang, Yi Ouyang, Ziheng Zhang, Huimin Wang, Zhenxi Lin, Jie Yang 0039, Shuang Zhao, Yefeng Zheng 0001. [doi]
• On the Benefits of Public Representations for Private Transfer Learning under Distribution ShiftPratiksha Thaker, Amrith Setlur, Steven Z. Wu, Virginia Smith. [doi]
• DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU ParallelismCheonjun Park, Mincheol Park, Hyunchan Moon, Myung Kuk Yoon, Seokjin Go, Suhyun Kim, Won Woo Ro. [doi]
• Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image FusionYu-Jie Liang, Zihan Cao, Shangqi Deng, Hong-Xia Dou, Liang-Jian Deng. [doi]
• Prune and Repaint: Content-Aware Image Retargeting for any RatioFeihong Shen, Chao Li, Yifeng Geng, Yongjian Deng, Hao Chen 0034. [doi]
• RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference ContentJoão Monteiro 0002, Pierre-André Noël, Étienne Marcotte, Sai Rajeswar Mudumba, Valentina Zantedeschi, David Vázquez 0001, Nicolas Chapados, Chris Pal, Perouz Taslakian. [doi]
• Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference TreesSijia Chen, Yibo Wang 0005, Yi-Feng Wu, Qingguo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang 0005. [doi]
• Proportional Fairness in Clustering: A Social Choice PerspectiveLeon Kellerhals, Jannik Peters 0001. [doi]
• GS-Hider: Hiding Messages into 3D Gaussian SplattingXuanyu Zhang, Jiarui Meng, Runyi Li, Zhipei Xu, Yongbing Zhang, Jian Zhang 0018. [doi]
• How Sparse Can We Prune A Deep Network: A Fundamental Limit PerspectiveQiaozhe Zhang, Ruijie Zhang, Jun Sun 0020, Yingzhuang Liu. [doi]
• Scene Graph Disentanglement and Composition for Generalizable Complex Image GenerationYunnan Wang, Ziqiang Li, Wenyao Zhang, Zequn Zhang, Baao Xie, Xihui Liu, Wenjun Zeng, Xin Jin. [doi]
• Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action DetectionYearang Lee, Ho Joong Kim, Seong-Whan Lee. [doi]
• SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment OptimizationWanhua Li 0001, Zibin Meng, Jiawei Zhou, Donglai Wei 0001, Chuang Gan, Hanspeter Pfister. [doi]
• Nearly Minimax Optimal Regret for Multinomial Logistic BanditJoongkyu Lee, Min-hwan Oh. [doi]
• UltraEdit: Instruction-based Fine-Grained Image Editing at ScaleHaozhe Zhao, Xiaojian (Shawn) Ma, Liang Chen 0024, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li 0003, Baobao Chang. [doi]
• Optimal Multiclass U-Calibration Error and BeyondHaipeng Luo, Spandan Senapati, Vatsal Sharan. [doi]
• Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-GuidanceJiwan Hur, Dong-Jae Lee, Gyojin Han, Jaehyun Choi, Yunho Jeon, Junmo Kim 0002. [doi]
• DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNAAman Patel, Arpita Singhal, Austin Wang, Anusri Pampari, Maya Kasowski, Anshul Kundaje. [doi]
• Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical SystemsAditi Jha, Diksha Gupta, Carlos D. Brody, Jonathan W. Pillow. [doi]
• S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial OptimizationLicheng Zhu, Mathias Oster, Yuehaw Khoo. [doi]
• Enhancing Preference-based Linear Bandits via Human Response TimeShen Li 0003, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, Julie A. Shah. [doi]
• ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language ModelsMingrui Wu, Xinyue Cai, Jiayi Ji, Jiale Li, Oucheng Huang, Gen Luo, Hao Fei 0001, Guannan Jiang, Xiaoshuai Sun, Rongrong Ji. [doi]
• LLaNA: Large Language and NeRF AssistantAndrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti, Samuele Salti, Luigi di Stefano. [doi]
• XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXAlexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov. [doi]
• SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery DetectionYachao Liang, Min Yu 0001, Gang Li 0009, Jianguo Jiang, Boquan Li 0002, Feng Yu, Ning Zhang, Xiang Meng, Weiqing Huang. [doi]
• Discrete Flow MatchingItai Gat, Tal Remez, Neta Shaul, Felix Kreuk, Ricky T. Q. Chen, Gabriel Synnaeve, Yossi Adi, Yaron Lipman. [doi]
• DMNet: Self-comparison Driven Model for Subject-independent Seizure DetectionShihao Tu, Linfeng Cao, Daoze Zhang, Junru Chen, Lvbin Ma, Yin Zhang 0006, Yang Yang 0009. [doi]
• EEG2Video: Towards Decoding Dynamic Visual Perception from EEG SignalsXuan-Hao Liu, Yan-Kai Liu, Yansen Wang, Kan Ren, Hanwen Shi, Zilong Wang, Dongsheng Li, Bao-Liang Lu, Wei-Long Zheng. [doi]
• Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure LearningZhixiang Shen, Shuo Wang, Zhao Kang 0001. [doi]
• Protected Test-Time Adaptation via Online Entropy Matching: A Betting ApproachYarin Bar, Shalev Shaer, Yaniv Romano. [doi]
• Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-WildJianan Yang, Chenchao Gao, Zhiqing Xiao, Junbo Zhao, Sai Wu, Gang Chen, Haobo Wang. [doi]
• MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-MakingYubin Kim 0002, Chanwoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff, Hyeonhoon Lee, Marzyeh Ghassemi, Cynthia Breazeal, Hae Won Park 0001. [doi]
• Cluster-wise Graph Transformer with Dual-granularity Kernelized AttentionSiyuan Huang 0003, Yunchong Song, Jiayue Zhou, Zhouhan Lin. [doi]
• PGN: The RNN's New Successor is Effective for Long-Range Time Series ForecastingYuxin Jia, Youfang Lin, Jing Yu, Shuo Wang, Tianhao Liu, Huaiyu Wan. [doi]
• Enhancing LLM Reasoning via Vision-Augmented PromptingZiyang Xiao, Dongxiang Zhang, Xiongwei Han, Xiaojin Fu, Wing Yin Yu, Tao Zhong, Sai Wu, Yuan Wang, Jianwei Yin, Gang Chen. [doi]
• FedGMark: Certifiably Robust Watermarking for Federated Graph LearningYuxin Yang, Qiang Li, Yuan Hong, Binghui Wang. [doi]
• Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space InferenceDeqian Kong, Dehong Xu, Minglu Zhao, Bo Pang 0004, Jianwen Xie, Andrew Lizarraga, Yuhao Huang, Sirui Xie, Ying Nian Wu. [doi]
• Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based InferenceSam Griesemer, Defu Cao, Zijun Cui, Carolina Osorio, Yan Liu 0002. [doi]
• The Implicit Bias of Gradient Descent on Separable Multiclass DataHrithik Ravi, Clayton Scott, Daniel Soudry, Yutong Wang 0002. [doi]
• A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme ConditionsHoonhee Cho, Taewoo Kim 0003, Yuhwan Jeong, Kuk-Jin Yoon. [doi]
• SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion ModelsZhaoyang Sun, Shengwu Xiong 0001, Yaxiong Chen, Fei Du, Weihua Chen, Fan Wang, Yi Rong. [doi]
• Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single ImageKailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang 0003, Yating Hu, Yueqi Duan, Kaisheng Ma. [doi]
• SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material EstimationJesus Zarzar, Bernard Ghanem. [doi]
• SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh DatasetYubin Hu 0001, Kairui Wen, Heng Zhou, Xiaoyang Guo, Yong-Jin Liu 0001. [doi]
• Interactive Deep Clustering via Value MiningHonglin Liu, Peng Hu, Changqing Zhang, Yunfan Li, Xi Peng. [doi]
• Automated Multi-level Preference for MLLMsMengxi Zhang, Wenhao Wu, Yu Lu, Yuxin Song, Kang Rong, Huanjin Yao, Jianbo Zhao, Fanglong Liu, Haocheng Feng, Jingdong Wang 0001, Yifan Sun 0003. [doi]
• Learning on Large Graphs using Intersecting CommunitiesBen Finkelshtein, Ismail Ilkan Ceylan, Michael M. Bronstein, Ron Levie. [doi]
• Unified Covariate Adjustment for Causal InferenceYonghan Jung, Jin Tian 0001, Elias Bareinboim. [doi]
• Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge DistillationJiaming Lv, Haoyuan Yang, Peihua Li. [doi]
• Learning diffusion at lightspeedAntonio Terpin, Nicolas Lanzetti, Martín Gadea, Florian Dörfler. [doi]
• Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent ModelingJiatao Gu, Ying Shen 0006, Shuangfei Zhai, Yizhe Zhang 0002, Navdeep Jaitly, Joshua M. Susskind. [doi]
• GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative ModelingBowen Zhang, Yiji Cheng, Jiaolong Yang, Chunyu Wang, Feng Zhao 0004, Yansong Tang, Dong Chen 0003, Baining Guo. [doi]
• MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane SweepsYating Xu, Chen Li, Gim Hee Lee. [doi]
• Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech SeparationUi-Hyeop Shin, Sangyoun Lee, Taehan Kim, Hyung-Min Park. [doi]
• Segment Anything without SupervisionXudong Wang 0007, Jingfeng Yang, Trevor Darrell. [doi]
• TaskBench: Benchmarking Large Language Models for Task AutomationYongliang Shen 0001, Kaitao Song, Xu Tan 0003, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu 0001, Dongsheng Li 0002, Yueting Zhuang. [doi]
• FouRA: Fourier Low-Rank AdaptationShubhankar Borse, Shreya Kadambi, Nilesh Prasad Pandey, Kartikeya Bhardwaj, Viswanath Ganapathy, Sweta Priyadarshi, Risheek Garrepalli, Rafael Esteves 0002, Munawar Hayat, Fatih Porikli. [doi]
• HardCore Generation: Generating Hard UNSAT Problems for Data AugmentationJoseph Cotnareanu, Zhanguang Zhang, Hui-Ling Zhen, Yingxue Zhang 0001, Mark Coates. [doi]
• How does PDE order affect the convergence of PINNs?Changhoon Song, Yesom Park, Myungjoo Kang. [doi]
• Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization RegimeHaoyu Geng, Hang Ruan, Runzhong Wang, Yang Li, Yang Wang, Lei Chen, Junchi Yan. [doi]
• Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel TimesPei Xiao, Zizhen Zhang, Jinbiao Chen, Jiahai Wang, Zhenzhen Zhang. [doi]
• Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem SolvingAniket Didolkar, Anirudh Goyal, Nan Rosemary Ke, Siyuan Guo, Michal Valko, Timothy P. Lillicrap, Danilo Jimenez Rezende, Yoshua Bengio, Michael C. Mozer, Sanjeev Arora. [doi]
• MC-DiT: Contextual Enhancement via Clean-to-Clean Reconstruction for Masked Diffusion ModelsGuanghao Zheng, Yuchen Liu 0006, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong. [doi]
• Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and BeyondYingcong Li, Ankit Singh Rawat, Samet Oymak. [doi]
• Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion ModelHao Zhang 0073, Lei Cao, Jiayi Ma 0001. [doi]
• SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure InterpretationJonathan Roberts 0004, Kai Han 0001, Neil Houlsby, Samuel Albanie. [doi]
• RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression SegmentationChangli Wu, Qi Chen, Jiayi Ji, Haowei Wang 0001, Yiwei Ma, You Huang, Gen Luo, Hao Fei 0001, Xiaoshuai Sun, Rongrong Ji. [doi]
• Opponent Modeling with In-context SearchYuheng Jing, Bingyun Liu, Kai Li, Yifan Zang 0001, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. [doi]
• Multi-Label Learning with Stronger Consistency GuaranteesAnqi Mao, Mehryar Mohri, Yutao Zhong 0002. [doi]
• WikiDBs: A Large-Scale Corpus Of Relational Databases From WikidataLiane Vogel, Jan-Micha Bodensohn, Carsten Binnig. [doi]
• Intruding with Words: Towards Understanding Graph Injection Attacks at the Text LevelRunlin Lei, Yuwei Hu, Yuchen Ren, Zhewei Wei. [doi]
• Deep Equilibrium Algorithmic ReasoningDobrik Georgiev, Joseph Wilson, Davide Buffelli, Pietro Lió. [doi]
• Learning Discrete Latent Variable Structures with Tensor Rank ConditionsZhengming Chen, Ruichu Cai, Feng Xie 0002, Jie Qiao, Anpeng Wu, Zijian Li 0001, Zhifeng Hao, Kun Zhang 0001. [doi]
• Training an Open-Vocabulary Monocular 3D Detection Model without 3D DataRui Huang, Henry Zheng, Yan Wang, Zhuofan Xia, Marco Pavone 0001, Gao Huang 0001. [doi]
• VLG-CBM: Training Concept Bottleneck Models with Vision-Language GuidanceDivyansh Srivastava, Ge Yan, Lily Weng. [doi]
• Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous ComputationsAlexander Tyurin, Kaja Gruntkowska, Peter Richtárik. [doi]
• Multi-Stage Predict+Optimize for (Mixed Integer) Linear ProgramsXinyi Hu, Jasper C. H. Lee, Jimmy H. M. Lee, Peter J. Stuckey. [doi]
• Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language ModelsLetian Gong, Yan Lin 0006, Xinyue Zhang, Yiwen Lu, Xuedi Han, Yichen Liu 0003, Shengnan Guo 0001, Youfang Lin, Huaiyu Wan. [doi]
• Latent Representation Matters: Human-like Sketches in One-shot Drawing TasksVictor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen. [doi]
• Mars: Situated Inductive Reasoning in an Open-World EnvironmentXiaojuan Tang, Jiaqi Li, Yitao Liang, Song Chun Zhu, Muhan Zhang, Zilong Zheng. [doi]
• Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play PriorsZihui Wu, Yu Sun, Yifan Chen, Bingliang Zhang, Yisong Yue, Katherine L. Bouman. [doi]
• ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language ModelsYuzhe Gu, Ziwei Ji, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen 0026. [doi]
• FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge InjectionJiaqi Wang 0002, Xiaochen Wang 0002, Lingjuan Lyu, Jinghui Chen, Fenglong Ma. [doi]
• Causal Temporal Representation Learning with Nonstationary Sparse TransitionXiangchen Song, Zijian Li 0001, Guangyi Chen 0002, Yujia Zheng 0001, Yewen Fan, Xinshuai Dong, Kun Zhang 0001. [doi]
• Unified Graph Augmentations for Generalized Contrastive Learning on GraphsJiaming Zhuo, Yintong Lu, Hui Ning, Kun Fu, Bingxin Niu, Dongxiao He, Chuan Wang 0002, Yuanfang Guo, Zhen Wang 0004, Xiaochun Cao, Liang Yang 0002. [doi]
• DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMsLingchen Meng, Jianwei Yang, Rui Tian, Xiyang Dai, Zuxuan Wu, Jianfeng Gao 0001, Yu-Gang Jiang 0001. [doi]
• Learning from Offline Foundation Features with Tensor AugmentationsEmir Konuk, Christos Matsoukas, Moein Sorkhei, Phitchapha Lertsiravarameth, Kevin Smith 0001. [doi]
• Addressing Hidden Confounding with Heterogeneous Observational Datasets for RecommendationYanghao Xiao, Haoxuan Li, Yongqiang Tang, Wensheng Zhang 0002. [doi]
• A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning ShortcutsSamuele Bortolotti, Emanuele Marconato, Tommaso Carraro, Paolo Morettin, Emile van Krieken, Antonio Vergari, Stefano Teso, Andrea Passerini. [doi]
• Overcoming Common Flaws in the Evaluation of Selective Classification SystemsJeremias Traub, Till J. Bungert, Carsten T. Lüth, Michael Baumgartner 0001, Klaus H. Maier-Hein, Lena Maier-Hein, Paul F. Jaeger. [doi]
• Adversarially Robust Dense-Sparse Tradeoffs via Heavy-HittersDavid P. Woodruff, Samson Zhou. [doi]
• Tetrahedron Splatting for 3D GenerationChun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang. [doi]
• Preference-based Pure ExplorationApurv Shukla 0001, Debabrota Basu. [doi]
• TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent CollaborationYiwei Guo, Shaobin Zhuang, Kunchang Li 0002, Yu Qiao 0001, Yali Wang 0001. [doi]
• Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement LearningYuefei Lyu, Chaozhuo Li 0001, Sihong Xie, Xi Zhang 0008. [doi]
• Light Unbalanced Optimal TransportMilena Gazdieva, Arip Asadulaev, Evgeny Burnaev, Aleksandr Korotin. [doi]
• Locally Private and Robust Multi-Armed BanditsXingyu Zhou, Komo (Wei) Zhang. [doi]
• Autoregressive Policy Optimization for Constrained Allocation TasksDavid Winkel, Niklas Strauß, Maximilian Bernhard, Zongyue Li, Thomas Seidl 0001, Matthias Schubert. [doi]
• A Siamese Transformer with Hierarchical Refinement for Lane DetectionZinan Lv, Dong Han, Wenzhe Wang, Danny Z. Chen. [doi]
• Towards Visual Text Design Transfer Across LanguagesYejin Choi 0001, Jiwan Chung, Sumin Shim, Giyeong Oh, Youngjae Yu. [doi]
• Provable Editing of Deep Neural Networks using Parametric Linear RelaxationZhe Tao, Aditya V. Thakur. [doi]
• Out-Of-Distribution Detection with Diversification (Provably)Haiyun Yao, Zongbo Han, Huazhu Fu, Xi Peng 0001, Qinghua Hu, Changqing Zhang. [doi]
• A Systematic Review of NeurIPS Dataset Management PracticesYiwei Wu, Leah Ajmani, Shayne Longpre, Hanlin Li. [doi]
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics PredictionJongmin Lee, Minsu Cho. [doi]
• Unified Gradient-Based Machine Unlearning with Remain Geometry EnhancementZhehao Huang, Xinwen Cheng, Jinghao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang. [doi]
• Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian InputZiang Chen, Rong Ge. [doi]
• Language Grounded Multi-agent Reinforcement Learning with Human-interpretable CommunicationHuao Li, Hossein Nourkhiz Mahjoub, Behdad Chalaki, Vaishnav Tadiparthi, Kwonjoon Lee, Ehsan Moradi-Pari, Charles Lewis, Katia P. Sycara. [doi]
• SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature AnalysisHuzaifa Pardawala, Siddhant Sukhani, Agam Shah, Veer Kejriwal, Abhishek Pillai, Rohan Bhasin, Andrew DiBiasio, Tarun Mandapati, Dhruv Adha, Sudheer Chava. [doi]
• N-agent Ad Hoc TeamworkCaroline Wang, Arrasy Rahman, Ishan Durugkar, Elad Liebman, Peter Stone 0001. [doi]
• EGonc : Energy-based Open-Set Node Classification with substitute UnknownsQin Zhang, Zelin Shi, Shirui Pan, Junyang Chen 0001, Huisi Wu, Xiaojun Chen 0006. [doi]
• Autonomous Driving with Spiking Neural NetworksRuijie Zhu 0003, Ziqing Wang, Leilani Gilpin, Jason Eshraghian. [doi]
• On Affine Homotopy between Language EncodersRobin Chan, Reda Boumasmoud, Anej Svete, Yuxin Ren, Qipeng Guo, Zhijing Jin 0001, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Mennatallah El-Assady, Ryan Cotterell. [doi]
• Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and ModelsXin Li, Weize Chen, Qizhi Chu, Haopeng Li, Zhaojun Sun, Ran Li, Chen Qian, Yiwei Wei, Chuan Shi 0001, Zhiyuan Liu 0001, Maosong Sun 0001, Cheng Yang. [doi]
• D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language ModelsHaoran Que, Jiaheng Liu, Ge Zhang, Chenchen Zhang, Xingwei Qu, Yinghao Ma, Feiyu Duan, Zhiqi Bai, Jiakai Wang, Yuanxing Zhang, Xu Tan 0003, Jie Fu 0001, Jiamang Wang, Lin Qu, Wenbo Su, Bo Zheng 0007. [doi]
• Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic AmbiguityJikai Jin, Vasilis Syrgkanis. [doi]
• Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and LearningOtmane Sakhi, Imad Aouali, Pierre Alquier, Nicolas Chopin. [doi]
• Warped Diffusion: Solving Video Inverse Problems with Image Diffusion ModelsGiannis Daras, Weili Nie, Karsten Kreis, Alex Dimakis, Morteza Mardani, Nikola B. Kovachki, Arash Vahdat. [doi]
• The Fine-Grained Complexity of Gradient Computation for Training Large Language ModelsJosh Alman, Zhao Song 0002. [doi]
• Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step SizesDan Qiao 0002, Kaiqi Zhang 0002, Esha Singh, Daniel Soudry, Yu-Xiang Wang 0003. [doi]
• Linguistic Collapse: Neural Collapse in (Large) Language ModelsRobert Wu, Vardan Papyan. [doi]
• The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs BetterScott Geng, Cheng-Yu Hsieh, Vivek Ramanujan, Matthew Wallingford, Chun-Liang Li, Pang Wei Koh, Ranjay Krishna. [doi]
• Euclidean distance compression via deep random featuresBrett Leroux, Luis Rademacher. [doi]
• Online Non-convex Learning in Dynamic EnvironmentsZhipan Xu, Lijun Zhang. [doi]
• Pessimistic Backward Policy for GFlowNetsHyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, Sungsoo Ahn. [doi]
• GeoNLF: Geometry guided Pose-Free Neural LiDAR FieldsWeiyi Xue, Zehan Zheng, Fan Lu 0001, Haiyun Wei, Guang Chen 0001, Changjun Jiang. [doi]
• When are dynamical systems learned from time series data statistically accurate?Jeongjin Park, Nicole Yang, Nisha Chandramoorthy. [doi]
• Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based ReasoningBrian Zhang, Zhuo Zhang 0002. [doi]
• Invisible Image Watermarks Are Provably Removable Using Generative AIXuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang 0003, Lei Li 0005. [doi]
• Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian SplattingHaiqian Han, Jianing Li 0001, Henglu Wei, Xiangyang Ji. [doi]
• MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision TasksXingkui Zhu, Yiran Guan, Dingkang Liang, Yuchao Chen, Yuliang Liu, Xiang Bai. [doi]
• On the Power of Decision Trees in Auto-Regressive Language ModelingYulu Gan, Tomer Galanti, Tomaso A. Poggio, Eran Malach. [doi]
• On Weak Regret Analysis for Dueling BanditsEl Mehdi Saad, Alexandra Carpentier, Tomás Kocák, Nicolas Verzelen. [doi]
• OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary UnderstandingYanmin Wu, Jiarui Meng, Haijie Li, Chenming Wu, Yahao Shi, Xinhua Cheng, Chen Zhao 0011, Haocheng Feng, Errui Ding, Jingdong Wang 0001, Jian Zhang 0018. [doi]
• AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion ModelsYuchen Fu, Zhiwei Jiang, Yuliang Liu, Cong Wang, Zexuan Deng, Zhaoling Chen, Qing Gu. [doi]
• ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic FieldKiyohiro Nakayama, Mikaela Angelina Uy, Yang You 0004, Ke Li 0011, Leonidas J. Guibas. [doi]
• Pseudo-Siamese Blind-spot Transformers for Self-Supervised Real-World DenoisingYuhui Quan, Tianxiang Zheng, Hui Ji. [doi]
• Continual Learning with Global AlignmentXueying Bai, Jinghuan Shang, Yifan Sun, Niranjan Balasubramanian. [doi]
• Personalizing Reinforcement Learning from Human Feedback with Variational Preference LearningSriyash Poddar, Yanming Wan, Hamish Ivison, Abhishek Gupta, Natasha Jaques. [doi]
• ComBack: A Versatile Dataset for Enhancing Compiler Backend Development EfficiencyMing Zhong, Fang Lyu, Lulin Wang, Hongna Geng, Lei Qiu, Huimin Cui, Xiaobing Feng. [doi]
• How to Use Diffusion Priors under Sparse Views?Qisen Wang, Yifan Zhao, Jiawei Ma, Jia Li. [doi]
• Stepping Forward on the Last MileChen Feng, Jay Zhuo, Parker Zhang, Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Andrew Zou Li. [doi]
• Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal MaskingZijian Dong, Ruilin Li, Yilei Wu, Thuan Tinh Nguyen, Joanna Su Xian Chong, Fang Ji, Nathanael Ren Jie Tong, Christopher Chen, Juan Helen Zhou. [doi]
• Enhancing Semi-Supervised Learning via Representative and Diverse Sample SelectionQian Shao, Jiangrui Kang, Qiyuan Chen 0003, Zepeng Li, Hongxia Xu, Yiwen Cao, Jiajuan Liang, Jian Wu 0001. [doi]
• From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular OptimizationMohammad Pedramfar, Vaneet Aggarwal. [doi]
• DINTR: Tracking via Diffusion-based InterpolationPha A. Nguyen, Ngan Le, Jackson David Cothren, Alper Yilmaz, Khoa Luu. [doi]
• Learning from Snapshots of Discrete and Continuous Data StreamsPramith Devulapalli, Steve Hanneke. [doi]
• HourVideo: 1-Hour Video-Language UnderstandingKeshigeyan Chandrasegaran, Agrim Gupta, Lea M. Hadzic, Taran Kota, Jimming He, Cristóbal Eyzaguirre, Zane Durante, Manling Li, Jiajun Wu 0001, Li Fei-Fei 0001. [doi]
• Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical CodesJerry Yao-Chieh Hu, Dennis Wu, Han Liu 0001. [doi]
• MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-StepTakeshi Noda, Chao Chen, Weiqi Zhang, Xinhai Liu, Yu-Shen Liu, Zhizhong Han. [doi]
• Private and Personalized Frequency Estimation in a Federated SettingAmrith Setlur, Vitaly Feldman, Kunal Talwar. [doi]
• Oracle-Efficient Reinforcement Learning for Max Value EnsemblesMarcel Hussing, Michael Kearns, Aaron Roth 0001, Sikata Bela Sengupta, Jessica Sorrell. [doi]
• Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture ModelsWeihang Xu, Maryam Fazel, Simon S. Du. [doi]
• Score-Optimal Diffusion SchedulesChristopher Williams, Andrew Campbell, Arnaud Doucet, Saifuddin Syed. [doi]
• Multidimensional Fractional Programming for Normalized CutsYannan Chen, Beichen Huang, Licheng Zhao, Kaiming Shen. [doi]
• Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and GeneralizationMucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou 0001, Tom Goldstein, John Langford 0001, Animashree Anandkumar, Furong Huang. [doi]
• Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification WayMing Chen, Jie Chun, Shang Xiang, Luona Wei, Yonghao Du, Qian Wan, Yuning Chen, Yingwu Chen. [doi]
• Rethinking Parity Check Enhanced Symmetry-Preserving AnsatzGe Yan 0001, Mengfei Ran, Ruocheng Wang, Kaisen Pan, Junchi Yan. [doi]
• Bias Amplification in Language Model Evolution: An Iterated Learning PerspectiveYi Ren, Shangmin Guo, Linlu Qiu, Bailin Wang, Danica J. Sutherland. [doi]
• xLSTM: Extended Long Short-Term MemoryMaximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp 0001, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter. [doi]
• The Power of Resets in Online Reinforcement LearningZakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin. [doi]
• One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object DetectionZhenyu Wang, Yali Li, Hengshuang Zhao, Shengjin Wang. [doi]
• Efficiency of the First-Price Auction in the Autobidding WorldYuan Deng, Jieming Mao, Vahab Mirrokni, Hanrui Zhang 0001, Song Zuo. [doi]
• Distributional Preference Alignment of LLMs via Optimal TransportIgor Melnyk, Youssef Mroueh, Brian Belgodere, Mattia Rigotti, Apoorva Nitsure, Mikhail Yurochkin, Kristjan H. Greenewald, Jirí Navrátil 0001, Jarret Ross. [doi]
• Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function ValuesAleksandr V. Lobanov, Alexander V. Gasnikov, Andrey Krasnov. [doi]
• Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question AnsweringZhihua Wen, Zhiliang Tian, Zexin Jian, Zhen Huang 0006, Pei Ke, Yifu Gao, Minlie Huang, Dongsheng Li. [doi]
• Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamicsWilliam Qian, Jacob A. Zavatone-Veth, Benjamin S. Ruben, Cengiz Pehlevan. [doi]
• DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography ReconstructionBowen Song, Jason Hu, Zhaoxu Luo, Jeffrey A. Fessler, Liyue Shen. [doi]
• Bifröst: 3D-Aware Image Compositing with Language InstructionsLingxiao Li, Kaixiong Gong, Weihong Li, Xili Dai, Tao Chen 0003, Xiaojun Yuan, Xiangyu Yue 0001. [doi]
• HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction AwarenessZihui Xue, Romy Luo, Changan Chen, Kristen Grauman. [doi]
• Batched Energy-Entropy acquisition for Bayesian OptimizationFelix Teufel, Carsten Stahlhut, Jesper Ferkinghoff-Borg. [doi]
• dattri: A Library for Efficient Data AttributionJunwei Deng, Ting-Wei Li, Shiyuan Zhang, Shixuan Liu, Yijun Pan, Hao Huang, Xinhe Wang, Pingbang Hu, Xingjian Zhang, Jiaqi W. Ma. [doi]
• BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-HaystackYuri Kuratov, Aydar Bulatov, Petr Anokhin, Ivan Rodkin, Dmitry Sorokin, Artyom Y. Sorokin, Mikhail Burtsev 0001. [doi]
• Physics-Informed Variational State-Space Gaussian ProcessesOliver Hamelijnck, Arno Solin, Theodoros Damoulas. [doi]
• Optimal Multi-Fidelity Best-Arm IdentificationRiccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli. [doi]
• On the Surprising Effectiveness of Attention Transfer for Vision TransformersAlexander C. Li, Yuandong Tian, Beidi Chen, Deepak Pathak, Xinlei Chen. [doi]
• Fine-grained Control of Generative Data Augmentation in IoT SensingTianshi Wang, Qikai Yang, Ruijie Wang 0004, Dachun Sun, Jinyang Li 0004, Yizhuo Chen, Yigong Hu, Chaoqi Yang, Tomoyoshi Kimura, Denizhan Kara, Tarek F. Abdelzaher. [doi]
• Large Language Model UnlearningYuanshun Yao, Xiaojun Xu, Yang Liu. [doi]
• One-shot Federated Learning via Synthetic Distiller-Distillate CommunicationJunyuan Zhang, Songhua Liu, Xinchao Wang. [doi]
• Preference Alignment with Flow MatchingMinu Kim, Yongsik Lee, Sehyeok Kang, Jihwan Oh, Song Chong, Se-Young Yun. [doi]
• Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation LearningThe Viet Bui, Tien Mai, Thanh Hong Nguyen. [doi]
• JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated ImagesZhecan Wang, Junzhang Liu, Chia-Wei Tang, Hani AlOmari, Anushka Sivakumar, Rui Sun, Wenhao Li, Md. Atabuzzaman, Hammad A. Ayyubi, Haoxuan You, Alvi Md. Ishmam, Kai-Wei Chang, Shih-Fu Chang, Christopher Thomas 0004. [doi]
• CaptainCook4D: A Dataset for Understanding Errors in Procedural ActivitiesRohith Peddi, Shivvrat Arya, Bharath Challa, Likhitha Pallapothula, Akshay Vyas, Bhavya Gouripeddi, Qifan Zhang, Jikai Wang, Vasundhara Komaragiri, Eric D. Ragan, Nicholas Ruozzi, Yu Xiang 0001, Vibhav Gogate. [doi]
• MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space ModelsZunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang 0001, Xiu Li 0001. [doi]
• One Sample Fits All: Approximating All Probabilistic Values Simultaneously and EfficientlyWeida Li, Yaoliang Yu. [doi]
• SMART: Scalable Multi-agent Real-time Motion Generation via Next-token PredictionWei Wu 0021, Xiaoxin Feng, Ziyan Gao, Yuheng Kan. [doi]
• Multi-times Monte Carlo Rendering for Inter-reflection ReconstructionTengjie Zhu, Zhuo Chen, Jingnan Gao, Yichao Yan, Xiaokang Yang. [doi]
• RAGraph: A General Retrieval-Augmented Graph Learning FrameworkXinke Jiang, Rihong Qiu, Yongxin Xu, Wentao Zhang, Yichen Zhu, Ruizhe Zhang 0013, Yuchen Fang 0001, Chu Xu, Junfeng Zhao 0001, Yasha Wang. [doi]
• Causal language modeling can elicit search and reasoning capabilities on logic puzzlesKulin Shah, Nishanth Dikkala, Xin Wang, Rina Panigrahy. [doi]
• BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-RaysYang Zhou, Tan Li Hui Faith, Yanyu Xu, Sicong Leng, Xinxing Xu, Yong Liu 0026, Rick Siow Mong Goh. [doi]
• Fairness without Harm: An Influence-Guided Active Sampling ApproachJinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu 0018. [doi]
• What do Graph Neural Networks learn? Insights from Tropical GeometryTuan Anh Pham, Vikas Garg 0001. [doi]
• FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic ModelXiaobao Wu, Thong Nguyen 0003, Delvin Zhang, William Yang Wang, Anh Tuan Luu. [doi]
• Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series RepresentationsShivam Grover, Amin Jalali, Ali Etemad. [doi]
• CiteME: Can Language Models Accurately Cite Scientific Claims?Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, Matthias Bethge. [doi]
• BitDelta: Your Fine-Tune May Only Be Worth One BitJames Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han 0003, Tri Dao, Tianle Cai. [doi]
• The Empirical Impact of Neural Parameter Symmetries, or Lack ThereofDerek Lim, Theo Putterman, Robin Walters 0001, Haggai Maron, Stefanie Jegelka. [doi]
• AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any ScenarioYuhan Li 0003, Hao Zhou, Wenxiang Shang, Ran Lin, Xuanhong Chen, Bingbing Ni. [doi]
• Sparse High Rank AdaptersKartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi, Viswanath Ganapathy, Shreya Kadambi, Rafael Esteves 0002, Shubhankar Borse, Paul N. Whatmough, Risheek Garrepalli, Mart van Baalen, Harris Teague, Markus Nagel. [doi]
• Discretely beyond 1/e: Guided Combinatorial Algortihms for Submodular MaximizationYixin Chen, Ankur Nath, Chunli Peng, Alan Kuhnle. [doi]
• Not Just Object, But State: Compositional Incremental Learning without ForgettingYanyi Zhang, Binglin Qiu, Qi Jia, Yu Liu, Ran He. [doi]
• Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn TreeChengwei Ren, Yifan Feng, Weixiang Zhang, Xiao-Ping (Steven) Zhang, Yue Gao. [doi]
• The Map Equation Goes Neural: Mapping Network Flows with Graph Neural NetworksChristopher Blöcker, Chester Tan, Ingo Scholtes. [doi]
• Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ NormsPierre Clavier, Laixi Shi, Erwan Le Pennec, Eric Mazumdar, Adam Wierman, Matthieu Geist. [doi]
• Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming DataXuxing Chen, Abhishek Roy 0005, Yifan Hu, Krishnakumar Balasubramanian 0002. [doi]
• FindingEmo: An Image Dataset for Emotion Recognition in the WildLaurent Mertens, Elahe Yargholi, Hans P. Op de Beeck, Jan Van den Stock, Joost Vennekens. [doi]
• Information-theoretic Limits of Online Classification with Noisy LabelsChanglong Wu, Ananth Grama, Wojciech Szpankowski. [doi]
• The Art of Saying No: Contextual Noncompliance in Language ModelsFaeze Brahman, Sachin Kumar 0009, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Raghavi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi 0001, Hanna Hajishirzi. [doi]
• BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional BootstrappingTaolin Zhang 0003, Jinpeng Wang 0002, Hang Guo, Tao Dai 0001, Bin Chen 0011, Shu-Tao Xia. [doi]
• Preference Learning Algorithms Do Not Learn Preference RankingsAngelica Chen, Sadhika Malladi, Lily H. Zhang, Xinyi Chen 0001, Qiuyi (Richard) Zhang, Rajesh Ranganath, KyungHyun Cho. [doi]
• DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image GenerationHao Phung, Quan Dao, Trung Tuan Dao, Viet-Hoang Phan, Dimitris N. Metaxas, Anh Tuan Tran 0001. [doi]
• Retrieval-Augmented Diffusion Models for Time Series ForecastingJingwei Liu, Ling Yang 0006, Hongyan Li 0002, Shenda Hong. [doi]
• Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency modelJing Zhang, Linjiajie Fang, Kexin Shi, Wenjia Wang, Bingyi Jing. [doi]
• Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace LearningAndrew Bond, Zafer Dogan. [doi]
• Unified Lexical Representation for Interpretable Visual-Language AlignmentYifan Li, Yikai Wang 0002, Yanwei Fu 0001, Dongyu Ru, Zheng Zhang 0001, Tong He 0002. [doi]
• STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomicsJiawen Chen, Muqing Zhou, Wenrong Wu, Jinwei Zhang, Yun Li, Didong Li. [doi]
• Efficiency for Free: Ideal Data Are Transportable RepresentationsPeng Sun, Yi Jiang, Tao Lin. [doi]
• Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement LearningZhishuai Liu, Pan Xu 0002. [doi]
• Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest FireYanzhi Li, Keqiu Li, Li Guohui, Zumin Wang, Changqing Ji, Lubo Wang, Die Zuo, Qing Guo 0005, Feng Zhang, Manyu Wang, Di Lin 0002. [doi]
• Towards Global Optimal Visual In-Context Learning Prompt SelectionChengming Xu 0001, Chen Liu, Yikai Wang 0002, Yuan Yao 0011, Yanwei Fu 0001. [doi]
• MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition DatasetXin Shen, Heming Du, Hongwei Sheng, Shuyun Wang, Hui Chen, Huiqiang Chen, Zhuojie Wu, Xiaobiao Du, Jiaying Ying, Ruihan Lu, Qingzheng Xu, Xin Yu 0002. [doi]
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought ReasoningHao Shao, Shengju Qian, Han Xiao 0010, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu 0015, Hongsheng Li 0001. [doi]
• NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore SequencingGuangzhao Cheng, Chengbo Fu, Lu Cheng. [doi]
• Worst-Case Offline Reinforcement Learning with Arbitrary Data SupportKohei Miyaguchi. [doi]
• ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language ModelsJio Oh, Soyeon Kim, JunSeok Seo, Jindong Wang 0001, Ruochen Xu, Xing Xie 0001, Steven Whang 0001. [doi]
• DI-MaskDINO: A Joint Object Detection and Instance Segmentation ModelZhixiong Nan, Xianghong Li, Tao Xiang, Jifeng Dai. [doi]
• A Sober Look at the Robustness of CLIPs to Spurious FeaturesQizhou Wang, Yong Lin, Yongqiang Chen 0002, Ludwig Schmidt, Bo Han 0003, Tong Zhang 0001. [doi]
• SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operationYiqi Zhang, Yang You. [doi]
• DenoiseRep: Denoising Model for Representation LearningZhengrui Xu, Guan'an Wang, Xiaowen Huang, Jitao Sang. [doi]
• Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language InteractionGuobin Shen, Dongcheng Zhao, Xiang He 0004, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng 0001. [doi]
• Instruction Tuning With Loss Over InstructionsZhengxiang Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani. [doi]
• BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion ModelBoris Repasky, Ehsan Abbasnejad, Anthony R. Dick. [doi]
• Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-RationalizationWei Liu, Zhiying Deng, Zhongyu Niu, Jun Wang, Haozhao Wang, Yuankai Zhang, Ruixuan Li 0001. [doi]
• A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured DatasetsKyungeun Lee, Wonjong Rhee. [doi]
• Continual Audio-Visual Sound SeparationWeiguo Pian, Yiyang Nan, Shijian Deng, Shentong Mo, Yunhui Guo, Yapeng Tian. [doi]
• Provably Efficient Reinforcement Learning with Multinomial Logit Function ApproximationLong-Fei Li, Yu-Jie Zhang, Peng Zhao 0006, Zhi-Hua Zhou. [doi]
• FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor ScenesYunsong Wang, Tianxin Huang, Hanlin Chen, Gim Hee Lee. [doi]
• Multimodal Task Vectors Enable Many-Shot Multimodal In-Context LearningBrandon Huang, Chancharik Mitra, Leonid Karlinsky, Assaf Arbelle, Trevor Darrell, Roei Herzig. [doi]
• Learning Segmentation from Point TrajectoriesLaurynas Karazija, Iro Laina, Christian Rupprecht 0001, Andrea Vedaldi. [doi]
• Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple ReductionsHilal Asi, Daogao Liu, Kevin Tian. [doi]
• Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent MisspecificationHaolin Liu, Artin Tajdini, Andrew Wagenmaker, Chen-Yu Wei. [doi]
• Minimum Entropy Coupling with BottleneckM. Reza Ebrahimi, Jun Chen 0005, Ashish Khisti. [doi]
• FlowLLM: Flow Matching for Material Generation with Large Language Models as Base DistributionsAnuroop Sriram, Benjamin Kurt Miller, Ricky T. Q. Chen, Brandon M. Wood. [doi]
• T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward FeedbackJiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang 0003, Sugato Basu, Wenhu Chen, William Yang Wang. [doi]
• SCOREQ: Speech Quality Assessment with Contrastive RegressionAlessandro Ragano, Jan Skoglund, Andrew Hines. [doi]
• Adversarially Robust Decision TransformerXiaohang Tang, Afonso Marques, Parameswaran Kamalaruban, Ilija Bogunovic. [doi]
• Theoretical Analysis of Weak-to-Strong GeneralizationHunter Lang, David A. Sontag, Aravindan Vijayaraghavan. [doi]
• Stochastic Optimal Control for Diffusion Bridges in Function SpacesByoungwoo Park, Jungwon Choi, Sungbin Lim, Juho Lee. [doi]
• Hierarchical Uncertainty Exploration via Feedforward Posterior TreesElias Nehme, Rotem Mulayoff, Tomer Michaeli. [doi]
• Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass ClassificationEnrique B. Nueve, Dhamma Kimpara, Bo Waggoner, Jessica Finocchiaro. [doi]
• Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation LearningMingcheng Li, Dingkang Yang, Yang Liu 0246, Shunli Wang 0001, Jiawei Chen 0012, Shuaibing Wang, Jinjie Wei, Yue Jiang, Qingyao Xu, Xiaolu Hou, Mingyang Sun, Ziyun Qian, Dongliang Kou, Lihua Zhang. [doi]
• Adversarially Robust Multi-task Representation LearningAustin Watkins, Thanh Nguyen-Tang, Enayat Ullah, Raman Arora. [doi]
• Compressing Large Language Models using Low Rank and Low Precision DecompositionRajarshi Saha, Naomi Sagan, Varun Srivastava, Andrea Goldsmith, Mert Pilanci. [doi]
• Compositional 3D-aware Video Generation with LLM DirectorHanxin Zhu, Tianyu He, Anni Tang, Junliang Guo, Zhibo Chen 0001, Jiang Bian 0002. [doi]
• Sparsity-Agnostic Linear Bandits with Adaptive AdversariesTianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi. [doi]
• Language Models as Hierarchy EncodersYuan He 0008, Moy Yuan, Jiaoyan Chen 0001, Ian Horrocks 0001. [doi]
• Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map FilteringIdo Sobol, Chenfeng Xu, Or Litany. [doi]
• Deterministic Policies for Constrained Reinforcement Learning in Polynomial TimeJeremy McMahan. [doi]
• Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space ModelWenbing Li, Hang Zhou 0010, Junqing Yu, Zikai Song, Wei Yang 0034. [doi]
• Reciprocal LearningJulian Rodemann, Christoph Jansen, Georg Schollmeyer. [doi]
• IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTSAshwin Sankar, Srija Anand, Praveen Srinivasa Varadhan, Sherry Thomas, Mehak Singal, Shridhar Kumar, Deovrat Mehendale, Aditi Krishana, Giri Raju, Mitesh M. Khapra. [doi]
• Schur Nets: exploiting local structure for equivariance in higher order graph neural networksQingqi Zhang, Ruize Xu, Risi Kondor. [doi]
• Global Rewards in Restless Multi-Armed BanditsNaveen Raman, Zheyuan Shi, Fei Fang 0001. [doi]
• A Functional Extension of Semi-Structured NetworksDavid Rügamer, Bernard X. W. Liew, Zainab Altai, Almond Stöcker. [doi]
• FIFO-Diffusion: Generating Infinite Videos from Text without TrainingJihwan Kim, Junoh Kang, Jinyoung Choi, Bohyung Han. [doi]
• Quantum Algorithms for Non-smooth Non-convex OptimizationChengchang Liu, Chaowen Guan, Jianhao He, John C. S. Lui. [doi]
• RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy EvaluationJeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni. [doi]
• Melting Pot Contest: Charting the Future of Generalized Cooperative IntelligenceRakshit Trivedi, Akbir Khan, Jesse Clifton, Lewis Hammond, Edgar A. Duéñez-Guzmán, Dipam Chakraborty, John P. Agapiou, Jayd Matyas, Alexander Sasha Vezhnevets, Barna Pásztor, Yunke Ao, Omar G. Younis, Jiawei Huang, Benjamin Swain, Haoyuan Qin, Mian Deng, Ziwei Deng, Utku Erdoganaras, Yue Zhao 0023, Marko Tesic, Natasha Jaques, Jakob Foerster, Vincent Conitzer, José Hernández-Orallo, Dylan Hadfield-Menell, Joel Z. Leibo. [doi]
• Distribution Learning with Valid Outputs Beyond the Worst-CaseNicholas Rittler, Kamalika Chaudhuri. [doi]
• Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in TransformersGavia Gray, Aman Tiwari, Shane Bergsma, Joel Hestness. [doi]
• On the Convergence of Loss and Uncertainty-based Active Learning AlgorithmsDaniel Haimovich, Dima Karamshuk, Fridolin Linder, Niek Tax, Milan Vojnovic. [doi]
• Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuseSamuel Lippl, Jack W. Lindsey. [doi]
• GLBench: A Comprehensive Benchmark for Graph with Large Language ModelsYuhan Li 0001, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai 0002, Wai Kin (Victor) Chan, Jia Li 0009. [doi]
• Robust Neural Contextual Bandit against Adversarial CorruptionsYunzhe Qi, Yikun Ban, Arindam Banerjee 0001, Jingrui He. [doi]
• M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and GenerationMingshuang Luo, Ruibing Hou, Zhuo Li, Hong Chang 0001, Zimo Liu, Yaowei Wang, Shiguang Shan. [doi]
• WindsorML: High-Fidelity Computational Fluid Dynamics Dataset For Automotive AerodynamicsNeil Ashton, Jordan B. Angel, Aditya S. Ghate, Gaetan K. W. Kenway, Man Long Wong, Cetin C. Kiris, Astrid Walle, Danielle Maddix, Gary Page. [doi]
• Cross-modal Representation Flattening for Multi-modal Domain GeneralizationYunfeng Fan, Wenchao Xu 0001, Haozhao Wang, Song Guo 0001. [doi]
• PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language ModelsLemei Zhang, Peng Liu 0025, Marcus Tiedemann Oekland Henriksboe, Even W. Lauvrak, Jon Atle Gulla, Heri Ramampiaro. [doi]
• Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text ModelsQingyuan Zeng, Zhenzhong Wang, Yiu-ming Cheung, Min Jiang 0005. [doi]
• GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open ScenesGaochao Song, Chong Cheng, Hao Wang. [doi]
• Achieving Õ(1/ε) Sample Complexity for Constrained Markov Decision ProcessJiashuo Jiang, Yinyu Ye 0001. [doi]
• QBB: Quantization with Binary Bases for LLMsAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos. [doi]
• Dynamic Model Predictive Shielding for Provably Safe Reinforcement LearningArko Banerjee, Kia Rahmani, Joydeep Biswas, Isil Dillig. [doi]
• TACT: Advancing Complex Aggregative Reasoning with Information Extraction ToolsAvi Caciularu, Alon Jacovi, Eyal Ben-David, Sasha Goldshtein, Tal Schuster, Jonathan Herzig, Gal Elidan, Amir Globerson. [doi]
• LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed ProblemsPengkun Wang, Zhe Zhao 0008, Haibin Wen, Fanfu Wang, Binwu Wang, Qingfu Zhang 0001, Yang Wang 0015. [doi]
• Kermut: Composite kernel regression for protein variant effectsPeter Mørch Groth, Mads Herbert Kerrn, Lars Olsen, Jesper Salomon, Wouter Boomsma. [doi]
• Slice-100K: A Multimodal Dataset for Extrusion-based 3D PrintingAnushrut Jignasu, Kelly O. Marshall, Ankush Kumar Mishra, Lucas Nerone Rillo, Baskar Ganapathysubramanian, Aditya Balu, Chinmay Hegde, Adarsh Krishnamurthy. [doi]
• PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and BeyondChen Song, Zhenxiao Liang, Bo Sun, Qixing Huang. [doi]
• Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based BackpropagationChengting Yu, Lei Liu, Gaoang Wang, Erping Li, Aili Wang 0002. [doi]
• Memory-Efficient LLM Training with Online Subspace DescentKaizhao Liang, Bo Liu, Lizhang Chen, Qiang Liu. [doi]
• Rethinking Weight Decay for Robust Fine-Tuning of Foundation ModelsJunjiao Tian, Chengyue Huang, Zsolt Kira. [doi]
• SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing PansharpeningYu Zhong, Xiao Wu, Liang-Jian Deng, Zihan Cao, Hong-Xia Dou. [doi]
• LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video ReconstructionKanghao Chen, Hangyu Li, Jiazhou Zhou, Zeyu Wang, Lin Wang 0025. [doi]
• ViLCo-Bench: VIdeo Language COntinual learning BenchmarkTianqi Tang 0002, Shohreh Deldari, Hao Xue 0001, Celso de Melo, Flora D. Salim. [doi]
• CLUES: Collaborative Private-domain High-quality Data Selection for LLMs via Training DynamicsWanru Zhao, Hongxiang Fan, Shell Xu Hu, Wangchunshu Zhou, Nicholas D. Lane. [doi]
• Cost-aware Bayesian Optimization via the Pandora's Box Gittins IndexQian Xie 0005, Raul Astudillo, Peter I. Frazier, Ziv Scully, Alexander Terenin. [doi]
• PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for RecommendationWeiqin Yang 0002, Jiawei Chen 0007, Xin Xin 0003, Sheng Zhou 0004, Binbin Hu, Yan Feng, Chun Chen 0001, Can Wang 0001. [doi]
• Newton Losses: Using Curvature Information for Learning with Differentiable AlgorithmsFelix Petersen, Christian Borgelt, Tobias Sutter, Hilde Kuehne, Oliver Deussen, Stefano Ermon. [doi]
• FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal ModelsPengxiang Li 0002, Zhi Gao, Bofei Zhang, Tao Yuan, Yuwei Wu 0001, Mehrtash Harandi, Yunde Jia, Song Chun Zhu, Qing Li 0003. [doi]
• SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural NetworkWeiyu Guo, Ying Sun 0006, Yijie Xu, Ziyue Qiao, Yongkui Yang, Hui Xiong 0001. [doi]
• Multilingual Diversity Improves Vision-Language RepresentationsThao Nguyen, Matthew Wallingford, Sebastin Santy, Wei-Chiu Ma, Sewoong Oh, Ludwig Schmidt, Pang Wei W. Koh, Ranjay Krishna. [doi]
• Qualitative Mechanism IndependenceOliver Richardson, Spencer J. Peters, Joseph Y. Halpern. [doi]
• Learning to Reason via Program Generation, Emulation, and SearchNathaniel Weir, Muhammad Khalifa, Linlu Qiu, Orion Weller, Peter Clark. [doi]
• Fair and Welfare-Efficient Constrained Multi-Matchings under UncertaintyElita A. Lobo, Justin Payan, Cyrus Cousins, Yair Zick. [doi]
• Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional OptimizationZhuanghua Liu, Luo Luo, Bryan Kian Hsiang Low. [doi]
• Generalization Error Bounds for Two-stage Recommender Systems with Tree StructureJin Zhang, Ze Liu, Defu Lian, Enhong Chen. [doi]
• Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image EditingHaonan Lin, Yan Chen 0031, Jiahao Wang, Wenbin An, Mengmeng Wang, Feng Tian 0002, Yong Liu, Guang Dai, Jingdong Wang, QianYing Wang. [doi]
• UGC: Universal Graph CoarseningMohit Kataria, Sandeep Kumar, Jayadeva. [doi]
• No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting InterestsDavide Legacci, Panayotis Mertikopoulos, Christos H. Papadimitriou, Georgios Piliouras, Bary S. R. Pradelski. [doi]
• Separations in the Representational Capabilities of Transformers and Recurrent ArchitecturesSatwik Bhattamishra, Michael Hahn 0001, Phil Blunsom, Varun Kanade. [doi]
• Dense Associative Memory Through the Lens of Random FeaturesBenjamin Hoover, Duen Horng Chau, Hendrik Strobelt, Parikshit Ram, Dmitry Krotov. [doi]
• RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and LocalizationBing Yang, Changsheng Quan, Yabo Wang, Pengyu Wang, Yujie Yang, Ying Fang, Nian Shao, Hui Bu, Xin Xu, Xiaofei Li. [doi]
• Convolutional Differentiable Logic Gate NetworksFelix Petersen, Hilde Kuehne, Christian Borgelt, Julian Welzel, Stefano Ermon. [doi]
• Entropy testing and its application to testing Bayesian networksClément L. Canonne, Joy Qiping Yang. [doi]
• Contrastive losses as generalized models of global epistasisDavid H. Brookes, Jakub Otwinowski, Sam Sinai. [doi]
• Upping the Game: How 2D U-Net Skip Connections Flip 3D SegmentationXingru Huang, Yihao Guo, Jian Huang, Tianyun Zhang, Hong He, Shaowei Jiang, Yaoqi Sun. [doi]
• Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGradSayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takác 0001, Eduard Gorbunov. [doi]
• Conditioning non-linear and infinite-dimensional diffusion processesElizabeth Louise Baker, Gefan Yang, Michael L. Severinsen, Christy Anna Hipsley, Stefan Sommer. [doi]
• Efficient and Private Marginal Reconstruction with Local Non-NegativityBrett Mullins, Miguel Fuentes, Yingtai Xiao, Daniel Kifer, Cameron Musco, Daniel R. Sheldon. [doi]
• MultiOOD: Scaling Out-of-Distribution Detection for Multiple ModalitiesHao Dong, Yue Zhao 0016, Eleni N. Chatzi, Olga Fink. [doi]
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language ModelsBaao Xie, Qiuyu Chen, Yunnan Wang, Zequn Zhang, Xin Jin, Wenjun Zeng. [doi]
• Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code GenerationXuehao Cui, Guangyang Wu, Zhenghao Gan, Guangtao Zhai, Xiaohong Liu 0001. [doi]
• Improved Regret of Linear Ensemble SamplingHarin Lee, Min-hwan Oh. [doi]
• CALVIN: Improved Contextual Video Captioning via Instruction TuningGowthami Somepalli, Arkabandhu Chowdhury, Jonas Geiping, Ronen Basri, Tom Goldstein, David Jacobs 0001. [doi]
• Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language ModelsDongwon Jo, Taesu Kim, Yulhwa Kim, Jae-Joon Kim. [doi]
• SAND: Smooth imputation of sparse and noisy functional data with Transformer networksJu-Sheng Hong, Junwen Yao, Jonas W. Mueller, Jane-ling Wang. [doi]
• Automatically Learning Hybrid Digital Twins of Dynamical SystemsSamuel Holt, Tennison Liu, Mihaela van der Schaar. [doi]
• MADiff: Offline Multi-agent Learning with Diffusion ModelsZhengbang Zhu, Minghuan Liu, Liyuan Mao, Bingyi Kang, Minkai Xu, Yong Yu 0001, Stefano Ermon, Weinan Zhang 0001. [doi]
• QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor ExpansionYixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Emad Barsoum. [doi]
• Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse ProblemsJason Hu, Bowen Song, Xiaojian Xu 0002, Liyue Shen, Jeffrey A. Fessler. [doi]
• From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsZhuoshi Pan, Yuguang Yao, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Kompella, Sijia Liu 0001. [doi]
• Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the ScaryZhuoyan Li, Ming Yin 0001. [doi]
• MKGL: Mastery of a Three-Word LanguageLingbing Guo, Zhongpu Bo, Zhuo Chen 0007, Yichi Zhang 0009, Jiaoyan Chen 0001, Yarong Lan, Mengshu Sun, Zhiqiang Zhang, Yangyifei Luo, Qian Li, Qiang Zhang, Wen Zhang, Huajun Chen. [doi]
• Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationShreyas Chaudhari, Ameet Deshpande, Bruno C. da Silva 0001, Philip S. Thomas. [doi]
• SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial OptimizationTaisuke Yasuda 0002, Kyriakos Axiotis, Gang Fu, Mohammad Hossein Bateni 0001, Vahab Mirrokni. [doi]
• DMesh: A Differentiable Mesh RepresentationSanghyun Son 0003, Matheus Gadelha, Yang Zhou, Zexiang Xu, Ming C. Lin, Yi Zhou 0023. [doi]
• OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised LearningShengjie Niu, Lifan Lin, Jian Huang, Chao Wang. [doi]
• Efficient Federated Learning against Heterogeneous and Non-stationary Client UnavailabilityMing Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, Lili Su. [doi]
• Interpretable Mesomorphic Networks for Tabular DataArlind Kadra, Sebastian Pineda-Arango, Josif Grabocka. [doi]
• Almost Surely Asymptotically Constant Graph Neural NetworksSam Adam-Day, Michael Benedikt, Ismail Ilkan Ceylan, Ben Finkelshtein. [doi]
• On the Expressive Power of Tree-Structured Probabilistic CircuitsLang Yin, Han Zhao 0002. [doi]
• Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration BonusYiming Wang, Kaiyan Zhao, Furui Liu, Leong Hou U. [doi]
• ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language ModelsShuo Liu, Kaining Ying, Hao Zhang, Yue Yang, Yuqi Lin, Tianle Zhang, Chuanhao Li, Yu Qiao 0001, Ping Luo 0002, Wenqi Shao, Kaipeng Zhang. [doi]
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringXiaoxin He, Yijun Tian 0001, Yifei Sun, Nitesh V. Chawla, Thomas Laurent 0001, Yann LeCun, Xavier Bresson, Bryan Hooi. [doi]
• WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language ArtsJiahuan Cao, Yang Liu, Yongxin Shi, Kai Ding 0009, Lianwen Jin. [doi]
• Do causal predictors generalize better to new domains?Vivian Y. Nastl, Moritz Hardt. [doi]
• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous LearnerHanwen Zhong, Jiaxin Chen, Yutong Zhang, Di Huang, Yunhong Wang. [doi]
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work TasksLéo Boisvert, Megh Thakkar, Maxime Gasse, Massimo Caccia, Thibault Le Sellier De Chezelles, Quentin Cappart, Nicolas Chapados, Alexandre Lacoste, Alexandre Drouin. [doi]
• MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse AttentionHuiqiang Jiang, Yucheng Li, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir Abdi, Dongsheng Li 0002, Chin-Yew Lin, Yuqing Yang 0001, Lili Qiu. [doi]
• Pard: Permutation-Invariant Autoregressive Diffusion for Graph GenerationLingxiao Zhao, Xueying Ding, Leman Akoglu. [doi]
• AdaNovo: Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data BiasesJun Xia 0001, Shaorong Chen, Jingbo Zhou, Xiaojun Shan, Wenjie Du, Zhangyang Gao, Cheng Tan 0012, Bozhen Hu, Jiangbin Zheng, Stan Z. Li. [doi]
• Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image EditingSiyi Chen, Huijie Zhang, Minzhe Guo, Yifu Lu, Peng Wang 0098, Qing Qu 0001. [doi]
• Reinforcement Learning with Lookahead InformationNadav Merlis. [doi]
• Clustering in Causal Attention MaskingNikita Karagodin, Yury Polyanskiy, Philippe Rigollet. [doi]
• Learning from Teaching Regularization: Generalizable Correlations Should be Easy to ImitateCan Jin, Tong Che, Hongwu Peng, Yiyuan Li, Dimitris N. Metaxas, Marco Pavone 0001. [doi]
• Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language ModelsYushi Hu, Weijia Shi, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Ranjay Krishna. [doi]
• FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards ModelsJiachang Liu 0001, Rui Zhang, Cynthia Rudin. [doi]
• Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object DetectionDingrong Wang, Hitesh Sapkota, Qi Yu 0001. [doi]
• Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge IntegrationMahdi Morafah, Vyacheslav Kungurtsev, Hojin Chang, Chen Chen 0001, Bill Lin 0001. [doi]
• Generalization Bounds via Conditional f-InformationZiqiao Wang, Yongyi Mao. [doi]
• Diffusion Model with Cross Attention as an Inductive Bias for DisentanglementTao Yang, Cuiling Lan, Yan Lu 0001, Nanning Zheng 0001. [doi]
• Graph Diffusion Policy OptimizationYijing Liu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Wei Chen 0001. [doi]
• Equivariant Blurring Diffusion for Hierarchical Molecular Conformer GenerationJiwoong Park, Yang Shen. [doi]
• Terra: A Multimodal Spatio-Temporal Dataset Spanning the EarthWei Chen 0070, Xixuan Hao, Yuankai Wu, Yuxuan Liang. [doi]
• MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their UsabilityYanrui Du, Sendong Zhao, Danyang Zhao, Ming Ma, Yuhan Chen 0002, Liangyu Huo, Qing Yang 0033, Dongliang Xu, Bing Qin 0001. [doi]
• Breaking Semantic Artifacts for Generalized AI-generated Image DetectionChende Zheng, Chenhao Lin, Zhengyu Zhao 0001, Hang Wang, Xu Guo, Shuai Liu, Chao Shen 0001. [doi]
• Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual ReconstructionChen-Long Duan, Yong Li, Xiu-Shen Wei, Lin Zhao. [doi]
• Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational DataMiruna Oprescu, Nathan Kallus. [doi]
• Multi-Reward Best Policy IdentificationAlessio Russo, Filippo Vannella. [doi]
• Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence DetectionJiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen 0001, Xinbo Gao 0001. [doi]
• Zero-Shot Reinforcement Learning from Low Quality DataScott R. Jeen, Tom Bewley, Jonathan M. Cullen. [doi]
• MiniCache: KV Cache Compression in Depth Dimension for Large Language ModelsAkide Liu, Jing Liu, Zizheng Pan, Yefei He, Reza Haffari, Bohan Zhuang. [doi]
• Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operatorsZekun Shi, Zheyuan Hu, Min Lin, Kenji Kawaguchi. [doi]
• Learning 1D Causal Visual Representation with De-focus Attention NetworksChenxin Tao, Xizhou Zhu, Shiqian Su, Lewei Lu, Changyao Tian, Xuan Luo, Gao Huang 0001, Hongsheng Li 0001, Yu Qiao 0001, Jie Zhou 0001, Jifeng Dai. [doi]
• Hybrid Mamba for Few-Shot SegmentationQianxiong Xu, Xuanyi Liu, Lanyun Zhu, Guosheng Lin, Cheng Long 0001, Ziyue Li 0002, Rui Zhao 0001. [doi]
• Stochastic Optimal Control MatchingCarles Domingo-Enrich, Jiequn Han, Brandon Amos, Joan Bruna, Ricky T. Q. Chen. [doi]
• In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory TerminatesShicheng Liu, Minghui Zhu. [doi]
• Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular DataKai Helli, David Schnurr, Noah Hollmann, Samuel Müller 0005, Frank Hutter. [doi]
• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized CutPaul Couairon, Mustafa Shukor, Jean-Emmanuel Haugeard, Matthieu Cord, Nicolas Thome. [doi]
• Diffusion Actor-Critic with Entropy RegulatorYinuo Wang, Likun Wang, Yuxuan Jiang 0011, Wenjun Zou, Tong Liu, Xujie Song, Wenxuan Wang 0004, Liming Xiao, Jiang Wu, Jingliang Duan, Shengbo Li 0001. [doi]
• Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow AnalysisHongru Yang, Bhavya Kailkhura, Zhangyang Wang, Yingbin Liang. [doi]
• BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety AlignmentJiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Sharon Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao. [doi]
• Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion PerspectiveChengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun 0001, Zirui Zhuang, Jinming Wu, Jianxin Liao. [doi]
• Image2Struct: Benchmarking Structure Extraction for Vision-Language ModelsJosselin Somerville Roberts, Tony Lee, Chi Heem Wong, Michihiro Yasunaga, Yifan Mai, Percy Liang. [doi]
• Adaptive Proximal Gradient Method for Convex OptimizationYura Malitsky, Konstantin Mishchenko. [doi]
• SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax OperationSangwoo Hwang, Seunghyun Lee, Dahoon Park, Donghun Lee, Jaeha Kung. [doi]
• Continuous Partitioning for Graph-Based Semi-Supervised LearningChester Holtz, Pengwen Chen, Zhengchao Wan, Chung-Kuan Cheng, Gal Mishne. [doi]
• CoMix: A Comprehensive Benchmark for Multi-Task Comic UnderstandingEmanuele Vivoli, Marco Bertini 0001, Dimosthenis Karatzas. [doi]
• NVRC: Neural Video Representation CompressionHo Man Kwan, Ge Gao, Fan Zhang 0017, Andrew Gower, David Bull 0001. [doi]
• Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant ProblemsBingcong Li, Liang Zhang, Niao He. [doi]
• Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasksTianyu He, Darshil Doshi, Aritra Das, Andrey Gromov. [doi]
• Length Optimization in Conformal PredictionShayan Kiyani, George J. Pappas, Hamed Hassani. [doi]
• Instruction-Guided Visual MaskingJinliang Zheng, Jianxiong Li, Sijie Cheng, Yinan Zheng, Jiaming Li, Jihao Liu, Yu Liu, Jingjing Liu, Xianyuan Zhan. [doi]
• Unsupervised Anomaly Detection in The Presence of Missing ValuesFeng Xiao, Jicong Fan 0001. [doi]
• Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited ModalitiesAdriel Saporta, Aahlad Manas Puli, Mark Goldstein, Rajesh Ranganath. [doi]
• Discrete-state Continuous-time Diffusion for Graph GenerationZhe Xu 0007, Ruizhong Qiu, Yuzhong Chen, Huiyuan Chen, Xiran Fan, Menghai Pan, Zhichen Zeng 0001, Mahashweta Das, Hanghang Tong. [doi]
• The tree autoencoder model, with application to hierarchical data visualizationMiguel Á. Carreira-Perpiñán, Kuat Gazizov. [doi]
• Goal-Conditioned On-Policy Reinforcement LearningXudong Gong, Dawei Feng, Kele Xu, Bo Ding, Huaimin Wang. [doi]
• Training-Free Adaptive Diffusion with Bounded Difference Approximation StrategyHancheng Ye, Jiakang Yuan, Renqiu Xia, Xiangchao Yan, Tao Chen 0003, Junchi Yan, Botian Shi, Bo Zhang 0069. [doi]
• How Does Message Passing Improve Collaborative Filtering?Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye 0001, Yozen Liu, Neil Shah, Tong Zhao 0003. [doi]
• Measuring Dejavu Memorization EfficientlyNarine Kokhlikyan, Bargav Jayaraman, Florian Bordes, Chuan Guo 0001, Kamalika Chaudhuri. [doi]
• Generative ForestsRichard Nock, Mathieu Guillame-Bert. [doi]
• YouDream: Generating Anatomically Controllable Consistent Text-to-3D AnimalsSandeep Mishra, Oindrila Saha, Alan C. Bovik. [doi]
• Can We Leave Deepfake Data Behind in Training Deepfake Detector?Jikang Cheng, Zhiyuan Yan 0002, Ying Zhang, Yuhao Luo, Zhongyuan Wang 0001, Chen Li. [doi]
• Recovering Complete Actions for Cross-dataset Skeleton Action RecognitionHanchao Liu, Yujiang Li, Tai-Jiang Mu, Shi-Min Hu 0001. [doi]
• Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signalsAbhiram Iyer, Sarthak Chandra, Sugandha Sharma, Ila Fiete. [doi]
• Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic SegmentationYu Zheng, Guangming Wang 0001, Jiuming Liu, Marc Pollefeys, Hesheng Wang 0001. [doi]
• CAT3D: Create Anything in 3D with Multi-View Diffusion ModelsRuiQi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul P. Srinivasan, Jonathan T. Barron, Ben Poole. [doi]
• Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence ModelingSili Huang, Jifeng Hu, Zhejian Yang, Liwei Yang, Tao Luo, Hechang Chen, Lichao Sun 0001, Bo Yang. [doi]
• Piecewise-Stationary Bandits with KnapsacksXilin Zhang, Wang Chi Cheung. [doi]
• CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-trainingDavid Brandfonbrener, Hanlin Zhang, Andreas Kirsch 0002, Jonathan Richard Schwarz, Sham M. Kakade. [doi]
• Fast samplers for Inverse Problems in Iterative Refinement modelsKushagra Pandey, Ruihan Yang, Stephan Mandt. [doi]
• SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet KnowledgeChuanhao Li, Zhen Li 0026, Chenchen Jing, Shuo Liu, Wenqi Shao, Yuwei Wu 0001, Ping Luo 0002, Yu Qiao 0001, Kaipeng Zhang. [doi]
• Understanding Transformers via N-Gram StatisticsTimothy Nguyen. [doi]
• Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit LearnabilityFan Chen, Dylan J. Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu. [doi]
• Personalized Federated Learning via Feature Distribution AdaptationConnor McLaughlin, Lili Su. [doi]
• Discovering Creative Behaviors through DUPLEX: Diverse Universal Features for Policy ExplorationBorja G. León, Francesco Riccio, Kaushik Subramanian, Peter R. Wurman, Peter Stone 0001. [doi]
• Robust Reinforcement Learning with General UtilityZiyi Chen 0002, Yan Wen, Zhengmian Hu, Heng Huang. [doi]
• Reinforced Cross-Domain Knowledge Distillation on Time Series DataQing Xu 0015, Min Wu 0008, Xiaoli Li 0001, Kezhi Mao, Zhenghua Chen. [doi]
• Fairness in Social Influence Maximization via Optimal TransportShubham Chowdhary, Giulia De Pasquale, Nicolas Lanzetti, Ana-Andreea Stoica, Florian Dörfler. [doi]
• Online Classification with PredictionsVinod Raman, Ambuj Tewari. [doi]
• How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular RetrievalPhilip Fradkin, Puria Azadi Moghadam, Karush Suri, Frederik Wenkel, Ali Bashashati, Maciej Sypetkowski, Dominique Beaini. [doi]
• On the Optimal Time Complexities in Decentralized Stochastic Asynchronous OptimizationAlexander Tyurin, Peter Richtárik. [doi]
• FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal AttentionYu Lu, Yuanzhi Liang, Linchao Zhu, Yi Yang 0001. [doi]
• A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud RegistrationRenlang Huang, Yufan Tang, Jiming Chen, Liang Li. [doi]
• Federated Learning over Connected ModesDennis Grinwald, Philipp Wiesner, Shinichi Nakajima. [doi]
• Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and AnalysisMichael Crawshaw, Mingrui Liu. [doi]
• Invariant Tokenization of Crystalline Materials for Language Model Enabled GenerationKeqiang Yan, Xiner Li, Hongyi Ling, Kenna Ashen, Carl Edwards, Raymundo Arróyave, Marinka Zitnik, Heng Ji, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji. [doi]
• Is Multiple Object Tracking a Matter of Specialization?Gianluca Mancusi, Mattia Bernardi, Aniello Panariello, Angelo Porrello, Rita Cucchiara, Simone Calderara. [doi]
• Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt AdaptationAbhinav Jain 0001, Swarat Chaudhuri, Thomas W. Reps, Christopher M. Jermaine. [doi]
• Understanding Hallucinations in Diffusion Models through Mode InterpolationSumukh K. Aithal, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter. [doi]
• Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEsMd. Ashiqur Rahman, Robert Joseph George, Mogab Elleithy, Daniel V. Leibovici, Zongyi Li, Boris Bonev, Colin White, Julius Berner, Raymond A. Yeh, Jean Kossaifi, Kamyar Azizzadenesheli, Animashree Anandkumar. [doi]
• Evidential Stochastic Differential Equations for Time-Aware Sequential RecommendationKrishna Prasad Neupane, Ervine Zheng, Qi Yu 0001. [doi]
• Iterative Methods via Locally Evolving Set ProcessBaojian Zhou, Yifan Sun, Reza Babanezhad Harikandeh, Xingzhi Guo, Deqing Yang, Yanghua Xiao. [doi]
• Diffusion-based Curriculum Reinforcement LearningErdi Sayar, Giovanni Iacca, Ozgur S. Oguz, Alois Knoll. [doi]
• Explaining Datasets in Words: Statistical Models with Natural Language ParametersRuiqi Zhong, Heng Wang, Dan Klein, Jacob Steinhardt. [doi]
• Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised LearningShentong Mo, Peter Tong. [doi]
• Learning-Augmented Algorithms for the Bahncard ProblemHailiang Zhao, Xueyan Tang, Peng Chen, ShuiGuang Deng. [doi]
• AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular VideosYuze He, Wang Zhao 0001, Shaohui Liu, Yubin Hu 0001, Yushi Bai, Yu-Hui Wen, Yongjin Liu 0001. [doi]
• Improved Regret for Bandit Convex Optimization with Delayed FeedbackYuanyu Wan, Chang Yao, Mingli Song, Lijun Zhang 0005. [doi]
• A Study of Plasticity Loss in On-Policy Deep Reinforcement LearningArthur Juliani, Jordan T. Ash. [doi]
• UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion ModelsYihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Kompella, Xiaoming Liu 0002, Sijia Liu 0001. [doi]
• Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion ModelYiming Lei, Zilong Li, Junping Zhang, Hongming Shan. [doi]
• Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGDJie Hu, Yi-Ting Ma, Do Young Eun. [doi]
• Peri-midFormer: Periodic Pyramid Transformer for Time Series AnalysisQiang Wu, Gechang Yao, Zhixi Feng, Shuyuan Yang. [doi]
• Towards General Loop Invariant Generation: A Benchmark of Programs with Memory ManipulationChang Liu, Xiwei Wu, Yuan Feng 0001, Qinxiang Cao, Junchi Yan. [doi]
• Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical PerspectiveXinhao Yao, Xiaolin Hu, Shenzhi Yang, Yong Liu. [doi]
• Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect SignalsLisa Bedin, Gabriel Cardoso 0001, Josselin Duchateau, Rémi Dubois, Eric Moulines. [doi]
• Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language ModelYanpeng Ye, Jie Ren, Shaozhou Wang, Yuwei Wan, Imran Razzak, Bram Hoex, Haofen Wang, Tong Xie, Wenjie Zhang 0001. [doi]
• SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated DataJialu Li 0001, Jaemin Cho 0001, Yi-Lin Sung, Jaehong Yoon, Mohit Bansal. [doi]
• Towards the Dynamics of a DNN Learning Symbolic InteractionsQihan Ren, Junpeng Zhang, Yang Xu, Yue Xin, Dongrui Liu, Quanshi Zhang. [doi]
• Dissecting the Failure of Invariant Learning on GraphsQixun Wang 0002, Yifei Wang 0001, Yisen Wang 0001, Xianghua Ying. [doi]
• An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement LearningQian Lin, Zongkai Liu, Danying Mo, Chao Yu 0004. [doi]
• Evaluating language models as risk scoresAndré F. Cruz, Moritz Hardt, Celestine Mendler-Dünner. [doi]
• Hyperbolic Embeddings of Supervised ModelsRichard Nock, Ehsan Amid, Frank Nielsen, Alexander Soen, Manfred K. Warmuth. [doi]
• Subject-driven Text-to-Image Generation via Preference-based Reinforcement LearningYanting Miao, William Loh, Suraj Kothawade, Pascal Poupart, Abdullah Rashwan, Yeqing Li. [doi]
• GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing TasksYu Zhang 0126, Changhao Pan, Wenxiang Guo, Ruiqi Li, Zhiyuan Zhu, Jialei Wang, Wenhao Xu, Jingyu Lu, Zhiqing Hong, Chuxin Wang, Lichao Zhang, Jinzheng He, Ziyue Jiang 0001, Yuxin Chen, Chen Yang, Jiecheng Zhou, Xinyu Cheng, Zhou Zhao. [doi]
• SCube: Instant Large-Scale Scene Reconstruction using VoxSplatsXuanchi Ren, Yifan Lu, Hanxue Liang, Jay Zhangjie Wu, Huan Ling, Mike Chen, Sanja Fidler, Francis Williams, Jiahui Huang. [doi]
• UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph ConstructionYansong Ning, Hao Liu. [doi]
• TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust ClusteringJun Dan, Weiming Liu 0005, Chunfeng Xie, Hua Yu 0006, Shunjie Dong, Yanchao Tan. [doi]
• ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian SplattingsSuyoung Lee, Jaeyoung Chung, Jaeyoo Huh, Kyoung Mu Lee. [doi]
• CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker ConversationsLeying Zhang, Yao Qian, Long Zhou, Shujie Liu 0001, Dongmei Wang, Xiaofei Wang, Midia Yousefi, Yanmin Qian, Jinyu Li 0001, Lei He 0005, Sheng Zhao, Michael Zeng 0001. [doi]
• Don't Compress Gradients in Random Reshuffling: Compress Gradient DifferencesAbdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov 0001, Ahmed Khaled 0001, Konstantin Burlachenko, Peter Richtárik. [doi]
• Nearly Tight Black-Box Auditing of Differentially Private Machine LearningMeenatchi Sundaram Muthu Selva Annamalai, Emiliano De Cristofaro. [doi]
• Dynamic Conditional Optimal Transport through Simulation-Free FlowsGavin Kerrigan, Giosue Migliorini, Padhraic Smyth. [doi]
• MECD: Unlocking Multi-Event Causal Discovery in Video ReasoningTieyuan Chen, Huabin Liu 0001, Tianyao He, Yihang Chen, Chaofan Gan, Xiao Ma, Cheng Zhong, Yang Zhang, Yingxue Wang, Hui Lin, Weiyao Lin. [doi]
• PANORAMIA: Privacy Auditing of Machine Learning Models without RetrainingMishaal Kazmi, Hadrien Lautraite, Alireza Akbari, Qiaoyue Tang, Mauricio Soroco, Tao Wang, Sébastien Gambs, Mathias Lécuyer. [doi]
• Distribution Guidance Network for Weakly Supervised Point Cloud Semantic SegmentationZhiyi Pan, Wei Gao 0003, Shan Liu 0001, Ge Li 0002. [doi]
• Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope TheoryPasan Dissanayake, Sanghamitra Dutta. [doi]
• Memorize What Matters: Emergent Scene Decomposition from MultitraverseYiming Li, Zehong Wang, Yue Wang 0036, Zhiding Yu, Zan Gojcic, Marco Pavone 0001, Chen Feng 0002, José M. Álvarez 0004. [doi]
• OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetShubham Toshniwal, Ivan Moshkov, Sean Narenthiran, Daria Gitman, Fei Jia, Igor Gitman. [doi]
• Reranking Laws for Language Generation: A Communication-Theoretic PerspectiveAntónio Farinhas, Haau-Sing Li, André Martins. [doi]
• Intrinsic Self-Supervision for Data Quality AuditsFabian Gröger, Simone Lionetti, Philippe Gottfrois, Álvaro González-Jiménez, Ludovic Amruthalingam, Matthew Groh, Alexander A. Navarini, Marc Pouly. [doi]
• Easy-to-Hard Generalization: Scalable Alignment Beyond Human SupervisionZhiqing Sun, Longhui Yu, Yikang Shen, Weiyang Liu, Yiming Yang, Sean Welleck, Chuang Gan. [doi]
• Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based ModelsSangwoong Yoon, Himchan Hwang, Dohyun Kwon 0002, Yung-Kyun Noh, Frank C. Park 0001. [doi]
• The Impact of Initialization on LoRA Finetuning DynamicsSoufiane Hayou, Nikhil Ghosh, Bin Yu 0001. [doi]
• DistrictNet: Decision-aware learning for geographical districtingCheikh Ahmed, Alexandre Forel, Axel Parmentier, Thibaut Vidal. [doi]
• Addressing Bias in Online Selection with Limited Budget of ComparisonsZiyad Benomar, Evgenii Chzhen, Nicolas Schreuder, Vianney Perchet. [doi]
• Noise-Aware Differentially Private Regression via Meta-LearningOssi Räisä, Stratis Markou, Matthew Ashman, Wessel P. Bruinsma, Marlon Tobaben, Antti Honkela, Richard E. Turner. [doi]
• BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityZahra Gharaee, Scott C. Lowe, ZeMing Gong, Pablo Millan Arias, Nicholas Pellegrino, Austin T. Wang, Joakim Bruslund Haurum, Iuliia Eyriay, Lila Kari, Dirk Steinke, Graham W. Taylor, Paul W. Fieguth, Angel X. Chang. [doi]
• Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion EffectsAlexander Levis, Gabriel Loewinger, Francisco Pereira. [doi]
• Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language ModelsAlkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis. [doi]
• The Evolution of Statistical Induction Heads: In-Context Learning Markov ChainsEzra Edelman, Nikolaos Tsilivis 0002, Benjamin L. Edelman, Eran Malach, Surbhi Goel. [doi]
• Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit FeedbackHaolin Liu, Zakaria Mhammedi, Chen-Yu Wei, Julian Zimmert. [doi]
• Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient AlgorithmQinbo Bai, Washim Uddin Mondal, Vaneet Aggarwal. [doi]
• Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node ClassificationYihong Luo, Yuhan Chen, Siya Qiu, Yiwei Wang, Chen Zhang 0013, Yan Zhou, Xiaochun Cao, Jing Tang 0004. [doi]
• Pearls from Pebbles: Improved Confidence Functions for Auto-labelingHarit Vishwakarma, Yi Chen, Sui Jiet Tay, Satya Sai Srinath Namburi, Frederic Sala, Ramya Korlakai Vinayak. [doi]
• A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose EmbeddingYitong Dong, Yijin Li, Zhaoyang Huang, Weikang Bian, Jingbo Liu, Hujun Bao, Zhaopeng Cui, Hongsheng Li 0001, Guofeng Zhang 0001. [doi]
• Multi-view Masked Contrastive Representation Learning for Endoscopic Video AnalysisKai Hu, Ye Xiao, Yuan Zhang, Xieping Gao. [doi]
• Matching the Statistical Query Lower Bound for k-Sparse Parity Problems with Sign Stochastic Gradient DescentYiwen Kou, Zixiang Chen, Quanquan Gu, Sham M. Kakade. [doi]
• On scalable oversight with weak LLMs judging strong LLMsZachary Kenton, Noah Y. Siegel, János Kramár, Jonah Brown-Cohen, Samuel Albanie, Jannis Bulian, Rishabh Agarwal, David Lindner, Yunhao Tang, Noah D. Goodman, Rohin Shah. [doi]
• Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph ConstructionHaoran Luo 0001, Haihong E, Yuhao Yang 0006, Tianyu Yao, Yikai Guo, Zichen Tang, Wentai Zhang 0004, Shiyao Peng, Kaiyang Wan, Meina Song, Wei Lin, Yifan Zhu 0001, Anh Tuan Luu. [doi]
• Compositional Automata Embeddings for Goal-Conditioned Reinforcement LearningBeyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit Seshia. [doi]
• Aligner-Encoders: Self-Attention Transformers Can Be Self-TransducersAdam Stooke, Rohit Prabhavalkar, Khe Chai Sim, Pedro Moreno Mengibar. [doi]
• Beyond Optimism: Exploration With Partially Observable RewardsSimone Parisi, Alireza Kazemipour, Michael Bowling. [doi]
• ActAnywhere: Subject-Aware Video Background GenerationBoxiao Pan, Zhan Xu, Chun-Hao Paul Huang, Krishna Kumar Singh, Yang Zhou 0009, Leonidas J. Guibas, Jimei Yang. [doi]
• Kraken: Inherently Parallel Transformers For Efficient Multi-Device InferenceRohan Baskar Prabhakar, Hengrui Zhang, David Wentzlaff. [doi]
• Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal LearnerValentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar. [doi]
• Self-Guiding Exploration for Combinatorial ProblemsZangir Iklassov, Yali Du 0001, Farkhad Akimov, Martin Takác 0001. [doi]
• SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual RegularizationZixuan Chen, Ze Ji, Jing Huo, Yang Gao. [doi]
• CryoGEM: Physics-Informed Generative Cryo-Electron MicroscopyJiakai Zhang, Qihe Chen, Yan Zeng, Wenyuan Gao, Xuming He 0001, Zhijie Liu, Jingyi Yu. [doi]
• Fisher Flow Matching for Generative Modeling over Discrete DataOscar Davis, Samuel Kessler, Mircea Petrache, Ismail Ilkan Ceylan, Michael M. Bronstein, Avishek Joey Bose. [doi]
• A Globally Optimal Portfolio for m-Sparse Sharpe Ratio MaximizationYizun Lin, Zhao-Rong Lai, Cheng Li 0018. [doi]
• SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and BenchmarkingJin Wu, Haoying Zhou, Peter Kazanzides, Adnan Munawar, Anqi Liu. [doi]
• Mitigating Reward Overoptimization via Lightweight Uncertainty EstimationXiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, Yang Liu 0018. [doi]
• A Bayesian Approach for Personalized Federated Learning in Heterogeneous SettingsDisha Makhija, Joydeep Ghosh, Nhat Ho. [doi]
• DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial PurificationKaibo Wang, Xiaowen Fu, Yuxuan Han, Yang Xiang. [doi]
• Derivatives of Stochastic Gradient Descent in parametric optimizationFranck Iutzeler, Edouard Pauwels, Samuel Vaiter. [doi]
• MimicTalk: Mimicking a personalized and expressive 3D talking face in minutesZhenhui Ye, Tianyun Zhong, Yi Ren 0006, Ziyue Jiang 0001, Jiawei Huang 0008, Rongjie Huang, Jinglin Liu, Jinzheng He, Chen Zhang 0020, Zehan Wang 0001, Xize Cheng, Xiang Yin 0006, Zhou Zhao. [doi]
• Noise Contrastive Alignment of Language Models with Explicit RewardsHuayu Chen, Guande He, Lifan Yuan, Ganqu Cui, Hang Su, Jun Zhu. [doi]
• Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-ExpertsHang Guo, Tao Dai 0001, Yuanchao Bai, Bin Chen 0011, Xudong Ren, Zexuan Zhu, Shu-Tao Xia. [doi]
• Active Learning with LLMs for Partially Observed and Cost-Aware ScenariosNicolás Astorga, Tennison Liu, Nabeel Seedat, Mihaela van der Schaar. [doi]
• Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation PuzzlesQi Chen, Bowen Zhang, Gang Wang, Qi Wu. [doi]
• Unified Guidance for Geometry-Conditioned Molecular GenerationSirine Ayadi, Leon Hetzel, Johanna Sommer, Fabian J. Theis, Stephan Günnemann. [doi]
• Capturing the denoising effect of PCA via compression ratioChandra Sekhar Mukherjee, Nikhil Deorkar, Jiapeng Zhang. [doi]
• Improving Subgroup Robustness via Data SelectionSaachi Jain, Kimia Hamidieh, Kristian Georgiev, Andrew Ilyas, Marzyeh Ghassemi, Aleksander Madry. [doi]
• Seeing the Image: Prioritizing Visual Correlation by Contrastive AlignmentXin Xiao, Bohong Wu, Jiacong Wang, Chunyuan Li, Xun Zhou, Haoyuan Guo. [doi]
• ROIDICE: Offline Return on Investment Maximization for Efficient Decision MakingWoosung Kim, Hayeong Lee, Jongmin Lee, Byung Jun Lee. [doi]
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in TransformersSiyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang. [doi]
• Chain of Thoughtlessness? An Analysis of CoT in PlanningKaya Stechly, Karthik Valmeekam, Subbarao Kambhampati. [doi]
• Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RLAndrew Wagenmaker, Kevin Huang, Liyiming Ke, Kevin G. Jamieson, Abhishek Gupta 0004. [doi]
• John Ellipsoids via Lazy UpdatesDavid P. Woodruff, Taisuke Yasuda 0002. [doi]
• Efficient Sketches for Training Data Attribution and Studying the Loss LandscapeAndrea Schioppa. [doi]
• Improving Deep Learning Optimization through Constrained Parameter RegularizationJörg K. H. Franke, Michael Hefenbrock, Gregor Köhler, Frank Hutter. [doi]
• Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural NetworksZhenghao Xu, Yuqing Wang, Tuo Zhao, Rachel Ward, Molei Tao. [doi]
• AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial AttacksJin Li, Ziqiang He, Anwei Luo, Jian-Fang Hu, Z. Jane Wang 0001, Xiangui Kang. [doi]
• Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing FlowsAlberto Cabezas, Louis Sharrock, Christopher Nemeth. [doi]
• PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language ModelsFanxu Meng, Zhaohui Wang, Muhan Zhang. [doi]
• Improving Decision SparsityYiyang Sun, Tong Wang 0011, Cynthia Rudin. [doi]
• SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query BenchmarkSithursan Sivasubramaniam, Cedric Osei-Akoto, Yi Zhang, Kurt Stockinger, Jonathan Fürst. [doi]
• On Socially Fair Low-Rank Approximation and Column Subset SelectionZhao Song 0002, Ali Vakilian, David P. Woodruff, Samson Zhou. [doi]
• Customized Subgraph Selection and Encoding for Drug-drug Interaction PredictionHaotong Du, Quanming Yao, Juzheng Zhang, Yang Liu, Zhen Wang. [doi]
• Octopus: A Multi-modal LLM with Parallel Recognition and Sequential UnderstandingChuyang Zhao, Yuxin Song, Junru Chen, Kang Rong, Haocheng Feng, Gang Zhang, Shufan Ji, Jingdong Wang 0001, Errui Ding, Yifan Sun 0003. [doi]
• Public-data Assisted Private Stochastic Optimization: Power and LimitationsEnayat Ullah, Michael Menart, Raef Bassily, Cristóbal Guzmán, Raman Arora. [doi]
• Understanding Visual Feature Reliance through the Lens of ComplexityThomas Fel, Louis Béthune, Andrew K. Lampinen, Thomas Serre, Katherine L. Hermann. [doi]
• Neural Embeddings Rank: Aligning 3D latent dynamics with movementsChenggang Chen, Zhiyu Yang, Xiaoqin Wang. [doi]
• Variational Distillation of Diffusion Policies into Mixture of ExpertsHongyi Zhou, Denis Blessing, Ge Li, Onur Celik, Xiaogang Jia, Gerhard Neumann, Rudolf Lioutikov. [doi]
• Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion ModelWenjia Xie, Hao Wang 0076, Luankang Zhang, Rui Zhou, Defu Lian, Enhong Chen. [doi]
• Revisiting Ensembling in One-Shot Federated LearningYoussef Allouah, Akash Dhasade, Rachid Guerraoui, Nirupam Gupta, Anne-Marie Kermarrec, Rafael Pinot, Rafael Pires 0001, Rishi Sharma 0001. [doi]
• Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor LocalizationMichal Balcerak, Tamaz Amiranashvili, Andreas Wagner, Jonas Weidner, Petr Karnakov, Johannes C. Paetzold, Ivan Ezhov, Petros Koumoutsakos, Benedikt Wiestler, Bjoern H. Menze. [doi]
• Generate Universal Adversarial Perturbations for Few-Shot LearningYiman Hu, Yixiong Zou, Ruixuan Li 0001, Yuhua Li 0003. [doi]
• FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisionJay Shah, Ganesh Bikshandi, Ying Zhang, Vijay Thakkar, Pradeep Ramani, Tri Dao. [doi]
• ProSST: Protein Language Modeling with Quantized Structure and Disentangled AttentionMingchen Li, Yang Tan, Xinzhu Ma, Bozitao Zhong, Huiqun Yu, Ziyi Zhou, Wanli Ouyang, Bingxin Zhou, Pan Tan, Liang Hong. [doi]
• Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object DetectionDongsu Song, Daehwa Ko, Jay Hoon Jung. [doi]
• WildGaussians: 3D Gaussian Splatting In the WildJonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler. [doi]
• Transfer Q-star : Principled Decoding for LLM AlignmentSouradip Chakraborty, Soumya Suvra Ghosal, Ming Yin 0003, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang. [doi]
• Adaptive Layer Sparsity for Large Language Models via Activation Correlation AssessmentWei Li, Lujun Li, Mark Lee, Shengjie Sun. [doi]
• Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language ModelsShengyun Peng, Pin-Yu Chen, Matthew Hull, Duen Horng Chau. [doi]
• Predictive Attractor ModelsRamy Mounir, Sudeep Sarkar. [doi]
• S-STE: Continuous Pruning Function for Efficient 2: 4 Sparse Pre-trainingYuezhou Hu, Jun Zhu, Jianfei Chen. [doi]
• CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper InfluenceChaochao Chen, Jiaming Zhang, Yizhao Zhang, Li Zhang, Lingjuan Lyu, Yuyuan Li, Biao Gong, Chenggang Yan. [doi]
• Adversarial Moment-Matching Distillation of Large Language ModelsChen Jia. [doi]
• How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE TransformersXin Lu, Yanyan Zhao, Bing Qin 0001, Liangyu Huo, Qing Yang 0033, Dongliang Xu. [doi]
• Quantum Deep Equilibrium ModelsPhilipp Schleich, Marta Skreta, Lasse Bjørn Kristensen, Rodrigo A. Vargas-Hernández, Alán Aspuru-Guzik. [doi]
• Tackling Uncertain Correspondences for Multi-Modal Entity AlignmentLiyi Chen, Ying Sun, Shengzhe Zhang, Yuyang Ye, Wei Wu, Hui Xiong 0001. [doi]
• AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process FeedbackJian Guan 0002, Wei Wu 0014, Zujie Wen, Peng Xu, Hongning Wang, Minlie Huang. [doi]
• A Concept-Based Explainability Framework for Large Multimodal ModelsJayneel Parekh, Pegah Khayatan, Mustafa Shukor, Alasdair Newson, Matthieu Cord. [doi]
• Pure Message Passing Can Estimate Common Neighbor for Link PredictionKaiwen Dong, Zhichun Guo, Nitesh V. Chawla. [doi]
• Beyond Accuracy: Tracking more like Human via Visual SearchDailing Zhang, Shiyu Hu, Xiaokun Feng, Xuchen Li, Meiqi Wu, Jing Zhang, Kaiqi Huang. [doi]
• Pretrained Optimization Model for Zero-Shot Black Box OptimizationXiaobin Li, Kai Wu 0003, Yujian Betterest Li, Xiaoyu Zhang 0010, Handing Wang, Jing Liu 0006. [doi]
• Rad-NeRF: Ray-decoupled Training of Neural Radiance FieldLidong Guo, Xuefei Ning, Yonggan Fu, Tianchen Zhao, Zhuoliang Kang, Jincheng Yu, Yingyan (Celine) Lin, Yu Wang 0002. [doi]
• ReGS: Reference-based Controllable Scene Stylization with Gaussian SplattingYiqun Mei, Jiacong Xu, Vishal M. Patel. [doi]
• Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse TrainingPihe Hu, Shaolong Li, Zhuoran Li, Ling Pan, Longbo Huang. [doi]
• Conformalized Time Series with Semantic FeaturesBaiting Chen, Zhimei Ren, Lu Cheng. [doi]
• ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasetsYiqi Jiang, Hakki O. Akengin, Ji Zhou, Mehmet Aslihak, Yang Li, Radoslaw Chrapkiewicz, Oscar Hernandez, Sadegh Ebrahimi, Omar Jaidar, Yanping Zhang, Hakan Inan, Christopher Miranda, Fatih Dinc, Marta Blanco-Pozo, Mark J. Schnitzer. [doi]
• Swift Sampler: Efficient Learning of Sampler by 10 ParametersJiawei Yao, Chuming Li, Canran Xiao. [doi]
• Graph neural networks and non-commuting operatorsMauricio Velasco, Kaiying O'Hare, Bernardo Rychtenberg, Soledad Villar. [doi]
• MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze PredictionAnshul Gupta, Samy Tafasca, Arya Farkhondeh, Pierre Vuillecard, Jean-Marc Odobez. [doi]
• Advancing Video Anomaly Detection: A Concise Review and a New DatasetLiyun Zhu, Lei Wang, Arjun Raj, Tom Gedeon, Chen Chen. [doi]
• HelpSteer 2: Open-source dataset for training top-performing reward modelsZhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy Zhang, Makesh Narsimhan Sreedhar, Oleksii Kuchaiev. [doi]
• A Huber Loss Minimization Approach to Mean Estimation under User-level Differential PrivacyPuning Zhao, Lifeng Lai, Li Shen, Qingming Li, Jiafei Wu, Zhe Liu. [doi]
• Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural DynamicsYenho Chen, Noga Mudrik, Kyle A. Johnsen, Sankaraleengam Alagapan, Adam S. Charles, Christopher Rozell. [doi]
• A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse TrainingJie Ji, Gen Li 0012, Jingjing Fu, Fatemeh Afghah, Linke Guo, Xiaoyong Yuan, Xiaolong Ma. [doi]
• Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust OptimizationSeyed Amir Saberi, Amir Najafi 0001, Amin Behjati, Ala Emrani, Yasaman Zolfimoselo, Mahdi Shadrooy, Abolfazl S. Motahari, Babak H. Khalaj. [doi]
• Active, anytime-valid risk controlling prediction setsZiyu Xu, Nikos Karampatziakis, Paul Mineiro. [doi]
• Invariant subspaces and PCA in nearly matrix multiplication timeAleksandros Sobczyk, Marko Mladenovic, Mathieu Luisier. [doi]
• Discovering Preference Optimization Algorithms with and for Large Language ModelsChris Lu 0001, Samuel Holt, Claudio Fanconi, Alex J. Chan, Jakob N. Foerster, Mihaela van der Schaar, Robert T. Lange. [doi]
• Conformalized Multiple Testing after Data-dependent SelectionXiaoning Wang, Yuyang Huo, Liuhua Peng, Changliang Zou. [doi]
• Identifying General Mechanism Shifts in Linear Causal RepresentationsTianyu Chen, Kevin Bello, Francesco Locatello, Bryon Aragam, Pradeep Ravikumar. [doi]
• Scalable Bayesian Optimization via Focalized Sparse Gaussian ProcessesYunyue Wei, Vincent Zhuang, Saraswati Soedarmadji, Yanan Sui. [doi]
• Beyond Slow Signs in High-fidelity Model ExtractionHanna Foerster, Robert D. Mullins, Ilia Shumailov, Jamie Hayes. [doi]
• CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision MakingZibin Dong, Yifu Yuan, Jianye Hao, Fei Ni 0001, Yi Ma 0005, Pengyi Li, Yan Zheng 0002. [doi]
• cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific PapersAnirudh Sundar, Jin Xu, William Gay, Christopher Richardson, Larry Heck. [doi]
• DiffSF: Diffusion Models for Scene Flow EstimationYushan Zhang, Bastian Wandt, Maria Magnusson, Michael Felsberg. [doi]
• Provable Benefits of Complex Parameterizations for Structured State Space ModelsYuval Ran-Milo, Eden Lumbroso, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen. [doi]
• Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and PropagationNayeon Kim, Hongje Seong, Daehyun Ji, Sujin Jang. [doi]
• Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative ModelingsMilad Khademi Nori, Il-Min Kim 0001. [doi]
• Geometric Analysis of Nonlinear Manifold ClusteringNimita Shinde, Tianjiao Ding, Daniel P. Robinson, René Vidal. [doi]
• Reinforcement Learning Policy as Macro Regulator Rather than Macro PlacerKe Xue 0001, Ruo-Tong Chen, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan Xu, Chao Qian 0001. [doi]
• FuseMoE: Mixture-of-Experts Transformers for Fleximodal FusionXing Han, Huy Nguyen, Carl Harris, Nhat Ho, Suchi Saria. [doi]
• $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label NoiseJialiang Wang, Xiong Zhou, Deming Zhai, Junjun Jiang, Xiangyang Ji, Xianming Liu. [doi]
• Empowering Visible-Infrared Person Re-Identification with Large Foundation ModelsZhangyi Hu, Bin Yang 0026, Mang Ye. [doi]
• Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily FusingChu Zhou, Yixing Liu, Chao Xu, Boxin Shi. [doi]
• Symmetries in Overparametrized Neural Networks: A Mean Field ViewJavier Maass Martínez, Joaquín Fontbona. [doi]
• Hydra: Bidirectional State Space Models Through Generalized Matrix MixersSukjun Hwang, Aakash Sunil Lahoti, Ratish Puduppully, Tri Dao, Albert Gu. [doi]
• Improving self-training under distribution shifts via anchored confidence with theoretical guaranteesTaejong Joo, Diego Klabjan. [doi]
• Non-asymptotic Analysis of Biased Adaptive Stochastic ApproximationSobihan Surendran, Adeline Fermanian, Antoine Godichon-Baggioni, Sylvain Le Corff. [doi]
• Instance-adaptive Zero-shot Chain-of-Thought PromptingXiaosong Yuan, Chen Shen 0003, Shaotian Yan, Xiaofeng Zhang, Liang Xie, Wenxiao Wang 0001, Renchu Guan, Ying Wang, Jieping Ye. [doi]
• Low-Rank Optimal Transport through Factor Relaxation with Latent CouplingPeter Halmos, Xinhao Liu 0009, Julian Gold, Benjamin J. Raphael. [doi]
• Truth is Universal: Robust Detection of Lies in LLMsLennart Bürger, Fred A. Hamprecht, Boaz Nadler. [doi]
• E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion DetectionJiaqing Zhang, Mingxiang Cao, Weiying Xie, Jie Lei 0001, Daixun Li, Wenbo Huang, Yunsong Li, Xue Yang. [doi]
• Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion PredictionZhenyu Lou, Qiongjie Cui, Tuo Wang, Zhenbo Song, Luoming Zhang, Cheng Cheng, Haofan Wang, Xu Tang, Huaxia Li, Hong Zhou. [doi]
• $C^2M^3$: Cycle-Consistent Multi-Model MergingDonato Crisostomi, Marco Fumero, Daniele Baieri, Florian Bernard, Emanuele Rodolà. [doi]
• Self-Calibrating Conformal PredictionLars van der Laan, Ahmed M. Alaa. [doi]
• Convergence of No-Swap-Regret Dynamics in Self-PlayRenato Paes Leme, Georgios Piliouras, Jon Schneider. [doi]
• Validating Climate Models with Spherical Convolutional Wasserstein DistanceRobert C. Garrett, Trevor Harris, Zhuo Wang, Bo Li. [doi]
• Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot LearningYixiong Zou, Ran Ma, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling DatasetsZuxin Liu, Thai-Hoang, Jianguo Zhang, Ming Zhu, Tian Lan, Shirley Kokane, Juntao Tan, Weiran Yao, Zhiwei Liu 0001, Yihao Feng, Rithesh R. N., Liangwei Yang, Silvio Savarese, Juan Carlos Niebles, Huan Wang 0016, Shelby Heinecke, Caiming Xiong. [doi]
• BendVLM: Test-Time Debiasing of Vision-Language EmbeddingsWalter Gerych, Haoran Zhang 0003, Kimia Hamidieh, Eileen Pan, Maanas K. Sharma, Tom Hartvigsen, Marzyeh Ghassemi. [doi]
• An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessXiaochuan Gong, Jie Hao, Mingrui Liu. [doi]
• Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?Garud Iyengar, Henry Lam, Tianyu Wang. [doi]
• End-to-End Ontology Learning with Large Language ModelsAndy Lo, Albert Q. Jiang, Wenda Li, Mateja Jamnik. [doi]
• On the Efficiency of ERM in Feature LearningAyoub El Hanchi, Chris J. Maddison, Murat A. Erdogdu. [doi]
• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive NegotiationSahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz. [doi]
• Graph-based Uncertainty Metrics for Long-form Language Model GenerationsMingjian Jiang, Yangjun Ruan, Prasanna Sattigeri, Salim Roukos, Tatsunori B. Hashimoto. [doi]
• Transferable Adversarial Attacks on SAM and Its Downstream ModelsSong Xia, Wenhan Yang, Yi Yu 0011, Xun Lin, Henghui Ding, Lingyu Duan, Xudong Jiang 0001. [doi]
• VISA: Variational Inference with Sequential Sample-Average ApproximationsHeiko Zimmermann, Christian Andersson Naesseth, Jan-Willem van de Meent. [doi]
• Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization ExperimentsYanping Li, Jingshen Wang, Waverly Wei. [doi]
• Artificial Generational Intelligence: Cultural Accumulation in Reinforcement LearningJonathan Cook 0004, Chris Lu 0001, Edward Hughes 0001, Joel Z. Leibo, Jakob Foerster. [doi]
• Generalized Protein Pocket Generation with Prior-Informed Flow MatchingZaixi Zhang, Marinka Zitnik, Qi Liu 0003. [doi]
• DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset CurationYuang Ai, Xiaoqiang Zhou, Huaibo Huang, Xiaotian Han, Zhengyu Chen, Quanzeng You, Hongxia Yang. [doi]
• ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose EstimationCédric Rommel, Victor Letzelter, Nermin Samet, Renaud Marlet, Matthieu Cord, Patrick Pérez, Eduardo Valle. [doi]
• CLIP in Mirror: Disentangling text from visual images through reflectionTiancheng Wang, Yuguang Yang 0007, Linlin Yang, Shaohui Lin, Juan Zhang, Guodong Guo, Baochang Zhang 0001. [doi]
• Code Repair with LLMs gives an Exploration-Exploitation TradeoffHao Tang, Keya Hu, Jin Zhou, Sicheng Zhong, Wei-Long Zheng, Xujie Si, Kevin Ellis. [doi]
• Learning Better Representations From Less Data For Propositional SatisfiabilityMohamed Ghanem, Frederik Schmitt, Julian Siber, Bernd Finkbeiner. [doi]
• ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate PredictionJuan Nathaniel, Yongquan Qu, Tung Nguyen, Sungduk Yu, Julius Busecke, Aditya Grover, Pierre Gentine. [doi]
• Bridge the Modality and Capability Gaps in Vision-Language Model SelectionChao Yi, Yuhang He, De-Chuan Zhan, Han-Jia Ye. [doi]
• DeepITE: Designing Variational Graph Autoencoders for Intervention Target EstimationHongyuan Tao, Hang Yu, Jianguo Li. [doi]
• Randomized Truthful Auctions with Learning AgentsGagan Aggarwal, Anupam Gupta 0001, Andrés Perlroth, Grigoris Velegkas. [doi]
• Bayes-optimal learning of an extensive-width neural network from quadratically many samplesAntoine Maillard, Emanuele Troiani, Simon Martin 0008, Florent Krzakala, Lenka Zdeborová. [doi]
• SpaceByte: Towards Deleting Tokenization from Large Language ModelingKevin Slagle. [doi]
• Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss LandscapesXiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho. [doi]
• Interventionally Consistent Surrogates for Complex Simulation ModelsJoel Dyer, Nicholas Bishop, Yorgos Felekis, Fabio Massimo Zennaro, Anisoara Calinescu, Theodoros Damoulas, Michael J. Wooldridge. [doi]
• StreamBench: Towards Benchmarking Continuous Improvement of Language AgentsCheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee. [doi]
• Efficient Reinforcement Learning by Discovering Neural PathwaysSamin Yeasar Arnob, Riyasat Ohib, Sergey M. Plis, Amy Zhang 0001, Alessandro Sordoni, Doina Precup. [doi]
• Classification Done Right for Vision-Language Pre-TrainingZilong Huang, Qinghao Ye, Bingyi Kang, Jiashi Feng, Haoqi Fan 0001. [doi]
• NaturalBench: Evaluating Vision-Language Models on Natural Adversarial SamplesBaiqi Li, Zhiqiu Lin, Wenxuan Peng, Jean de Dieu Nyandwi, Daniel Jiang, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan. [doi]
• MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-TrainingBo Chen 0026, Zhilei Bei, Xingyi Cheng, Pan Li, Jie Tang 0001, Le Song. [doi]
• Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMsZhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao 0001, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei W. Koh, Bryan Hooi. [doi]
• Inferring stochastic low-rank recurrent neural networks from neural dataMatthijs Pals, A Erdem Sagtekin, Felix Pei, Manuel Glöckler, Jakob H. Macke. [doi]
• A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class ClassifiersXin Zou, Zhengyu Zhou, Jingyuan Xu, Weiwei Liu. [doi]
• Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training DataJohannes Treutlein, Dami Choi, Jan Betley, Samuel Marks, Cem Anil, Roger B. Grosse, Owain Evans. [doi]
• Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement LearningShuGuang Yu, Shuxing Fang, Ruixin Peng, Zhengling Qi, Fan Zhou, Chengchun Shi. [doi]
• Efficient Streaming Algorithms for Graphlet SamplingYann Bourreau, Marco Bressan 0002, T.-H. Hubert Chan, Qipeng Kuang, Mauro Sozio. [doi]
• Diffeomorphic interpolation for efficient persistence-based topological optimizationMathieu Carrière, Marc Theveneau, Théo Lacombe. [doi]
• Zero-shot Generalizable Incremental Learning for Vision-Language Object DetectionJieren Deng, Haojian Zhang, Kun Ding, Jianhua Hu, Xingxuan Zhang, Yunkuan Wang. [doi]
• Ultrafast classical phylogenetic method beats large protein language models on variant effect predictionSebastian Prillo, Wilson Wu, Yun Song. [doi]
• Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz ConstraintsJay Bear, Adam Prügel-Bennett, Jonathon Hare. [doi]
• Discovering Sparsity Allocation for Layer-wise Pruning of Large Language ModelsLujun Li, Peijie Dong, Zhenheng Tang, Xiang Liu, Qiang Wang, Wenhan Luo, Wei Xue, Qifeng Liu, Xiaowen Chu, Yike Guo. [doi]
• Towards a Scalable Reference-Free Evaluation of Generative ModelsAzim Ospanov, Jingwei Zhang, Mohammad Jalali, Xuenan Cao, Andrej Bogdanov, Farzan Farnia. [doi]
• Analytically deriving Partial Information Decomposition for affine systems of stable and convolution-closed distributionsChaitanya Goswami, Amanda Merkley. [doi]
• DisCEdit: Model Editing by Identifying Discriminative ComponentsChaitanya Murti, Chiranjib Bhattacharyya. [doi]
• Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource AllocationDu Chen, Geoffrey A. Chua. [doi]
• Scalable Early Childhood Reading Performance PredictionZhongkai Shangguan, Zanming Huang, Eshed Ohn-Bar, Ola Ozernov-Palchik, Derek Kosty, Michael Stoolmiller, Hank Fien. [doi]
• Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online AdaptationHaoqi Yuan, Yuhui Fu 0005, Feiyang Xie, Zongqing Lu. [doi]
• Boosting Weakly Supervised Referring Image Segmentation via Progressive ComprehensionZaiquan Yang, Yuhao Liu 0001, Jiaying Lin, Gerhard P. Hancke 0002, Rynson W. H. Lau. [doi]
• FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel ExtractionFeijie Wu, XingChen Wang, Yaqing Wang, Tianci Liu 0003, Lu Su 0001, Jing Gao 0004. [doi]
• Learning to Assist Humans without Inferring RewardsVivek Myers, Evan Ellis, Sergey Levine, Benjamin Eysenbach, Anca D. Dragan. [doi]
• CycleNet: Enhancing Time Series Forecasting through Modeling Periodic PatternsShengsheng Lin, Weiwei Lin 0001, Xinyi Hu, Wentai Wu, Ruichao Mo, Haocheng Zhong. [doi]
• Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantificationJannik Franzen, Claudia Winklmayr, Vanessa Emanuela Guarino, Christoph Karg, Xiaoyan Yu, Nora Koreuber, Jan Philipp Albrecht, Philip Bischoff, Dagmar Kainmueller. [doi]
• Improved Sample Complexity for Multiclass PAC LearningSteve Hanneke, Shay Moran, Qian Zhang. [doi]
• Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language ModelsSadegh Mahdavi, Raquel Aoki, Keyi Tang, Yanshuai Cao. [doi]
• HairDiffusion: Vivid Multi-Colored Hair Editing via Latent DiffusionYu Zeng, Yang Zhang 0012, Jiachen Liu, LinLin Shen, Kaijun Deng, Weizhao He, Jinbao Wang. [doi]
• Revisiting motion information for RGB-Event tracking with MOT philosophyTianlu Zhang, Kurt Debattista, Qiang Zhang 0020, Guiguang Ding, Jungong Han. [doi]
• Enhancing Feature Diversity Boosts Channel-Adaptive Vision TransformersChau Pham, Bryan A. Plummer. [doi]
• Piecewise deterministic generative modelsAndrea Bertazzi, Dario Shariatian, Umut Simsekli, Eric Moulines, Alain Durmus. [doi]
• The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion ModelsSaravanan Kandasamy 0002, Dheeraj Nagaraj. [doi]
• RedPajama: an Open Dataset for Training Large Language ModelsMaurice Weber, Daniel Y. Fu, Quentin Anthony, Yonatan Oren, Shane Adams, Anton Alexandrov, Xiaozhong Lyu, Huu Nguyen, Xiaozhe Yao, Virginia Adams, Ben Athiwaratkun, Rahul Chalamala, Kezhen Chen, Max Ryabinin, Tri Dao, Percy Liang, Christopher Ré, Irina Rish, Ce Zhang 0001. [doi]
• Efficient Adversarial Training in LLMs with Continuous AttacksSophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn. [doi]
• CRAG - Comprehensive RAG BenchmarkXiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze Daniel Gui, Ziran Will Jiang, Ziyu Jiang, Lingkun Kong, Brian Moran, Jiaqi Wang, Yifan Xu, an Yan, Chenyu Yang, Eting Yuan, Hanwen Zha, Nan Tang 0001, Lei Chen 0002, Nicolas Scheffer, Yue Liu, Nirav Shah, Rakesh Wanga, Anuj Kumar, Scott Yih, Xin Dong 0001. [doi]
• TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting ModelsZhen Chen, Yi Zhang, Fu Wang, Xingyu Zhao 0001, Xiaowei Huang 0001, Wenjie Ruan. [doi]
• FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized PreferenceZihan Tan, Guancheng Wan, Wenke Huang, Mang Ye. [doi]
• Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image CodecJun Hyuk Kim, Seungeon Kim, Won-Hee Lee, Dokwan Oh. [doi]
• Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao 0001, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao. [doi]
• MassSpecGym: A benchmark for the discovery and identification of moleculesRoman Bushuiev, Anton Bushuiev, Niek F. de Jonge, Adamo Young, Fleming Kretschmer, Raman Samusevich, Janne Heirman, Fei Wang, Luke Zhang, Kai Dührkop, Marcus Ludwig, Nils A. Haupt, Apurva Kalia, Corinna Brungs, Robin Schmid, Russell Greiner, Bo Wang, David S. Wishart, Liping Liu 0001, Juho Rousu, Wout Bittremieux, Hannes Rost, Tytus D. Mak, Soha Hassoun, Florian Huber, Justin J. J. van der Hooft, Michael A. Stravs, Sebastian Böcker, Josef Sivic, Tomás Pluskal. [doi]
• On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and CapabilityChenyu Zheng, Wei Huang, Rongzhen Wang, Guoqiang Wu, Jun Zhu, Chongxuan Li. [doi]
• AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental LearningMinghao Chen 0001, Yihang Li, Yanting Yang, Shiyu Yu, Binbin Lin, Xiaofei He 0001. [doi]
• A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-LipschitznessYuri Kinoshita, Taro Toyoizumi. [doi]
• ReactZyme: A Benchmark for Enzyme-Reaction PredictionChenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, Shuangjia Zheng. [doi]
• A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion ModelsHamidreza Kamkari, Brendan Leigh Ross, Rasa Hosseinzadeh, Jesse C. Cresswell, Gabriel Loaiza-Ganem. [doi]
• FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node FeaturesJitao Zhao, Di Jin 0001, Meng Ge, Lianze Shan, Xin Wang 0030, Dongxiao He, Zhiyong Feng 0002. [doi]
• Nearly Optimal Approximation of Matrix Functions by the Lanczos MethodNoah Amsel, Tyler Chen, Anne Greenbaum, Cameron Musco, Christopher Musco. [doi]
• Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic SpaceXin Qiu, Risto Miikkulainen. [doi]
• BioTrove: A Large Curated Image Dataset Enabling AI for BiodiversityChih-Hsuan Yang, Benjamin Feuer, Talukder Zaki Jubery, Zi K. Deng, Andre Nakkab, Md. Zahid Hasan, Shivani Chiranjeevi, Kelly O. Marshall, Nirmal Baishnab, Asheesh Kumar Singh, Arti Singh, Soumik Sarkar, Nirav C. Merchant, Chinmay Hegde, Baskar Ganapathysubramanian. [doi]
• Fully Explicit Dynamic Gaussian SplattingJunoh Lee, Changyeon Won, Hyunjun Jung, Inhwan Bae, Hae-Gon Jeon. [doi]
• Entrywise error bounds for low-rank approximations of kernel matricesAlexander Modell. [doi]
• Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample RegimeLasse Vuursteen. [doi]
• ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation SamplingFrancesca Babiloni, Alexandros Lattas, Jiankang deng, Stefanos Zafeiriou. [doi]
• Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression LearningChenyu Yang, Xizhou Zhu, Jinguo Zhu, Weijie Su 0002, Junjie Wang, Xuan Dong, Wenhai Wang, Bin Li 0025, Jie Zhou 0001, Yu Qiao 0001, Jifeng Dai. [doi]
• The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer PerceptionsZheng Wang 0074, Geyong Min, Wenjie Ruan. [doi]
• Transfer Learning for Diffusion ModelsYidong Ouyang, Liyan Xie, Hongyuan Zha, Guang Cheng. [doi]
• Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimensionKedar Karhadkar, Michael Murray, Guido F. Montúfar. [doi]
• You Only Cache Once: Decoder-Decoder Architectures for Language ModelsYutao Sun, Li Dong 0010, Yi Zhu, Shaohan Huang, Wenhui Wang 0003, Shuming Ma, Quanlu Zhang, Jianyong Wang 0001, Furu Wei. [doi]
• Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language ModelsHanxiao Zhang, Lin Ju, Chan Wu, Jinjing Huang, Youshao Xiao, Zhenglei Zhou, Zhiming Fan, Zhaoxin Huan, Siyuan Li, Fanzhuang Meng, Lei Liang, Xiaolu Zhang, Jun Zhou. [doi]
• Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised LearningKeying Kuang, Frances Dean, Jack B. Jedlicki, David Ouyang, Anthony Philippakis, David A. Sontag, Ahmed M. Alaa. [doi]
• AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant DeploymentYonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, Yingyan (Celine) Lin. [doi]
• Continual learning with the neural tangent ensembleAri S. Benjamin, Christian-Gernot Pehle, Kyle Daruwalla. [doi]
• Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent CollaborationJunyang Wang 0001, Haiyang Xu, Haitao Jia, Xi Zhang, Ming Yan, Weizhou Shen, Ji Zhang 0011, Fei Huang 0004, Jitao Sang. [doi]
• Fast Encoder-Based 3D from Casual Videos via Point Track ProcessingYoni Kasten, Wuyue Lu 0004, Haggai Maron. [doi]
• Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model ApproachLei Ding 0013, Yang Hu, Nicole Denier, Enze Shi, Junxi Zhang, Qirui Hu, Karen D. Hughes, Linglong Kong, Bei Jiang. [doi]
• STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge BasesShirley Wu, Shiyu Zhao, Michihiro Yasunaga, Kexin Huang, Kaidi Cao, Qian Huang, Vassilis N. Ioannidis, Karthik Subbian, James Y. Zou, Jure Leskovec. [doi]
• LACIE: Listener-Aware Finetuning for Calibration in Large Language ModelsElias Stengel-Eskin, Peter Hase, Mohit Bansal. [doi]
• Long-range Brain Graph TransformerShuo Yu, Shan Jin, Ming Li, Tabinda Sarwar, Feng Xia 0001. [doi]
• Kernel PCA for Out-of-Distribution DetectionKun Fang 0004, Qinghua Tao, Kexin Lv, Mingzhen He, Xiaolin Huang, Jie Yang 0002. [doi]
• Referring Human Pose and Mask Estimation In the WildBo Miao, Mingtao Feng, Zijie Wu, Mohammed Bennamoun, Yongsheng Gao 0001, Ajmal Mian. [doi]
• DiffGS: Functional Gaussian Splatting DiffusionJunsheng Zhou, Weiqi Zhang, Yu-Shen Liu. [doi]
• Soft Superpixel Neighborhood AttentionKent W. Gauen, Stanley H. Chan. [doi]
• VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot ManipulationYoupeng Wen, Junfan Lin, Yi Zhu 0004, Jianhua Han, Hang Xu 0004, Shen Zhao, Xiaodan Liang. [doi]
• Sample Selection via Contrastive Fragmentation for Noisy Label RegressionChris Dongjoo Kim, Sangwoo Moon 0001, Jihwan Moon 0002, Dongyeon Woo, Gunhee Kim. [doi]
• SimPO: Simple Preference Optimization with a Reference-Free RewardYu Meng 0001, Mengzhou Xia, Danqi Chen 0001. [doi]
• Animate3D: Animating Any 3D Model with Multi-view Video DiffusionYanqin Jiang, Chaohui Yu, Chenjie Cao, Fan Wang 0019, Weiming Hu, Jin Gao. [doi]
• Continual Learning in the Frequency DomainRuiqi Liu, Boyu Diao, Libo Huang, Zijia An, Zhulin An, Yongjun Xu 0001. [doi]
• PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in ProteomicsWassim Gabriel, Omar Shouman, Eva Ayla Schröder, Florian Bößl, Mathias Wilhelm 0001. [doi]
• Learning to Decouple the Lights for 3D Face Texture ModelingTianxin Huang, Zhenyu Zhang 0005, Ying Tai, Gim Hee Lee. [doi]
• Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible SetsTaira Tsuchiya, Shinji Ito. [doi]
• Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample ComplexityQian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee. [doi]
• Symmetry-Informed Governing Equation DiscoveryJianke Yang, Wang Rao, Nima Dehmamy, Robin Walters, Rose Yu. [doi]
• Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner ModelingWeibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Hao Wang, Yin Gu, Zheng Zhang. [doi]
• Targeted Sequential Indirect Experiment DesignElisabeth Ailer, Niclas Dern, Jason S. Hartford, Niki Kilbertus. [doi]
• GrounDiT: Grounding Diffusion Transformers via Noisy Patch TransplantationYuseung Lee, Taehoon Yoon, Minhyuk Sung. [doi]
• Multi-Instance Partial-Label Learning with Margin AdjustmentWei Tang, Yin-Fang Yang, Zhaofei Wang, Weijia Zhang, Min-Ling Zhang. [doi]
• Reconstruction Attacks on Machine Unlearning: Simple Models are VulnerableMartín Bertran, Shuai Tang, Michael Kearns, Jamie H. Morgenstern, Aaron Roth 0001, Steven Z. Wu. [doi]
• Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category DiscoveryHaonan Lin, Wenbin An, Jiahao Wang, Yan Chen, Feng Tian, Mengmeng Wang, QianYing Wang, Guang Dai, Jingdong Wang 0001. [doi]
• Neural Gaffer: Relighting Any Object via DiffusionHaian Jin, Yuan Li, Fujun Luan, Yuanbo Xiangli, Sai Bi, Kai Zhang, Zexiang Xu, Jin Sun 0009, Noah Snavely. [doi]
• Surge Phenomenon in Optimal Learning Rate and Batch Size ScalingShuaipeng Li, Penghao Zhao, Hailin Zhang 0004, Xingwu Sun, Hao Wu, Dian Jiao, Weiyan Wang, Chengjun Liu, Zheng Fang, Jinbao Xue, Yangyu Tao, Bin Cui 0001, Di Wang. [doi]
• Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMsAbhimanyu Hans, John Kirchenbauer, Yuxin Wen, Neel Jain, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, Jonas Geiping, Abhinav Bhatele, Tom Goldstein. [doi]
• Faster Differentially Private Top-k Selection: A Joint Exponential Mechanism with PruningHao Wu, Hanwen Zhang. [doi]
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMsZhongshen Zeng, Yinhong Liu, Yingjia Wan, Jingyao Li, Pengguang Chen, Jianbo Dai, Yuxuan Yao, Rongwu Xu, Zehan Qi, Wanru Zhao, Linling Shen, Jianqiao Lu, Haochen Tan, Yukang Chen, Hao Zhang, Zhan Shi, Bailin Wang, Zhijiang Guo, Jiaya Jia. [doi]
• Stabilized Proximal-Point Methods for Federated OptimizationXiaowen Jiang, Anton Rodomanov, Sebastian U. Stich. [doi]
• Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum S. Anderson, Yaron Singer, Amin Karbasi. [doi]
• MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-LearningBin-Bin Gao. [doi]
• Hierarchical Visual Feature Aggregation for OCR-Free Document UnderstandingJaeyoo Park, Jin-Young Choi, Jeonghyung Park, Bohyung Han. [doi]
• TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-casesThibault Simonetto, Salah Ghamizi, Maxime Cordy. [doi]
• LiT: Unifying LiDAR "Languages" with LiDAR TranslatorYixing Lao, Tao Tang, Xiaoyang Wu 0002, Peng Chen, Kaicheng Yu, Hengshuang Zhao. [doi]
• CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle DetectorsLinye Lyu, Jiawei Zhou, Daojing He, Yu Li 0007. [doi]
• Demystify Mamba in Vision: A Linear Attention PerspectiveDongchen Han, Ziyi Wang, Zhuofan Xia, Yizeng Han, Yifan Pu, Chunjiang Ge, Jun Song, Shiji Song, Bo Zheng, Gao Huang 0001. [doi]
• Learning to Embed Distributions via Maximum Kernel EntropyOleksii Kachaiev, Stefano Recanatesi. [doi]
• Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot LearningHaoyi Zhu, Yating Wang, Di Huang, Weicai Ye, Wanli Ouyang, Tong He 0001. [doi]
• AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-MakingYizhe Huang, Xingbo Wang, Hao Liu, Fanqi Kong, Aoyang Qin, Min Tang 0001, Xiaoxi Wang, Song Chun Zhu, Mingjie Bi, Siyuan Qi, Xue Feng. [doi]
• Nearest Neighbor Speculative Decoding for LLM Generation and AttributionMinghan Li 0002, Xilun Chen 0002, Ari Holtzman, Beidi Chen, Jimmy Lin, Scott Yih, Victoria Lin 0002. [doi]
• Safe Exploitative Play with Untrusted Type BeliefsTongxin Li, Tinashe Handina, Shaolei Ren, Adam Wierman. [doi]
• Higher-Order Causal Message Passing for Experimentation with Complex InterferenceMohsen Bayati, Yuwei Luo, William Overman, Mohamad Sadegh Shirani Faradonbeh, Ruoxuan Xiong. [doi]
• Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random FeaturesBonwoo Lee, Jeongyoun Ahn, Cheolwoo Park. [doi]
• Goal Conditioned Reinforcement Learning for Photo Finishing TuningJiarui Wu, Yujin Wang, Lingen Li, Zhang Fan, Tianfan Xue. [doi]
• Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt TemplatesKaifeng Lyu, Haoyu Zhao, Xinran Gu, Dingli Yu, Anirudh Goyal, Sanjeev Arora. [doi]
• MedCalc-Bench: Evaluating Large Language Models for Medical CalculationsNikhil Khandekar, Qiao Jin 0001, Guangzhi Xiong, Soren Dunn, Serina S. Applebaum, Zain Anwar, Maame Sarfo-Gyamfi, Conrad W. Safranek, Abid A Anwar, Andrew Zhang, Aidan Gilson, Maxwell B. Singer, Amisha D. Dave, Andrew Taylor, Aidong Zhang, Qingyu Chen 0001, Zhiyong Lu. [doi]
• How to Boost Any Loss FunctionRichard Nock, Yishay Mansour. [doi]
• Adversarial Schrödinger Bridge MatchingNikita Gushchin, Daniil Selikhanovych, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin. [doi]
• Beyond Accuracy: Ensuring Correct Predictions With Correct RationalesTang Li 0005, Mengmeng Ma 0002, Xi Peng 0005. [doi]
• AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based PoliciesXixi Hu 0001, Qiang Liu, Xingchao Liu, Bo Liu. [doi]
• BertaQA: How Much Do Language Models Know About Local Culture?Julen Etxaniz, Gorka Azkune, Aitor Soroa, Oier Lopez de Lacalle, Mikel Artetxe. [doi]
• Optimization Algorithm Design via Electric CircuitsStephen Boyd, Tetiana Parshakova, Ernest K. Ryu, Jaewook J. Suh. [doi]
• Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph RetrievalAshwin Ramachandran, Vaibhav Raj, Indradyumna Roy, Soumen Chakrabarti, Abir De. [doi]
• Semidefinite Relaxations of the Gromov-Wasserstein DistanceJunyu Chen, Binh T. Nguyen, Shang Koh, Yong Sheng Soh. [doi]
• Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle GenerationYunlu Chen, Francisco Vicente Carrasco 0001, Christian Häne, Giljoo Nam, Jean Charles Bazin, Fernando De la Torre. [doi]
• Automated Efficient Estimation using Monte Carlo Efficient Influence FunctionsRaj Agrawal, Sam Witty, Andy Zane, Elias Bingham. [doi]
• No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model PerformanceVishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma 0001, Philip Torr 0001, Adel Bibi, Samuel Albanie, Matthias Bethge. [doi]
• Identifying Selections for Unsupervised Subtask DiscoveryYiwen Qiu, Yujia Zheng 0001, Kun Zhang 0001. [doi]
• Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic GuaranteesNegin Musavi, Ziyao Guo, Geir E. Dullerud, Yingying Li. [doi]
• BAKU: An Efficient Transformer for Multi-Task Policy LearningSiddhant Haldar, Zhuoran Peng, Lerrel Pinto. [doi]
• Supra-Laplacian Encoding for Transformer on Dynamic GraphsYannis Karmim, Marc Lafon, Raphaël Fournier-S'niehotta, Nicolas Thome. [doi]
• Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive StepsizesYan Huang 0036, Xiang Li, Yipeng Shen, Niao He, Jinming Xu 0002. [doi]
• Verified Code Transpilation with LLMsSahil Bhatia, Jie Qiu, Niranjan Hasabnis, Sanjit Seshia, Alvin Cheung. [doi]
• Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingJiewen Yang, Yiqun Lin, Bin Pu, Xiaomeng Li. [doi]
• SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluationMisha Khodak, Lester Mackey, Alexandra Chouldechova, Miro Dudík. [doi]
• FastDrag: Manipulate Anything in One StepXuanjia Zhao, Jian Guan 0001, Congyi Fan, Dongli Xu, Youtian Lin, Haiwei Pan, Pengming Feng. [doi]
• Non-asymptotic Convergence of Training Transformers for Next-token PredictionRuiquan Huang, Yingbin Liang, Jing Yang 0002. [doi]
• Long-range Meta-path Search on Large-scale Heterogeneous GraphsChao Li, Zijie Guo, Qiuting He, Kun He 0001. [doi]
• Towards Understanding Evolving Patterns in Sequential DataQiuhao Zeng, Long-Kai Huang, Qi Chen, Charles X. Ling, Boyu Wang 0004. [doi]
• Is Your LiDAR Placement Optimized for 3D Scene Understanding?Ye Li, Lingdong Kong, Hanjiang Hu, Xiaohao Xu, Xiaonan Huang. [doi]
• Oja's Algorithm for Streaming Sparse PCASyamantak Kumar, Purnamrita Sarkar. [doi]
• Adaptable Logical Control for Large Language ModelsHonghua Zhang, Po-Nien Kung, Masahiro Yoshida, Guy Van den Broeck, Nanyun Peng 0001. [doi]
• Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language ModelsChia-Yi Hsu, Yu-Lin Tsai, Chih-Hsun Lin, Pin-Yu Chen, Chia-Mu Yu, Chun-Ying Huang. [doi]
• Grasp as You Say: Language-guided Dexterous Grasp GenerationYi-Lin Wei, Jian-Jian Jiang, Chengyi Xing, Xiantuo Tan, Xiao-Ming Wu 0002, Hao Li 0076, Mark R. Cutkosky, Wei-Shi Zheng 0001. [doi]
• On Causal Discovery in the Presence of Deterministic RelationsLoka Li, Haoyue Dai, Hanin Al Ghothani, Biwei Huang, Jiji Zhang, Shahar Harel, Isaac Bentwich, Guangyi Chen 0002, Kun Zhang 0001. [doi]
• Robust Contrastive Multi-view Clustering against Dual Noisy CorrespondenceRuiming Guo, Mouxing Yang, Yijie Lin 0001, Xi Peng 0001, Peng Hu 0002. [doi]
• Deep Submodular Peripteral NetworksGantavya Bhatt, Arnav Das, Jeff A. Bilmes. [doi]
• Evidence of Learned Look-Ahead in a Chess-Playing Neural NetworkErik Jenner, Shreyas Kapur, Vasil Georgiev, Cameron Allen, Scott Emmons, Stuart J. Russell. [doi]
• Text-Aware Diffusion for Policy LearningCalvin Luo, Mandy He, Zilai Zeng, Chen Sun 0002. [doi]
• FineStyle: Fine-grained Controllable Style Personalization for Text-to-image ModelsGong Zhang 0011, Kihyuk Sohn, Meera Hahn, Humphrey Shi, Irfan Essa. [doi]
• Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual LearningXinrui Wang, Chuanxing Geng, Wenhai Wan, Shao-Yuan Li, Songcan Chen. [doi]
• Robust Sparse Regression with Non-Isotropic DesignsChih-Hung Liu 0001, Gleb Novikov. [doi]
• Generative Fractional Diffusion ModelsGabriel Nobis, Maximilian Springenberg, Marco Aversa, Michael Detzel, Rembert Daems, Roderick Murray-Smith, Shinichi Nakajima, Sebastian Lapuschkin, Stefano Ermon, Tolga Birdal, Manfred Opper, Christoph Knochenhauer, Luis Oala, Wojciech Samek. [doi]
• Block Transformer: Global-to-Local Language Modeling for Fast InferenceNamgyu Ho, Sangmin Bae, Taehyeon Kim 0001, Hyunjik Jo, Yireun Kim, Tal Schuster, Adam Fisch, James Thorne, Se-Young Yun. [doi]
• Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videosPolina Turishcheva, Paul G. Fahey, Michaela Vystrcilová, Laura Hansel, Rachel Froebe, Kayla Ponder, Yongrong Qiu, Konstantin Willeke, Mohammad Bashiri, Ruslan Baikulov, Yu Zhu, Lei Ma 0008, Shan Yu, Tiejun Huang 0001, Bryan Li, Wolf De Wulf, Nina Kudryashova, Matthias H. Hennig, Nathalie Rochefort, Arno Onken, Eric Y. Wang, Zhiwei Ding, Andreas S. Tolias, Fabian H. Sinz, Alexander S. Ecker. [doi]
• Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud SegmentationLili Wei, Congyan Lang, Ziyi Chen, Tao Wang 0011, Yidong Li, Jun Liu 0036. [doi]
• Con4m: Context-aware Consistency Learning Framework for Segmented Time Series ClassificationJunru Chen, Tianyu Cao, Jing Xu, Jiahe Li 0008, Zhilong Chen, Tao Xiao, Yang Yang 0009. [doi]
• Advancing Cross-domain Discriminability in Continual Learning of Vision-Language ModelsYicheng Xu, Yuxin Chen, Jiahao Nie 0002, Yusong Wang, Huiping Zhuang, Manabu Okumura. [doi]
• A Combinatorial Algorithm for the Semi-Discrete Optimal Transport ProblemPankaj K. Agarwal, Sharath Raghvendra, Pouyan Shirzadian, Keegan Yao. [doi]
• Risk-Averse Fine-tuning of Large Language ModelsSapana Chaudhary, Ujwal Dinesha, Dileep Kalathil, Srinivas Shakkottai. [doi]
• Zero-Shot Transfer of Neural ODEsTyler Ingebrand, Adam J. Thorpe, Ufuk Topcu. [doi]
• Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?Yang Dai, Oubo Ma, Longfei Zhang, Xingxing Liang, Shengchao Hu, Mengzhu Wang, Shouling Ji, Jincai Huang 0001, Li Shen 0008. [doi]
• VeLoRA: Memory Efficient Training using Rank-1 Sub-Token ProjectionsRoy Miles, Pradyumna Reddy, Ismail Elezi, Jiankang deng. [doi]
• Separation and Bias of Deep Equilibrium Models on Expressivity and Learning DynamicsZhoutong Wu, Yimu Zhang, Cong Fang 0001, Zhouchen Lin. [doi]
• DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image MattingXiaodi Li, Zongxin Yang, Ruijie Quan, Yi Yang. [doi]
• Mixture of Link Predictors on GraphsLi Ma 0012, Haoyu Han 0001, Juanhui Li, Harry Shomer, Hui Liu 0031, Xiaofeng Gao 0001, Jiliang Tang. [doi]
• Few-Shot Adversarial Prompt Learning on Vision-Language ModelsYiwei Zhou, Xiaobo Xia, Zhiwei Lin, Bo Han 0003, Tongliang Liu. [doi]
• MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked AutoencodersXueying Jiang, Sheng Jin 0002, Xiaoqin Zhang 0002, Ling Shao 0001, Shijian Lu. [doi]
• Hierarchical and Density-based Causal ClusteringKwangho Kim, Jisu Kim, Larry A. Wasserman, Edward H. Kennedy. [doi]
• Generating Origin-Destination Matrices in Neural Spatial Interaction ModelsIoannis Zachos, Mark Girolami, Theodoros Damoulas. [doi]
• Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic GraphsFranziska Heeg, Ingo Scholtes. [doi]
• Functionally Constrained Algorithm Solves Convex Simple Bilevel ProblemHuaqing Zhang, Lesi Chen, Jing Xu, Jingzhao Zhang. [doi]
• Pricing and Competition for Generative AIRafid Mahmood. [doi]
• 4Diffusion: Multi-view Video Diffusion Model for 4D GenerationHaiyu Zhang, Xinyuan Chen, Yaohui Wang, Xihui Liu, Yunhong Wang, Yu Qiao. [doi]
• Selective ExplanationsLucas Monteiro Paes, Dennis Wei, Flávio P. Calmon. [doi]
• Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-ContextKazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu. [doi]
• Protecting Your LLMs with Information BottleneckZichuan Liu, Zefan Wang, Linjie Xu, Jinyu Wang, Lei Song, Tianchun Wang, Chunlin Chen, Wei Cheng 0002, Jiang Bian. [doi]
• TSDS: Data Selection for Task-Specific Model FinetuningZifan Liu, Amin Karbasi, Theodoros Rekatsinas. [doi]
• Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person DetectionHui Wei 0004, Zhixiang Wang, Kewei Zhang, Jiaqi Hou, Yuanwei Liu, Hao Tang 0005, Zheng Wang 0007. [doi]
• Learning to compute Gröbner basesHiroshi Kera, Yuki Ishihara, Yuta Kambe, Tristan Vaccon, Kazuhiro Yokoyama. [doi]
• UniAudio 1.5: Large Language Model-Driven Audio Codec is A Few-Shot Audio Task LearnerDongchao Yang, Haohan Guo, Yuanyuan Wang, Rongjie Huang, Xiang Li, Xu Tan 0003, Xixin Wu, Helen Meng. [doi]
• Train-Attention: Meta-Learning Where to Focus in Continual Knowledge LearningYeongbin Seo, Dongha Lee 0003, Jinyoung Yeo. [doi]
• DISP-LLM: Dimension-Independent Structural Pruning for Large Language ModelsShangqian Gao, Chi-Heng Lin, Ting Hua, Zheng Tang, Yilin Shen, Hongxia Jin, Yen-Chang Hsu. [doi]
• A hierarchical decomposition for explaining ML performance discrepanciesHarvineet Singh, Fan Xia, Adarsh Subbaswamy, Alexej Gossmann, Jean Feng. [doi]
• Emergence of heavy tails in homogenized stochastic gradient descentZhezhe Jiao, Martin Keller-Ressel. [doi]
• A Local Method for Satisfying Interventional Fairness with Partially Known Causal GraphsHaoxuan Li, Yue Liu, Zhi Geng, Kun Zhang. [doi]
• E.T. Bench: Towards Open-Ended Event-Level Video-Language UnderstandingYe Liu, Zongyang Ma, Zhongang Qi, Yang Wu 0001, Ying Shan, Chang Wen Chen. [doi]
• The Space Complexity of Approximating Logistic LossGregory Dexter, Petros Drineas, Rajiv Khanna. [doi]
• LoFiT: Localized Fine-tuning on LLM RepresentationsFangcong Yin, Xi Ye, Greg Durrett. [doi]
• Learning-Augmented Dynamic Submodular MaximizationArpit Agarwal, Eric Balkanski. [doi]
• Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessMingyuan Fan 0003, Xiaodan Li, Cen Chen, Wenmeng Zhou, Yaliang Li. [doi]
• Quasi-Bayes meets VinesDavid Huk, Yuanhe Zhang, Ritabrata Dutta, Mark Steel. [doi]
• GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian SplattingXiufeng Huang, Ruiqi Li, Yiu-ming Cheung, Ka-Chun Cheung, Simon See, Renjie Wan. [doi]
• Adaptive Exploration for Data-Efficient General Value Function EvaluationsArushi Jain, Josiah Hanna, Doina Precup. [doi]
• Decentralized Noncooperative Games with Coupled Decision-Dependent DistributionsWenjing Yan, Xuanyu Cao. [doi]
• APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and CommentsXin Jin, Qianqian Qiao, Yi Lu, Huaye Wang, Heng Huang, Shan Gao, Jianfei Liu, Rui Li. [doi]
• DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric FinetuningYuxuan Duan, Yan Hong 0001, Bo Zhang 0075, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu Zhang 0003, Li Niu 0002, Liqing Zhang 0001. [doi]
• Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content GenerationHongbo Wang, Jie Cao 0002, Jin Liu, Xiaoqiang Zhou, Huaibo Huang, Ran He 0001. [doi]
• A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding OptimizationChieh-Yun Chen, Chiang Tseng, Li-Wu Tsao, Hong-Han Shuai. [doi]
• Advancing Fine-Grained Classification by Structure and Subject Preserving AugmentationEyal Michaeli, Ohad Fried. [doi]
• Binding in hippocampal-entorhinal circuits enables compositionality in cognitive mapsChristopher J. Kymn, Sonia Mazelet, Anthony Thomas, Denis Kleyko, Edward Paxon Frady, Fritz Sommer, Bruno A. Olshausen. [doi]
• Occupancy-based Policy Gradient: Estimation, Convergence, and OptimalityAudrey Huang, Nan Jiang 0008. [doi]
• Non-Euclidean Mixture Model for Social Network EmbeddingRoshni G. Iyer, Yewen Wang, Wei Wang 0010, Yizhou Sun. [doi]
• NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in ProteomicsJingbo Zhou, Shaorong Chen, Jun Xia 0001, Sizhe Liu, Tianze Ling, Wenjie Du, Yue Liu 0008, Jianwei Yin, Stan Z. Li. [doi]
• MARPLE: A Benchmark for Long-Horizon InferenceEmily Jin, Zhuoyi Huang, Jan-Philipp Fränken, Weiyu Liu, Hannah Cha, Erik Brockbank, Sarah Wu, Ruohan Zhang, Jiajun Wu 0001, Tobias Gerstenberg. [doi]
• MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video UnderstandingXinYu Fang, Kangrui Mao, Haodong Duan, Xiangyu Zhao, Yining Li, Dahua Lin, Kai Chen 0026. [doi]
• Implicit Bias of Mirror Flow on Separable DataScott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion. [doi]
• Policy Learning from Tutorial Books via Understanding, Rehearsing and IntrospectingXiong-Hui Chen, Ziyan Wang, Yali Du 0001, Shengyi Jiang, Meng Fang, Yang Yu, Jun Wang 0012. [doi]
• A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal SamplersYe He 0003, Alireza Mousavi Hosseini, Krishnakumar Balasubramanian 0001, Murat A. Erdogdu. [doi]
• Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement LearningQi Wang, Junming Yang, Yunbo Wang, Xin Jin, Wenjun Zeng, Xiaokang Yang. [doi]
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial RegularizerZhihan Liu, Miao Lu, Shenao Zhang, Boyi Liu 0001, Hongyi Guo, Yingxiang Yang, Jose H. Blanchet, Zhaoran Wang 0001. [doi]
• Rethinking Misalignment in Vision-Language Model Adaptation from a Causal PerspectiveYanan Zhang, Jiangmeng Li, Lixiang Liu, Wenwen Qiang. [doi]
• Leveraging Separated World Model for Exploration in Visually Distracted EnvironmentsKaichen Huang, Shenghua Wan, Minghao Shao, Hai-Hang Sun, Le Gan, Shuai Feng, De-Chuan Zhan. [doi]
• MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable ConvergenceIonut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert 0007, Peter Richtárik, Dan Alistarh. [doi]
• FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image ClassificationKexue Fu, Xiaoyuan Luo, Linhao Qu, Shuo Wang, Ying Xiong, Ilias Maglogiannis, Longxiang Gao, Manning Wang. [doi]
• Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion ModelsZiyi Wu, Yulia Rubanova, Rishabh Kabra, Drew A. Hudson, Igor Gilitschenski, Yusuf Aytar, Sjoerd van Steenkiste, Kelsey R. Allen, Thomas Kipf. [doi]
• Semantic Feature Learning for Universal Unsupervised Cross-Domain RetrievalLixu Wang, Xinyu Du, Qi Zhu 0002. [doi]
• Federated Model Heterogeneous Matryoshka Representation LearningLiping Yi, Han Yu 0001, Chao Ren 0006, Gang Wang, Xiaoguang Liu 0001, Xiaoxiao Li. [doi]
• OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree QueriesYuhang Lu, Xinge Zhu, Tai Wang, Yuexin Ma. [doi]
• SS1: Accelerating Inference with Fast and Expressive Sketch Structured TransformAditya Desai, Kimia Saedi, Apoorv Walia, Jihyeong Lee, Keren Zhou 0001, Anshumali Shrivastava. [doi]
• Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment ApproachHanyang Yuan, Jiarong Xu, Renhong Huang, Mingli Song, Chunping Wang 0001, Yang Yang 0009. [doi]
• LLM Dataset Inference: Did you train on my dataset?Pratyush Maini, Hengrui Jia, Nicolas Papernot, Adam Dziedzic. [doi]
• Harnessing small projectors and multiple views for efficient vision pretrainingArna Ghosh, Kumar Krishna Agrawal, Shagun Sodhani, Adam Oberman, Blake A. Richards. [doi]
• Simplified and Generalized Masked Diffusion for Discrete DataJiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, Michalis K. Titsias. [doi]
• Aligning to Thousands of Preferences via System Message GeneralizationSeongyun Lee, Sue Hyun Park, Seungone Kim, Minjoon Seo. [doi]
• Improved Sample Complexity Bounds for Diffusion Model TrainingShivam Gupta 0002, Aditya Parulekar, Eric Price 0001, Zhiyang Xun. [doi]
• Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and BenchmarkingPranav Singh Chib, Pravendra Singh. [doi]
• Learning to Edit Visual Programs with Self-SupervisionR. Kenny Jones, Renhao Zhang, Aditya Ganeshan, Daniel Ritchie. [doi]
• Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier ShiftingMan Zhou. [doi]
• HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation LearningLu Bai 0001, Zhuo Xu, Lixin Cui, Ming Li, Yue Wang 0014, Edwin R. Hancock. [doi]
• Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon TasksZaijing Li, Yuquan Xie, Rui Shao, Gongwei Chen, Dongmei Jiang, Liqiang Nie. [doi]
• Geometric-Averaged Preference Optimization for Soft Preference LabelsHiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu, Yutaka Matsuo, Aleksandra Faust, Heiga Zen, Izzeddin Gur. [doi]
• Adaptive Domain Learning for Cross-domain Image DenoisingZian Qian, Chenyang Qi, Ka Lung Law, Hao Fu, Chenyang Lei, Qifeng Chen. [doi]
• Robust Reinforcement Learning from Corrupted Human FeedbackAlexander Bukharin, Ilgee Hong, Haoming Jiang, Zichong Li, Qingru Zhang, Zixuan Zhang, Tuo Zhao. [doi]
• HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure PriorsPanwang Pan, Zhuo Su 0006, Chenguo Lin, Zhen Fan 0015, Yongjie Zhang, Zeming Li, Tingting Shen, Yadong Mu, Yebin Liu. [doi]
• CemiFace: Center-based Semi-hard Synthetic Face Generation for Face RecognitionZhonglin Sun, Siyang Song, Ioannis Patras, Georgios Tzimiropoulos. [doi]
• A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular DataAndrej Tschalzev, Sascha Marton, Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt. [doi]
• Optimal Batched Best Arm IdentificationTianyuan Jin, Yu Yang 0001, Jing Tang 0004, Xiaokui Xiao, Pan Xu 0002. [doi]
• Evaluating alignment between humans and neural network representations in image-based learning tasksCan Demircan, Tankred Saanum, Leonardo Pettini, Marcel Binz, Blazej M. Baczkowski, Christian F. Doeller, Mona M. Garvert, Eric Schulz. [doi]
• Generating compositional scenes via Text-to-image RGBA Instance GenerationAlessandro Fontanella, Petru-Daniel Tudosiu, Yongxin Yang, Shifeng Zhang, Sarah Parisot. [doi]
• An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive ModelingShenbao Yu, Yinghui Pan, Yifeng Zeng, Prashant Doshi, Guoquan Liu, Kim-Leng Poh, Mingwei Lin. [doi]
• DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor ControlZichen Jeff Cui, Hengkai Pan, Aadhithya Iyer, Siddhant Haldar, Lerrel Pinto. [doi]
• Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function ConstraintsZhenwei Lin, Qi Deng. [doi]
• Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI SystemsLingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei A. Zaharia, James Y. Zou. [doi]
• Evaluating Numerical Reasoning in Text-to-Image ModelsIvana Kajic, Olivia Wiles, Isabela Albuquerque, Matthias Bauer, Su Wang 0001, Jordi Pont-Tuset, Aida Nematzadeh. [doi]
• RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and ManipulationJiaming Liu, Mengzhen Liu, Zhenyu Wang, Pengju An, Xiaoqi Li, Kaichen Zhou, Senqiao Yang, Renrui Zhang, Yandong Guo, Shanghang Zhang. [doi]
• CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive LearningYiping Wang, Yifang Chen 0001, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin G. Jamieson, Simon S. Du. [doi]
• BAN: Detecting Backdoors Activated by Adversarial Neuron NoiseXiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Shujian Yu, Stjepan Picek. [doi]
• OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned ImagesYe Mao, Junpeng Jing, Krystian Mikolajczyk. [doi]
• Learning Representations for Hierarchies with Minimal SupportBenjamin Rozonoyer, Michael Boratko, Dhruvesh Patel, Wenlong Zhao 0001, Shib Sankar Dasgupta, Hung Le, Andrew McCallum. [doi]
• ProtGO: Function-Guided Protein Modeling for Unified Representation LearningBozhen Hu, Cheng Tan 0012, Yongjie Xu, Zhangyang Gao, Jun Xia 0001, Lirong Wu, Stan Z. Li. [doi]
• OT4P: Unlocking Effective Orthogonal Group Path for Permutation RelaxationYaming Guo, Chen Zhu 0003, Hengshu Zhu, Tieru Wu. [doi]
• Multi-Winner ReconfigurationJiehua Chen 0001, Christian Hatschka, Sofia Simola. [doi]
• Accelerated Regularized Learning in Finite N-Person GamesKyriakos Lotidis, Angeliki Giannou, Panayotis Mertikopoulos, Nicholas Bambos. [doi]
• Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport LossPaul Krzakala, Junjie Yang, Rémi Flamary, Florence d'Alché-Buc, Charlotte Laclau, Matthieu Labeau. [doi]
• TPC: Test-time Procrustes Calibration for Diffusion-based Human Image AnimationSunjae Yoon, Gwanhyeong Koo, Younghwan Lee, Chang Dong Yoo. [doi]
• Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based PoliciesYipu Chen, Haotian Xue 0002, Yongxin Chen. [doi]
• Improving Context-Aware Preference Modeling for Language ModelsSilviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni. [doi]
• Using Unity to Help Solve Reinforcement LearningConnor Brennan, Andrew Williams, Omar G. Younis, Vedant Vyas, Daria Yasafova, Irina Rish. [doi]
• Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian SplattingZiyi Yang, Xinyu Gao, Yang-Tian Sun, Yihua Huang 0002, Xiaoyang Lyu, Wen Zhou, Shaohui Jiao, Xiaojuan Qi 0001, Xiaogang Jin 0001. [doi]
• Controlling Multiple Errors Simultaneously with a PAC-Bayes BoundReuben Adams, John Shawe-Taylor, Benjamin Guedj. [doi]
• Proving Theorems RecursivelyHaiming Wang, Huajian Xin, Zhengying Liu, Wenda Li, Yinya Huang, Jianqiao Lu, Zhicheng Yang, Jing Tang 0004, Jian Yin 0001, Zhenguo Li, Xiaodan Liang. [doi]
• Conditional Controllable Image FusionBing Cao 0002, Xingxin Xu, Pengfei Zhu 0001, Qilong Wang 0001, Qinghua Hu. [doi]
• PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic DevicesHanqing Zhu, Wenyan Cong, Guojin Chen, Shupeng Ning, Ray Chen, Jiaqi Gu 0002, David Z. Pan. [doi]
• Fair Online Bilateral TradeFrançois Bachoc, Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni. [doi]
• Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data CoverageHaobo Zhang, Xiyue Peng, Honghao Wei, Xin Liu. [doi]
• MetaAligner: Towards Generalizable Multi-Objective Alignment of Language ModelsKailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang, Tianlin Zhang, Sophia Ananiadou. [doi]
• PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical CompetitionGeorge Tsoukalas, Jasper Lee, John Jennings, Jimmy Xin, Michelle Ding, Michael Jennings, Amitayush Thakur, Swarat Chaudhuri. [doi]
• Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space ModelsAli Behrouz, Michele Santacatterina, Ramin Zabih. [doi]
• Large language model validity via enhanced conformal prediction methodsJohn J. Cherian, Isaac Gibbs, Emmanuel J. Candès. [doi]
• Scalable Neural Network Verification with Branch-and-bound Inferred Cutting PlanesDuo Zhou, Christopher Brix, Grani A. Hanasusanto, Huan Zhang 0001. [doi]
• LLM-based Skill Diffusion for Zero-shot Policy AdaptationWoo Kyung Kim, Youngseok Lee, Jooyoung Kim, Honguk Woo. [doi]
• The surprising efficiency of temporal difference learning for rare event predictionXiaoou Cheng, Jonathan Weare. [doi]
• Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMsChing-An Cheng, Allen Nie, Adith Swaminathan. [doi]
• Doing Experiments and Revising Rules with Natural Language and Probabilistic ReasoningTop Piriyakulkij, Cassidy Langenfeld, Tuan Anh Le 0001, Kevin Ellis. [doi]
• IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear ProgramsXi Gao, Jinxin Xiong, Akang Wang, Qihong Duan, Jiang Xue, Qingjiang Shi. [doi]
• The Selective G-Bispectrum and its Inversion: Applications to G-Invariant NetworksSimon Mataigne, Johan Mathe, Sophia Sanborn, Christopher Hillar, Nina Miolane. [doi]
• GSDF: 3DGS Meets SDF for Improved Neural Rendering and ReconstructionMulin Yu, Tao Lu 0005, Linning Xu, Lihan Jiang, Yuanbo Xiangli, Bo Dai 0002. [doi]
• UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization ProblemsZhi Zheng, Changliang Zhou, Xialiang Tong, Mingxuan Yuan, Zhenkun Wang 0001. [doi]
• CondTSF: One-line Plugin of Dataset Condensation for Time Series ForecastingJianrong Ding, Zhanyu Liu, Guanjie Zheng, Haiming Jin, Linghe Kong. [doi]
• MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure PredictionsLe Zhang, Jiayang Chen, Tao Shen, Yu Li 0006, Siqi Sun. [doi]
• Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization ProblemFivos Kalogiannis, Jingming Yan, Ioannis Panageas. [doi]
• Most Influential Subset Selection: Challenges, Promises, and BeyondYuzheng Hu, Pingbang Hu, Han Zhao 0002, Jiaqi W. Ma. [doi]
• Voila-A: Aligning Vision-Language Models with User's Gaze AttentionKun Yan, Zeyu Wang, Lei Ji 0001, Yuntao Wang 0001, Nan Duan, Shuai Ma 0001. [doi]
• Learning Distinguishable Trajectory Representation with Contrastive LossTianxu Li, Kun Zhu 0001, Juan Li, Yang Zhang. [doi]
• Multi-Chain Graphs of Graphs: A New Approach to Analyzing Blockchain DatasetsBingqiao Luo, Zhen Zhang 0023, Qian Wang, Bingsheng He. [doi]
• Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game ModelsAdam Karvonen, Benjamin Wright, Can Rager, Rico Angell, Jannik Brinkmann, Logan Smith, Claudio Mayrink Verdun, David Bau, Samuel Marks. [doi]
• Make Your LLM Fully Utilize the ContextShengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng 0001, Jian-Guang Lou, Weizhu Chen. [doi]
• Identifying Equivalent Training DynamicsWilliam T. Redman, Juan M. Bello-Rivas, Maria Fonoberova, Ryan Mohr, Yannis G. Kevrekidis, Igor Mezic. [doi]
• DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted AveragingMatteo Pagliardini, Amirkeivan Mohtashami, François Fleuret, Martin Jaggi. [doi]
• No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPOSkander Moalla, Andrea Miele, Daniil Pyatko, Razvan Pascanu, Caglar Gulcehre. [doi]
• Improving Sparse Decomposition of Language Model Activations with Gated Sparse AutoencodersSenthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda. [doi]
• SAMPa: Sharpness-aware Minimization ParallelizedWanyun Xie, Thomas Pethick, Volkan Cevher. [doi]
• From Instance Training to Instruction Learning: Task Adapters Generation from InstructionsHuanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Yanchao Hao, Shengping Liu, Kang Liu, Jun Zhao. [doi]
• Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and LimitsHaya Diwan, Jinrui Gou, Cameron Musco, Christopher Musco, Torsten Suel. [doi]
• Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe SamplingYiran Zhao 0006, Wenyue Zheng, Tianle Cai, Do Xuan Long, Kenji Kawaguchi, Anirudh Goyal, Michael Qizhe Shieh. [doi]
• A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic ModelsShivvrat Arya, Tahrima Rahman, Vibhav Gogate. [doi]
• Tolerant Algorithms for Learning with Arbitrary Covariate ShiftSurbhi Goel, Abhishek Shetty, Konstantinos Stavropoulos, Arsen Vasilyan. [doi]
• CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search FrameworkYiyang Zhao, Yunzhuo Liu, Bo Jiang 0003, Tian Guo 0001. [doi]
• What If the Input is Expanded in OOD Detection?Boxuan Zhang, Jianing Zhu, Zengmao Wang, Tongliang Liu, Bo Du 0001, Bo Han 0003. [doi]
• HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language ModelKhoa Vo 0001, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le. [doi]
• Local and Adaptive Mirror Descents in Extensive-Form GamesCôme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko. [doi]
• WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language ModelsLiwei Jiang, Kavel Rao, Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar 0009, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi 0001, Nouha Dziri. [doi]
• Confidence Regulation Neurons in Language ModelsAlessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda. [doi]
• Grammar-Aligned DecodingKanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick, Nadia Polikarpova, Loris D'Antoni. [doi]
• SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D PriorsChenyang Ma, Kai Lu, Ta Ying Cheng, Niki Trigoni, Andrew Markham. [doi]
• Language Model as Visual ExplainerXingyi Yang, Xinchao Wang. [doi]
• An Information Theoretic Perspective on Conformal PredictionAlvaro H. C. Correia, Fabio Valerio Massoli, Christos Louizos, Arash Behboodi. [doi]
• Color-Oriented Redundancy Reduction in Dataset DistillationBowen Yuan, Zijian Wang 0009, Mahsa Baktashmotlagh, Yadan Luo, Zi Huang. [doi]
• Algorithmic progress in language modelsAnson Ho, Tamay Besiroglu, Ege Erdil, Zifan Carl Guo, David Owen 0001, Robi Rahman, David Atkinson, Neil Thompson, Jaime Sevilla. [doi]
• Reinforcing LLM Agents via Policy Optimization with Action DecompositionMuning Wen, Ziyu Wan, Jun Wang, Weinan Zhang, Ying Wen 0001. [doi]
• FlexCap: Describe Anything in Images in Controllable DetailDebidatta Dwibedi, Vidhi Jain, Jonathan Tompson, Andrew Zisserman, Yusuf Aytar. [doi]
• Video Token Merging for Long Video UnderstandingSeon-Ho Lee, Jue Wang, Zhikang Zhang, David Fan, Xinyu Li. [doi]
• Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial OptimizationYang Li, Jinpei Guo, Runzhong Wang, Hongyuan Zha, Junchi Yan. [doi]
• Foundations of Multivariate Distributional Reinforcement LearningHarley Wiltzer, Jesse Farebrother, Arthur Gretton, Mark Rowland 0001. [doi]
• Off-Policy Selection for Initiating Human-Centric Experimental DesignGe Gao, Xi Yang, Qitong Gao, Song Ju, Miroslav Pajic, Min Chi. [doi]
• Training-Free Open-Ended Object Detection and Segmentation via Attention as PromptsZhiwei Lin, Yongtao Wang, Zhi Tang 0001. [doi]
• Transductive Learning is CompactJulian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng. [doi]
• Watermarking Makes Language Models RadioactiveTom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon. [doi]
• StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video SequencesShangkun Sun, Jiaming Liu, Huaxia Li, Guoqing Liu, Thomas H. Li, Wei Gao 0003. [doi]
• Stronger Than You Think: Benchmarking Weak Supervision on Realistic TasksTianyi Zhang, Linrong Cai, Jeffrey Li, Nicholas Roberts, Neel Guha, Frederic Sala. [doi]
• Scaling Laws and Compute-Optimal Training Beyond Fixed Training DurationsAlexander Hägele, Elie Bakouch, Atli Kosson, Loubna Ben Allal, Leandro von Werra, Martin Jaggi. [doi]
• Learning rigid-body simulators over implicit shapes for large-scale scenes and visionYulia Rubanova, Tatiana Lopez-Guevara, Kelsey R. Allen, Will Whitney, Kimberly L. Stachenfeld, Tobias Pfaff. [doi]
• Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient DifferencesGrigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov. [doi]
• Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View ClusteringSuyuan Liu, Siwei Wang 0001, Ke Liang 0006, Junpu Zhang, Zhibin Dong, Tianrui Liu, En Zhu, Xinwang Liu 0002, Kunlun He. [doi]
• Marrying Causal Representation Learning with Dynamical Systems for ScienceDingling Yao, Caroline Muller, Francesco Locatello. [doi]
• GRANOLA: Adaptive Normalization for Graph Neural NetworksMoshe Eliasof, Beatrice Bevilacqua, Carola-Bibiane Schönlieb, Haggai Maron. [doi]
• Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous controlMichal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski, Piotr Milos, Marek Cygan. [doi]
• Learning from Pattern Completion: Self-supervised Controllable GenerationZhiqiang Chen, Guofan Fan, Jinying Gao, Lei Ma 0008, Bo Lei, Tiejun Huang, Shan Yu. [doi]
• Towards Harmless Rawlsian Fairness Regardless of Demographic PriorXuanqian Wang, Jing Li 0009, Ivor W. Tsang, Yew-Soon Ong. [doi]
• The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine LearningRuben Ohana, Michael McCabe, Lucas Meyer, Rudy Morel, Fruzsina J. Agocs, Miguel Beneitez, Marsha Berger, Blakesley Burkhart, Stuart B. Dalziel, Drummond B. Fielding, Daniel Fortunato, Jared A. Goldberg, Keiya Hirashima, Yan-Fei Jiang, Rich R. Kerswell, Suryanarayana Maddu, Jonah Miller, Payel Mukhopadhyay, Stefan S. Nixon, Jeff Shen, Romain Watteaux, Bruno Régaldo-Saint Blancard, François Rozet, Liam Holden Parker, Miles D. Cranmer, Shirley Ho. [doi]
• S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule SearchGengmo Zhou, Zhen Wang, Feng Yu, Guolin Ke, Zhewei Wei, Zhifeng Gao. [doi]
• WizardArena: Post-training Large Language Models via Simulated Offline Chatbot ArenaHaipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao 0004, Qingwei Lin, Jian-Guang Lou, Shifeng Chen, Yansong Tang, Weizhu Chen. [doi]
• Online Learning of Delayed ChoicesRecep Yusuf Bekci. [doi]
• FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic UnderstandingShuai Yuan, Guancong Lin, Lixian Zhang, Runmin Dong, Jinxiao Zhang, Shuang Chen, Juepeng Zheng, Jie Wang, Haohuan Fu. [doi]
• emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface ElectromyographyViswanath Sivakumar, Jeffrey Seely, Alan Du, Sean R. Bittner, Adam Berenzweig, Anuoluwapo Bolarinwa, Alexandre Gramfort, Michael I. Mandel. [doi]
• Reinforcement Learning with LTL and ω-Regular Objectives via Optimality-Preserving Translation to Average RewardsXuan Bach Le, Dominik Wagner 0001, Leon Witzman, Alexander Rabinovich, Luke Ong. [doi]
• TrackIME: Enhanced Video Point Tracking via Instance Motion EstimationSeong Hyeon Park, Huiwon Jang, Byungwoo Jeon, Sukmin Yun, Paul Hongsuck Seo, Jinwoo Shin. [doi]
• II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language ModelsZiqiang Liu, Feiteng Fang, Xi Feng, Xeron Du, Chenhao Zhang 0005, Noah Wang, Yuelin Bai, Qixuan Zhao, Liyang Fan, Chengguang Gan, Hongquan Lin, Jiaming Li, Yuansheng Ni, Haihong Wu, Yaswanth Narsupalli, Zhigang Zheng, Chengming Li, Xiping Hu 0001, Ruifeng Xu 0001, Xiaojun Chen 0006, Min Yang 0007, Jiaheng Liu, Ruibo Liu, Wenhao Huang, Ge Zhang, Shiwen Ni. [doi]
• Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo CollectionsJiacong Xu, Yiqun Mei, Vishal M. Patel. [doi]
• Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric VideosLuigi Seminara, Giovanni Maria Farinella, Antonino Furnari. [doi]
• SE(3)-bi-equivariant Transformers for Point Cloud AssemblyZiming Wang, Rebecka Jörnsten. [doi]
• Measuring Per-Unit Interpretability at Scale Without HumansRoland S. Zimmermann, David A. Klindt, Wieland Brendel. [doi]
• Parameter Symmetry and Noise Equilibrium of Stochastic Gradient DescentZiyin Liu, Mingze Wang, Hongchao Li, Lei Wu. [doi]
• Typicalness-Aware Learning for Failure DetectionYijun Liu, Jiequan Cui, Zhuotao Tian, Senqiao Yang, Qingdong He, Xiaoling Wang, Jingyong Su. [doi]
• Time-Constrained Robust MDPsAdil Zouitine, David Bertoin, Pierre Clavier, Matthieu Geist, Emmanuel Rachelson. [doi]
• Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile DevicesZhihao Shu, Xiaowei Yu, Zihao Wu 0001, Wenqi Jia 0003, Yinchen Shi, Miao Yin, Tianming Liu 0001, Dajiang Zhu, Wei Niu 0002. [doi]
• Efficient Lifelong Model Evaluation in an Era of Rapid ProgressAmeya Prabhu, Vishaal Udandarao, Philip Torr 0001, Matthias Bethge, Adel Bibi, Samuel Albanie. [doi]
• Resolving Discrepancies in Compute-Optimal Scaling of Language ModelsTomer Porian, Mitchell Wortsman, Jenia Jitsev, Ludwig Schmidt, Yair Carmon. [doi]
• Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement LearningAbdullah Akgül, Manuel Haussmann, Melih Kandemir. [doi]
• Amortizing intractable inference in diffusion models for vision, language, and controlSiddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin. [doi]
• Mixed Dynamics In Linear Networks: Unifying the Lazy and Active RegimesZhenfeng Tu, Santiago Aranguri, Arthur Jacot. [doi]
• A Unified Confidence Sequence for Generalized Linear Models, with Applications to BanditsJunghyun Lee, Se-Young Yun, Kwang-Sung Jun. [doi]
• Constrained Diffusion with Trust SamplingWilliam Huang, Yifeng Jiang 0002, Tom Van Wouwe, C. Karen Liu. [doi]
• Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation ModelSai Wang, Yutian Lin, Yu Wu 0011, Bo Du 0001. [doi]
• Neural Krylov Iteration for Accelerating Linear System SolvingJian Luo, Jie Wang 0005, Hong Wang, Huanshuo Dong, Zijie Geng, Hanzhu Chen, Yufei Kuang. [doi]
• HuRef: HUman-REadable Fingerprint for Large Language ModelsBoyi Zeng, Lizheng Wang, Yuncong Hu, Yi Xu, Chenghu Zhou, Xinbing Wang, Yu Yu, Zhouhan Lin. [doi]
• LLM Evaluators Recognize and Favor Their Own GenerationsArjun Panickssery, Samuel R. Bowman, Shi Feng. [doi]
• Boosted Conformal Prediction IntervalsRan Xie, Rina Barber, Emmanuel J. Candès. [doi]
• HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image GenerationBo Cheng, Yuhang Ma, wuliebucha, Shanyuan Liu, Ao Ma, Xiaoyu Wu, Dawei Leng, Yuhui Yin. [doi]
• Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time SeriesIlan Naiman, Nimrod Berman, Itai Pemper, Idan Arbiv, Gal Fadlon, Omri Azencot. [doi]
• Trans-LoRA: towards data-free Transferable Parameter Efficient FinetuningRunqian Wang, Soumya Ghosh, David D. Cox, Diego Antognini, Aude Oliva, Rogério Feris, Leonid Karlinsky. [doi]
• Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial ClientsYoussef Allouah, Abdellah El Mrini, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot. [doi]
• Binary Search with Distributional PredictionsMichael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley, Aidin Niaparast, Sergei Vassilvitskii. [doi]
• MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language ModelsTessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju. [doi]
• Fully Unconstrained Online LearningAshok Cutkosky, Zakaria Mhammedi. [doi]
• IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & LocalizationXiaochen Ma 0001, Xuekang Zhu, Lei Su, Bo Du, Zhuohang Jiang, Bingkui Tong, Zeyu Lei, Xinyu Yang, Chi-Man Pun, Jiancheng Lv 0001, Jizhe Zhou. [doi]
• Integrating Deep Metric Learning with Coreset for Active Learning in 3D SegmentationArvind Vepa, Zukang Yang, Andrew Choi, Jungseock Joo, Fabien Scalzo, Yizhou Sun. [doi]
• Marginal Causal Flows for Validation and InferenceDaniel de Vassimon Manela, Laura Battaglia, Robin J. Evans. [doi]
• Extending Video Masked Autoencoders to 128 framesNitesh Bharadwaj Gundavarapu, Luke Friedman, Raghav Goyal, Chaitra Hegde, Eirikur Agustsson, Sagar Waghmare, Mikhail Sirotenko, Ming-Hsuan Yang 0001, Tobias Weyand, Boqing Gong, Leonid Sigal. [doi]
• Information-theoretic Generalization Analysis for Expected Calibration ErrorFutoshi Futami, Masahiro Fujisawa. [doi]
• Real-Time Recurrent Learning using Trace Units in Reinforcement LearningEsraa Elelimy, Adam White 0001, Michael Bowling, Martha White. [doi]
• Boosting Alignment for Post-Unlearning Text-to-Image Generative ModelsMyeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker, Jiachen T. Wang, Qinbin Li, Ming Jin 0002, Dawn Song, Ruoxi Jia 0001. [doi]
• Local to Global: Learning Dynamics and Effect of Initialization for TransformersAshok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar, Chanakya Ekbote. [doi]
• Understanding Transformer Reasoning Capabilities via Graph AlgorithmsClayton Sanford, Bahare Fatemi, Ethan Hall, Anton Tsitsulin, Mehran Kazemi, Jonathan Halcrow, Bryan Perozzi, Vahab Mirrokni. [doi]
• Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learningDaniel Kunin, Allan Raventós, Clémentine Dominé, Feng Chen, David A. Klindt, Andrew M. Saxe, Surya Ganguli. [doi]
• Few-Shot Task Learning through Inverse Generative ModelingAviv Netanyahu, Yilun Du, Antonia Bronars, Jyothish Pari, Josh Tenenbaum 0001, Tianmin Shu, Pulkit Agrawal 0001. [doi]
• Finding good policies in average-reward Markov Decision Processes without prior knowledgeAdrienne Tuynman, Rémy Degenne, Emilie Kaufmann. [doi]
• From Biased to Unbiased Dynamics: An Infinitesimal Generator ApproachTimothée Devergne, Vladimir Kostic, Michele Parrinello, Massimiliano Pontil. [doi]
• Gaussian Process Bandits for Top-k RecommendationsMohit Yadav, Cameron Musco, Daniel R. Sheldon. [doi]
• A Generative Model of Symmetry TransformationsJames Urquhart Allingham, Bruno Mlodozeniec, Shreyas Padhy, Javier Antorán, David Krueger 0001, Richard E. Turner, Eric T. Nalisnick, José Miguel Hernández-Lobato. [doi]
• Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion ModelYifan Duan, Jian Zhao, Pengcheng, Junyuan Mao, Hao Wu, Jingyu Xu, Shilong Wang, Caoyuan Ma, Kai Wang, Kun Wang, Xuelong Li. [doi]
• LIVE: Learnable In-Context Vector for Visual Question AnsweringYingzhe Peng, Chenduo Hao, Xinting Hu, Jiawei Peng, Xin Geng 0001, Xu Yang 0021. [doi]
• SIRIUS : Contexual Sparisty with Correction for Efficient LLMsYang Zhou, Zhuoming Chen, Zhaozhuo Xu, Victoria Lin 0002, Beidi Chen. [doi]
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid ModelingWanghan Xu, Fenghua Ling, zhangwenlong, Tao Han 0002, Hao Chen 0045, Wanli Ouyang, Lei Bai 0001. [doi]
• Provable Tempered Overfitting of Minimal Nets and Typical NetsItamar Harel, William Hoza, Gal Vardi, Itay Evron, Nati Srebro, Daniel Soudry. [doi]
• Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection AdaptationShen Yuan, Haotian Liu, Hongteng Xu. [doi]
• Adjust Pearson's $r$ to Measure Arbitrary Monotone DependenceXinbo Ai. [doi]
• BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End LearningJianming Pan, Zeqi Ye, Xiao Yang, Xu Yang, Weiqing Liu, Lewen Wang, Jiang Bian 0002. [doi]
• Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image SynthesisYuxi Ren, Xin Xia, Yanzuo Lu, Jiacheng Zhang, Jie Wu, Pan Xie, Xing Wang, XueFeng Xiao. [doi]
• xRAG: Extreme Context Compression for Retrieval-augmented Generation with One TokenXin Cheng 0002, Xun Wang, Xingxing Zhang 0002, Tao Ge 0001, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao 0001. [doi]
• Theoretical Characterisation of the Gauss Newton Conditioning in Neural NetworksJim Zhao, Sidak Pal Singh, Aurélien Lucchi. [doi]
• On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a SolutionYubo Ye, Maryam Toloubidokhti, Sumeet Vadhavkar, Xiajun Jiang, Huafeng Liu 0003, Linwei Wang. [doi]
• Agent Planning with World Knowledge ModelShuofei Qiao, Runnan Fang, Ningyu Zhang 0001, Yuqi Zhu, Xiang Chen 0016, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen. [doi]
• Precipitation Downscaling with Spatiotemporal Video DiffusionPrakhar Srivastava 0003, Ruihan Yang, Gavin Kerrigan, Gideon Dresdner, Jeremy McGibbon, Christopher S. Bretherton, Stephan Mandt. [doi]
• Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust OptimizationRonak Mehta, Jelena Diakonikolas, Zaïd Harchaoui. [doi]
• Minimizing UCB: a Better Local Search Strategy in Local Bayesian OptimizationZheyi Fan, Wenyu Wang, Szu-Hui Ng, Qingpei Hu. [doi]
• OPUS: Occupancy Prediction Using a Sparse SetJiabao Wang, Zhaojiang Liu, Qiang Meng, Liujiang Yan, Ke Wang, Jie Yang, Wei Liu, Qibin Hou, Ming-Ming Cheng. [doi]
• Ordered Momentum for Asynchronous SGDChang-Wei Shi, Yi-Rui Yang, Wu-Jun Li. [doi]
• Should We Really Edit Language Models? On the Evaluation of Edited Language ModelsQi Li, Xiang Liu, Zhenheng Tang, Peijie Dong, ZeYu Li, Xinglin Pan, Xiaowen Chu. [doi]
• Doubly Mild Generalization for Offline Reinforcement LearningYixiu Mao, Qi Wang, Yun Qu 0002, Yuhang Jiang, Xiangyang Ji. [doi]
• Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion ModelsTuomas Kynkäänniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen. [doi]
• KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model RolloutsJing-Cheng Pang, Si-Hang Yang, Kaiyuan Li, Jiaji Zhang, Xiong-Hui Chen, Nan Tang, Yang Yu 0001. [doi]
• Scaling transformer neural networks for skillful and reliable medium-range weather forecastingTung Nguyen, Rohan Shah, Hritik Bansal, Troy Arcomano, Romit Maulik, Rao Kotamarthi, Ian T. Foster, Sandeep Madireddy, Aditya Grover. [doi]
• The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks TrackEshta Bhardwaj, Harshit Gujral, Siyi Wu, Ciara Zogheib, Tegan Maharaj, Christoph Becker 0001. [doi]
• Differentially Private Reinforcement Learning with Self-PlayDan Qiao 0002, Yu-Xiang Wang 0003. [doi]
• Equivariant spatio-hemispherical networks for diffusion MRI deconvolutionAxel Elaldi, Guido Gerig, Neel Dey. [doi]
• Expectile Regularization for Fast and Accurate Training of Neural Optimal TransportNazar Buzun, Maksim Bobrin, Dmitry V. Dylov. [doi]
• Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic SegmentationQi Bi, Jingjun Yi, Hao Zheng 0008, Haolan Zhan, Yawen Huang, Wei Ji 0011, Yuexiang Li, Yefeng Zheng 0001. [doi]
• Skinned Motion Retargeting with Dense Geometric Interaction PerceptionZijie Ye, Jia-Wei Liu, Jia Jia, Shikun Sun, Mike Zheng Shou. [doi]
• Interpretable Image Classification with Adaptive Prototype-based Vision TransformersChiyu Ma, Jon Donnelly, Wenjun Liu, Soroush Vosoughi, Cynthia Rudin, Chaofan Chen. [doi]
• MG-Net: Learn to Customize QAOA with Circuit Depth AwarenessYang Qian, Xinbiao Wang, Yuxuan Du, Yong Luo 0002, Dacheng Tao. [doi]
• Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID DataXiaohong Chen, Canran Xiao, Yongmei Liu. [doi]
• Yo'LLaVA: Your Personalized Language and Vision AssistantThao Nguyen, Haotian Liu, Yuheng Li, Mu Cai, Utkarsh Ojha, Yong Jae Lee. [doi]
• Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial ImagesZihan Lu, Chenxu Wang, Chunyan Xu, Xiangwei Zheng 0001, Zhen Cui 0001. [doi]
• LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential RecommendationQidong Liu, Xian Wu 0001, Yejing Wang, Zijian Zhang 0009, Feng Tian 0002, Yefeng Zheng 0001, Xiangyu Zhao 0001. [doi]
• LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct LanguagesAndrew M. Bean, Simi Hellsten, Harry Mayne, Jabez Magomere, Ethan Chi, Ryan Chi, Scott Hale, Hannah Rose Kirk. [doi]
• A Full-duplex Speech Dialogue Scheme Based On Large Language ModelPeng Wang, Songshuo Lu, Yaohua Tang, Sijie Yan, Wei Xia, Yuanjun Xiong. [doi]
• Human Expertise in Algorithmic PredictionRohan Alur, Manish Raghavan, Devavrat Shah. [doi]
• Layer-Adaptive State Pruning for Deep State Space ModelsMinseon Gwak, Seongrok Moon, Joohwan Ko, PooGyeon Park. [doi]
• Croissant: A Metadata Format for ML-Ready DatasetsMubashara Akhtar, Omar Benjelloun, Costanza Conforti, Luca Foschini, Joan Giner-Miguelez, Pieter Gijsbers, Sujata S. Goswami, Nitisha Jain, Michalis Karamousadakis, Michael Kuchnik, Satyapriya Krishna, Sylvain Lesage, Quentin Lhoest, Pierre Marcenac, Manil Maskey, Peter Mattson, Luis Oala, Hamidah Oderinwale, Pierre Ruyssen, Tim Santos, Rajat Shinde, Elena Simperl, Arjun Suresh, Goeffry Thomas, Slava Tykhonov, Joaquin Vanschoren, Susheel Varma, Jos van der Velde, Steffen Vogler, Carole-Jean Wu, Luyao Zhang. [doi]
• Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of ExpertsHuy Nguyen, Nhat Ho, Alessandro Rinaldo. [doi]
• Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networksEszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt. [doi]
• RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-FoldAmrith Setlur, Saurabh Garg, Xinyang Geng, Naman Garg, Virginia Smith, Aviral Kumar. [doi]
• PRODuctive bandits: Importance Weighting No MoreJulian Zimmert, Teodor Vanislavov Marinov. [doi]
• Adaptive Preference Scaling for Reinforcement Learning with Human FeedbackIlgee Hong, Zichong Li, Alexander Bukharin, Yixiao Li, Haoming Jiang, Tianbao Yang, Tuo Zhao. [doi]
• Consistency of Neural Causal Partial IdentificationJiyuan Tan, Jose H. Blanchet, Vasilis Syrgkanis. [doi]
• ArkVale: Efficient Generative LLM Inference with Recallable Key-Value EvictionRenze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng 0001, Xiuhong Li, Xuechao Wei, Shengen Yan, Meng Li, Yun Liang 0001. [doi]
• Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement LearningXuehui Yu, Mhairi Dunion, Xin Li, Stefano V. Albrecht. [doi]
• Provably and Practically Efficient Adversarial Imitation Learning with General Function ApproximationTian Xu, Zhilong Zhang, Ruishuo Chen, Yihao Sun, Yang Yu. [doi]
• DOFEN: Deep Oblivious Forest ENsembleKuan-Yu Chen, Ping-Han Chiang, Hsin-Rung Chou, Chih-Sheng Chen, Tien-Hao Chang. [doi]
• Understanding the Role of Equivariance in Self-supervised LearningYifei Wang 0001, Kaiwen Hu, Sharut Gupta, Ziyu Ye, Yisen Wang 0001, Stefanie Jegelka. [doi]
• ContextCite: Attributing Model Generation to ContextBenjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Madry. [doi]
• Dual Critic Reinforcement Learning under Partial ObservabilityJinqiu Li, Enmin Zhao, Tong Wei, Junliang Xing, Shiming Xiang. [doi]
• Unlocking Tokens as Data Points for Generalization Bounds on Larger Language ModelsSanae Lotfi, Yilun Kuang, Marc Finzi, Brandon Amos, Micah Goldblum, Andrew Gordon Wilson. [doi]
• AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality MaskingShiqi Sun, Yantao Lu, Ning Liu, Bo Jiang, Jinchao Chen, Ying Zhang 0060. [doi]
• Dimension-free Private Mean Estimation for Anisotropic DistributionsYuval Dagan, Michael I. Jordan, Xuelin Yang, Lydia Zakynthinou, Nikita Zhivotovskiy. [doi]
• Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMsRudolf Laine, Bilal Chughtai, Jan Betley, Kaivalya Hariharan, Mikita Balesni, Jérémy Scheurer, Marius Hobbhahn, Alexander Meinke, Owain Evans. [doi]
• Cloud Object Detector Adaptation by Integrating Different Source KnowledgeShuaifeng Li, Mao Ye 0001, Lihua Zhou, Nianxin Li, Siying Xiao, Song Tang 0001, Xiatian Zhu. [doi]
• Mechanism design augmented with output adviceGeorge Christodoulou 000, Alkmini Sgouritsa, Ioannis Vlachos. [doi]
• DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text DetectionXiao Yu, Yuang Qi, Kejiang Chen, Guoqiang Chen, Xi Yang, Pengyuan Zhu, Xiuwei Shang, Weiming Zhang, Nenghai Yu. [doi]
• Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal ConsistencyYue Li, Yi Sun, Shida Sun, Juntian Ye, Yueyi Zhang, Feihu Xu, Zhiwei Xiong. [doi]
• Neural Network Reparametrization for Accelerated Optimization in Molecular SimulationsNima Dehmamy, Csaba Both, Jeet Mohapatra, Subhro Das, Tommi Jaakkola. [doi]
• The Many Faces of Optimal Weak-to-Strong LearningMikael Møller Høgsgaard, Kasper Green Larsen, Markus Engelund Mathiasen. [doi]
• Functional Bilevel Optimization for Machine LearningIeva Petrulionyte, Julien Mairal, Michael Arbel. [doi]
• Inverse M-Kernels for Linear Universal Approximators of Non-Negative FunctionsHideaki Kim. [doi]
• RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric SpaceJingdi Chen, Hanhan Zhou, Yongsheng Mei, Carlee Joe-Wong, Gina C. Adam, Nathaniel D. Bastian, Tian Lan 0001. [doi]
• Predicting Ground State Properties: Constant Sample Complexity and Deep Learning AlgorithmsMarc Wanner, Laura Lewis, Chiranjib Bhattacharyya, Devdatt P. Dubhashi, Alexandru Gheorghiu. [doi]
• DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene RenderingJiahao Lu, Jiacheng Deng 0002, Ruijie Zhu 0002, Yanzhe Liang, Wenfei Yang, Xu Zhou, Tianzhu Zhang. [doi]
• Toward Semantic Gaze Target DetectionSamy Tafasca, Anshul Gupta, Victor Bros, Jean-Marc Odobez. [doi]
• Diffusion-Reward Adversarial Imitation LearningChun-Mao Lai, Hsiang-Chun Wang, Ping-Chun Hsieh, Yu-Chiang Frank Wang, Min-Hung Chen, Shao-Hua Sun. [doi]
• Post-Hoc Reversal: Are We Selecting Models Prematurely?Rishabh Ranjan, Saurabh Garg, Mrigank Raman, Carlos Guestrin, Zachary C. Lipton. [doi]
• GarmentLab: A Unified Simulation and Benchmark for Garment ManipulationHaoran Lu, Ruihai Wu, Yitong Li, Sijie Li, Ziyu Zhu, Chuanruo Ning, Yan Zhao 0035, Longzan Luo, Yuanpei Chen, Hao Dong 0003. [doi]
• DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine DomainKun Wang, Zhiqiang Yan, Junkai Fan, Wanlu Zhu, Xiang Li, Jun Li, Jian Yang. [doi]
• Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept SpaceCore Francisco Park, Maya Okawa, Andrew Lee, Ekdeep Singh Lubana, Hidenori Tanaka. [doi]
• 4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBsMinjie Wang, Quan Gan, David Wipf, Zheng Zhang 0001, Christos Faloutsos, Weinan Zhang 0001, Muhan Zhang, Zhenkun Cai, Jiahang Li, Zunyao Mao, Yakun Song, Jianheng Tang, Yanlin Zhang, Guang Yang, Chuan Lei, Xiao Qin, Ning Li 0029, Han Zhang 0057, Yanbo Wang, Zizhao Zhang. [doi]
• Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and BaselineQi Jia 0004, Baoyu Fan, Cong Xu, Lu Liu, Liang Jin, Guoguang Du, Zhenhua Guo 0003, Yaqian Zhao, Xuanjing Huang 0001, RenGang Li. [doi]
• Graph Neural Networks Do Not Always OversmoothBastian Epping, Alexandre René, Moritz Helias, Michael T. Schaub. [doi]
• Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF DatasetsIke Obi, Rohan Pant, Srishti Shekhar Agrawal, Maham Ghazanfar, Aaron Basiletti. [doi]
• Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of ExemplarsZhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low. [doi]
• Effective Rank Analysis and Regularization for Enhanced 3D Gaussian SplattingJunha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, Jin-Hwa Kim. [doi]
• TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language NegativesMaitreya Patel, Abhiram Kusumba, Sheng Cheng, Changhoon Kim, Tejas Gokhale, Chitta Baral, Yezhou Yang. [doi]
• Carrot and Stick: Eliciting Comparison Data and BeyondYiling Chen, Shi Feng, Fang-Yi Yu. [doi]
• Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series ForecastingRunze Yang 0002, Longbing Cao, Jie Yang 0002, Jianxun Li. [doi]
• Online Learning with Sublinear Best-Action QueriesMatteo Russo 0002, Andrea Celli, Riccardo Colini-Baldeschi, Federico Fusco, Daniel Haimovich, Dima Karamshuk, Stefano Leonardi 0001, Niek Tax. [doi]
• EM Distillation for One-step Diffusion ModelsSirui Xie, Zhisheng Xiao, Diederik P. Kingma, Tingbo Hou, Ying Nian Wu, Kevin P. Murphy, Tim Salimans, Ben Poole, RuiQi Gao. [doi]
• Mixture of neural fields for heterogeneous reconstruction in cryo-EMAxel Levy, Rishwanth Raghu, David Shustin, Adele Rui-Yang Peng, Huan Li, Oliver Biggs Clarke, Gordon Wetzstein, Ellen D. Zhong. [doi]
• DAPE: Data-Adaptive Positional Encoding for Length ExtrapolationChuanyang Zheng, Yihang Gao, Han Shi, Minbin Huang, Jingyao Li, Jing Xiong, Xiaozhe Ren, Michael K. Ng 0001, Xin Jiang, Zhenguo Li, Yu Li. [doi]
• Vision Mamba MenderJiacong Hu, Anda Cao, Zunlei Feng, Shengxuming Zhang, Yi Wang, Lingxiang Jia, Mingli Song. [doi]
• Aligning Diffusion Behaviors with Q-functions for Efficient Continuous ControlHuayu Chen, Kaiwen Zheng, Hang Su, Jun Zhu. [doi]
• Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakesWeifeng Liu, Tianyi She, Jiawei Liu, Boheng Li, Dongyu Yao, Ziyou Liang, Run Wang. [doi]
• MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionHaoyang He, Yuhu Bai, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie 0007. [doi]
• GIC: Gaussian-Informed Continuum for Physical Property Identification and SimulationJunhao Cai, Yuji Yang, Weihao Yuan 0001, Yisheng He, Zilong Dong, Liefeng Bo, Hui Cheng, Qifeng Chen. [doi]
• Variational Flow Matching for Graph GenerationFloor Eijkelboom, Grigory Bartosh, Christian Andersson Naesseth, Max Welling, Jan-Willem van de Meent. [doi]
• Quantifying the Gain in Weak-to-Strong GeneralizationMoses Charikar, Chirag Pabbaraju, Kirankumar Shiragur. [doi]
• What Factors Affect Multi-Modal In-Context Learning? An In-Depth ExplorationLibo Qin 0001, Qiguang Chen, Hao Fei 0003, Zhi Chen 0006, Min Li 0007, Wanxiang Che. [doi]
• Efficient Centroid-Linkage ClusteringMohammad Hossein Bateni 0001, Laxman Dhulipala, Willem Fletcher, Kishen N. Gowda, D. Ellis Hershkowitz, Rajesh Jayaram, Jakub Lacki. [doi]
• MambaLRP: Explaining Selective State Space Sequence ModelsFarnoush Rezaei Jafari, Grégoire Montavon, Klaus-Robert Müller, Oliver Eberle. [doi]
• Newton Informed Neural Operator for Solving Nonlinear Partial Differential EquationsWenrui Hao, Xinliang Liu, Yahong Yang. [doi]
• Data Augmentation with Diffusion for Open-Set Semi-Supervised LearningSeonghyun Ban, Heesan Kong, Kee-Eung Kim. [doi]
• WildVision: Evaluating Vision-Language Models in the Wild with Human PreferencesYujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi 0001, Bill Yuchen Lin. [doi]
• Solving Minimum-Cost Reach Avoid using Reinforcement LearningOswin So, Cheng Ge, Chuchu Fan. [doi]
• Monoculture in Matching MarketsKenny Peng, Nikhil Garg 0001. [doi]
• Historical Test-time Prompt Tuning for Vision Foundation ModelsJingyi Zhang 0005, Jiaxing Huang 0001, Xiaoqin Zhang 0002, Ling Shao 0001, Shijian Lu. [doi]
• Breaking the False Sense of Security in Backdoor Defense through Re-Activation AttackMingli Zhu, Siyuan Liang, Baoyuan Wu. [doi]
• Convergence Analysis of Split Federated Learning on Heterogeneous DataPengchao Han, Chao Huang, Geng Tian, Ming Tang, Xin Liu. [doi]
• Rule Based Rewards for Language Model SafetyTong Mu, Alec Helyar, Johannes Heidecke, Joshua Achiam, Andrea Vallone, Ian Kivlichan, Molly Lin, Alex Beutel, John Schulman, Lilian Weng. [doi]
• An In-depth Investigation of Sparse Rate Reduction in Transformer-like ModelsYunzhe Hu, Difan Zou, Dong Xu. [doi]
• A versatile informative diffusion model for single-cell ATAC-seq data generation and analysisLei Huang, Lei Xiong, Na Sun, Zunpeng Liu, Ka Chun Wong, Manolis Kellis. [doi]
• Selective Generation for Controllable Language ModelsMinJae Lee, Kyungmin Kim, Taesoo Kim, Sangdon Park 0001. [doi]
• A Simple Framework for Generalization in Visual RL under Dynamic Scene PerturbationsWonil Song, Hyesong Choi, Kwanghoon Sohn, Dongbo Min. [doi]
• Approximation Rate of the Transformer Architecture for Sequence ModelingHaotian Jiang, Qianxiao Li. [doi]
• Any2Policy: Learning Visuomotor Policy with Any-ModalityYichen Zhu, Zhicai Ou, Feifei Feng, Jian Tang 0008. [doi]
• SF-V: Single Forward Video Generation ModelZhixing Zhang, Yanyu Li, Yushu Wu, Yanwu Xu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Junli Cao, Dimitris N. Metaxas, Sergey Tulyakov, Jian Ren 0005. [doi]
• Causal Effect Identification in a Sub-Population with Latent VariablesAmir Mohammad Abouei, Ehsan Mokhtarian, Negar Kiyavash, Matthias Grossglauser. [doi]
• Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle ActivationsDavid Schneider, Simon Reiß, Marco Kugler, Alexander Jaus, Kunyu Peng, Susanne Sutschet, M. Saquib Sarfraz, Sven Matthiesen, Rainer Stiefelhagen. [doi]
• A Kernel Perspective on Distillation-based Collaborative LearningSejun Park, Kihun Hong, Ganguk Hwang. [doi]
• Non-geodesically-convex optimization in the Wasserstein spaceHoang Phuc Hau Luu, Hanlin Yu, Bernardo Williams, Petrus Mikkola, Marcelo Hartmann, Kai Puolamäki, Arto Klami. [doi]
• Expected Probabilistic HierarchiesMarcel Kollovieh, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann. [doi]
• Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud AnalysisHongyu Sun 0006, Qiuhong Ke, Yongcai Wang, Wang Chen, Kang Yang, Deying Li 0001, Jianfei Cai 0001. [doi]
• Multi-modal Situated Reasoning in 3D ScenesXiongkun Linghu, Jiangyong Huang, Xuesong Niu, Xiaojian (Shawn) Ma, Baoxiong Jia, Siyuan Huang 0001. [doi]
• Self-playing Adversarial Language Game Enhances LLM ReasoningPengyu Cheng, Tianhao Hu, Han Xu, Zhisong Zhang, Yong Dai, Lei Han, Nan Du, Xiaolong Li. [doi]
• Complete Graphical Criterion for Sequential Covariate Adjustment in Causal InferenceYonghan Jung, Min Woo Park, Sanghack Lee. [doi]
• GREATS: Online Selection of High-Quality Data for LLM Training in Every IterationJiachen T. Wang, Tong Wu, Dawn Song, Prateek Mittal, Ruoxi Jia 0001. [doi]
• Compact Language Models via Pruning and Knowledge DistillationSaurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov 0001. [doi]
• UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language ModelsJiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang 0001, Shiguang Shan, Xilin Chen 0001. [doi]
• Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)Michael Saxon, Fatima Jahara, Mahsa Khoshnoodi, Yujie Lu, Aditya Sharma, William Yang Wang. [doi]
• Optimization Can Learn Johnson Lindenstrauss EmbeddingsNikos Tsikouras, Constantine Caramanis, Christos Tzamos. [doi]
• Cal-DPO: Calibrated Direct Preference Optimization for Language Model AlignmentTeng Xiao, Yige Yuan, Huaisheng Zhu, Mingxiao Li, Vasant G. Honavar. [doi]
• Amortized Fourier Neural OperatorsZipeng Xiao, Siqi Kou, Zhongkai Hao, Bokai Lin, Zhijie Deng. [doi]
• Pseudo-Private Data Guided Model Inversion AttacksXiong Peng, Bo Han 0003, Feng Liu 0003, Tongliang Liu, Mingyuan Zhou. [doi]
• Learning from Highly Sparse Spatio-temporal DataLeyan Deng, Chenwang Wu, Defu Lian, Enhong Chen. [doi]
• Aligning Diffusion Models by Optimizing Human UtilityShufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka. [doi]
• HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated LearningMomin Ahmad Khan, Yasra Chandio, Fatima M. Anwar 0001. [doi]
• Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias CorrectingXingyu Zhu, Beier Zhu, Yi Tan 0001, Shuo Wang 0008, Yanbin Hao, Hanwang Zhang. [doi]
• Robust Graph Neural Networks via Unbiased AggregationZhichao Hou, Ruiqi Feng, Tyler Derr, Xiaorui Liu. [doi]
• FreqBlender: Enhancing DeepFake Detection by Blending Frequency KnowledgeHanzhe Li, Jiaran Zhou, Yuezun Li, Baoyuan Wu, Bin Li 0011, Junyu Dong. [doi]
• Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning FrameworkZhongchao Yi, Zhengyang Zhou, Qihe Huang, Yanjiang Chen, Liheng Yu, Xu Wang, Yang Wang 0015. [doi]
• DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise ReductionXinwei Zhang 0001, Zhiqi Bu, Mingyi Hong 0001, Meisam Razaviyayn. [doi]
• UNIT: Unifying Image and Text Recognition in One Vision EncoderYi Zhu 0004, Yanpeng Zhou, Chunwei Wang, Yang Cao, Jianhua Han, Lu Hou, Hang Xu. [doi]
• One-Shot Safety Alignment for Large Language Models via Optimal DualizationXinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding. [doi]
• Efficient LLM Scheduling by Learning to RankYichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang 0108. [doi]
• eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modelingMatthew Dowling, Yuan Zhao 0004, Memming Park. [doi]
• Unveiling Encoder-Free Vision-Language ModelsHaiwen Diao, Yufeng Cui, Xiaotong Li, Yueze Wang, Huchuan Lu, Xinlong Wang. [doi]
• SwitchHead: Accelerating Transformers with Mixture-of-Experts AttentionRóbert Csordás, Piotr Piekos, Kazuki Irie, Jürgen Schmidhuber. [doi]
• Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference HeadsAvelina Asada Hadji-Kyriacou, Ognjen Arandjelovic. [doi]
• VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion ModelsWenhao Wang, Yi Yang. [doi]
• GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned ExpertsShirley Wu, Kaidi Cao, Bruno Ribeiro 0001, James Y. Zou, Jure Leskovec. [doi]
• Neural Model CheckingMirco Giacobbe, Daniel Kroening, Abhinandan Pal, Michael Tautschnig. [doi]
• Listenable Maps for Zero-Shot Audio ClassifiersFrancesco Paissan, Luca Della Libera, Mirco Ravanelli, Cem Subakan. [doi]
• Learning-Augmented Priority QueuesZiyad Benomar, Christian Coester. [doi]
• Robust Mixture Learning when Outliers Overwhelm Small GroupsDaniil Dmitriev, Rares-Darius Buhai, Stefan Tiegel, Alexander Wolters, Gleb Novikov, Amartya Sanyal, David Steurer, Fanny Yang. [doi]
• Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identificationRui Li, Tingting Ren, Jie Wen 0001, Jinxing Li. [doi]
• Full-Distance Evasion of Pedestrian Detectors in the Physical WorldZhi-cheng, Zhanhao Hu, Yuqiu Liu, Jianmin Li 0001, Hang Su, Xiaolin Hu 0001. [doi]
• Generalizablity of Memorization Neural NetworkLijia Yu, Xiao-Shan Gao, Lijun Zhang, Yibo Miao. [doi]
• EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language ModelsJinhee Kim, Taesung Kim, Jaegul Choo. [doi]
• Spiking Graph Neural Network on Riemannian ManifoldsLi Sun 0008, Zhenhao Huang, Qiqi Wan, Hao Peng 0001, Philip S. Yu. [doi]
• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?Ruisheng Cao, Fangyu Lei, Haoyuan Wu, Jixuan Chen, Yeqiao Fu, Hongcheng Gao, Xinzhuang Xiong, Hanchong Zhang, Wenjing Hu, Yuchen Mao, Tianbao Xie, Hongshen Xu, Danyang Zhang, Sida I. Wang, Ruoxi Sun 0002, Pengcheng Yin, Caiming Xiong, Ansong Ni, Qian Liu, Victor Zhong, Lu Chen 0002, Kai Yu, Tao Yu 0009. [doi]
• Optimal Hypothesis Selection in (Almost) Linear TimeMaryam Aliakbarpour, Mark Bun, Adam Smith. [doi]
• EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health RecordsYeonsu Kwon, Jiho Kim, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi. [doi]
• Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world CorruptionsJie Wang, Tingfa Xu, Lihe Ding, Jianan Li 0001. [doi]
• Conditional Synthesis of 3D Molecules with Time Correction SamplerHojung Jung, Youngrok Park, Laura Schmid, Jaehyeong Jo, Dongkyu Lee, Bongsang Kim, Se-Young Yun, Jinwoo Shin. [doi]
• The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine LearningJake Fawkes, Nic Fishman, Mel Andrews, Zachary C. Lipton. [doi]
• Continuous Temporal Domain GeneralizationZekun Cai, Guangji Bai, Renhe Jiang, Xuan Song 0001, Liang Zhao 0002. [doi]
• PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation TechniquesDerui Zhu, Dingfan Chen, Xiongfei Wu, Jiahui Geng, Zhuo Li, Jens Grossklags, Lei Ma 0003. [doi]
• Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal LearningDivyam Madaan, Taro Makino, Sumit Chopra, KyungHyun Cho. [doi]
• Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and ToolboxHaohui Wang, Weijie Guan, Jianpeng Chen, Zi Wang, Dawei Zhou 0003. [doi]
• ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous DrivingTao Ma 0002, Hongbin Zhou, Qiusheng Huang, Xuemeng Yang, Jianfei Guo, Bo Zhang, Min Dou, Yu Qiao 0001, Botian Shi, Hongsheng Li 0001. [doi]
• Collaborative Refining for Learning from Inaccurate LabelsBin Han, Yi-Xuan Sun, Ya-Lin Zhang 0001, Libang Zhang, Haoran Hu, Longfei Li, Jun Zhou 0011, Guo Ye, Huimei He. [doi]
• HYDRA: Model Factorization Framework for Black-Box LLM PersonalizationYuchen Zhuang, Haotian Sun, Yue Yu, Rushi Qiang, Qifan Wang, Chao Zhang, Bo Dai 0001. [doi]
• Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual RecognitionMengke Li 0001, Ye Liu, Yang Lu 0009, Yiqun Zhang 0006, Yiu-ming Cheung, Hui Huang 0004. [doi]
• InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context MemoryChaojun Xiao, Pengle Zhang, Xu Han 0007, Guangxuan Xiao, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Improving robustness to corruptions with multiplicative weight perturbationsTrung Q. Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski. [doi]
• LoTLIP: Improving Language-Image Pre-training for Long Text UnderstandingWei Wu, Kecheng Zheng, Shuailei Ma, Fan Lu, Yuxin Guo, Yifei Zhang, Wei Chen 0001, Qingpei Guo, Yujun Shen, Zheng-Jun Zha. [doi]
• How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation NetworksEtai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang 0001, Joshua M. Susskind. [doi]
• EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object DetectionSheng Wu, Hang-sheng, Hui Feng 0001, Bo Hu 0002. [doi]
• GV-Rep: A Large-Scale Dataset for Genetic Variant Representation LearningZehui Li, Vallijah Subasri, Guy-Bart Stan, Yiren Zhao, Bo Wang. [doi]
• Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language ModelsMengyuan Chen, Junyu Gao 0001, Changsheng Xu. [doi]
• ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based EvaluationJingnan Zheng, Han Wang, An Zhang, Tai D. Nguyen, Jun Sun 0001, Tat-Seng Chua. [doi]
• Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of ViewAnlan Yu, Shusen Jing, Ning Lyu, Wujie Wen, Zhiyuan Yan. [doi]
• Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD PromptsAnna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszar. [doi]
• ChronoEpilogi: Scalable Time Series Selection with Multiple SolutionsEtienne Vareille, Michele Linardi, Ioannis Tsamardinos, Vassilis Christophides. [doi]
• I2EBench: A Comprehensive Benchmark for Instruction-based Image EditingYiwei Ma, Jiayi Ji, Ke Ye, Weihuang Lin, Zhibin Wang, Yonghan Zheng, Qiang Zhou, Xiaoshuai Sun, Rongrong Ji. [doi]
• Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid ViewsXinyue Chen, Yazhou Ren 0001, Jie Xu 0044, Fangfei Lin, Xiaorong Pu, Yang Yang 0002. [doi]
• Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering PerspectiveYujie Mo, Zhihe Lu, Runpeng Yu, Xiaofeng Zhu 0001, Xinchao Wang. [doi]
• Mitigating Object Hallucination via Concentric Causal AttentionYun Xing, Yiheng Li, Ivan Laptev, Shijian Lu. [doi]
• Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph TransformersJinsong Chen 0002, Hanpeng Liu, John E. Hopcroft, Kun He 0001. [doi]
• CIFD: Controlled Information Flow to Enhance Knowledge DistillationYashas Malur Saidutta, Rakshith Sharma Srinivasa, Jaejin Cho, Ching Hua Lee, Chouchang Yang, Yilin Shen, Hongxia Jin. [doi]
• 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and ComposabilityBaohao Liao, Christof Monz. [doi]
• A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencesMiguel González Duque, Richard Michael, Simon Bartels, Yevgen Zainchkovskyy, Søren Hauberg, Wouter Boomsma. [doi]
• BiDM: Pushing the Limit of Quantization for Diffusion ModelsXingyu Zheng, Xianglong Liu 0001, Yichen Bian, Xudong Ma, Yulun Zhang 0001, Jiakai Wang, Jinyang Guo, Haotong Qin. [doi]
• Parallelizing Model-based Reinforcement Learning Over the Sequence LengthZirui Wang, Yue Deng, Junfeng Long, Yin Zhang. [doi]
• What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsXin Wen 0004, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, Xiaojuan Qi 0001. [doi]
• What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic InformationYiting Chen 0003, Junchi Yan. [doi]
• OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring ModelingLinhui Xiao, Xiaoshan Yang, Fang Peng, Yaowei Wang 0001, Changsheng Xu. [doi]
• Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint PredictionBavesh Balaji, Jerrin Bright, Yuhao Chen 0001, Sirisha Rambhatla, John S. Zelek, David A. Clausi. [doi]
• Understanding the Gains from Repeated Self-DistillationDivyansh Pareek, Simon S. Du, Sewoong Oh. [doi]
• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMsSaleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman. [doi]
• Fair Allocation in Dynamic Mechanism DesignAlireza Fallah 0001, Michael I. Jordan, Annie Ulichney. [doi]
• A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample PerspectiveYeonsung Jung, Jaeyun Song, June Yong Yang, Jin-Hwa Kim, Sungyub Kim, Eunho Yang. [doi]
• DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EMYingjun Shen, Haizhao Dai, Qihe Chen, Yan Zeng, Jiakai Zhang, Yuan Pei, Jingyi Yu. [doi]
• BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGOSebastian Dittert, Vincent Moens, Gianni De Fabritiis. [doi]
• Benchmarking the Attribution Quality of Vision ModelsRobin Hesse, Simone Schaub-Meyer, Stefan Roth 0001. [doi]
• Towards Effective Planning Strategies for Dynamic Opinion NetworksBharath Muppasani, Protik Nag, Vignesh Narayanan, Biplav Srivastava, Michael N. Huhns. [doi]
• Conformal Classification with Equalized Coverage for Adaptively Selected GroupsYanfei Zhou, Matteo Sesia. [doi]
• What type of inference is planning?Miguel Lázaro-Gredilla, Li Yang Ku, Kevin P. Murphy, Dileep George. [doi]
• Sketched Lanczos uncertainty score: a low-memory summary of the Fisher informationMarco Miani, Lorenzo Beretta 0001, Søren Hauberg. [doi]
• Learning Complete Protein Representation by Dynamically Coupling of Sequence and StructureBozhen Hu, Cheng Tan 0012, Jun Xia 0001, Yue Liu 0008, Lirong Wu, Jiangbin Zheng, Yongjie Xu, Yufei Huang 0002, Stan Z. Li. [doi]
• Jailbreaking Large Language Models Against Moderation Guardrails via Cipher CharactersHaibo Jin, Andy Zhou, Joe D. Menke, Haohan Wang. [doi]
• MVGamba: Unify 3D Content Generation as State Space Sequence ModelingXuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu 0001, Pan Zhou 0002, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang. [doi]
• CoBo: Collaborative Learning via Bilevel OptimizationDiba Hashemi, Lie He, Martin Jaggi. [doi]
• Bisimulation Metrics are Optimal Transport Distances, and Can be Computed EfficientlySergio Calo, Anders Jonsson 0001, Gergely Neu, Ludovic Schwartz, Javier Segovia Aguas. [doi]
• MUVERA: Multi-Vector Retrieval via Fixed Dimensional EncodingRajesh Jayaram, Laxman Dhulipala, Majid Hadian, Jason Lee, Vahab Mirrokni. [doi]
• Reasons and Solutions for the Decline in Model Performance after EditingXiusheng Huang, Jiaxiang Liu, Yequan Wang, Kang Liu 0001. [doi]
• Induced Model Matching: Restricted Models Help Train Full-Featured ModelsUsama Muneeb, Mesrob I. Ohannessian. [doi]
• Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upsFengyu Gao, Ruiquan Huang, Jing Yang. [doi]
• Learning Group Actions on Latent RepresentationsYinzhu Jin, Aman Shrivastava, Tom Fletcher. [doi]
• On the Expressivity and Sample Complexity of Node-Individualized Graph Neural NetworksPaolo Pellizzoni, Till Hendrik Schulz, Dexiong Chen, Karsten M. Borgwardt. [doi]
• TSGM: A Flexible Framework for Generative Modeling of Synthetic Time SeriesAlexander V. Nikitin, Letizia Iannucci, Samuel Kaski. [doi]
• Identifiable Object-Centric Representation Learning via Probabilistic Slot AttentionAvinash Kori, Francesco Locatello, Ainkaran Santhirasekaram, Francesca Toni, Ben Glocker, Fabio De Sousa Ribeiro. [doi]
• Implicit Optimization Bias of Next-token Prediction in Linear ModelsChristos Thrampoulidis. [doi]
• Replicability in Learning: Geometric Partitions and KKM-Sperner LemmaJason Vander Woude, Peter Dixon 0002, Aduri Pavan, Jamie Radcliffe, N. V. Vinodchandran. [doi]
• Consent in Crisis: The Rapid Decline of the AI Data CommonsShayne Longpre, Robert Mahari, Ariel Lee, Campbell Lund, Hamidah Oderinwale, William Brannon, Nayan Saxena, Naana Obeng-Marnu, Tobin South, Cole-Hunter, Kevin Klyman, Christopher Klamm, Hailey Schoelkopf, Nikhil Singh 0003, Manuel Cherep, Ahmad Anis, An Dinh, Caroline Shamiso Chitongo, Da Yin, Damien Sileo, Deividas Mataciunas, Diganta Misra, Emad A. Alghamdi, Enrico Shippole, Jianguo Zhang 0005, Joanna Materzynska, Kun Qian 0016, Kushagra Tiwary, Lester James V. Miranda, Manan Dey, Minnie Liang, Mohammed Hamdy, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Shrestha Mohanty, Vipul Gupta, Vivek Sharma 0001, Minh Chien Vu, Xuhui Zhou, Yizhi Li, Caiming Xiong, Luis Villa, Stella Biderman, Hanlin Li, Daphne Ippolito, Sara Hooker, Jad Kabbara, Alex Pentland. [doi]
• DarkSAM: Fooling Segment Anything Model to Segment NothingZiqi Zhou 0001, Yufei Song, Minghui Li, Shengshan Hu, Xianlong Wang 0001, Leo Yu Zhang, Dezhong Yao 0001, Hai Jin 0001. [doi]
• Introspective Planning: Aligning Robots' Uncertainty with Inherent Task AmbiguityKaiqu Liang, Zixu Zhang, Jaime F. Fisac. [doi]
• Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without GuidanceKuan Heng Lin, Sicheng Mo, Ben Klingher, Fangzhou Mu, Bolei Zhou. [doi]
• Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution DetectionYing Yang, De Cheng, Chaowei Fang, Yubiao Wang, Changzhe Jiao, Lechao Cheng, Nannan Wang 0001, Xinbo Gao 0001. [doi]
• Breaking the curse of dimensionality in structured density estimationRobert A. Vandermeulen, Wai Ming Tai, Bryon Aragam. [doi]
• DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal PerceptionXiaotong Li, Fan Zhang, Haiwen Diao, Yueze Wang, Xinlong Wang, Lingyu Duan. [doi]
• Dense Connector for MLLMsHuanjin Yao, Wenhao Wu, Taojiannan Yang, Yuxin Song, Mengxi Zhang, Haocheng Feng, Yifan Sun 0003, Zhiheng Li, Wanli Ouyang, Jingdong Wang 0001. [doi]
• Bayesian Domain Adaptation with Gaussian Mixture Domain-IndexingYanfang Ling, Jiyong Li, Lingbo Li, Shangsong Liang. [doi]
• Boosting Graph Pooling with Persistent HomologyChaolong Ying, Xinjian Zhao, Tianshu Yu. [doi]
• Similarity-Navigated Conformal Prediction for Graph Neural NetworksJianqing Song, Jianguo Huang, Wenyu Jiang, Baoming Zhang, Shuangjie Li, Chongjun Wang. [doi]
• SeTAR: Out-of-Distribution Detection with Selective Low-Rank ApproximationYixia Li, Boya Xiong, Guanhua Chen 0001, Yun Chen 0007. [doi]
• Linking In-context Learning in Transformers to Human Episodic MemoryJi-An Li, Corey Y. Zhou, Marcus K. Benna, Marcelo G. Mattar. [doi]
• Antigen-Specific Antibody Design via Direct Energy-based Preference OptimizationXiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng, Liang Wang 0001, Quanquan Gu. [doi]
• Generating Code World Models with Large Language Models Guided by Monte Carlo Tree SearchNicola Dainese, Matteo Merler, Minttu Alakuijala, Pekka Marttinen. [doi]
• Visual Data Diagnosis and Debiasing with Concept GraphsRwiddhi Chakraborty, Yinong Wang, Jialu Gao, Runkai Zheng, Cheng Zhang 0014, Fernando De la Torre. [doi]
• Learning Elastic Costs to Shape Monge DisplacementsMichal Klein, Aram-Alexandre Pooladian, Pierre Ablin, Eugène Ndiaye, Jonathan Niles-Weed, Marco Cuturi. [doi]
• Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural GradientShaoqi Wang, Chunjie Yang, Siwei Lou. [doi]
• Graph Classification via Reference Distribution Learning: Theory and PracticeZixiao Wang, Jicong Fan. [doi]
• Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious PlayQi Ju 0001, Falin Hei, Ting Feng, Dengbing Yi, Zhemei Fang, Yunfeng Luo. [doi]
• ST$_k$: A Scalable Module for Solving Top-k ProblemsHanchen Xia, Weidong Liu 0005, Xiaojun Mao. [doi]
• LG-CAV: Train Any Concept Activation Vector with Language GuidanceQihan Huang, Jie Song, Mengqi Xue, Haofei Zhang, Bingde Hu, Huiqiong Wang, Hao Jiang, Xingen Wang, Mingli Song. [doi]
• Vector Quantization Prompting for Continual LearningLi Jiao, Qiuxia Lai, Yu Li 0007, Qiang Xu 0001. [doi]
• DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume RenderingZhongpai Gao, Benjamin Planche, Meng Zheng 0002, Xiao Chen, Terrence Chen, Ziyan Wu. [doi]
• VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D PerceptionYuzhe Ji, Yijie Chen, Liuqing Yang 0001, Rui Ding, Meng Yang, Xinhu Zheng. [doi]
• Taming the Long Tail in Human Mobility PredictionXiaohang Xu 0002, Renhe Jiang, Chuang Yang, Zipei Fan, Kaoru Sezaki. [doi]
• Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral GamesGabriele Farina, Charilaos Pipis. [doi]
• LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorchXiaoyuan Zhang, Liang Zhao, Yingying Yu, Xi Lin 0001, Yifan Chen 0001, Han Zhao 0002, Qingfu Zhang 0001. [doi]
• Estimating Ego-Body Pose from Doubly Sparse Egocentric Video DataSeunggeun Chi, Pin-Hao Huang, Enna Sachdeva, Hengbo Ma, Karthik Ramani, Kwonjoon Lee. [doi]
• emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose EstimationSasha Salter, Richard Warren, Collin Schlager, Adrian Spurr, Shangchen Han, Rohin Bhasin, Yujun Cai, Peter Walkington, Anuoluwapo Bolarinwa, Robert J. Wang, Nathan Danielson, Josh Merel, Eftychios A. Pnevmatikakis, Jesse Marshall. [doi]
• Low Precision Local Training is Enough for Federated LearningZhiwei Li, YiQiu Li, Binbin Lin, Zhongming Jin, Weizhong Zhang. [doi]
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM AgentsChang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, Junxian He. [doi]
• DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion ModelAbdullah Bin Jasni, Akiko Manada, Kohei Watabe. [doi]
• Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced TabletabilityNina Gubina, Andrei Dmitrenko, Gleb V. Solovev, Lyubov Yamshchikova, Oleg Petrov, Ivan Lebedev, Nikita Serov, Grigorii Kirgizov, Nikolay O. Nikitin, Vladimir Vinogradov. [doi]
• Large Language Models Must Be Taught to Know What They Don't KnowSanyam Kapoor, Nate Gruver, Manley Roberts, Katie Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson. [doi]
• Customizing Language Models with Instance-wise LoRA for Sequential RecommendationXiaoyu Kong, Jiancan Wu, An Zhang 0003, Leheng Sheng, Hui Lin, Xiang Wang, Xiangnan He 0001. [doi]
• Testably Learning Polynomial Threshold FunctionsLucas Slot, Stefan Tiegel, Manuel Wiedmer. [doi]
• Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signalsHui Zheng, Haiteng Wang, Wei-Bang Jiang, Zhongtao Chen, Li He, Pei-Yang Lin, Peng-Hu Wei, Guo-Guang Zhao, Yun-Zhe Liu. [doi]
• Who's asking? User personas and the mechanics of latent misalignmentAsma Ghandeharioun, Ann Yuan, Marius Guerard, Emily Reif, Michael A. Lepori, Lucas Dixon. [doi]
• On the Target-kernel Alignment: a Unified Analysis with Kernel ComplexityChao Wang, Xin He, Yuwen Wang, Junhui Wang. [doi]
• Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD TrainingAnchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli. [doi]
• Multi-Label Open Set RecognitionYibo Wang, Jun-Yi Hang, Min-Ling Zhang. [doi]
• Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep LearningChia-Hsiang Kao, Bharath Hariharan. [doi]
• Generalizable and Animatable Gaussian Head AvatarXuangeng Chu, Tatsuya Harada. [doi]
• Contextual Bilevel Reinforcement Learning for Incentive AlignmentVinzenz Thoma, Barna Pásztor, Andreas Krause 0001, Giorgia Ramponi, Yifan Hu. [doi]
• Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order MethodsFelix Dangel. [doi]
• SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignmentJovin Leong, Koa Di, Benjamin Cham, Shaun Heng. [doi]
• Learning De-Biased Representations for Remote-Sensing ImageryZichen Tian, Zhaozheng Chen, Qianru Sun. [doi]
• WeiPer: OOD Detection using Weight Perturbations of Class ProjectionsMaximilian Granz, Manuel Heurich, Tim Landgraf. [doi]
• IMAGPose: A Unified Conditional Framework for Pose-Guided Person GenerationFei Shen, Jinhui Tang 0001. [doi]
• Perceiving Longer Sequences With Bi-Directional Cross-Attention TransformersMarkus Hiller, Krista A. Ehinger, Tom Drummond. [doi]
• Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement LearningAneesh Muppidi, Zhiyu Zhang, Heng Yang. [doi]
• Supervised Kernel ThinningAlbert Gong, Kyuseong Choi, Raaz Dwivedi. [doi]
• Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep LearningRonglong Fang, Yuesheng Xu. [doi]
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained ModelsYuxin Wen, Leo Marchyok, Sanghyun Hong 0001, Jonas Geiping, Tom Goldstein, Nicholas Carlini. [doi]
• Stochastic Newton Proximal Extragradient MethodRuichen Jiang, Michal Derezinski, Aryan Mokhtari. [doi]
• CARE: a Benchmark Suite for the Classification and Retrieval of EnzymesJason Yang, Ariane Mora, Shengchao Liu, Bruce J. Wittmann, Animashree Anandkumar, Frances H. Arnold, Yisong Yue. [doi]
• Great Minds Think Alike: The Universal Convergence Trend of Input SalienceYipei Wang, Jeffrey Siskind, Xiaoqian Wang. [doi]
• General Detection-based Text Line RecognitionRaphaël Baena, Syrine Kalleli, Mathieu Aubry. [doi]
• Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational LearningRaffaele Paolino, Sohir Maskey, Pascal Welke, Gitta Kutyniok. [doi]
• LLMCBench: Benchmarking Large Language Model Compression for Efficient DeploymentGe Yang, Changyi He, Jinyang Guo, Jianyu Wu, Yifu Ding, Aishan Liu, Haotong Qin, Pengliang Ji, Xianglong Liu 0001. [doi]
• SceneCraft: Layout-Guided 3D Scene GenerationXiuyu Yang, Yunze Man, Junkun Chen, Yu-Xiong Wang. [doi]
• Debiasing Synthetic Data Generated by Deep Generative ModelsAlexander Decruyenaere, Heidelinde Dehaene, Paloma Rabaey, Johan Decruyenaere, Christiaan Polet, Thomas Demeester, Stijn Vansteelandt. [doi]
• Hints-In-Browser: Benchmarking Language Models for Programming Feedback GenerationNachiket Kotalwar, Alkis Gotovos, Adish Singla. [doi]
• DiP-GO: A Diffusion Pruner via Few-step Gradient OptimizationHaowei Zhu, Dehua Tang, Ji Liu, Mingjie Lu, Jintu Zheng, Jinzhang Peng, Dong Li 0025, Yu Wang 0002, Fan Jiang, Lu Tian, Spandan Tiwari, Ashish Sirasao, Jun-Hai Yong, Bin Wang 0034, Emad Barsoum. [doi]
• Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian StructureXiang Li, Yixiang Dai, Qing Qu 0001. [doi]
• UV-free Texture Generation with Denoising and Geodesic Heat DiffusionSimone Foti, Stefanos Zafeiriou, Tolga Birdal. [doi]
• Geodesic Optimization for Predictive Shift Adaptation on EEG dataApolline Mellot, Antoine Collas, Sylvain Chevallier, Alexandre Gramfort, Denis A. Engemann. [doi]
• Improved Analysis for Bandit Learning in Matching MarketsFang Kong 0002, Zilong Wang, Shuai Li 0010. [doi]
• RETR: Multi-View Radar Detection Transformer for Indoor PerceptionRyoma Yataka, Adriano Cardace, Perry Wang 0004, Petros Boufounos, Ryuhei Takahashi. [doi]
• LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single ImageRuikai Cui, Xibin Song, Weixuan Sun, Senbo Wang, Weizhe Liu, Shenzhou Chen, Taizhang Shang, Yang Li 0193, Nick Barnes, Hongdong Li, Pan Ji. [doi]
• A Surprisingly Simple Approach to Generalized Few-Shot Semantic SegmentationTomoya Sakai, Haoxiang Qiu, Takayuki Katsuki, Daiki Kimura, Takayuki Osogami, Tadanobu Inoue. [doi]
• Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation ModelsYeming Wen, Swarat Chaudhuri. [doi]
• Observational Scaling Laws and the Predictability of Langauge Model PerformanceYangjun Ruan, Chris J. Maddison, Tatsunori B. Hashimoto. [doi]
• Efficient Adaptation of Pre-trained Vision Transformer via Householder TransformationWei Dong, Yuan Sun, Yiting Yang, Xing Zhang, Zhijun Lin, Qingsen Yan, Haokui Zhang, Peng Wang, Yang Yang, Hengtao Shen. [doi]
• π-realizable Constrained MDPsTian Tian, Lin Yang 0011, Csaba Szepesvári. [doi]
• State Chrono Representation for Enhancing Generalization in Reinforcement LearningJianda Chen, Wen Zheng Terence Ng, Zichen Chen, Sinno Jialin Pan, Tianwei Zhang 0004. [doi]
• When is Multicalibration Post-Processing Necessary?Dutch Hansen, Siddartha Devic, Preetum Nakkiran, Vatsal Sharan. [doi]
• Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion ModelsGen Li 0005, Yuling Yan. [doi]
• A Recipe for Charge Density PredictionXiang Fu 0005, Andrew S. Rosen, Kyle Bystrom, Rui Wang 0086, Albert Musaelian, Boris Kozinsky, Tess E. Smidt, Tommi S. Jaakkola. [doi]
• Causal Imitation for Markov Decision Processes: a Partial Identification ApproachKangrui Ruan, Junzhe Zhang 0001, Xuan Di, Elias Bareinboim. [doi]
• CALE: Continuous Arcade Learning EnvironmentJesse Farebrother, Pablo Samuel Castro. [doi]
• Linear Regression using Heterogeneous Data BatchesAyush Jain 0001, Rajat Sen, Weihao Kong, Abhimanyu Das, Alon Orlitsky. [doi]
• Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal TensorDaniel Miao, Gilad Lerman, Joe Kileel 0001. [doi]
• Graph-enhanced Optimizers for Structure-aware Recommendation Embedding EvolutionCong Xu, Jun Wang 0006, Jianyong Wang 0001, Wei Zhang 0056. [doi]
• Uncovering the Redundancy in Graph Self-supervised Learning ModelsZhibiao Wang, Xiao Wang, Haoyue Deng, Nian Liu, Shirui Pan, Chunming Hu. [doi]
• Towards Robust Multimodal Sentiment Analysis with Incomplete DataHaoyu Zhang, Wenbin Wang, Tianshu Yu. [doi]
• Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language ModelsLu Yu 0004, Haiyang Zhang, Changsheng Xu. [doi]
• Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise ModelsSujai Hiremath, Jacqueline R. M. A. Maasch, Mengxiao Gao, Promit Ghosal, Kyra Gan. [doi]
• On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form GamesZhiyuan Fan, Christian Kroer, Gabriele Farina. [doi]
• DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward PropagationSunghyeon Woo, Baeseong Park, Byeongwook Kim, Minjung Jo, Se Jung Kwon, Dongsuk Jeon, Dongsoo Lee. [doi]
• Blind Image Restoration via Fast Diffusion InversionHamadi Chihaoui, Abdelhak Lemkhenter, Paolo Favaro. [doi]
• Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of AttentionSusung Hong. [doi]
• You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised LearningThéo Moutakanni, Maxime Oquab, Marc Szafraniec, Maria Vakalopoulou, Piotr Bojanowski. [doi]
• Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language ModelsSamuel Holt, Zhaozhi Qian, Tennison Liu, James Weatherall, Mihaela van der Schaar. [doi]
• DiffPO: A causal diffusion model for learning distributions of potential outcomesYuchen Ma 0005, Valentyn Melnychuk, Jonas Schweisthal, Stefan Feuerriegel. [doi]
• On Convergence of Adam for Stochastic Optimization under Relaxed AssumptionsYusu Hong, Junhong Lin. [doi]
• SA3DIP: Segment Any 3D Instance with Potential 3D PriorsXi Yang 0011, Xu Gu, Xingyilang Yin, Xinbo Gao 0001. [doi]
• Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational InequalitiesZaiwei Chen, Eric Mazumdar. [doi]
• Improving Generalization of Dynamic Graph Learning via Environment PromptKuo Yang, Zhengyang Zhou, Qihe Huang, Limin Li, Yuxuan Liang, Yang Wang. [doi]
• Transcendence: Generative Models Can Outperform The Experts That Train ThemEdwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach. [doi]
• SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small ModelsYu Yang 0007, Siddhartha Mishra, Jeffrey N. Chiang, Baharan Mirzasoleiman. [doi]
• Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern GeneratorsChangze Lv, Dongqi Han, Yansen Wang, Xiaoqing Zheng, Xuanjing Huang 0001, Dongsheng Li 0002. [doi]
• Are Language Models Actually Useful for Time Series Forecasting?Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, Tom Hartvigsen. [doi]
• Sample-Efficient Constrained Reinforcement Learning with General ParameterizationWashim Uddin Mondal, Vaneet Aggarwal. [doi]
• SGD vs GD: Rank Deficiency in Linear NetworksAditya Vardhan Varre, Margarita Sagitova, Nicolas Flammarion. [doi]
• Towards Open Respiratory Acoustic Foundation Models: Pretraining and BenchmarkingYuwei Zhang, Tong Xia, Jing Han 0010, Yu Wu, Georgios Rizos, Yang Liu 0101, Mohammed Mosuily, Jagmohan Chauhan, Cecilia Mascolo. [doi]
• Estimating Epistemic and Aleatoric Uncertainty with a Single ModelMatthew Chan, Maria Molina, Chris Metzler. [doi]
• Decomposed Prompt Decision Transformer for Efficient Unseen Task GeneralizationHongling Zheng, Li Shen 0008, Yong Luo 0002, Tongliang Liu, Jialie Shen 0001, Dacheng Tao. [doi]
• ImageNet3D: Towards General-Purpose Object-Level 3D UnderstandingWufei Ma, Guofeng Zhang 0020, Qihao Liu, Guanning Zeng, Adam Kortylewski, Yaoyao Liu 0001, Alan L. Yuille. [doi]
• LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3DZeng Tao, Tong Yang, Junxiong Lin, Xinji Mai, Haoran Wang, Beining Wang, Enyu Zhou, Yan Wang, Wenqiang Zhang. [doi]
• Reinforcement Learning with Adaptive Regularization for Safe Control of Critical SystemsHaozhe Tian, Homayoun Hamedmoghadam, Robert Shorten, Pietro Ferraro. [doi]
• OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization DatasetAllen Roush, Yusuf Shabazz, Arvind Balaji, Peter Zhang, Stefano Mezza, Markus Zhang, Sanjay Basu, Sriram Vishwanath, Ravid Shwartz-Ziv. [doi]
• Multi-Scale Representation Learning for Protein Fitness PredictionZuobai Zhang, Pascal Notin, Yining Huang, Aurélie C. Lozano, Vijil Chenthamarakshan, Debora S. Marks, Payel Das, Jian Tang 0005. [doi]
• Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RLQi Lv, Xiang Deng, Gongwei Chen, Michael Yu Wang, Liqiang Nie. [doi]
• Learning Truncated Causal History Model for Video RestorationAmirhosein Ghasemabadi, Muhammad Kamran Janjua, Mohammad Salameh, Di Niu. [doi]
• SOI: Scaling Down Computational Complexity by Estimating Partial States of the ModelGrzegorz Stefanski, Pawel Daniluk, Artur Szumaczuk, Jakub Tkaczuk. [doi]
• Active Classification with Few Queries under MisspecificationVasilis Kontonis, Mingchen Ma, Christos Tzamos. [doi]
• No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design ChoicesQi Pang, Shengyuan Hu 0001, Wenting Zheng, Virginia Smith. [doi]
• Few-shot Algorithms for Consistent Neural Decoding (FALCON) BenchmarkBrianna Karpowicz, Joel Ye, Chaofei Fan, Pablo Tostado-Marcos, Fabio Rizzoglio, Clayton Washington, Thiago Scodeler, Diogo de Lucena, Samuel R. Nason-Tomaszewski, Matthew Mender, Xuan Ma, Ezequiel M. Arneodo, Leigh R. Hochberg, Cynthia A. Chestek, Jaimie M. Henderson, Timothy Gentner, Vikash Gilja, Lee E. Miller, Adam Rouse, Robert Gaunt, Jennifer L. Collinger, Chethan Pandarinath. [doi]
• SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained ModelsLinglan Zhao, Xuerui Zhang, Ke Yan, Shouhong Ding, Weiran Huang 0001. [doi]
• ACFun: Abstract-Concrete Fusion Facial StylizationJiapeng Ji, Kun Wei, Ziqi Zhang, Cheng Deng. [doi]
• MetaCURL: Non-stationary Concave Utility Reinforcement LearningBianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane. [doi]
• Copycats: the many lives of a publicly available medical imaging datasetAmelia Jiménez-Sánchez, Natalia Rozalia Avlona, Dovile Juodelyte, Théo Sourget, Caroline Vang-Larsen, Anna Rogers, Hubert Dariusz Zajac, Veronika Cheplygina. [doi]
• Self-Distilled Depth Refinement with Noisy Poisson FusionJiaqi Li, Yiran Wang 0005, Jinghong Zheng 0002, Zihao Huang 0001, Ke Xian, Zhiguo Cao 0001, Jianming Zhang 0001. [doi]
• MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion TokensAnas Awadalla, Le Xue, Oscar Lo, Manli Shu, Hannah Lee, Etash Guha, Sheng Shen, Mohamed Awadalla, Silvio Savarese, Caiming Xiong, Ran Xu 0001, Yejin Choi 0001, Ludwig Schmidt. [doi]
• Learning the Infinitesimal Generator of Stochastic Diffusion ProcessesVladimir Kostic, Hélène Halconruy, Timothée Devergne, Karim Lounici, Massimiliano Pontil. [doi]
• Diffusion-Inspired Truncated Sampler for Text-Video RetrievalJiamian Wang, Pichao Wang, Dongfang Liu, Qiang Guan, Sohail A. Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao. [doi]
• Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug DesignXiangxin Zhou, Jiaqi Guan, Yijia Zhang, Xingang Peng, Liang Wang 0001, Jianzhu Ma. [doi]
• NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video ReconstructionZixuan Gong, Guangyin Bao, Qi Zhang 0020, Zhongwei Wan, Duoqian Miao 0001, Shoujin Wang, Lei Zhu 0003, Changwei Wang 0001, Rongtao Xu, Liang Hu 0004, Ke Liu, Yu Zhang 0133. [doi]
• Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual ClassificationZhaorui Tan, Xi Yang, Qiufeng Wang, Anh Nguyen 0003, Kaizhu Huang. [doi]
• Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal ModelsYang Jiao, Shaoxiang Chen 0001, Zequn Jie, Jingjing Chen 0001, Lin Ma 0002, Yu-Gang Jiang 0001. [doi]
• DataComp-LM: In search of the next generation of training sets for language modelsJeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Guha, Sedrick Scott Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner 0001, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alex Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar. [doi]
• Scalable DBSCAN with Random ProjectionsHaochuan Xu, Ninh Pham. [doi]
• Secret Collusion among AI Agents: Multi-Agent Deception via SteganographySumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip Torr 0001, Lewis Hammond, Christian Schröder de Witt. [doi]
• The Limits of Differential Privacy in Online LearningBo Li 0001, Wei Wang 0030, Peng Ye. [doi]
• When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human FeedbackLeon Lang, Davis Foote, Stuart J. Russell, Anca D. Dragan, Erik Jenner, Scott Emmons. [doi]
• Nearly Minimax Optimal Submodular Maximization with Bandit FeedbackArtin Tajdini, Lalit Jain, Kevin G. Jamieson. [doi]
• Your contrastive learning problem is secretly a distribution alignment problemZihao Chen, Chi-Heng Lin, Ran Liu, Jingyun Xiao, Eva L. Dyer. [doi]
• Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution AdaptationWenjun Miao, Guansong Pang, Jin Zheng, Xiao Bai 0001. [doi]
• Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural RepresentationTianjing Zhang, Yuhui Quan, Hui Ji. [doi]
• Causal Contrastive Learning for Counterfactual Regression Over TimeMouad El Bouchattaoui, Myriam Tami, Benoit Lepetit, Paul-Henry Cournède. [doi]
• Testing Semantic Importance via BettingJacopo Teneggi, Jeremias Sulam. [doi]
• Reward Machines for Deep RL in Noisy and Uncertain EnvironmentsAndrew C. Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith. [doi]
• Dimension-free deterministic equivalents and scaling laws for random feature regressionLeonardo Defilippis, Bruno Loureiro, Theodor Misiakiewicz. [doi]
• CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept MatchingDongzhi Jiang, Guanglu Song, Xiaoshi Wu, Renrui Zhang, Dazhong Shen, Zhuofan Zong, Yu Liu 0015, Hongsheng Li 0001. [doi]
• On the Sparsity of the Strong Lottery Ticket HypothesisEmanuele Natale, Davide Ferré, Giordano Giambartolomei, Frédéric Giroire, Frederik Mallmann-Trenn. [doi]
• Derivative-enhanced Deep Operator NetworkYuan Qiu 0012, Nolan Bridges, Peng Chen. [doi]
• FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and DetectionXinting Liao, Weiming Liu 0005, Pengyang Zhou, Fengyuan Yu, Jiahe Xu 0003, Jun Wang, Wenjie Wang, Chaochao Chen 0001, Xiaolin Zheng. [doi]
• DAGER: Exact Gradient Inversion for Large Language ModelsIvo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev. [doi]
• Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural NetworksJerome Sieber, Carmen Amo Alonso, Alexandre Didier, Melanie N. Zeilinger, Antonio Orvieto. [doi]
• Guiding a Diffusion Model with a Bad Version of ItselfTero Karras, Miika Aittala, Tuomas Kynkäänniemi, Jaakko Lehtinen, Timo Aila, Samuli Laine. [doi]
• Vision Foundation Model Enables Generalizable Object Pose EstimationKai Chen 0028, Yiyao Ma, Xingyu Lin, Stephen James, Jianshu Zhou, Yun-Hui Liu, Pieter Abbeel, Dou Qi 0001. [doi]
• Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain KnowledgeFang Dong, Mengyi Chen, Jixian Zhou, Yubin Shi, Yixuan Chen 0003, Mingzhi Dong, Yujiang Wang 0001, Dongsheng Li 0002, Xiaochen Yang, Rui Zhu 0006, Robert P. Dick, Qin Lv, Fan Yang 0001, Tun Lu, Ning Gu, Li Shang. [doi]
• FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep LearningTristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler. [doi]
• Towards Human-AI Complementarity with Prediction SetsGiovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri, Manuel Rodriguez. [doi]
• JaxMARL: Multi-Agent RL Environments and Algorithms in JAXAlexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook 0004, Andrei Lupu, Garðar Ingvarsson, Timon Willi, Ravi Hammond, Akbir Khan, Christian Schröder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert T. Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktäschel, Chris Lu 0001, Jakob Foerster. [doi]
• Uncovering Safety Risks of Large Language Models through Concept Activation VectorZhihao Xu, Ruixuan Huang, Changyu Chen, Xiting Wang. [doi]
• Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language ModelsWenshan Wu, Shaoguang Mao, Yadong Zhang, Yan Xia 0005, Li Dong 0004, Lei Cui 0001, Furu Wei. [doi]
• Trajectory Diffusion for ObjectGoal NavigationXinyao Yu 0002, Sixian Zhang, Xinhang Song, Xiaorong Qin, Shuqiang Jiang. [doi]
• Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form GamesBrian Hu Zhang, Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm. [doi]
• The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix SensingYang Xu, Yihong Gu, Cong Fang 0001. [doi]
• Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised LearningTakuo Matsubara. [doi]
• Deep linear networks for regression are implicitly regularized towards flat minimaPierre Marion, Lénaïc Chizat. [doi]
• Neural Pfaffians: Solving Many Many-Electron Schrödinger EquationsNicholas Gao, Stephan Günnemann. [doi]
• OccamLLM: Fast and Exact Language Model Arithmetic in a Single StepOwen Dugan, Donato Jiménez-Benetó, Charlotte Loh, Zhuo Chen, Rumen Dangovski, Marin Soljacic. [doi]
• IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code ProgramsPatrick Tser Jern Kon, Jiachen Liu, Yiming Qiu, Weijun Fan, Ting He, Lei Lin, Haoran Zhang, Owen Park, George Elengikal, Yuxin Kang, Ang Chen 0001, Mosharaf Chowdhury, Myungjin Lee, Xinyu Wang. [doi]
• Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation ScatteringDongxiao He, Lianze Shan, Jitao Zhao, Hengrui Zhang, Zhen Wang, Weixiong Zhang. [doi]
• MeLLoC: Lossless Compression with High-order Mechanism LearningXinyue Luo, Jin Cheng 0003, Yu Chen. [doi]
• Multi-language Diversity Benefits AutoformalizationAlbert Q. Jiang, Wenda Li, Mateja Jamnik. [doi]
• Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language TasksZijian Gao, Xingxing Zhang, Kele Xu, XinJun Mao, Huaimin Wang. [doi]
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction TuningHang Zhou, Yehui Tang, Haochen Qin, Yujie Yang, Renren Jin, Deyi Xiong, Kai Han 0002, Yunhe Wang 0001. [doi]
• ProEdit: Simple Progression is All You Need for High-Quality 3D Scene EditingJunkun Chen, Yu-Xiong Wang. [doi]
• MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D EditingChenjie Cao, Chaohui Yu, Fan Wang 0019, Xiangyang Xue 0001, Yanwei Fu 0001. [doi]
• SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object DetectionYuxuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang. [doi]
• Understanding Information Storage and Transfer in Multi-Modal Large Language ModelsSamyadeep Basu, Martin Grayson, Cecily Morrison, Besmira Nushi, Soheil Feizi, Daniela Massiceti. [doi]
• What does guidance do? A fine-grained analysis in a simple settingMuthu Chidambaram, Khashayar Gatmiry, Sitan Chen, Holden Lee, Jianfeng Lu 0001. [doi]
• Adaptive Passive-Aggressive Framework for Online Regression with Side InformationRunhao Shi, Jiaxi Ying, Daniel P. Palomar. [doi]
• LP-3DGS: Learning to Prune 3D Gaussian SplattingZhaoliang Zhang, Tianchen Song, Yongjae Lee, Li Yang 0009, Cheng Peng 0008, Rama Chellappa, Deliang Fan. [doi]
• RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure AggregationPeihua Mai, Ran Yan, Yan Pang. [doi]
• How many classifiers do we need?Hyunsuk Kim, Liam Hodgkinson, Ryan Theisen, Michael W. Mahoney. [doi]
• Reparameterized Multi-Resolution Convolutions for Long Sequence ModellingJake Cunningham, Giorgio Giannone, Mingtian Zhang, Marc Peter Deisenroth. [doi]
• GeoPlant: Spatial Plant Species Prediction DatasetLukás Picek, Christophe Botella, Maximilien Servajean, César Leblanc, Rémi Palard, Théo Larcher, Benjamin Deneu, Diego Marcos, Pierre Bonnet, Alexis Joly. [doi]
• Universal Physics Transformers: A Framework For Efficiently Scaling Neural OperatorsBenedikt Alkin, Andreas Fürst, Simon Schmid, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter. [doi]
• Robust Fine-tuning of Zero-shot Models via Variance ReductionBeier Zhu, Jiequan Cui, Hanwang Zhang. [doi]
• Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural NetworksYufei Guo, Yuanpei Chen, Zecheng Hao, Weihang Peng 0001, Zhou Jie, Yuhan Zhang, Xiaode Liu, Zhe Ma 0001. [doi]
• Multi-Agent Imitation Learning: Value is Easy, Regret is HardJingwu Tang, Gokul Swamy, Fei Fang 0001, Zhiwei Steven Wu. [doi]
• Learning to Discuss Strategically: A Case Study on One Night Ultimate WerewolfXuanfa Jin, Ziyan Wang, Yali Du 0001, Meng Fang, Haifeng Zhang, Jun Wang. [doi]
• SELF-DISCOVER: Large Language Models Self-Compose Reasoning StructuresPei Zhou, Jay Pujara, Xiang Ren 0001, Xinyun Chen, Heng Tze Cheng, Quoc V. Le, Ed H. Chi, Denny Zhou, Swaroop Mishra, Huaixiu Steven Zheng. [doi]
• A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement LearningTom Yan, Zachary C. Lipton. [doi]
• GFlowNet Assisted Biological Sequence EditingPouya M. Ghari, Alex M. Tseng, Gökcen Eraslan, Romain Lopez, Tommaso Biancalani, Gabriele Scalia, Ehsan Hajiramezanali. [doi]
• GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian SplatsSangeek Hyun, Jae-Pil Heo. [doi]
• Embodied Agent Interface: Benchmarking LLMs for Embodied Decision MakingManling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li Erran Li, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei 0001, Jiayuan Mao, Jiajun Wu 0001. [doi]
• Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase TransitionRui Ai, David Simchi-Levi, Feng Zhu. [doi]
• AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image GenerationLianyu Pang, Jian Yin 0001, Baoquan Zhao, Feize Wu, Fu Lee Wang, Qing Li 0001, Xudong Mao. [doi]
• When does perceptual alignment benefit vision representations?Shobhita Sundaram, Stephanie Fu, Lukas Muttenthaler, Netanel Tamir, Lucy Chai, Simon Kornblith, Trevor Darrell, Phillip Isola. [doi]
• A generalized neural tangent kernel for surrogate gradient learningLuke Eilers, Raoul-Martin Memmesheimer, Sven Goedeke. [doi]
• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision ComputationShiwei Wu, Joya Chen, Kevin Qinghong Lin, Qimeng Wang, Yan Gao, Qianli Xu, Tong Xu 0001, Yao Hu, Enhong Chen, Mike Zheng Shou. [doi]
• Instruction Embedding: Latent Representations of Instructions Towards Task IdentificationYiwei Li 0001, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Boyuan Pan, Heda Wang, Yao Hu, Prof. Kan. [doi]
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language ModelsBowen Ping, Shuo Wang, Hanqing Wang, Xu Han 0007, Yuzhuang Xu, Yukun Yan, Yun Chen 0007, Baobao Chang, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNsRong Ma, Jie Chen, Xiangyang Xue 0001, Jian Pu. [doi]
• Periodic agent-state based Q-learning for POMDPsAmit Sinha, Matthieu Geist, Aditya Mahajan. [doi]
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement LearningTong Yang, Shicong Cen, Yuting Wei 0001, Yuxin Chen 0002, Yuejie Chi. [doi]
• Unified Mechanism-Specific Amplification by Subsampling and Group Privacy AmplificationJan Schuchardt, Mihail Stoian, Arthur Kosmala, Stephan Günnemann. [doi]
• Gradient-free Decoder Inversion in Latent Diffusion ModelsSeongmin Hong, Suh Yoon Jeon, Kyeonghyun Lee, Ernest K. Ryu, Se Young Chun. [doi]
• Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based ModelsDaniela de Albuquerque, John M. Pearson. [doi]
• CoSW: Conditional Sample Weighting for Smoke Segmentation with Label NoiseLujian Yao, Haitao Zhao 0002, Zhongze Wang, Kaijie Zhao, Jingchao Peng. [doi]
• Rethinking Optimal Transport in Offline Reinforcement LearningArip Asadulaev, Rostislav Korst, Aleksandr Korotin, Vage Egiazarian, Andrey Filchenkov, Evgeny Burnaev. [doi]
• ETO: Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography HypothesesJunjie Ni, Guofeng Zhang 0001, Guanglin Li 0005, Yijin Li, Xinyang Liu, Zhaoyang Huang, Hujun Bao. [doi]
• Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for ChemistryMarvin Alberts, Oliver Schilter, Federico Zipoli, Nina Hartrampf, Teodoro Laino. [doi]
• TopoFR: A Closer Look at Topology Alignment on Face RecognitionJun Dan, Yang Liu 0155, Jiankang deng, Haoyu Xie, Siyuan Li 0002, Baigui Sun, Shan Luo 0001. [doi]
• Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering PlaylistsJoachim Baumann 0002, Celestine Mendler-Dünner. [doi]
• Trajectory Flow Matching with Applications to Clinical Time Series ModellingXi Zhang, Yuan Pu, Yuki Kawamura, Andrew Loza, Yoshua Bengio, Dennis L. Shung, Alexander Tong 0001. [doi]
• Regret Minimization in Stackelberg Games with Side InformationKeegan Harris, Zhiwei Steven Wu, Maria-Florina Balcan. [doi]
• Expecting The Unexpected: Towards Broad Out-Of-Distribution DetectionCharles Guille-Escuret, Pierre-André Noël, Ioannis Mitliagkas, David Vázquez 0001, João Monteiro 0002. [doi]
• Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language ModelsAdam Fisch, Joshua Maynez, R. Alex Hofer, Bhuwan Dhingra, Amir Globerson, William W. Cohen. [doi]
• Is Behavior Cloning All You Need? Understanding Horizon in Imitation LearningDylan J. Foster, Adam Block, Dipendra Misra. [doi]
• UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New PeaksJingjing Ren, Wenbo Li, Haoyu Chen, Renjing Pei, Bin Shao, Yong Guo, Long Peng, Fenglong Song, Lei Zhu. [doi]
• A Simple yet Universal Framework for Depth CompletionJin-Hwi Park, Hae-Gon Jeon. [doi]
• Can neural operators always be continuously discretized?Takashi Furuya, Michael Puthawala, Matti Lassas, Maarten V. De Hoop. [doi]
• 3D Gaussian Splatting as Markov Chain Monte CarloShakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Yang-Che Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi. [doi]
• Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view ClusteringFangdi Wang, Jiaqi Jin, Jingtao Hu, Suyuan Liu, Xihong Yang, Siwei Wang 0001, Xinwang Liu 0002, En Zhu. [doi]
• Cardinality-Aware Set Prediction and Top-$k$ ClassificationCorinna Cortes, Anqi Mao, Christopher Mohri, Mehryar Mohri, Yutao Zhong 0002. [doi]
• Towards Estimating Bounds on the Effect of Policies under Unobserved ConfoundingAlexis Bellot, Silvia Chiappa. [doi]
• The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networksLénaïc Chizat, Praneeth Netrapalli. [doi]
• TARSS-Net: Temporal-Aware Radar Semantic Segmentation NetworkYoucheng Zhang, Liwen Zhang 0001, ZijunHu, Pengcheng Pi, Teng Li, Yuanpei Chen, Shi Peng, Zhe Ma 0001. [doi]
• DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple TrojansYuan Gan, Jiaxu Miao, Yi Yang. [doi]
• Learning Where to Edit Vision TransformersYunqiao Yang, Long-Kai Huang, Shengzhuang Chen, Kede Ma, Ying Wei 0001. [doi]
• Estimating the Hallucination Rate of Generative AIAndrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David M. Blei. [doi]
• Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text RecognitionMehreen Saeed, Adrian Chan, Anupam Mijar, Joseph Moukarzel, Georges Habchi, Carlos Younes, Amin Elias, Chau-Wai Wong, Akram Khater. [doi]
• DALD: Improving Logits-based Detector without Logits from Black-box LLMsCong Zeng, Shengkun Tang, Xianjun Yang, Yuanzhou Chen, Yiyou Sun, Zhiqiang Xu, Yao Li, Haifeng Chen, Wei Cheng 0002, Dongkuan Xu. [doi]
• A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware PerspectiveYunpeng Qing, Shunyu Liu 0001, Jingyuan Cong, Kaixuan Chen 0004, Yihe Zhou, Mingli Song. [doi]
• A Synthetic Dataset for Personal Attribute InferenceHanna Yukhymenko, Robin Staab, Mark Vero, Martin T. Vechev. [doi]
• GO4Align: Group Optimization for Multi-Task AlignmentJiayi Shen, Qi Wang 0009, Zehao Xiao, Nanne van Noord, Marcel Worring. [doi]
• Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex FunctionsQuanqi Hu, Qi Qi 0006, Zhaosong Lu, Tianbao Yang. [doi]
• Mixture of Nested Experts: Adaptive Processing of Visual TokensGagan Jain, Nidhi Hegde 0003, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain 0002, Anurag Arnab, Sujoy Paul. [doi]
• Implicit Curriculum in Procgen Made ExplicitZhenxiong Tan, Kaixin Wang, Xinchao Wang. [doi]
• Nonparametric Instrumental Variable Regression through Stochastic Approximate GradientsYuri R. Fonseca, Caio Peixoto, Yuri F. Saporito. [doi]
• Poseidon: Efficient Foundation Models for PDEsMaximilian Herde, Bogdan Raonic, Tobias Rohner, Roger Käppeli, Roberto Molinaro, Emmanuel de Bézenac, Siddhartha Mishra. [doi]
• Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel MachinesEdward Milsom, Ben Anson, Laurence Aitchison. [doi]
• Beyond Efficiency: Molecular Data Pruning for Enhanced GeneralizationDingshuo Chen, Zhixun Li, Yuyan Ni, Guibin Zhang, Ding Wang, Qiang Liu 0006, Shu Wu, Jeffrey Xu Yu, Liang Wang. [doi]
• Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language ModelsJiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang 0066, Sharon Li 0001, Neel Joshi. [doi]
• Constructing Semantics-Aware Adversarial Examples with a Probabilistic PerspectiveAndi Zhang 0001, Mingtian Zhang, Damon Wischik. [doi]
• Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual StructuresYadong Sun, Xiaofeng Cao, Yu Wang, Wei Ye, Jingcai Guo, Qing Guo. [doi]
• Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated LearningDario Fenoglio, Gabriele Dominici, Pietro Barbiero, Alberto Tonda, Martin Gjoreski, Marc Langheinrich. [doi]
• Certified Machine Unlearning via Noisy Stochastic Gradient DescentEli Chien, Haoyu Wang 0004, Ziang Chen, Pan Li 0005. [doi]
• Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language ModelsArshia Hemmat, Adam Davies, Tom A. Lamb, Jianhao Yuan, Philip Torr 0001, Ashkan Khakzar, Francesco Pinto. [doi]
• Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D ScenesQi Ma, Danda Pani Paudel, Ender Konukoglu, Luc Van Gool. [doi]
• DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic StatesBozhou Zhang, Nan Song, Li Zhang. [doi]
• The Sample-Communication Complexity Trade-off in Federated Q-LearningSudeep Salgia, Yuejie Chi. [doi]
• Transformers need glasses! Information over-squashing in language tasksFederico Barbero, Andrea Banino, Steven Kapturowski, Dharshan Kumaran, João Guilherme Madeira Araújo, Oleksandr Vitvitskyi, Razvan Pascanu, Petar Velickovic. [doi]
• Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous ContradictionsZhe Hu, Tuo Liang, Jing Li, Yiren Lu 0002, Yunlai Zhou, Yiran Qiao, Jing Ma 0002, Yu Yin 0001. [doi]
• Don't Look Twice: Faster Video Transformers with Run-Length TokenizationRohan Choudhury, Guanglei Zhu, Sihan Liu, Koichiro Niinuma, Kris Kitani, László A. Jeni. [doi]
• Membership Inference Attacks against Large Vision-Language ModelsZhan Li, Yongtao Wu, Yihang Chen, Francesco Tonin, Elías Abad-Rocamora, Volkan Cevher. [doi]
• SlimSAM: 0.1% Data Makes Segment Anything SlimZigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang. [doi]
• How does Inverse RL Scale to Large State Spaces? A Provably Efficient ApproachFilippo Lazzati, Mirco Mutti, Alberto Maria Metelli. [doi]
• Controlling Continuous Relaxation for Combinatorial OptimizationYuma Ichikawa. [doi]
• DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose OptimizationYueming Xu, Haochen Jiang, Zhongyang Xiao, Jianfeng Feng, Li Zhang 0040. [doi]
• Approaching Human-Level Forecasting with Language ModelsDanny Halawi, Fred Zhang, Chen Yueh-Han, Jacob Steinhardt. [doi]
• Non-convolutional graph neural networksYuanqing Wang, KyungHyun Cho. [doi]
• SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal DomainPierre Colombo, Telmo Pessoa Pires, Malik Boudiaf, Rui Melo, Gabriel Hautreux, Etienne Malaboeuf, Johanne Charpentier, Dominic Culver, Michael Desa. [doi]
• Randomized Exploration in Cooperative Multi-Agent Reinforcement LearningHao-Lun Hsu, Weixin Wang, Miroslav Pajic, Pan Xu 0002. [doi]
• First-Order Minimax Bilevel OptimizationYifan Yang, Zhaofeng Si, Siwei Lyu, Kaiyi Ji. [doi]
• SGLang: Efficient Execution of Structured Language Model ProgramsLianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang 0001, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark W. Barrett, Ying Sheng 0007. [doi]
• OTTER: Effortless Label Distribution Adaptation of Zero-shot ModelsChangho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma, Frederic Sala. [doi]
• Alias-Free Mamba Neural OperatorJianwei Zheng 0001, Wei Li, Ni Xu, Junwei Zhu, Xiaoxu Lin, Xiaoqin Zhang. [doi]
• Towards Open-Vocabulary Semantic Segmentation Without Semantic LabelsHeeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim. [doi]
• MultiOrg: A Multi-rater Organoid-detection DatasetChristina Bukas, Harshavardhan Subramanian, Fenja See, Carina Steinchen, Ivan Ezhov, Gowtham Boosarpu, Sara Asgharpour, Gerald Burgstaller, Mareike Lehmann, Florian Kofler, Marie Piraud. [doi]
• Task-oriented Time Series Imputation Evaluation via Generalized RepresentersZhixian Wang, Linxiao Yang, Liang Sun, Qingsong Wen, Yi Wang 0022. [doi]
• You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object DetectionMingbo Hong, Shen Cheng, Haibin Huang, Haoqiang Fan, Shuaicheng Liu. [doi]
• On $f$-Divergence Principled Domain Adaptation: An Improved FrameworkZiqiao Wang, Yongyi Mao. [doi]
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache QuantizationColeman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami. [doi]
• A Gradient Accumulation Method for Dense Retriever under Memory ConstraintJaehee Kim, Yukyung Lee, Pilsung Kang 0001. [doi]
• Refusal in Language Models Is Mediated by a Single DirectionAndy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda. [doi]
• Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained OptimizationKai Hu, Weichen Yu, Yining Li, Tianjun Yao, Xiang Li, Wenhe Liu, Lijun Yu, Zhiqiang Shen, Kai Chen 0026, Matt Fredrikson. [doi]
• Interaction-Force Transport Gradient FlowsEgor Gladin, Pavel E. Dvurechenskii, Alexander Mielke, Jia-Jie Zhu. [doi]
• Unconditional stability of a recurrent neural circuit implementing divisive normalizationShivang Rawat, David J. Heeger, Stefano Martiniani. [doi]
• Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMsXuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, Min Lin. [doi]
• Understanding Linear Probing then Fine-tuning Language Models from NTK PerspectiveAkiyoshi Tomihari, Issei Sato. [doi]
• Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable SystemsRohan R. Paleja, Michael Munje, Kimberlee Chestnut Chang, Reed Jensen, Matthew C. Gombolay. [doi]
• Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and SmoothnessXiaoge Deng, Tao Sun 0005, Shengwei Li, Dongsheng Li 0001, Xicheng Lu. [doi]
• ARC: A Generalist Graph Anomaly Detector with In-Context LearningYixin Liu 0001, Shiyuan Li, Yu Zheng 0013, Qingfeng Chen, Chengqi Zhang, Shirui Pan. [doi]
• 4M-21: An Any-to-Any Vision Model for Tens of Tasks and ModalitiesRoman Bachmann 0001, Oguzhan Fatih Kar, David Mizrahi, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir. [doi]
• Where Do Large Learning Rates Lead Us?Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva, Dmitry P. Vetrov. [doi]
• GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingJunyoung Seo, Kazumi Fukuda, Takashi Shibuya 0001, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim, Yuki Mitsufuji. [doi]
• LVD-2M: A Long-take Video Dataset with Temporally Dense CaptionsTianwei Xiong, Yuqing Wang, Daquan Zhou, Zhijie Lin, Jiashi Feng, Xihui Liu. [doi]
• Conditional Outcome Equivalence: A Quantile Alternative to CATEJosh Givens, Henry W. J. Reeve, Song Liu, Katarzyna Reluga. [doi]
• Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-imageYu Zhao, Hao Fei 0001, Xiangtai Li, Libo Qin 0004, Jiayi Ji, Hongyuan Zhu, Meishan Zhang, Min Zhang 0005, Jianguo Wei. [doi]
• Strategic Multi-Armed Bandit Problems Under Debt-Free ReportingAhmed Ben Yahmed, Clément Calauzènes, Vianney Perchet. [doi]
• Distribution-Aware Data Expansion with Diffusion ModelsHaowei Zhu, Ling Yang, Jun-Hai Yong, Hongzhi Yin, Jiawei Jiang, Meng Xiao, Wentao Zhang, Bin Wang. [doi]
• Finding Transformer Circuits With Edge PruningAdithya Bhaskar, Alexander Wettig, Dan Friedman, Danqi Chen 0001. [doi]
• Fetch and Forge: Efficient Dataset Condensation for Object DetectionDing Qi, Jian Li 0062, Jinlong Peng, Bo Zhao, Shuguang Dou, Jialin Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cairong Zhao. [doi]
• SkiLD: Unsupervised Skill Discovery Guided by Factor InteractionsZizhao Wang, Jiaheng Hu, Caleb Chuck, Stephen Chen, Roberto Martín-Martín, Amy Zhang 0001, Scott Niekum, Peter Stone 0001. [doi]
• π-Realizability and ConcentrabilityVolodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári. [doi]
• AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language ModelsYabin Zhang, Lei Zhang. [doi]
• Decision-Focused Learning with Directional GradientsMichael Huang, Vishal Gupta 0004. [doi]
• Semi-Random Matrix Completion via Flow-Based Adaptive ReweightingJonathan A. Kelner, Jerry Li 0001, Allen Liu, Aaron Sidford, Kevin Tian. [doi]
• RegExplainer: Generating Explanations for Graph Neural Networks in Regression TasksJiaxing Zhang 0002, Zhuomin Chen, Hao Mei, Longchao Da, Dongsheng Luo, Hua Wei 0001. [doi]
• InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object InteractionSirui Xu 0002, Ziyin Wang, Yu-Xiong Wang, Liangyan Gui. [doi]
• Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap FeaturesChengkai Hou, Zhengrong Xue, Bingyang Zhou, JingHan Ke, Lin Shao 0002, Huazhe Xu. [doi]
• ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMsZhaochen Su, Jun Zhang, Xiaoye Qu, Tong Zhu 0002, Yanshu Li, Jiashuo Sun, Juntao Li, Min Zhang, Yu Cheng. [doi]
• Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-ExpertsSukwon Yun, Inyoung Choi, Jie Peng, Yangfan Wu, Jingxuan Bao, Qiyiwen Zhang, Jiayi Xin, Qi Long, Tianlong Chen. [doi]
• Iterative Reasoning Preference OptimizationRichard Yuanzhe Pang, Weizhe Yuan, He He, KyungHyun Cho, Sainbayar Sukhbaatar, Jason Weston. [doi]
• Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR MaterialsYawar Siddiqui, Tom Monnier, Filippos Kokkinos, Mahendra Kariya, Yanir Kleiman, Emilien Garreau, Oran Gafni, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotný. [doi]
• ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context ModelYufei Wang, Zhihao Li, Lanqing Guo, Wenhan Yang, Alex C. Kot, Bihan Wen. [doi]
• Set-based Neural Network Encoding Without Weight TyingBruno Andreis, Bedionita Soro, Philip H. S. Torr, Sung Ju Hwang. [doi]
• A Canonicalization Perspective on Invariant and Equivariant LearningGeorge Ma, Yifei Wang 0001, Derek Lim, Stefanie Jegelka, Yisen Wang 0001. [doi]
• Slicing Vision Transformer for Flexible InferenceYitian Zhang, Huseyin Coskun, Xu Ma 0005, Huan Wang, Ke Ma, Xi Stephen Chen, Derek Hao Hu, Yun Fu 0001. [doi]
• A Layer-Wise Natural Gradient Optimizer for Training Deep Neural NetworksXiaolei Liu, Shaoshuai Li, Kaixin Gao, Binfeng Wang. [doi]
• Reflective Multi-Agent Collaboration based on Large Language ModelsXiaohe Bo, Zeyu Zhang 0007, Quanyu Dai, Xueyang Feng, Lei Wang, Rui Li 0086, Xu Chen 0017, Ji-Rong Wen. [doi]
• Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and OptimizationMingwei Xu, Xiaofeng Cao 0002, Ivor W. Tsang. [doi]
• DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion ModelsHengkang Wang, Xu Zhang, Taihui Li, Yuxiang Wan, Tiancong Chen, Ju Sun. [doi]
• Approximating mutual information of high-dimensional variables using learned representationsGokul Gowri, Xiao-Kang Lun, Allon M. Klein, Peng Yin. [doi]
• Constant Acceleration FlowDogyun Park, Sojin Lee, Sihyeon Kim, Taehoon Lee, Youngjoon Hong, Hyunwoo J. Kim. [doi]
• GAIA: Rethinking Action Quality Assessment for AI-Generated VideosZijian Chen 0001, Wei Sun 0029, Yuan Tian 0017, Jun Jia, Zicheng Zhang, Jiarui Wang, Ru Huang 0002, Xiongkuo Min, Guangtao Zhai, Wen-Jun Zhang 0005. [doi]
• Accelerating Transformers with Spectrum-Preserving Token MergingChau Tran, Duy M. H. Nguyen, Manh-Duy Nguyen, TrungTin Nguyen, Ngan Le, Pengtao Xie, Daniel Sonntag, James Y. Zou, Binh Nguyen, Mathias Niepert. [doi]
• Can LLMs Learn by Teaching for Better Reasoning? A Preliminary StudyXuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin 0001, Peiran Yao, Tianyu Fu 0004, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang 0002. [doi]
• Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMsSukmin Yun, Haokun Lin, Rusiru Thushara, Mohammad Qazim Bhat, Yongxin Wang, Zutao Jiang, Mingkai Deng, Jinhong Wang, Tianhua Tao, Junbo Li, Haonan Li 0002, Preslav Nakov, Timothy Baldwin, Zhengzhong Liu 0001, Eric P. Xing, Xiaodan Liang, Zhiqiang Shen. [doi]
• An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted ObservationsWeimin Bai, Yifei Wang, Wenzheng Chen, He Sun. [doi]
• Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical SystemsAmber Hu, David M. Zoltowski, Aditya Nair, David Anderson, Lea Duncker, Scott W. Linderman. [doi]
• Novel Object Synthesis via Adaptive Text-Image HarmonyZeren Xiong, Zedong Zhang, Zikun Chen, Shuo Chen 0003, Xiang Li, Gan Sun, Jian Yang, Jun Li. [doi]
• QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule GenerationHuaijin Wu, Xinyu Ye, Junchi Yan. [doi]
• Boosting Generalization in Parametric PDE Neural Solvers through Adaptive ConditioningArmand Kassaï Koupaï, Jorge Mifsut Benet, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari. [doi]
• Variational Delayed Policy OptimizationQingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Chao Huang. [doi]
• Real-time Stereo-based 3D Object Detection for Streaming PerceptionChangcai Li, Zonghua Gu 0001, Gang Chen, Libo Huang, Wei Zhang 0092, Huihui Zhou. [doi]
• Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix ModelsHao Yan, Keith Levin. [doi]
• ♮-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information SettingTaihei Oki, Shinsaku Sakaue. [doi]
• FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality RepresentationRuizhe Zhong, Xingbo Du, Shixiong Kai, Zhentao Tang, Siyuan Xu, Jianye Hao, Mingxuan Yuan, Junchi Yan. [doi]
• One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosZechen Bai, Tong He 0002, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, liulei, Zheng Zhang 0001, Mike Zheng Shou. [doi]
• Multi-Group Proportional Representation in RetrievalAlex Oesterling, Claudio Mayrink Verdun, Alex Glynn, Carol Xuan Long, Lucas Monteiro Paes, Sajani Vithana, Martina Cardone, Flávio P. Calmon. [doi]
• DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object DetectionJia Syuen Lim, Zhuoxiao Chen, Zhi Chen 0010, Mahsa Baktashmotlagh, Xin Yu 0002, Zi Huang, Yadan Luo. [doi]
• Relational Verification Leaps Forward with RABBitTarun Suresh, Debangshu Banerjee, Gagandeep Singh 0001. [doi]
• LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban SimulationBowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia P. Sycara, Pradeep Ravikumar, Alexander G. Gray, Xujie Si, Sebastian A. Scherer. [doi]
• Gated Slot Attention for Efficient Linear-Time Sequence ModelingYu Zhang 0092, Songlin Yang, Rui-Jie Zhu 0003, Yue Zhang 0004, Leyang Cui, Yiqiao Wang 0005, Bolun Wang, Freda Shi, Bailin Wang, Wei Bi, Peng Zhou, Guohong Fu. [doi]
• Bandits with Preference Feedback: A Stackelberg Game PerspectiveBarna Pásztor, Parnian Kassraie, Andreas Krause 0001. [doi]
• On the Scalability of GNNs for Molecular GraphsMaciej Sypetkowski, Frederik Wenkel, Farimah Poursafaei, Nia Dickson, Karush Suri, Philip Fradkin, Dominique Beaini. [doi]
• On the Impacts of the Random Initialization in the Neural Tangent Kernel TheoryGuhan Chen, Yicheng Li 0002, Qian Lin. [doi]
• SkipPredict: When to Invest in Predictions for SchedulingRana Shahout, Michael Mitzenmacher. [doi]
• Offline Multitask Representation Learning for Reinforcement LearningHaque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora, Mengdi Wang, Ming Yin 0003, Doina Precup. [doi]
• Non-Stationary Learning of Neural Networks with Automatic Soft Parameter ResetAlexandre Galashov, Michalis K. Titsias, András György 0001, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani. [doi]
• I Don't Know: Explicit Modeling of Uncertainty with an [IDK] TokenRoi Cohen, Konstantin Dobler, Eden Biran, Gerard de Melo. [doi]
• Can Simple Averaging Defeat Modern Watermarks?Pei Yang, Hai Ci, Yiren Song, Mike Zheng Shou. [doi]
• Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization AlgorithmLeo Zhou, Joao Basso, Song Mei. [doi]
• Replicable Uniformity TestingSihan Liu, Christopher Ye 0001. [doi]
• LESS: Label-Efficient and Single-Stage Referring 3D SegmentationXuexun Liu, Xiaoxu Xu, Jinlong Li, Qiudan Zhang, Xu Wang 0006, Nicu Sebe, Lin Ma 0002. [doi]
• WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery BenchmarkingYunchao Liu, Ha Dong, Xin Wang, Rocco Moretti, Yu Wang 0160, Zhaoqian Su, Jiawei Gu, Bobby Bodenheimer, Charles David Weaver, Jens Meiler, Tyler Derr. [doi]
• Provable Posterior Sampling with Denoising Oracles via Tilted TransportJoan Bruna, Jiequn Han. [doi]
• Overcoming Brittleness in Pareto-Optimal Learning Augmented AlgorithmsAlex Elenter, Spyros Angelopoulos 0001, Christoph Dürr, Yanni Lefki. [doi]
• X-Ray: A Sequential 3D Representation For GenerationTao Hu 0011, Wenhang Ge, Yuyang Zhao, Gim Hee Lee. [doi]
• BitsFusion: 1.99 bits Weight Quantization of Diffusion ModelYang Sui, Yanyu Li, Anil Kag, Yerlan Idelbayev, Junli Cao, Ju Hu, Dhritiman Sagar, Bo Yuan 0001, Sergey Tulyakov, Jian Ren 0005. [doi]
• Generative Hierarchical Materials SearchSherry Yang 0001, Simon L. Batzner, RuiQi Gao, Muratahan Aykol, Alexander L. Gaunt, Brendan McMorrow, Danilo Jimenez Rezende, Dale Schuurmans, Igor Mordatch, Ekin Dogus Cubuk. [doi]
• First-Order Methods for Linearly Constrained Bilevel OptimizationGuy Kornowski, Swati Padmanabhan, Kai Wang, Zhe Zhang, Suvrit Sra. [doi]
• Reproducibility of predictive networks for mouse visual cortexPolina Turishcheva, Max F. Burg, Fabian H. Sinz, Alexander S. Ecker. [doi]
• Edit Distance Robust Watermarks via Indexing Pseudorandom CodesNoah Golowich, Ankur Moitra. [doi]
• QueST: Self-Supervised Skill Abstractions for Learning Continuous ControlAtharva Mete, Haotian Xue 0002, Albert Wilcox, Yongxin Chen, Animesh Garg. [doi]
• Incorporating Surrogate Gradient Norm to Improve Offline Optimization TechniquesCuong Dao, Phi-Le Nguyen, Truong Thao Nguyen, Nghia Hoang. [doi]
• Language Without Borders: A Dataset and Benchmark for Code-Switching Lip ReadingXueyi Zhang, Mingrui Lao, Peng Zhao, Jun Tang 0001, Yanming Guo, Siqi Cai, Xianghu Yue, Haizhou Li 0001. [doi]
• Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling ParadoxRaymond Zhang, Richard Combes. [doi]
• Diffusion Imitation from ObservationBo-Ruei Huang, Chun-Kai Yang, Chun-Mao Lai, Dai-Jie Wu, Shao-Hua Sun. [doi]
• Learning to Merge Tokens via Decoupled Embedding for Efficient Vision TransformersDong-Hoon Lee, Seunghoon Hong. [doi]
• Approximately Equivariant Neural ProcessesMatthew Ashman, Cristiana Diaconu, Adrian Weller, Wessel P. Bruinsma, Richard E. Turner. [doi]
• FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series GenerationAsadullah Hill Galib, Pang-Ning Tan, Lifeng Luo. [doi]
• Active learning of neural population dynamics using two-photon holographic optogeneticsAndrew Wagenmaker, Lu Mi, Marton Rozsa, Matthew S. Bull, Karel Svoboda, Kayvon Daie, Matthew D. Golub, Kevin G. Jamieson. [doi]
• Enhancing Efficiency of Safe Reinforcement Learning via Sample ManipulationShangding Gu, Laixi Shi, Yuhao Ding, Alois Knoll, Costas J. Spanos, Adam Wierman, Ming Jin 0002. [doi]
• DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing DataHanyang Chen, Yang Jiang, Shengnan Guo 0001, Xiaowei Mao, Youfang Lin, Huaiyu Wan. [doi]
• Model Sensitivity Aware Continual LearningZhenyi Wang 0001, Heng Huang. [doi]
• Identifying Latent State-Transition Processes for Individualized Reinforcement LearningYuewen Sun, Biwei Huang, Yu Yao, Donghuo Zeng, Xinshuai Dong, Songyao Jin, Boyang Sun, Roberto Legaspi, Kazushi Ikeda, Peter Spirtes, Kun Zhang. [doi]
• CultureLLM: Incorporating Cultural Differences into Large Language ModelsCheng Li, Mengzhuo Chen, Jindong Wang 0001, Sunayana Sitaram, Xing Xie 0001. [doi]
• Efficient Leverage Score Sampling for Tensor Train DecompositionVivek Bharadwaj, Beheshteh T. Rakhshan, Osman Asif Malik, Guillaume Rabusseau. [doi]
• Cost-efficient Knowledge-based Question Answering with Large Language ModelsJunnan Dong, Qinggang Zhang, Chuang Zhou 0002, Hao Chen, Daochen Zha, Xiao Huang 0002. [doi]
• Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence GuaranteesTaiki Miyagawa, Takeru Yokota. [doi]
• 3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face RecognitionJianqing Xu, Shen Li 0004, Jiaying Wu, Miao Xiong, Ailin Deng, Jiazhen Ji, Yuge Huang, Guodong Mu, Wenjie Feng 0001, Shouhong Ding, Bryan Hooi. [doi]
• UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and BeyondKun Zhou 0001, Xinyu Lin, Zhonghang Liu, Xiaoguang Han 0001, Jiangbo Lu. [doi]
• Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative ModelMark Rowland 0001, Kevin Kevin Li, Rémi Munos, Clare Lyle, Yunhao Tang, Will Dabney. [doi]
• Unifying Generation and Prediction on Graphs with Latent Graph DiffusionCai Zhou, Xiyuan Wang, Muhan Zhang. [doi]
• Assemblage: Automatic Binary Dataset Construction for Machine LearningChang Liu, Rebecca Saul, Yihao Sun, Edward Raff, Maya Fuchs, Townsend Southard Pantano, James Holt, Kristopher K. Micinski. [doi]
• Latent Neural Operator for Solving Forward and Inverse PDE ProblemsTian Wang, Chuang Wang. [doi]
• United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial TrajectoriesTianlong Xu, Chen Wang, Gaoyang Liu, Yang Yang, Kai Peng 0001, Wei Liu. [doi]
• Spectral Learning of Shared Dynamics Between Generalized-Linear ProcessesLucine L. Oganesian, Omid G. Sani, Maryam Shanechi. [doi]
• FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological SensingJitesh Joshi, Sos S. Agaian, Youngjun Cho. [doi]
• Online Composite Optimization Between Stochastic and Adversarial EnvironmentsYibo Wang 0005, Sijia Chen, Wei Jiang, Wenhao Yang, Yuanyu Wan, Lijun Zhang 0005. [doi]
• Beyond Prompts: Dynamic Conversational Benchmarking of Large Language ModelsDavid Castillo-Bolado, Joseph Davidson, Finlay Gray, Marek Rosa. [doi]
• Autonomous Agents for Collaborative Task under Information AsymmetryWei Liu, Chenxi Wang, Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian. [doi]
• TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving ScenesYanping Fu, Wenbin Liao, Xinyuan Liu 0003, Hang Xu, Yike Ma, Yucheng Zhang, Feng Dai. [doi]
• EMR-Merging: Tuning-Free High-Performance Model MergingChenyu Huang, Peng Ye, Tao Chen 0003, Tong He 0001, Xiangyu Yue 0001, Wanli Ouyang. [doi]
• Web-Scale Visual Entity Recognition: An LLM-Driven Data ApproachMathilde Caron, Alireza Fathi, Cordelia Schmid, Ahmet Iscen. [doi]
• Identity Decoupling for Multi-Subject Personalization of Text-to-Image ModelsSangwon Jang, Jaehyeong Jo, Kimin Lee, Sung Ju Hwang. [doi]
• Decomposable Transformer Point ProcessesAristeidis Panos. [doi]
• Simplifying Latent Dynamics with Softly State-Invariant World ModelsTankred Saanum, Peter Dayan, Eric Schulz. [doi]
• Mind the Gap Between Prototypes and Images in Cross-domain FinetuningHongduan Tian, Feng Liu 0003, Zhanke Zhou, Tongliang Liu, Chengqi Zhang, Bo Han 0003. [doi]
• B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading MemoryLuca Zancato, Arjun Seshadri, Yonatan Dukler, Aditya Golatkar, Yantao Shen 0002, Benjamin Bowman, Matthew Trager, Alessandro Achille, Stefano Soatto. [doi]
• Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal InputsMustafa Shukor, Matthieu Cord. [doi]
• Generalized Eigenvalue Problems with Generative PriorsZhaoqiang Liu, Wen Li, Junren Chen. [doi]
• Diffusion Tuning: Transferring Diffusion Models via Chain of ForgettingJincheng Zhong, Xingzhuo Guo, Jiaxiang Dong, Mingsheng Long. [doi]
• Partial Transportability for Domain GeneralizationKasra Jalaldoust, Alexis Bellot, Elias Bareinboim. [doi]
• Harmonizing Visual Text Comprehension and GenerationZhen Zhao, Jingqun Tang, Binghong Wu, Chunhui Lin, Shu Wei, Hao Liu, Xin Tan 0002, Zhizhong Zhang 0001, Can Huang, Yuan Xie 0006. [doi]
• Neuro-Symbolic Data Generation for Math ReasoningZenan Li, Zhi Zhou, Yuan Yao 0001, Xian Zhang, Yu-Feng Li, Chun Cao, Fan Yang, Xiaoxing Ma. [doi]
• Sketching for Distributed Deep Learning: A Sharper AnalysisMayank Shrivastava, Berivan Isik, Qiaobo Li, Sanmi Koyejo, Arindam Banerjee. [doi]
• Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration ModelsRegev Cohen, Idan Kligvasser, Ehud Rivlin, Daniel Freedman. [doi]
• Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context LengthXuezhe Ma, Xiaomeng Yang, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang 0108, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou. [doi]
• Robust Conformal Prediction Using Privileged InformationShai Feldman, Yaniv Romano. [doi]
• Identifiability Analysis of Linear ODE Systems with Hidden ConfoundersYuanyuan Wang, Biwei Huang, Wei Huang, Xi Geng, Mingming Gong. [doi]
• Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang, Fabian Isensee, Zifu Wang, Jieneng Chen, Yu-Cheng Chou, Yannick Kirchhoff, Maximilian R. Rokuss, Ziyan Huang, Jin Ye, Junjun He, Tassilo Wald, Constantin Ulrich, Michael Baumgartner 0001, Saikat Roy, Klaus H. Maier-Hein, Paul F. Jaeger, Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Yong Xia 0001, Zhaohu Xing, Lei Zhu, Yousef Sadegheih, Afshin Bozorgpour, Pratibha Kumari 0001, Reza Azad, Dorit Merhof, Pengcheng Shi, Ting Ma, Yuxin Du, Fan Bai 0008, Tiejun Huang 0001, Bo Zhao, Haonan Wang, Xiaomeng Li, Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej A. Mazurowski, Saumya Gupta, Linshan Wu, Jia-Xin Zhuang, Hao Chen, Holger Roth, Daguang Xu, Matthew B. Blaschko, Sergio Decherchi, Andrea Cavalli, Alan L. Yuille, Zongwei Zhou. [doi]
• Bayesian Adaptive Calibration and Optimal DesignRafael Oliveira 0001, Dino Sejdinovic, David Howard, Edwin V. Bonilla. [doi]
• Perplexity-aware Correction for Robust Alignment with Noisy PreferencesKeyi Kong, Xilie Xu, Di Wang 0015, Jingfeng Zhang, Mohan S. Kankanhalli. [doi]
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior ModelsHui-Po Wang, Mario Fritz. [doi]
• Learn more, but bother less: parameter efficient continual learningFuli Qiao, Mehrdad Mahdavi. [doi]
• Robot Policy Learning with Temporal Optimal Transport RewardYuwei Fu, Haichao Zhang, Di Wu, Wei Xu, Benoit Boulet. [doi]
• Is Score Matching Suitable for Estimating Point Processes?Haoqun Cao, Zizhuo Meng, Tianjun Ke, Feng Zhou. [doi]
• 2: Effective Sharpness Aware Minimization Requires Layerwise Perturbation ScalingMoritz Haas, Jin Xu, Volkan Cevher, Leena Chennuru Vankadara. [doi]
• VHELM: A Holistic Evaluation of Vision Language ModelsTony Lee, Haoqin Tu, Chi Heem Wong, Wenhao Zheng, Yiyang Zhou, Yifan Mai, Josselin Somerville Roberts, Michihiro Yasunaga, Huaxiu Yao, Cihang Xie, Percy Liang. [doi]
• Multivariate Probabilistic Time Series Forecasting with Correlated ErrorsVincent Zhihao Zheng, Lijun Sun. [doi]
• Trade-Offs of Diagonal Fisher Information Matrix EstimatorsAlexander Soen, Ke Sun 0001. [doi]
• Online Bayesian Persuasion Without a ClueFrancesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi 0001, Nicola Gatti 0001. [doi]
• UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN ManipulationHanzhang Zhou, Zijian Feng, Zixiao Zhu, Junlang Qian, Kezhi Mao. [doi]
• SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-TuningYexiao He, Ziyao Wang, Zheyu Shen, Guoheng Sun, Yucong Dai, Yongkai Wu, Hongyi Wang 0001, Ang Li 0005. [doi]
• Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic ModelsAviv Bick, Kevin Y. Li, Eric P. Xing, J. Zico Kolter, Albert Gu. [doi]
• Why are Visually-Grounded Language Models Bad at Image Classification?Yuhui Zhang, Alyssa Unell, Xiaohan Wang, Dhruba Ghosh, Yuchang Su, Ludwig Schmidt, Serena Yeung. [doi]
• Revisiting Few-Shot Object Detection with Vision-Language ModelsAnish Madan, Neehar Peri, Shu Kong, Deva Ramanan. [doi]
• On Tractable Φ-Equilibria in Non-Concave GamesYang Cai 0001, Constantinos Daskalakis, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng. [doi]
• Abductive Reasoning in Logical Credal NetworksRadu Marinescu 0002, Junkyu Lee 0001, Debarun Bhattacharjya, Fábio Gagliardi Cozman, Alexander G. Gray. [doi]
• Understanding Bias in Large-Scale Visual DatasetsBoya Zeng, Yida Yin, Zhuang Liu 0003. [doi]
• Multi-Agent Coordination via Multi-Level CommunicationGang Ding, Zeyuan Liu, Zhirui Fang, Kefan Su, Liwen Zhu 0003, Zongqing Lu. [doi]
• STONE: A Submodular Optimization Framework for Active 3D Object DetectionRuiyu Mao, Sarthak Kumar Maharana, Rishabh K. Iyer, Yunhui Guo. [doi]
• Shared Autonomy with IDA: Interventional Diffusion AssistanceBrandon McMahan, Zhenghao Mark Peng, Bolei Zhou, Jonathan C. Kao. [doi]
• Retrieval & Fine-Tuning for In-Context Tabular ModelsValentin Thomas, Junwei Ma, Rasa Hosseinzadeh, Keyvan Golestan, Guangwei Yu, Maksims Volkovs, Anthony L. Caterini. [doi]
• KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image SynthesisYoungwan Lee, KwanYong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang. [doi]
• Safety through feedback in Constrained RLShashank Reddy Chirra, Pradeep Varakantham, Praveen Paruchuri. [doi]
• TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic SceneSandika Biswas, Qianyi Wu, Biplab Banerjee, Hamid Rezatofighi. [doi]
• CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat IntelligenceMd Tanvirul Alam, Dipkamal Bhusal, Le-Nguyen, Nidhi Rastogi. [doi]
• CV-VAE: A Compatible Video VAE for Latent Generative Video ModelsSijie Zhao, Yong Zhang 0034, Xiaodong Cun, Shaoshu Yang, Muyao Niu, Xiaoyu Li, Wenbo Hu 0002, Ying Shan. [doi]
• How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear RegressionXingwu Chen, Lei Zhao, Difan Zou. [doi]
• Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field PerspectiveTakeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato. [doi]
• Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series ForecastingQingxiang Liu, Xu Liu, Chenghao Liu, Qingsong Wen, Yuxuan Liang. [doi]
• Empowering Active Learning for 3D Molecular Graphs with Geometric Graph IsomorphismRonast Subedi, Lu Wei, Wenhan Gao 0002, Shayok Chakraborty, Yi Liu. [doi]
• Testing Calibration in Nearly-Linear TimeLunjia Hu, Arun Jambulapati, Kevin Tian, Chutong Yang. [doi]
• Extensive-Form Game Solving via Blackwell Approachability on TreeplexesDarshan Chakrabarti, Julien Grand-Clément, Christian Kroer. [doi]
• Controlled maximal variability along with reliable performance in recurrent neural networksChiara Mastrogiuseppe, Rubén Moreno-Bote. [doi]
• UDON: Universal Dynamic Online distillatioN for generic image representationsNikolaos-Antonios Ypsilantis, Kaifeng Chen, André Araújo 0001, Ondrej Chum. [doi]
• Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted ImagesQi Song 0003, Ziyuan Luo, Ka-Chun Cheung, Simon See, Renjie Wan. [doi]
• Hierarchical Selective ClassificationShani Goren, Ido Galil, Ran El-Yaniv. [doi]
• SyncVIS: Synchronized Video Instance SegmentationRongkun Zheng, Lu Qi, Xi Chen 0072, Yi Wang 0074, Kun Wang, Yu Qiao 0001, Hengshuang Zhao. [doi]
• Optimal Rates for Vector-Valued Spectral Regularization Learning AlgorithmsDimitri Meunier, Zikai Shen, Mattes Mollenhauer, Arthur Gretton, Zhu Li. [doi]
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative ModelsZaitang Li, Pin-Yu Chen, Tsung-Yi Ho. [doi]
• A Label is Worth A Thousand Images in Dataset DistillationTian Qin, Zhiwei Deng, David Alvarez-Melis. [doi]
• Smoothed Online Classification can be Harder than Batch ClassificationVinod Raman, Unique Subedi, Ambuj Tewari. [doi]
• Accelerating Pre-training of Multimodal LLMs via Chain-of-SightZiyuan Huang, Kaixiang Ji, Biao Gong, Zhiwu Qing, Qinglong Zhang, Kecheng Zheng, Jian Wang, Jingdong Chen, Ming Yang. [doi]
• GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic EvaluationsJinhao Duan, Renming Zhang, James Diffenderfer, Bhavya Kailkhura, Lichao Sun 0001, Elias Stengel-Eskin, Mohit Bansal, Tianlong Chen, Kaidi Xu. [doi]
• HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image AnalysisGuillaume Jaume, Paul Doucet, Andrew H. Song, Ming-Yang Lu, Cristina Almagro-Pérez, Sophia J. Wagner, Anurag Vaidya, Richard J. Chen, Drew F. K. Williamson, Ahrong Kim, Faisal Mahmood. [doi]
• Group-wise oracle-efficient algorithms for online multi-group learningSamuel Deng, Jingwen Liu, Daniel J. Hsu. [doi]
• Interfacing Foundation Models' EmbeddingsXueyan Zou, Linjie Li, Jianfeng Wang, Jianwei Yang, Mingyu Ding, Junyi Wei, Zhengyuan Yang, Feng Li 0040, Hao Zhang 0097, Shilong Liu, Arul Aravinthan, Yong Jae Lee, Lijuan Wang. [doi]
• Visual Anchors Are Strong Information Aggregators For Multimodal Large Language ModelHaogeng Liu, Quanzeng You, Xiaotian Han, Yongfei Liu, Huaibo Huang, Ran He 0001, Hongxia Yang. [doi]
• GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AIPengcheng Chen, Jin Ye, Guoan Wang, Yanjun Li, Zhongying Deng, Wei Li 0044, Tianbin Li, Haodong Duan, Ziyan Huang, Yanzhou Su, Benyou Wang, Shaoting Zhang 0001, Bin Fu, Jianfei Cai 0001, Bohan Zhuang, Eric J. Seibel, Junjun He, Yu Qiao 0001. [doi]
• Improving Adaptivity via Over-Parameterization in Sequence ModelsYicheng Li, Qian Lin. [doi]
• GraphTrail: Translating GNN Predictions into Human-Interpretable Logical RulesBurouj Armgaan, Manthan Dalmia, Sourav Medya, Sayan Ranu. [doi]
• Language Generation in the LimitJon M. Kleinberg, Sendhil Mullainathan. [doi]
• AHA: Human-Assisted Out-of-Distribution Generalization and DetectionHaoyue Bai 0001, Jifan Zhang, Robert D. Nowak. [doi]
• Universal Rates of Empirical Risk MinimizationSteve Hanneke, Mingyue Xu. [doi]
• Large Pre-trained time series models for cross-domain Time series analysis tasksHarshavardhan Kamarthi, B. Aditya Prakash. [doi]
• Towards Understanding the Working Mechanism of Text-to-Image Diffusion ModelMingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li. [doi]
• Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNALifeng Qiao, Peng Ye, Yuchen Ren, Weiqiang Bai, Chaoqi Liang, Xinzhu Ma, Nanqing Dong, Wanli Ouyang. [doi]
• TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of SightHyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon, Kuk-Jin Yoon. [doi]
• Performative Control for Linear Dynamical SystemsSongfu Cai, Fei Han, Xuanyu Cao. [doi]
• Transformers Can Do Arithmetic with the Right EmbeddingsSean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Jonas Geiping, Avi Schwarzschild, Tom Goldstein. [doi]
• Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion ModelsLiulei Li, Wenguan Wang, Yi Yang 0001. [doi]
• Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language ModelsYuancheng Xu, Jiarui Yao, Manli Shu, Yanchao Sun, Zichu Wu, Ning Yu 0006, Tom Goldstein, Furong Huang. [doi]
• ZeroMark: Towards Dataset Ownership Verification without Disclosing WatermarkJunfeng Guo, Yiming Li, Ruibo Chen, Yihan Wu, Chenxi Liu, Heng Huang. [doi]
• Non-parametric classification via expand-and-sparsify representationKaushik Sinha. [doi]
• EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific EvaluationsJia Li 0011, Ge Li 0001, Xuanming Zhang, Yunfei Zhao, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li. [doi]
• Topological obstruction to the training of shallow ReLU neural networksMarco Nurisso, Pierrick Leroy, Francesco Vaccarino. [doi]
• Communication Efficient Distributed Training with Distributed LionBo Liu, Lemeng Wu, Lizhang Chen, Kaizhao Liang, Jiaxu Zhu, Chen Liang, Raghuraman Krishnamoorthi, Qiang Liu. [doi]
• Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingDavid Perera, Victor Letzelter, Théo Mariotte, Adrien Cortés, Mickaël Chen, Slim Essid, Gaël Richard. [doi]
• Wasserstein convergence of Cech persistence diagrams for samplings of submanifoldsCharles Arnal, David Cohen-Steiner, Vincent Divol. [doi]
• Task Me AnythingJieyu Zhang, WeiKai Huang, Zixian Ma, Oscar Michel, Dong He 0002, Tanmay Gupta, Wei-Chiu Ma, Ali Farhadi, Aniruddha Kembhavi, Ranjay Krishna. [doi]
• Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or MemorizingZhongwang Zhang, Pengxiao Lin, Zhiwei Wang, Yaoyu Zhang, Zhi-Qin John Xu. [doi]
• Single Image Reflection Separation via Dual-Stream Interactive TransformersQiming Hu, Hainuo Wang, Xiaojie Guo 0001. [doi]
• MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with VisualizationsYubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen 0001, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, Pan Zhang 0001, Liangming Pan, Yu-Gang Jiang 0001, Jiaqi Wang 0003, Yixin Cao 0002, Aixin Sun. [doi]
• Paralinguistics-Aware Speech-Empowered Large Language Models for Natural ConversationHeeseung Kim, Soonshin Seo, Kyeongseok Jeong, Ohsung Kwon, Soyoon Kim, Jungwhan Kim, Jaehong Lee, Eunwoo Song, Myungwoo Oh, Jung-Woo Ha, Sungroh Yoon, Kang Min Yoo. [doi]
• Searching for Efficient Linear Layers over a Continuous Space of Structured MatricesAndres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Charlie Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson. [doi]
• Return of Unconditional Generation: A Self-supervised Representation Generation MethodTianhong Li, Dina Katabi, Kaiming He. [doi]
• MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction ModelMinghua Liu, Chong Zeng 0001, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu 0016, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su 0001. [doi]
• AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural FieldsLouis Serrano, Thomas X. Wang, Etienne Le Naour, Jean-Noël Vittaut, Patrick Gallinari. [doi]
• Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse ExpertsZhe Zhao 0008, Haibin Wen, Zikang Wang, Pengkun Wang, Fanfu Wang, Song Lai, Qingfu Zhang 0001, Yang Wang 0015. [doi]
• SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a BenchmarkHyunjun Jung, Weihang Li, Shun-Cheng Wu, William Bittner, Nikolas Brasch, Jifei Song, Eduardo Pérez-Pellitero, Zhensong Zhang, Arthur Moreau, Nassir Navab, Benjamin Busam. [doi]
• Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation ModelsShenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng 0001. [doi]
• Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow PerspectiveZhichao Chen 0001, Haoxuan Li 0001, Fangyikang Wang, Odin Zhang, Hu Xu, Xiaoyu Jiang, Zhihuan Song, Hao Wang. [doi]
• Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement LearningRiccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli. [doi]
• GFT: Graph Foundation Model with Transferable Tree VocabularyZehong Wang, Zheyuan Zhang, Nitesh V. Chawla, Chuxu Zhang, Yanfang Ye 0002. [doi]
• BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network InferenceChangwoo Lee 0001, Soo Min Kwon, Qing Qu 0001, Hun-Seok Kim. [doi]
• Improved learning rates in multi-unit uniform price auctionsMarius Potfer, Dorian Baudry, Hugo Richard, Vianney Perchet, Cheng Wan. [doi]
• Stochastic contextual bandits with graph feedback: from independence number to MAS numberYuxiao Wen, Yanjun Han, Zhengyuan Zhou. [doi]
• Going Beyond Heuristics by Imposing Policy Improvement as a ConstraintChi-Chang Lee, Zhang-Wei Hong, Pulkit Agrawal 0001. [doi]
• Optimal Aggregation of Prediction Intervals under Unsupervised Domain ShiftJiawei Ge, Debarghya Mukherjee, Jianqing Fan. [doi]
• Multiple Physics Pretraining for Spatiotemporal Surrogate ModelsMichael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Siavash Golkar, Géraud Krawezik, François Lanusse, Mariel Pettee, Tiberiu Tesileanu, KyungHyun Cho, Shirley Ho. [doi]
• Navigating the Effect of Parametrization for Dimensionality ReductionHaiyang Huang 0003, Yingfan Wang, Cynthia Rudin. [doi]
• $\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network PotentialsKuzma Khrabrov, Anton Ber, Artem Tsypin, Konstantin Ushenin, Egor Rumiantsev, Alexander Telepov, Dmitry Protasov, Ilya Shenbin, Anton Alekseev 0001, Mikhail Shirokikh, Sergey I. Nikolenko, Elena Tutubalina, Artur Kadurin. [doi]
• Combining Statistical Depth and Fermat Distance for Uncertainty QuantificationHai-Vy Nguyen, Fabrice Gamboa, Reda Chhaibi, Sixin Zhang, Serge Gratton, Thierry Giaccone. [doi]
• LLMDFA: Analyzing Dataflow in Code with Large Language ModelsChengpeng Wang, Wuqi Zhang, Zian Su, Xiangzhe Xu, Xiaoheng Xie, Xiangyu Zhang 0001. [doi]
• In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents AlignmentDongting Hu, Huan Fu, Jiaxian Guo, Liuhua Peng, Tingjin Chu, Feng Liu 0003, Tongliang Liu, Mingming Gong. [doi]
• Towards Scalable and Stable Parallelization of Nonlinear RNNsXavier Gonzalez, Andrew Warrington, Jimmy T. H. Smith, Scott W. Linderman. [doi]
• Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand AvatarsXuan Huang, Hanhui Li, Wanquan Liu, Xiaodan Liang, Yiqiang Yan, Yuhao Cheng, Chenqiang Gao. [doi]
• AID: Attention Interpolation of Text-to-Image DiffusionQiyuan He, Jinghao Wang, Ziwei Liu 0002, Angela Yao. [doi]
• Alignment for HonestyYuqing Yang 0004, Ethan Chern, Xipeng Qiu, Graham Neubig, Pengfei Liu 0003. [doi]
• Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough SignalsChristian Holberg, Cristopher Salvi. [doi]
• SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLMMing Nie, Dan Ding, Chunwei Wang, Yuanfan Guo, Jianhua Han, Hang Xu, Li Zhang. [doi]
• Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike ResolutionYizi Zhang, Yanchen Wang, Donato Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake A. Richards, Renee Tung, Olivier Winter, International Brain Laboratory, Eva L. Dyer, Liam Paninski, Cole L. Hurwitz. [doi]
• The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate AlgorithmsElizabeth Collins-Woodfin, Inbar Seroussi, Begoña García Malaxechebarría, Andrew W. Mackenzie, Elliot Paquette, Courtney Paquette. [doi]
• VLKEB: A Large Vision-Language Model Knowledge Editing BenchmarkHan Huang, Haitian Zhong, Tao Yu, Qiang Liu 0006, Shu Wu, Liang Wang 0001, Tieniu Tan. [doi]
• Facilitating Multimodal Classification via Dynamically Learning Modality GapYang Yang 0074, Fengqiang Wan, Qing-Yuan Jiang, Yi Xu 0008. [doi]
• Multistep Distillation of Diffusion Models via Moment MatchingTim Salimans, Thomas Mensink, Jonathan Heek, Emiel Hoogeboom. [doi]
• Streaming Bayes GFlowNetsTiago da Silva, Daniel Augusto de Souza, Diego Mesquita. [doi]
• Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data AugmentationNing-Hsu (Albert) Wang, Yu-Lun Liu. [doi]
• On the Saturation Effects of Spectral Algorithms in Large DimensionsWeihao Lu 0002, Haobo Zhang 0004, Yicheng Li, Qian Lin. [doi]
• Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image ModelsMatthew Zheng, Enis Simsar, Hidir Yesiltepe, Federico Tombari, Joel Simon, Pinar Yanardag Delul. [doi]
• Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge DistillationYu-Liang Zhan, Zhong-Yi Lu, Hao Sun, Ze-Feng Gao. [doi]
• LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe AlignmentJuelin Zhu, Shen Yan, Long Wang, Shengyue Zhang, Yu Liu 0008, Maojun Zhang. [doi]
• Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan H. Kim, Stephen Fitz, Dan Hendrycks. [doi]
• Conformal Prediction for Class-wise Coverage via Augmented Label Rank CalibrationYuanjie Shi, Subhankar Ghosh, Taha Belkhouja, Jana Doppa, Yan Yan 0006. [doi]
• ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial OptimizationHuayang Huang, Yu Wu, Qian Wang. [doi]
• Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial ConstraintsMartino Bernasconi, Matteo Castiglioni, Andrea Celli, Federico Fusco. [doi]
• Shaping the distribution of neural responses with interneurons in a recurrent circuit modelDavid Lipshutz, Eero P. Simoncelli. [doi]
• Nuclear Fusion Diamond Polishing DatasetAntonios Alexos, Junze Liu, Shashank Galla, Sean Hayes, Kshitij Bhardwaj, Alexander Schwartz, Monika Biener, Pierre Baldi, Satish T. S. Bukkapatnam, Suhas Bhandarkar. [doi]
• How Does Variance Shape the Regret in Contextual Bandits?Zeyu Jia, Jian Qian, Alexander Rakhlin, Chen-Yu Wei. [doi]
• Graphcode: Learning from multiparameter persistent homology using graph neural networksFlorian Russold, Michael Kerber. [doi]
• LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light ScenesZefan Qu, Ke Xu 0010, Gerhard P. Hancke 0002, Rynson W. H. Lau. [doi]
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code AgentsNiels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev. [doi]
• FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality ReductionZiwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao. [doi]
• Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP IterationHongming Zhang 0003, Chenjun Xiao, Chao Gao, Han Wang, Bo Xu 0002, Martin Müller 0003. [doi]
• Image Reconstruction Via Autoencoding Sequential Deep Image PriorIsmail Alkhouri, Shijun Liang, Evan Bell, Qing Qu 0001, Rongrong Wang, Saiprasad Ravishankar. [doi]
• FedGTST: Boosting Global Transferability of Federated Models via Statistics TuningEvelyn Ma, Chao Pan 0003, S. Rasoul Etesami 0001, Han Zhao, Olgica Milenkovic. [doi]
• Representation Noising: A Defence Mechanism Against Harmful FinetuningDomenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Robie Gonzales, Carsten Maple, Subhabrata Majumdar, Hassan Sajjad 0001, Frank Rudzicz. [doi]
• Disentangling Linear Quadratic Control with Untrusted ML PredictionsTongxin Li, Hao Liu, Yisong Yue. [doi]
• Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label NoiseShuyao Li, Sushrut Karmalkar, Ilias Diakonikolas, Jelena Diakonikolas. [doi]
• GAVEL: Generating Games via Evolution and Language ModelsGraham Todd, Alexander Padula, Matthew Stephenson, Éric Piette, Dennis J. N. J. Soemers, Julian Togelius. [doi]
• GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution ShiftsDeyu Zou, Shikun Liu, Siqi Miao 0001, Victor Fung, Shiyu Chang, Pan Li 0005. [doi]
• Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience RegularizationHaoran Li 0010, Zhennan Jiang, Yuhui Chen, Dongbin Zhao. [doi]
• Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation PlatformsFan Yao, Yiming Liao, Jingzhou Liu, Shaoliang Nie, Qifan Wang, Haifeng Xu, Hongning Wang. [doi]
• CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsJiachen Li 0003, Xinyao Wang, Sijie Zhu, Chia-Wen Kuo, Lu Xu, Fan Chen, Jitesh Jain, Humphrey Shi, Longyin Wen. [doi]
• A Compositional Atlas for Algebraic CircuitsBenjie Wang 0001, Denis Deratani Mauá, Guy Van den Broeck, YooJung Choi 0001. [doi]
• Classic GNNs are Strong Baselines: Reassessing GNNs for Node ClassificationYuankai Luo, Lei Shi 0002, Xiao-Ming Wu 0003. [doi]
• Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component AnalysisRachel S. Y. Teo, Tan Nguyen. [doi]
• StackEval: Benchmarking LLMs in Coding AssistanceNidhish Shah, Zulkuf Genc, Dogu Araci. [doi]
• Unrolled denoising networks provably learn to perform optimal Bayesian inferenceAayush Karan, Kulin Shah, Sitan Chen, Yonina C. Eldar. [doi]
• Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional EncodingZhenyu Zhang 0015, Runjin Chen, Shiwei Liu 0003, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang. [doi]
• Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation ModelsYuchen Hu, Chen Chen, Chao-Han Yang, Chengwei Qin, Pin-Yu Chen, Engsiong Chng, Chao Zhang. [doi]
• Is Function Similarity Over-Engineered? Building a BenchmarkRebecca Saul, Chang Liu, Noah Fleischmann, Richard Zak, Kristopher K. Micinski, Edward Raff, James Holt. [doi]
• Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy ChurnHongyao Tang, Glen Berseth. [doi]
• No Regrets: Investigating and Improving Regret Approximations for Curriculum DiscoveryAlexander Rutherford, Michael Beukman, Timon Willi, Bruno Lacerda, Nick Hawes, Jakob N. Foerster. [doi]
• Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAMChenxin Li, Yuzhi Huang, Wuyang Li, Hengyu Liu 0007, Xinyu Liu 0001, Qing Xu, Zhen Chen 0013, Yue Huang 0001, Yixuan Yuan. [doi]
• Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task StructureHanseul Cho 0002, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta 0001, Chulhee Yun. [doi]
• Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and BenchmarksShuai He, Shuntian Zheng, Anlong Ming, Banyu Wu, Huadong Ma. [doi]
• 2D-OOB: Attributing Data Contribution Through Joint Valuation FrameworkYifan Sun, Jingyan Shen, Yongchan Kwon. [doi]
• Implicitly Guided Design with PropEn: Match your Data to Follow the GradientNatasa Tagasovska, Vladimir Gligorijevic, KyungHyun Cho, Andreas Loukas. [doi]
• A Metalearned Neural Circuit for Nonparametric Bayesian InferenceJake Snell, Gianluca M. Bencomo, Tom Griffiths 0001. [doi]
• Universal Online Convex Optimization with 1 Projection per RoundWenhao Yang, Yibo Wang 0005, Peng Zhao 0006, Lijun Zhang 0005. [doi]
• Linear Uncertainty Quantification of Graphical Model InferenceChenghua Guo, Han Yu, Jiaxin Liu, Chao Chen, Qi Li, Sihong Xie, Xi Zhang. [doi]
• Bridge-IF: Learning Inverse Protein Folding with Markov BridgesYiheng Zhu, Jialu Wu, Qiuyi Li, Jiahuan Yan, Mingze Yin, Wei Wu, Mingyang Li, Jieping Ye, Zheng Wang, Jian Wu. [doi]
• Scale-invariant Optimal Sampling for Rare-events Data and Sparse ModelsJing Wang, HaiYing Wang 0004, Hao Zhang. [doi]
• SpeAr: A Spectral Approach for Zero-Shot Node ClassificationTing Guo, Da Wang, Jiye Liang, Kaihan Zhang, Jianchao Zeng 0001. [doi]
• Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts ConversionFilip Szatkowski, Bartosz Wójcik, Mikolaj Piórczynski, Simone Scardapane. [doi]
• Matryoshka Query Transformer for Large Vision-Language ModelsWenbo Hu 0006, Zi-Yi Dou, Liunian Harold Li, Amita Kamath, Nanyun Peng 0001, Kai-Wei Chang. [doi]
• Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement LearningHao Ma, Tianyi Hu, Zhiqiang Pu, Boyin Liu, Xiaolin Ai, Yanyan Liang 0001, Min Chen. [doi]
• The Surprising Effectiveness of SP Voting with Partial PreferencesHadi Hosseini, Debmalya Mandal, Amrit Puhan. [doi]
• Zipfian WhiteningSho Yokoi, Han Bao 0002, Hiroto Kurita, Hidetoshi Shimodaira. [doi]
• EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose EstimationXinyi Yu, Haonan Jiang, Li Zhang, Lin Yuanbo Wu, Linlin Ou, Liu Liu. [doi]
• DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion ModelsZhengyang Yu, Zhaoyuan Yang, Jing Zhang. [doi]
• SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and RolloutChiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis, Xiukun Huang, Hong Jeon, Sakshum Kulshrestha, John Lambert, Shuangyu Li, Xuanyu Zhou, Carlos Fuertes, Chang Yuan, Mingxing Tan, Yin Zhou, Dragomir Anguelov. [doi]
• Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled TransientsXingyu Cui, Huanjing Yue, Song Li, Xiangjun Yin, Yusen Hou, Yun Meng, Kai Zou, Xiaolong Hu, Jingyu Yang. [doi]
• Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton ApproximationsArtem Agafonov, Petr Ostroukhov, Roman Mozhaev, Konstantin Yakovlev, Eduard Gorbunov, Martin Takác, Alexander V. Gasnikov, Dmitry Kamzolov. [doi]
• Beyond the Doors of Perception: Vision Transformers Represent Relations Between ObjectsMichael A. Lepori, Alexa R. Tartaglini, Wai Keen Vong, Thomas Serre, Brenden M. Lake, Ellie Pavlick. [doi]
• Easy Regional Contrastive Learning of Expressive Fashion RepresentationsDaiqing Qi, Handong Zhao, Sheng Li 0001. [doi]
• TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency ModelsKiwoong Yoo, Owen Oertell, Junhyun Lee, Sanghoon Lee, Jaewoo Kang. [doi]
• Predicting Future Actions of Reinforcement Learning AgentsStephen Chung, Scott Niekum, David Krueger 0001. [doi]
• The GAN is dead; long live the GAN! A Modern GAN BaselineNick Huang, Aaron Gokaslan, Volodymyr Kuleshov, James Tompkin 0001. [doi]
• DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback AlignmentGongpei Zhao, Tao Wang 0011, Congyan Lang, Yi Jin 0001, Yidong Li, Haibin Ling. [doi]
• Principled Bayesian Optimization in Collaboration with Human ExpertsWenjie Xu, Masaki Adachi, Colin N. Jones, Michael A. Osborne. [doi]
• Thought of Search: Planning with Language Models Through The Lens of EfficiencyMichael Katz 0001, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi. [doi]
• Lookback Prophet InequalitiesZiyad Benomar, Dorian Baudry, Vianney Perchet. [doi]
• FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference ImagesZheng Yu, Yaohua Wang, Siying Cui, Aixi Zhang, Wei-Long Zheng, Senzhang Wang. [doi]
• Sample Complexity of Interventional Causal Representation LearningEmre Acartürk, Burak Varici, Karthikeyan Shanmugam, Ali Tajer. [doi]
• Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image GenerationJunlei Zhou, Jiashi Gao, Xiangyu Zhao 0001, Xin Yao 0001, Xuetao Wei. [doi]
• Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space ModelYuheng Shi, Minjing Dong, Chang Xu. [doi]
• Unscrambling disease progression at scale: fast inference of event permutations with optimal transportPeter A. Wijeratne, Daniel C. Alexander. [doi]
• GUIDE: Real-Time Human-Shaped AgentsLingyu Zhang, Zhengran Ji, Nicholas R. Waytowich, Boyuan Chen 0001. [doi]
• ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language ModelYiming Sun, Fan Yu, Shaoxiang Chen, Yu Zhang, Junwei Huang, Yang Li, Chenhui Li, Changbo Wang. [doi]
• Private Online Learning via Lazy AlgorithmsHilal Asi, Tomer Koren, Daogao Liu, Kunal Talwar. [doi]
• Progressive Entropic Optimal Transport SolversParnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi. [doi]
• Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward LayersXiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre. [doi]
• Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition TimeZixiang Chen, Huizhuo Yuan, Yongqian Li, Yiwen Kou, Junkai Zhang, Quanquan Gu. [doi]
• HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language ModelsRhea Sukthanker, Arber Zela, Benedikt Staffler, Aaron Klein, Lennart Purucker, Jörg K. H. Franke, Frank Hutter. [doi]
• RTify: Aligning Deep Neural Networks with Human Behavioral DecisionsYu-Ang Cheng, Ivan F. Rodriguez Rodriguez, Sixuan Chen, Kohitij Kar, Takeo Watanabe, Thomas Serre. [doi]
• BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopesHemal Naik, Junran Yang, Dipin Das, Margaret Crofoot, Akanksha Rathore, Vivek Hari Sridhar. [doi]
• Improved Guarantees for Fully Dynamic k-Center Clustering with Outliers in General Metric SpacesLeyla Biabani, Annika Hennes, Denise La Gordt Dillie, Morteza Monemizadeh, Melanie Schmidt 0001. [doi]
• A Framework for Bilevel Optimization on Riemannian ManifoldsAndi Han, Bamdev Mishra, Pratik Kumar Jawanpuria, Akiko Takeda. [doi]
• Coded Computing for Resilient Distributed Computing: A Learning-Theoretic FrameworkParsa Moradi, Behrooz Tahmasebi, Mohammad Ali Maddah-Ali. [doi]
• VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language TasksJiannan Wu, Muyan Zhong, Sen Xing, Zeqiang Lai, Zhaoyang Liu 0001, Zhe Chen 0017, Wenhai Wang, Xizhou Zhu, Lewei Lu, Tong Lu, Ping Luo 0002, Yu Qiao, Jifeng Dai. [doi]
• A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual GenerationGwanghyun Kim, Alonso-Martinez, Yu-Chuan Su, Brendan Jou, José Lezama, Agrim Gupta, Lijun Yu, Lu Jiang 0004, Aren Jansen, Jacob Walker, Krishna Somandepalli. [doi]
• NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network SimulationMomin Haider, Ming Yin, Menglei Zhang, Arpit Gupta, Jing Zhu, Yu-Xiang Wang. [doi]
• RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural ModelingTianhang Wang, Fan Lu 0001, Zehan Zheng, Zhijun Li 0001, Guang Chen 0001, Changjun Jiang. [doi]
• Superposed Decoding: Multiple Generations from a Single Autoregressive Inference PassEthan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati. [doi]
• PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for ManipulationFei Ni 0001, Jianye Hao, Shiguang Wu 0001, Longxin Kou, Yifu Yuan, Zibin Dong, Jinyi Liu 0002, Mingzhi Li, Yuzheng Zhuang, Yan Zheng 0002. [doi]
• Compact Proofs of Model Performance via Mechanistic InterpretabilityJason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan. [doi]
• Recurrent Reinforcement Learning with MemoroidsSteven D. Morad, Chris Lu 0001, Ryan Kortvelesy, Stephan Liwicki, Jakob Foerster, Amanda Prorok. [doi]
• Approximately Pareto-optimal Solutions for Bi-Objective k-ClusteringAnna Arutyunova, Jan Eube, Heiko Röglin, Melanie Schmidt 0001, Sarah Sturm, Julian Wargalla. [doi]
• Dendritic Integration Inspired Artificial Neural Networks Capture Data CorrelationChongming Liu, Jingyang Ma, Songting Li, Douglas Zhou. [doi]
• Is Your HD Map Constructor Reliable under Sensor Corruptions?Xiaoshuai Hao, Mengchuan Wei, Yifan Yang, Haimei Zhao, Hui Zhang 0093, Yi Zhou 0020, Qiang Wang, Weiming Li, Lingdong Kong, Jing Zhang 0037. [doi]
• Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language ModelsChengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Yichen Wang, Chen Liu, Yu Lan, Chao Shen. [doi]
• An Accelerated Gradient Method for Convex Smooth Simple Bilevel OptimizationJincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari. [doi]
• UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with ReflectionsFangjinhua Wang, Marie-Julie Rakotosaona, Michael Niemeyer, Richard Szeliski, Marc Pollefeys, Federico Tombari. [doi]
• CableInspect-AD: An Expert-Annotated Anomaly Detection DatasetAkshatha Arodi, Margaux Luck, Jean-Luc Bedwani, Aldo Zaimi, Ge Li, Nicolas Pouliot, Julien Beaudry, Gaétan Marceau-Caron. [doi]
• Benchmarking Complex Instruction-Following with Multiple Constraints CompositionBosi Wen, Pei Ke, Xiaotao Gu, Lindong Wu, Hao Huang, Jinfeng Zhou, Wenchuang Li, Binxin Hu, Wendy Gao, Jiaxing Xu, Yiming Liu, Jie Tang, Hongning Wang, Minlie Huang. [doi]
• Stealth edits to large language modelsOliver J. Sutton, Qinghua Zhou, Wei Wang 0357, Desmond J. Higham, Alexander N. Gorban, Alexander Bastounis, Ivan Tyukin. [doi]
• IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet VideosYunong Liu, Cristóbal Eyzaguirre, Manling Li, Shubh Khanna, Juan Carlos Niebles, Vineeth Ravi, Saumitra Mishra, Weiyu Liu, Jiajun Wu 0001. [doi]
• SVFT: Parameter-Efficient Fine-Tuning with Singular VectorsVijay Lingam, Atula Neerkaje, Aditya Vavre, Aneesh Shetty, Gautham Krishna Gudur, Joydeep Ghosh, Eunsol Choi, Alex Dimakis, Aleksandar Bojchevski, Sujay Sanghavi. [doi]
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot ExecutionYang Yue, Yulin Wang, Bingyi Kang, Yizeng Han, Shenzhi Wang, Shiji Song, Jiashi Feng, Gao Huang 0001. [doi]
• Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language ModelsZiyi Zhou, Xinwei Guo, Jiashi Gao, Xiangyu Zhao 0001, Shiyao Zhang, Xin Yao 0001, Xuetao Wei. [doi]
• KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled QuantizationTianyi Zhang 0011, Jonah Yi, Zhaozhuo Xu, Anshumali Shrivastava. [doi]
• The Impact of Geometric Complexity on Neural Collapse in Transfer LearningMichael Munn, Benoit Dherin, Javier Gonzalvo. [doi]
• Robust group and simultaneous inferences for high-dimensional single index modelWeiChao Yang, Hongwei Shi, Xu Guo, Changliang Zou. [doi]
• MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution ShiftsRenchunzi Xie, Ambroise Odonnat, Vasilii Feofanov, Weijian Deng, Jianfeng Zhang, Bo An 0001. [doi]
• MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence ModelsZichun Yu, Spandan Das, Chenyan Xiong. [doi]
• CriticEval: Evaluating Large-scale Language Model as CriticTian Lan 0003, Wenwei Zhang, Chen Xu, Heyan Huang, Dahua Lin, Kai Chen, Xian-Ling Mao. [doi]
• Robust Prompt Optimization for Defending Language Models Against Jailbreaking AttacksAndy Zhou, Bo Li, Haohan Wang. [doi]
• AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database QueriesIrina Saparina, Mirella Lapata. [doi]
• From Causal to Concept-Based Representation LearningGoutham Rajendran, Simon Buchholz, Bryon Aragam, Bernhard Schölkopf, Pradeep Ravikumar. [doi]
• How Far Can Transformers Reason? The Globality Barrier and Inductive ScratchpadEmmanuel Abbe, Samy Bengio, Aryo Lotfi, Colin Sandon, Omid Saremi. [doi]
• LeDex: Training LLMs to Better Self-Debug and Explain CodeNan Jiang 0012, Xiaopeng Li 0002, Shiqi Wang 0002, Qiang Zhou, Soneya Binta Hossain, Baishakhi Ray, Varun Kumar, Xiaofei Ma 0001, Anoop Deoras. [doi]
• Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based DiscriminationShelly Golan, Roy Ganz, Michael Elad. [doi]
• Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion ModelsRuofeng Yang, Zhijie Wang, Bo Jiang, Shuai Li. [doi]
• Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion ModellingGrigory Bartosh, Dmitry P. Vetrov, Christian Andersson Naesseth. [doi]
• Adaptive and Optimal Second-order Optimistic Methods for Minimax OptimizationRuichen Jiang, Ali Kavis, Qiujiang Jin, Sujay Sanghavi, Aryan Mokhtari. [doi]
• Global Convergence in Training Large-Scale TransformersCheng Gao, Yuan Cao, Zihao Li, Yihan He, Mengdi Wang, Han Liu, Jason M. Klusowski, Jianqing Fan. [doi]
• Decoupled Kullback-Leibler Divergence LossJiequan Cui, Zhuotao Tian, Zhisheng Zhong, Xiaojuan Qi 0001, Bei Yu 0001, Hanwang Zhang. [doi]
• Improving Neural Network Surface Processing with Principal CurvaturesJosquin Harrison, James Benn, Maxime Sermesant. [doi]
• Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal LikelihoodRayen Dhahri, Alexander Immer, Bertrand Charpentier, Stephan Günnemann, Vincent Fortuin. [doi]
• An effective framework for estimating individualized treatment rulesJoowon Lee, Jared D. Huling, Guanhua Chen. [doi]
• Faster Algorithms for User-Level Private Stochastic Convex OptimizationAndrew Lowy, Daogao Liu, Hilal Asi. [doi]
• Generalizable Person Re-identification via Balancing Alignment and UniformityYoonki Cho, Jaeyoon Kim, Woo-Jae Kim, Junsik Jung, Sung-Eui Yoon. [doi]
• SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike StreamsKang Chen, Shiyan Chen, Jiyuan Zhang, Baoyue Zhang, Yajing Zheng, Tiejun Huang 0001, Zhaofei Yu. [doi]
• Topic-Conversation Relevance (TCR) Dataset and BenchmarksYaran Fan, Jamie Pool, Senja Filipi, Ross Cutler. [doi]
• Model Fusion through Bayesian Optimization in Language Model Fine-TuningChaeyun Jang, Hyungi Lee, Jungtaek Kim, Juho Lee. [doi]
• Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformersYibo Jiang, Goutham Rajendran, Pradeep Ravikumar, Bryon Aragam. [doi]
• UniIF: Unified Molecule Inverse FoldingZhangyang Gao, Jue Wang 0004, Cheng Tan 0012, Lirong Wu, Yufei Huang 0002, Siyuan Li 0002, Zhirui Ye, Stan Z. Li. [doi]
• Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate ShiftJiayun Wu, Jiashuo Liu, Peng Cui, Steven Wu 0001. [doi]
• MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMsJihyung Kil, Zheda Mai, Justin Lee, Arpita Chowdhury, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Wei-Lun Chao. [doi]
• T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative ModelsYibo Miao, Yifan Zhu, Lijia Yu, Jun Zhu 0001, Xiao-Shan Gao, Yinpeng Dong. [doi]
• MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank ExpertsJie Zhu, Yixiong Chen, Mingyu Ding, Ping Luo 0002, Leye Wang, Jingdong Wang 0001. [doi]
• Context and Geometry Aware Voxel Transformer for Semantic Scene CompletionZhu Yu 0001, Runmin Zhang, Jiacheng Ying, Junchen Yu, Xiaohai Hu, Lun Luo, Si-Yuan Cao, Hui-Liang Shen. [doi]
• Multimodal Large Language Models Make Text-to-Image Generative Models Align BetterXun Wu, Shaohan Huang, Guolong Wang, Jing Xiong, Furu Wei. [doi]
• EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI DetectionQinqian Lei, Bo Wang 0019, Robby T. Tan. [doi]
• Action Imitation in Common Action Space for Customized Action Image SynthesisWang Lin, Jingyuan Chen, Jiaxin Shi, Zirun Guo, Yichen Zhu, Zehan Wang 0001, Tao Jin 0004, Zhou Zhao, Fei Wu 0001, Shuicheng Yan, Hanwang Zhang. [doi]
• Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert KnowledgeHeewoong Noh, Namkyeong Lee, Gyoung S. Na, Chanyoung Park 0001. [doi]
• START: A Generalized State Space Model with Saliency-Driven Token-Aware TransformationJintao Guo, Lei Qi 0001, Yinghuan Shi, Yang Gao 0001. [doi]
• ActionAtlas: A VideoQA Benchmark for Domain-specialized Action RecognitionMohammadreza Salehi, Jae Sung Park, Aditya Kusupati, Ranjay Krishna, Yejin Choi 0001, Hanna Hajishirzi, Ali Farhadi. [doi]
• Divergences between Language Models and Human BrainsYuchen Zhou, Emmy Liu, Graham Neubig, Michael J. Tarr, Leila Wehbe. [doi]
• Dual-Personalizing Adapter for Federated Foundation ModelsYiyuan Yang, Guodong Long, Tao Shen 0001, Jing Jiang 0002, Michael Blumenstein. [doi]
• VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector BanksYang Li 0146, Shaobo Han, Jonathan Shihao Ji. [doi]
• ProG: A Graph Prompt Learning BenchmarkChenyi Zi, Haihong Zhao, Xiangguo Sun, Yiqing Lin, Hong Cheng 0001, Jia Li 0009. [doi]
• HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian SplattingQiankun Gao, Jiarui Meng, Chengxiang Wen, Jie Chen, Jian Zhang. [doi]
• Deep Learning in Medical Image Registration: Magic or Mirage?Rohit Jena, Deeksha Sethi, Pratik Chaudhari, James C. Gee. [doi]
• The Best of Both Worlds: On the Dilemma of Out-of-distribution DetectionQingyang Zhang, Qiuxuan Feng, Joey Tianyi Zhou, Yatao Bian, Qinghua Hu, Changqing Zhang. [doi]
• Classifier-guided Gradient Modulation for Enhanced Multimodal LearningZirun Guo, Tao Jin, Jingyuan Chen, Zhou Zhao. [doi]
• Ad Auctions for LLMs via Retrieval Augmented GenerationMohammadTaghi Hajiaghayi, Sébastien Lahaie, Keivan Rezaei, Suho Shin. [doi]
• SPRINQL: Sub-optimal Demonstrations driven Offline Imitation LearningHuy Hoang, Tien Mai, Pradeep Varakantham. [doi]
• IR-CM: The Fast and General-purpose Image Restoration Method Based on Consistency ModelXiaoxuan Gong, Jie Ma. [doi]
• Vript: A Video Is Worth Thousands of WordsDongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, Hai Zhao 0001. [doi]
• Prototypical Hash Encoding for On-the-Fly Fine-Grained Category DiscoveryHaiyang Zheng, Nan Pu, Wenjing Li 0005, Nicu Sebe, Zhun Zhong. [doi]
• Neural Collapse To Multiple Centers For Imbalanced DataHongRen Yan, Yuhua Qian, Furong Peng, Jiachen Luo, Zheqing Zhu, Feijiang Li. [doi]
• A Topology-aware Graph Coarsening Framework for Continual Graph LearningXiaoxue Han, Zhuo Feng, Yue Ning 0001. [doi]
• Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement LearningYuanlin Duan, Guofeng Cui, He Zhu 0001. [doi]
• Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear AttentionPhilipp Froehlich, Heinz Koeppl. [doi]
• CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor SearchMing Yang, Yuzheng Cai, Weiguo Zheng. [doi]
• StepbaQ: Stepping backward as Correction for Quantized Diffusion ModelsYi-Chung Chen, Zhi-Kai Huang, Jing-Ren Chen. [doi]
• Learning Optimal Tax Design in Nonatomic Congestion GamesQiwen Cui, Maryam Fazel, Simon S. Du. [doi]
• Particle Semi-Implicit Variational InferenceJen Ning Lim, Adam M. Johansen. [doi]
• Generative Modelling of Structurally Constrained GraphsManuel Madeira, Clément Vignac, Dorina Thanou, Pascal Frossard. [doi]
• Generalization Analysis for Label-Specific Representation LearningYi-Fan Zhang, Min-Ling Zhang. [doi]
• 2DQuant: Low-bit Post-Training Quantization for Image Super-ResolutionKai Liu, Haotong Qin, Yong Guo, Xin Yuan 0002, Linghe Kong, Guihai Chen, Yulun Zhang 0001. [doi]
• Fairness-Aware Estimation of Graphical ModelsZhuoping Zhou, Davoud Ataee Tarzanagh, Bojian Hou, Qi Long, Li Shen 0001. [doi]
• RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable GuaranteesXun Xian, Ganghua Wang, Xuan Bi, Jayanth Srinivasa, Ashish Kundu, Mingyi Hong 0001, Jie Ding 0002. [doi]
• MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditionsFelix Fent, Fabian Kuttenreich, Florian Ruch, Farija Rizwin, Stefan Juergens, Lorenz Lechermann, Christian Nissler, Andrea Perl, Ulrich Voll, Min Yan, Markus Lienkamp. [doi]
• ReXTime: A Benchmark Suite for Reasoning-Across-Time in VideosJr-Jen Chen, Yu-Chien Liao, Hsi-Che Lin, Yu-Chu Yu, Yen-Chun Chen 0001, Yu-Chiang Frank Wang. [doi]
• Vivid-ZOO: Multi-View Video Generation with Diffusion ModelBing Li, Cheng Zheng, Wenxuan Zhu, Jinjie Mai, Biao Zhang 0005, Peter Wonka, Bernard Ghanem. [doi]
• Physically Compatible 3D Object Modeling from a Single ImageMinghao Guo, Bohan Wang, Pingchuan Ma 0002, Tianyuan Zhang, Crystal Elaine Owens, Chuang Gan, Josh Tenenbaum 0001, Kaiming He, Wojciech Matusik. [doi]
• Cross-model Control: Improving Multiple Large Language Models in One-time TrainingJiayi Wu, Hao Sun 0015, Hengyi Cai, Lixin Su, Shuaiqiang Wang, Dawei Yin, Xiang Li 0067, Ming Gao 0001. [doi]
• ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language ModelsXiang Meng, Kayhan Behdin, Haoyue Wang, Rahul Mazumder. [doi]
• DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed GraphsJiasheng Zhang, Jialin Chen, Menglin Yang 0004, Aosong Feng, Shuang Liang 0002, Jie Shao 0001, Rex Ying. [doi]
• Consistency Models for Scalable and Fast Simulation-Based InferenceMarvin Schmitt, Valentin Pratz, Ullrich Köthe, Paul-Christian Bürkner, Stefan T. Radev. [doi]
• Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object DetectionChaoda Zheng, Feng Wang 0018, Naiyan Wang, Shuguang Cui, Zhen Li 0026. [doi]
• Many-Shot In-Context LearningRishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie C. Y. Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D. Co-Reyes, Eric Chu, Feryal M. P. Behbahani, Aleksandra Faust, Hugo Larochelle. [doi]
• Mixture of Demonstrations for In-Context LearningSong Wang, Zihan Chen 0002, Chengshuai Shi, Cong Shen, Jundong Li. [doi]
• Fundamental Convergence Analysis of Sharpness-Aware MinimizationPham Khanh, Hoang-Chau Luong, Boris S. Mordukhovich, Dat Tran. [doi]
• Efficient Contextual LLM Cascades through Budget-Constrained Policy LearningXuechen Zhang 0002, Zijian Huang 0015, Ege Onur Taga, Carlee Joe-Wong, Samet Oymak, Jiasi Chen. [doi]
• Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision TransformersKai Yan, Alexander G. Schwing, Yu-Xiong Wang. [doi]
• SafeWorld: Geo-Diverse Safety AlignmentDa Yin, Haoyi Qiu, Kung-Hsiang Huang, Kai-Wei Chang, Nanyun Peng 0001. [doi]
• ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token IdentificationYefei He, Luoming Zhang, Weijia Wu 0001, Jing Liu 0048, Hong Zhou, Bohan Zhuang. [doi]
• Meteor: Mamba-based Traversal of Rationale for Large Language and Vision ModelsByung kwan Lee, Chae Won Kim, Beomchan Park, Yong Man Ro. [doi]
• Multi-Head Mixture-of-ExpertsXun Wu, Shaohan Huang, Wenhui Wang 0003, Shuming Ma, Li Dong 0004, Furu Wei. [doi]
• Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision ProcessesAsaf Cassel, Aviv Rosenberg 0002. [doi]
• OnlineTAS: An Online Baseline for Temporal Action SegmentationQing Zhong, Guodong Ding, Angela Yao. [doi]
• HGDL: Heterogeneous Graph Label Distribution LearningYufei Jin, Heng Lian, Yi He 0007, Xingquan Zhu 0001. [doi]
• VisMin: Visual Minimal-Change UnderstandingRabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal. [doi]
• Optimal Flow Matching: Learning Straight Trajectories in Just One StepNikita Kornilov, Petr Mokrov, Alexander V. Gasnikov, Alexander Korotin. [doi]
• Expressive Gaussian Human Avatars from Monocular RGB VideoHezhen Hu, Zhiwen Fan, Tianhao Wu, Yihan Xi, Seoyoung Lee, Georgios Pavlakos, Zhangyang Wang. [doi]
• Towards training digitally-tied analog blocks via hybrid gradient computationTimothy Nest, Maxence Ernoult. [doi]
• AUCSeg: AUC-oriented Pixel-level Long-tail Semantic SegmentationBoyu Han, Qianqian Xu, Zhiyong Yang 0001, Shilong Bao, Peisong Wen, Yangbangyan Jiang, Qingming Huang. [doi]
• Efficient Availability Attacks against Supervised and Contrastive Learning SimultaneouslyYihan Wang, Yifan Zhu, Xiao-Shan Gao. [doi]
• Geometric Exploitation for Indoor Panoramic Semantic SegmentationDinh Duc Cao, Seok-Joon Kim, Kyusung Cho. [doi]
• Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression GenerationYaoyuan Liang, Zhuojun Cai, Jian Xu, Guanbo Huang, Yiran Wang, Xiao Liang, Jiahao Liu, Ziran Li, Jingang Wang, Shao-Lun Huang. [doi]
• Group and Shuffle: Efficient Structured Orthogonal ParametrizationMikhail Gorbunov, Nikolay Yudin, Vera Soboleva, Aibek Alanov, Alexey Naumov, Maxim Rakhuba. [doi]
• p Perturbations for Universal RobustnessEnyi Jiang, Gagandeep Singh. [doi]
• REDUCR: Robust Data Downsampling using Class Priority ReweightingWilliam Bankes, George Hughes, Ilija Bogunovic, Zi Wang. [doi]
• Visual Pinwheel Centers Act as Geometric Saliency DetectorsHaixin Zhong, Mingyi Huang, Wei Dai, Haoyu Wang, Anna Roe, Yuguo Yu. [doi]
• Pre-training Differentially Private Models with Limited Public DataZhiqi Bu, Xinwei Zhang 0001, Sheng Zha, Mingyi Hong 0001, George Karypis. [doi]
• Chain-of-Thought Reasoning Without PromptingXuezhi Wang 0002, Denny Zhou. [doi]
• Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium ModelsZun Wang, Chang Liu, Nianlong Zou, He Zhang, Xinran Wei, Lin Huang, Lijun Wu, Bin Shao. [doi]
• Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiTLe Zhuo, Ruoyi Du, Han Xiao, Yangguang Li, Dongyang Liu, Rongjie Huang, Wenze Liu, Xiangyang Zhu, Fu-Yun Wang, Zhanyu Ma, Xu Luo, Zehan Wang 0001, Kaipeng Zhang, Lirui Zhao, Si Liu 0001, Xiangyu Yue 0001, Wanli Ouyang, Yu Qiao 0001, Hongsheng Li 0001, Peng Gao 0007. [doi]
• Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and ModulationYinghao Wu, Chaoran Wang, Lu Yin, Shihui Guo, Yipeng Qin. [doi]
• Optimal deep learning of holomorphic operators between Banach spacesBen Adcock, Nick C. Dexter, Sebastian Moraga Scheuermann. [doi]
• KptLLM: Unveiling the Power of Large Language Model for Keypoint ComprehensionJie Yang, Wang Zeng, Sheng Jin 0007, Lumin Xu, Wentao Liu 0002, Chen Qian 0006, Ruimao Zhang. [doi]
• Even Sparser Graph TransformersHamed Shirzad, Honghao Lin, Balaji Venkatachalam, Ameya Velingker, David P. Woodruff, Danica J. Sutherland. [doi]
• Revive Re-weighting in Imbalanced Learning by Density Ratio EstimationJiaan Luo, Feng Hong 0004, Jiangchao Yao, Bo Han 0003, Ya Zhang 0002, Yanfeng Wang 0001. [doi]
• $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose EstimationWeiquan Wang, Jun Xiao 0001, Chunping Wang, Wei Liu, Zhao Wang, Long Chen. [doi]
• In-Context Learning with Representations: Contextual Generalization of Trained TransformersTong Yang, Yu Huang 0023, Yingbin Liang, Yuejie Chi. [doi]
• DevBench: A multimodal developmental benchmark for language learningAlvin W. M. Tan, Chunhua Yu,