Table of Contents

• Optimizing Watermarks for Large Language ModelsBram Wouters. [doi]
• Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-CriticTianying Ji, Yu Luo, Fuchun Sun 0001, Xianyuan Zhan, Jianwei Zhang 0001, Huazhe Xu. [doi]
• Enhancing Implicit Shape Generators Using Topological RegularizationsLiyan Chen, Yan Zheng, Yang Li, Lohit Anirudh Jagarapu, Haoxiang Li, Hao Kang, Gang Hua 0001, Qixing Huang. [doi]
• ODIM: Outlier Detection via Likelihood of Under-Fitted Generative ModelsDongha Kim, Jaesung Hwang, Jongjin Lee, Kunwoong Kim, Yongdai Kim. [doi]
• SCoRe: Submodular Combinatorial Representation LearningAnay Majee, Suraj Kothawade, KrishnaTeja Killamsetty, Rishabh K. Iyer. [doi]
• An Embodied Generalist Agent in 3D WorldJiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li 0003, Song Chun Zhu, Baoxiong Jia, Siyuan Huang 0001. [doi]
• Navigating Scaling Laws: Compute Optimality in Adaptive Model TrainingSotiris Anagnostidis, Gregor Bachmann, Imanol Schlag, Thomas Hofmann. [doi]
• Smooth Tchebycheff Scalarization for Multi-Objective OptimizationXi Lin 0001, Xiaoyuan Zhang, Zhiyuan Yang 0003, Fei Liu 0044, Zhenkun Wang, Qingfu Zhang 0001. [doi]
• Position: Amazing Things Come From Having Many Good ModelsCynthia Rudin, Chudi Zhong, Lesia Semenova, Margo I. Seltzer, Ronald Parr, Jiachang Liu 0001, Srikar Katta, Jon Donnelly, Harry Chen, Zachery Boner. [doi]
• InfoNet: Neural Estimation of Mutual Information without Test-Time OptimizationZhengyang Hu, Song Kang, Qunsong Zeng, Kaibin Huang, Yanchao Yang. [doi]
• Distinguishing the Knowable from the Unknowable with Language ModelsGustaf Ahdritz, Tian Qin, Nikhil Vyas 0001, Boaz Barak, Benjamin L. Edelman. [doi]
• How to Escape Sharp Minima with Random PerturbationsKwangjun Ahn, Ali Jadbabaie, Suvrit Sra. [doi]
• SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking MechanismsXingrun Xing, Zheng Zhang, Ziyi Ni, Shitao Xiao, Yiming Ju, Siqi Fan 0001, Yequan Wang, Jiajun Zhang, Guoqi Li. [doi]
• Measures of diversity and space-filling designs for categorical dataCédric Malherbe, Emilio Domínguez-Sánchez, Merwan Barlier, Igor Colin, Haitham Bou-Ammar, Tom Diethe. [doi]
• Controlled Decoding from Language ModelsSidharth Mudgal, Jong Lee, Harish Ganapathy, Yaguang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel, Ahmad Beirami. [doi]
• Revisiting the Role of Language Priors in Vision-Language ModelsZhiqiu Lin, Xinyue Chen, Deepak Pathak, Pengchuan Zhang, Deva Ramanan. [doi]
• Lightweight Image Super-Resolution via Flexible Meta PruningYulun Zhang, Kai Zhang 0008, Luc Van Gool, Martin Danelljan, Fisher Yu 0001. [doi]
• Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and ConvergenceYancheng Huang, Kai Yang, Zelin Zhu, Leian Chen. [doi]
• Graph Neural Networks Use Graphs When They Shouldn'tMaya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson. [doi]
• CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language TransformersDachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang 0003. [doi]
• Mechanistic Design and Scaling of Hybrid ArchitecturesMichael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang 0001, Stefano Massaroli. [doi]
• UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series AnalysisYunhao Zhang, Minghao Liu, Shengyang Zhou, Junchi Yan. [doi]
• UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation LearningShikun Feng, Yuyan Ni, Minghao Li, Yanwen Huang, Zhi-Ming Ma, Wei-Ying Ma, Yanyan Lan. [doi]
• Energy-Efficient Gaussian Processes Using Low-Precision ArithmeticNicolas Alder, Ralf Herbrich. [doi]
• MD tree: a model-diagnostic tree grown on loss landscapeYefan Zhou, Jianlong Chen, Qinxue Cao, Konstantin Schürholt, Yaoqing Yang. [doi]
• Double Momentum Method for Lower-Level Constrained Bilevel OptimizationWanli Shi, Yi Chang, Bin Gu 0001. [doi]
• Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksWenhan Yang, Jingdong Gao, Baharan Mirzasoleiman. [doi]
• Getting the most out of your tokenizer for pre-training and domain adaptationGautier Dagan, Gabriel Synnaeve, Baptiste Rozière. [doi]
• ODIN: Disentangled Reward Mitigates Hacking in RLHFLichang Chen, Chen Zhu 0001, Jiuhai Chen, Davit Soselia, Tianyi Zhou 0001, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro. [doi]
• Matrix Information Theory for Self-Supervised LearningYifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang 0001, Yang Yuan. [doi]
• Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder StationingAmutheezan Sivagnanam, Ava Pettet, Hunter Lee, Ayan Mukhopadhyay, Abhishek Dubey, Aron Laszka. [doi]
• Differentially Private Domain Adaptation with Theoretical GuaranteesRaef Bassily, Corinna Cortes, Anqi Mao, Mehryar Mohri. [doi]
• Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator LearningJunfeng Chen, Kailiang Wu. [doi]
• On the Emergence of Cross-Task Linearity in Pretraining-Finetuning ParadigmZhanpeng Zhou, Zijun Chen, Yilan Chen 0002, Bo Zhang 0069, Junchi Yan. [doi]
• Optimal Coresets for Low-Dimensional Geometric MedianPeyman Afshani, Chris Schwiegelshohn. [doi]
• Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware MinimizationZiqing Fan, Shengchao Hu, Jiangchao Yao, Gang Niu 0001, Ya Zhang 0002, Masashi Sugiyama, Yanfeng Wang. [doi]
• HAMLET: Graph Transformer Neural Operator for Partial Differential EquationsAndrey Bryutkin, Jiahao Huang, Zhongying Deng, Guang Yang 0006, Carola-Bibiane Schönlieb, Angelica I. Avilés-Rivero. [doi]
• Model-based Reinforcement Learning for Confounded POMDPsMao Hong, Zhengling Qi, Yanxun Xu. [doi]
• RLVF: Learning from Verbal Feedback without OvergeneralizationMoritz Stephan, Alexander Khazatsky, Eric Mitchell, Annie S. Chen, Sheryl Hsu, Archit Sharma, Chelsea Finn. [doi]
• Generative Marginalization ModelsSulin Liu, Peter J. Ramadge, Ryan P. Adams. [doi]
• Adaptive Conformal Inference by BettingAleksandr Podkopaev, Dong Xu, Kuang-Chih Lee. [doi]
• Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM DynamicsAnkit Vani, Frederick Tung, Gabriel L. Oliveira, Hossein Sharifi Noghabi. [doi]
• Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language ModelsBilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Ruoxi Jia 0001, Ming Jin 0002. [doi]
• ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance GenerationZiao Guo, Yang Li, Chang Liu, Wenli Ouyang, Junchi Yan. [doi]
• Learning Constraints from Offline Demonstrations via Superior Distribution Correction EstimationGuorui Quan, Zhiqiang Xu, Guiliang Liu. [doi]
• Shifted Interpolation for Differential PrivacyJinho Bok, Weijie J. Su, Jason M. Altschuler. [doi]
• Neuro-Symbolic Temporal Point ProcessesYang Yang, Chao Yang, Boyang Li, Yinghao Fu, Shuang Li 0002. [doi]
• Codebook Features: Sparse and Discrete Interpretability for Neural NetworksAlex Tamkin, Mohammad Taufeeque, Noah D. Goodman. [doi]
• ATraDiff: Accelerating Online Reinforcement Learning with Imaginary TrajectoriesQianlan Yang, Yu-Xiong Wang. [doi]
• Position: What Can Large Language Models Tell Us about Time Series AnalysisMing Jin 0005, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang 0002, Jindong Wang, Shirui Pan, Qingsong Wen. [doi]
• Rethinking Momentum Knowledge Distillation in Online Continual LearningNicolas Michel, Maorong Wang, Ling Xiao 0001, Toshihiko Yamasaki. [doi]
• Bayesian Program Learning by Decompiling Amortized KnowledgeAlessandro B. Palmarini, Christopher G. Lucas, N. Siddharth 0001. [doi]
• Efficient and Effective Time-Series Forecasting with Spiking Neural NetworksChangze Lv, Yansen Wang, Dongqi Han, Xiaoqing Zheng, Xuanjing Huang 0001, Dongsheng Li 0002. [doi]
• Position: Intent-aligned AI Systems Must Optimize for Agency PreservationCatalin Mitelut, Benjamin J. Smith, Peter Vamplew 0001. [doi]
• Tandem Transformers for Inference Efficient LLMsAishwarya P. S., Pranav Ajit Nair, Yashas Samaga, Toby Boyd, Sanjiv Kumar, Prateek Jain 0002, Praneeth Netrapalli. [doi]
• Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online LearningJoon Suk Huh, Kirthevasan Kandasamy. [doi]
• Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision MakingParand A. Alamdari, Toryn Q. Klassen, Elliot Creager, Sheila A. McIlraith. [doi]
• Sample-Efficient Multiagent Reinforcement Learning with Reset ReplayYaodong Yang 0002, Guangyong Chen, Jianye Hao, Pheng-Ann Heng. [doi]
• DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied SystemsKaibo He, Chenhui Zuo, Chengtian Ma, Yanan Sui. [doi]
• SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language ModelsXiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu 0001, Jieyu Zhang, Satyen Subramaniam, Arjun R. Loomba, Shichang Zhang, Yizhou Sun, Wei Wang 0010. [doi]
• Non-convex Stochastic Composite Optimization with Polyak MomentumYuan Gao, Anton Rodomanov, Sebastian U. Stich. [doi]
• LLark: A Multimodal Instruction-Following Language Model for MusicJoshua Patrick Gardner, Simon Durand, Daniel Stoller, Rachel M. Bittner. [doi]
• When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal AbstractionsZhening Li, Gabriel Poesia, Armando Solar-Lezama. [doi]
• Position: A Call for Embodied AIGiuseppe Paolo, Jonas Gonzalez-Billandon, Balázs Kégl. [doi]
• Class-Imbalanced Graph Learning without Class RebalancingZhining Liu 0002, Ruizhong Qiu, Zhichen Zeng, Hyunsik Yoo, David Zhou, Zhe Xu 0007, Yada Zhu, Kommy Weldemariam, Jingrui He, Hanghang Tong. [doi]
• Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing BackpropagationYuchen Yang, Yingdong Shi, Cheems Wang, Xiantong Zhen, Yuxuan Shi, Jun Xu 0019. [doi]
• Membership Inference Attacks on Diffusion Models via Quantile RegressionShuai Tang, Steven Wu 0001, Sergül Aydöre, Michael Kearns, Aaron Roth 0001. [doi]
• QUEST: Query-Aware Sparsity for Efficient Long-Context LLM InferenceJiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, Song Han. [doi]
• Neural Networks Learn Statistics of Increasing ComplexityNora Belrose, Quintin Pope, Lucia Quirke, Alex Mallen, Xiaoli Z. Fern. [doi]
• Characterizing Overfitting in Kernel Ridgeless Regression Through the EigenspectrumTin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius. [doi]
• How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?Hongkang Li, Meng Wang 0003, Songtao Lu, Xiaodong Cui, Pin-Yu Chen. [doi]
• Language Models with Conformal Factuality GuaranteesChristopher Mohri, Tatsunori Hashimoto. [doi]
• Recovering the Pre-Fine-Tuning Weights of Generative ModelsEliahu Horwitz, Jonathan Kahana, Yedid Hoshen. [doi]
• Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate PredictionsSanjay Kariyappa, Freddy Lécué, Saumitra Mishra, Christopher Pond, Daniele Magazzeni, Manuela Veloso. [doi]
• Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement LearningYun-Hsuan Lien, Ping-Chun Hsieh, Tzu-Mao Li, Yu-Shuen Wang. [doi]
• Extreme Compression of Large Language Models via Additive QuantizationVage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh. [doi]
• Efficient Value Iteration for s-rectangular Robust Markov Decision ProcessesNavdeep Kumar, Kaixin Wang, Kfir Yehuda Levy, Shie Mannor. [doi]
• MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language BenchmarkDongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yinuo Liu, Huichi Zhou, Qihui Zhang, Yao Wan 0001, Pan Zhou 0001, Lichao Sun 0001. [doi]
• Towards Neural Architecture Search through Hierarchical Generative ModelingLichuan Xiang, Lukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Nicholas Donald Lane, Hongkai Wen 0001. [doi]
• Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features ModelHien Dang 0003, Tho Tran Huu, Tan Minh Nguyen, Nhat Ho. [doi]
• Probabilistic Subgoal Representations for Hierarchical Reinforcement LearningVivienne Huiling Wang, Tinghuai Wang, Wenyan Yang, Joni-Kristian Kämäräinen, Joni Pajarinen. [doi]
• MagicLens: Self-Supervised Image Retrieval with Open-Ended InstructionsKai Zhang 0033, Yi Luan, Hexiang Hu, Kenton Lee, Siyuan Qiao, Wenhu Chen, Yu Su 0001, Ming-Wei Chang. [doi]
• Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and VerificationYiming Meng, Ruikun Zhou, Amartya Mukherjee, Maxwell Fitzsimmons, Christopher Song, Jun Liu 0015. [doi]
• Creative Text-to-Audio Generation via Synthesizer ProgrammingManuel Cherep, Nikhil Singh 0003, Jessica Shand. [doi]
• Compressible Dynamics in Deep Overparameterized Low-Rank Learning & AdaptationCan Yaras, Peng Wang 0098, Laura Balzano, Qing Qu 0001. [doi]
• Learning Exceptional Subgroups by End-to-End Maximizing KL-DivergenceSascha Xu, Nils Philipp Walter, Janis Kalofolias, Jilles Vreeken. [doi]
• Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-AttentionAaron J. Havens, Alexandre Araujo, Huan Zhang, Bin Hu 0002. [doi]
• Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy LearningKakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki. [doi]
• Leveraging VLM-Based Pipelines to Annotate 3D ObjectsRishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy J. Mitra. [doi]
• Memorization Through the Lens of Curvature of Loss Function Around SamplesIsha Garg, Deepak Ravikumar, Kaushik Roy 0001. [doi]
• QuRating: Selecting High-Quality Data for Training Language ModelsAlexander Wettig, Aatmik Gupta, Saumya Malik, Danqi Chen 0001. [doi]
• Revisiting the Power of Prompt for Visual TuningYuzhu Wang, Lechao Cheng, Chaowei Fang, Dingwen Zhang, Manni Duan, Meng Wang. [doi]
• Position: Social Environment Design Should be Further Developed for AI-based Policy-MakingEdwin Zhang, Sadie Zhao, Tonghan Wang 0003, Safwan Hossain, Henry Gasztowtt, Stephan Zheng, David C. Parkes, Milind Tambe, Yiling Chen 0001. [doi]
• Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance ScaleCandi Zheng, Yuan Lan. [doi]
• Robust Yet Efficient Conformal Prediction SetsSoroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski. [doi]
• Self-Rewarding Language ModelsWeizhe Yuan, Richard Yuanzhe Pang, KyungHyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston. [doi]
• Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point ProcessZichong Li, Qunzhi Xu, Zhenghao Xu, Yajun Mei, Tuo Zhao, Hongyuan Zha. [doi]
• Switching the Loss Reduces the Cost in Batch Reinforcement LearningAlex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvári. [doi]
• How Smooth Is Attention?Valérie Castin, Pierre Ablin, Gabriel Peyré. [doi]
• No Free Prune: Information-Theoretic Barriers to Pruning at InitializationTanishq Kumar, Kevin Luo, Mark Sellke. [doi]
• Hierarchical State Space Models for Continuous Sequence-to-Sequence ModelingRaunaq M. Bhirangi, Chenyu Wang, Venkatesh Pattabiraman, Carmel Majidi, Abhinav Gupta 0001, Tess Lee Hellebrekers, Lerrel Pinto. [doi]
• Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity LearningJiaqi Wang 0002, Chenxu Zhao, Lingjuan Lyu, Quanzeng You, Mengdi Huai, Fenglong Ma. [doi]
• Neural Diffusion ModelsGrigory Bartosh, Dmitry P. Vetrov, Christian A. Naesseth. [doi]
• Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you NeedShangda Yang, Vitaly Zankin, Maximilian Balandat, Stefan Scherer, Kevin T. Carlberg, Neil Walton, Kody J. H. Law. [doi]
• Causal Inference from Competing TreatmentsAna-Andreea Stoica, Vivian Y. Nastl, Moritz Hardt. [doi]
• Predictive Dynamic FusionBing Cao, Yinan Xia, Yi Ding, Changqing Zhang, Qinghua Hu. [doi]
• Feasibility Consistent Representation Learning for Safe Reinforcement LearningZhepeng Cen, Yihang Yao, Zuxin Liu, Ding Zhao. [doi]
• Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural NetworksLorenzo Bardone, Sebastian Goldt. [doi]
• Prompt Sketching for Large Language ModelsLuca Beurer-Kellner, Mark Niklas Müller, Marc Fischer 0002, Martin T. Vechev. [doi]
• Manifold Integrated Gradients: Riemannian Geometry for Feature AttributionEslam Zaher, Maciej Trzaskowski, Quan Nguyen, Fred Roosta. [doi]
• Mollification Effects of Policy Gradient MethodsTao Wang, Sylvia L. Herbert, Sicun Gao. [doi]
• Differentiability and Optimization of Multiparameter Persistent HomologyLuis Scoccola, Siddharth Setlur, David Loiseaux, Mathieu Carrière, Steve Oudot. [doi]
• Disentangled 3D Scene Generation with Layout LearningDave Epstein, Ben Poole, Ben Mildenhall, Alexei A. Efros, Aleksander Holynski. [doi]
• Adaptive Stabilization Based on Machine Learning for Column GenerationYunzhuang Shen, Yuan Sun 0003, Xiaodong Li 0001, Zhiguang Cao, Andrew C. Eberhard, Guangquan Zhang 0001. [doi]
• Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formulaKirill Brilliantov, Fedor Pavutnitskiy, Dmitry Pasechnyuk, German Magai. [doi]
• Context-Guided Diffusion for Out-of-Distribution Molecular and Protein DesignLeo Klarner, Tim G. J. Rudner, Garrett M. Morris, Charlotte M. Deane, Yee Whye Teh. [doi]
• Towards Interpretable Deep Local Learning with Successive Gradient ReconciliationYibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Adel Bibi, Philip Torr 0001, Bernard Ghanem. [doi]
• Position: The Reasonable Person Standard for AISunayana Rane. [doi]
• Symbolic Music Generation with Non-Differentiable Rule Guided DiffusionYujia Huang, Adishree Ghatare, Yuanzhe Liu, Ziniu Hu, Qinsheng Zhang, Chandramouli Shama Sastry, Siddharth Gururani, Sageev Oore, Yisong Yue. [doi]
• NDOT: Neuronal Dynamics-based Online Training for Spiking Neural NetworksHaiyan Jiang, Giulia De Masi, Huan Xiong, Bin Gu 0001. [doi]
• Online Isolation ForestFilippo Leveni, Guilherme Weigert Cassales, Bernhard Pfahringer, Albert Bifet, Giacomo Boracchi. [doi]
• Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi, Stefanie Jegelka, Sanjiv Kumar. [doi]
• Nonlinear Filtering with Brenier Optimal Transport MapsMohammad Al-Jarrah, Niyizhen Jin, Bamdad Hosseini, Amirhossein Taghvaei. [doi]
• Stop Regressing: Training Value Functions via Classification for Scalable Deep RLJesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taïga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, Rishabh Agarwal. [doi]
• Position: Building Guardrails for Large Language Models Requires Systematic DesignYi Dong 0002, Ronghui Mu, Gaojie Jin, Yi Qi, Jinwei Hu, Xingyu Zhao 0001, Jie Meng, Wenjie Ruan, Xiaowei Huang 0001. [doi]
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and FeedbackSongyang Gao, Qiming Ge, Wei Shen, Shihan Dou, Junjie Ye, Xiao Wang 0001, Rui Zheng, Yicheng Zou, Zhi Chen, Hang Yan 0001, Qi Zhang 0001, Dahua Lin. [doi]
• Revealing Vision-Language Integration in the Brain with Multimodal NetworksVighnesh Subramaniam, Colin Conwell, Christopher Wang, Gabriel Kreiman, Boris Katz, Ignacio Cases, Andrei Barbu. [doi]
• Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language ModelFei Liu 0044, Xialiang Tong, Mingxuan Yuan, Xi Lin 0001, Fu Luo, Zhenkun Wang, Zhichao Lu, Qingfu Zhang 0001. [doi]
• Causal Effect Identification in LiNGAM Models with Latent ConfoundersDaniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Mathias Drton, Negar Kiyavash. [doi]
• All-in-one simulation-based inferenceManuel Glöckler, Michael Deistler, Christian Dietrich Weilbach, Frank Wood, Jakob H. Macke. [doi]
• Online Cascade Learning for Efficient Inference over StreamsLunyiu Nie, Zhimin Ding, Erdong Hu, Christopher M. Jermaine, Swarat Chaudhuri. [doi]
• Truly No-Regret Learning in Constrained MDPsAdrian Müller, Pragnya Alatur, Volkan Cevher, Giorgia Ramponi, Niao He. [doi]
• On Which Nodes Does GCN Fail? Enhancing GCN From the Node PerspectiveJincheng Huang, Jialie Shen 0001, Xiaoshuang Shi, Xiaofeng Zhu 0001. [doi]
• Promptbreeder: Self-Referential Self-Improvement via Prompt EvolutionChrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rocktäschel. [doi]
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding HeadsTianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao. [doi]
• Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation ModelsHengyi Wang, Shiwei Tan, Hao Wang. [doi]
• Efficient Exploration for LLMsVikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, Benjamin Van Roy. [doi]
• Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsBoyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson 0002. [doi]
• Exact Soft Analytical Side-Channel Attacks using Tractable CircuitsThomas Wedenig, Rishub Nagpal, Gaëtan Cassiers, Stefan Mangard, Robert Peharz. [doi]
• LASER: Linear Compression in Wireless Distributed OptimizationAshok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar. [doi]
• Explaining Probabilistic Models with Distributional ValuesLuca Franceschi 0001, Michele Donini, Cédric Archambeau, Matthias W. Seeger. [doi]
• Online Algorithms with Uncertainty-Quantified PredictionsBo Sun 0004, Jerry Huang, Nicolas Christianson, Mohammad Hajiesmaili, Adam Wierman, Raouf Boutaba. [doi]
• Think Before You Act: Decision Transformers with Working MemoryJikun Kang, Romain Laroche, Xingdi Yuan, Adam Trischler, Xue Liu 0001, Jie Fu. [doi]
• AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and TrainingZiyu Wan, Xidong Feng, Muning Wen, Stephen Marcus McAleer, Ying Wen 0001, Weinan Zhang 0001, Jun Wang 0012. [doi]
• Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI ResearchRiley Simmons-Edler, Ryan Paul Badman, Shayne Longpre, Kanaka Rajan. [doi]
• Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy PhysicsSiqi Miao 0001, Zhiyuan Lu, Mia Liu, Javier M. Duarte, Pan Li 0005. [doi]
• An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural NetworkTaeyoung Kim, Hongseok Yang. [doi]
• GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative DecodingCunxiao Du, Jing Jiang 0001, Yuanchen Xu, Jiawei Wu, Sicheng Yu, Yongqi Li 0001, Shenggui Li, Kai Xu, Liqiang Nie, Zhaopeng Tu, Yang You. [doi]
• How Transformers Learn Causal Structure with Gradient DescentEshaan Nichani, Alex Damian, Jason D. Lee. [doi]
• Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound AssumptionsKaihong Zhang, Heqi Yin, Feng Liang, Jingbo Liu. [doi]
• Hybrid2 Neural ODE Causal Modeling and an Application to Glycemic ResponseBob Junyi Zou, Matthew E. Levine, Dessi P. Zaharieva, Ramesh Johari, Emily B. Fox. [doi]
• Quality-Diversity with Limited ResourcesRen-Jian Wang, Ke Xue 0001, Cong Guan, Chao Qian 0001. [doi]
• Accelerating Federated Learning with Quick Distributed Mean EstimationRan Ben-Basat, Shay Vargaftik, Amit Portnoy, Gil Einziger, Yaniv Ben-Itzhak, Michael Mitzenmacher. [doi]
• Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution ApproximationBoheng Li, Yishuo Cai, Jisong Cai, Yiming Li 0004, Han Qiu 0001, Run Wang, Tianwei Zhang 0004. [doi]
• Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)Drew Prinster, Samuel Don Stanton, Anqi Liu, Suchi Saria. [doi]
• Compositional Few-Shot Class-Incremental LearningYixiong Zou, Shanghang Zhang, Haichen Zhou, Yuhua Li 0003, Ruixuan Li 0001. [doi]
• Differentiable Model Scaling using Differentiable TopkKai Liu, Ruohui Wang, Jianfei Gao 0003, Kai Chen. [doi]
• EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningJongsuk Kim, Hyeongkeun Lee, Kyeongha Rho, Junmo Kim, Joon Son Chung. [doi]
• When and How Does In-Distribution Label Help Out-of-Distribution Detection?Xuefeng Du, Yiyou Sun, Yixuan Li 0001. [doi]
• A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural NetworksBoqi Li, Weiwei Liu. [doi]
• Non-confusing Generation of Customized Concepts in Diffusion ModelsWang Lin, Jingyuan Chen, Jiaxin Shi, Yichen Zhu, Chen Liang, Junzhong Miao, Tao Jin 0004, Zhou Zhao, Fei Wu 0001, Shuicheng Yan, Hanwang Zhang. [doi]
• Sparsest Models Elude Pruning: An Exposé of Pruning's Current CapabilitiesStephen Zhang, Vardan Papyan. [doi]
• CompeteAI: Understanding the Competition Dynamics of Large Language Model-based AgentsQinlin Zhao, Jindong Wang 0001, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen 0102, Xing Xie 0001. [doi]
• Optimal Eye Surgeon: Finding image priors through sparse generators at initializationAvrajit Ghosh, Xitong Zhang, Kenneth K. Sun, Qing Qu 0001, Saiprasad Ravishankar, Rongrong Wang. [doi]
• Learning Reward for Robot Skills Using Large Language Models via Self-AlignmentYuwei Zeng, Yao Mu, Lin Shao 0002. [doi]
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based ReasoningSiyuan Guo, Cheng Deng, Ying Wen 0001, Hechang Chen, Yi Chang 0001, Jun Wang 0012. [doi]
• HyperFields: Towards Zero-Shot Generation of NeRFs from TextSudarshan Babu, Richard Liu, Avery Zhou, Michael Maire, Greg Shakhnarovich, Rana Hanocka. [doi]
• On PI Controllers for Updating Lagrange Multipliers in Constrained OptimizationMotahareh Sohrabi, Juan Ramirez, Tianyue H. Zhang, Simon Lacoste-Julien, Jose Gallego-Posada. [doi]
• Mitigating Privacy Risk in Membership Inference by Convex-Concave LossZhenlong Liu, Lei Feng 0006, Huiping Zhuang, Xiaofeng Cao, Hongxin Wei. [doi]
• Optimal Kernel Choice for Score Function-based Causal DiscoveryWenjie Wang, Biwei Huang, Feng Liu 0003, Xinge You, Tongliang Liu, Kun Zhang 0001, Mingming Gong. [doi]
• Disentangled Continual Graph Neural Architecture Search with Invariant Modular SupernetZeyang Zhang, Xin Wang 0019, Yijian Qin, Hong Chen, Ziwei Zhang, Xu Chu, Wenwu Zhu 0001. [doi]
• Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language ModelsJie Zhang 0076, Xiaosong Ma, Song Guo 0001, Peng Li 0017, Wenchao Xu 0001, Xueyang Tang, Zicong Hong. [doi]
• TVE: Learning Meta-attribution for Transferable Vision ExplainerGuanchu Wang, Yu-Neng Chuang, Fan Yang 0023, Mengnan Du, Chia-Yuan Chang, Shaochen Zhong, Zirui Liu, Zhaozhuo Xu, Kaixiong Zhou, Xuanting Cai, Xia Hu 0001. [doi]
• Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement LearningDonghu Kim, HoJoon Lee, Kyungmin Lee, Dongyoon Hwang, Jaegul Choo. [doi]
• Structured Chemistry Reasoning with Large Language ModelsSiru Ouyang, Zhuosheng Zhang 0001, Bing Yan, Xuan Liu, Yejin Choi 0001, Jiawei Han 0001, Lianhui Qin. [doi]
• RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow MatchingDivya Nori, Wengong Jin. [doi]
• Algorithm and Hardness for Dynamic Attention Maintenance in Large Language ModelsJan van den Brand, Zhao Song 0002, Tianyi Zhou 0001. [doi]
• Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-PolytopesWeijia Shao. [doi]
• Minimizing f-Divergences by Interpolating Velocity FieldsSong Liu, Jiahao Yu, Jack Simons, Mingxuan Yi, Mark Beaumont. [doi]
• ILILT: Implicit Learning of Inverse Lithography TechnologiesHaoyu Yang, Haoxing Ren. [doi]
• Compositional Text-to-Image Generation with Dense Blob RepresentationsWeili Nie, Sifei Liu, Morteza Mardani, Chao Liu 0064, Benjamin Eckart, Arash Vahdat. [doi]
• Position: Leverage Foundational Models for Black-Box OptimizationXingyou Song, Yingtao Tian, Robert Tjarko Lange, Chansoo Lee, Yujin Tang, Yutian Chen 0001. [doi]
• Make-A-Shape: a Ten-Million-scale 3D Shape ModelKa-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan, Zhengzhe Liu, Hooman Shayani, Chi-Wing Fu. [doi]
• When Will Gradient Regularization Be Harmful?Yang Zhao 0016, Hao Zhang 0005, Xiuyuan Hu. [doi]
• LangCell: Language-Cell Pre-training for Cell Identity UnderstandingSuyuan Zhao, Jiahuan Zhang, Yushuai Wu, Yizhen Luo, Zaiqing Nie. [doi]
• Conformal Prediction for Deep Classifier via Label RankingJianguo Huang, Huajun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei. [doi]
• Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network ParametrizationMudit Gaur, Amrit S. Bedi, Di Wang 0015, Vaneet Aggarwal. [doi]
• Domain Generalisation via Imprecise LearningAnurag Singh, Siu Lun Chau, Shahine Bouabid, Krikamol Muandet. [doi]
• DeCoOp: Robust Prompt Tuning with Out-of-Distribution DetectionZhi Zhou 0007, Ming Yang, Jiang-Xin Shi, Lan-Zhe Guo, Yu-Feng Li. [doi]
• Implicit meta-learning may lead language models to trust more reliable sourcesDmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Kacper Mlodozeniec, Tegan Maharaj, David Krueger 0001. [doi]
• Test-Time Regret Minimization in Meta Reinforcement LearningMirco Mutti, Aviv Tamar. [doi]
• IM-Unpack: Training and Inference with Arbitrarily Low Precision IntegersZhanpeng Zeng, Karthikeyan Sankaralingam, Vikas Singh. [doi]
• Fundamental Benefit of Alternating Updates in Minimax OptimizationJaewook Lee, Hanseul Cho 0002, Chulhee Yun. [doi]
• MILP-FBGen: LP/MILP Instance Generation with Feasibility/BoundednessYahong Zhang, Chenchen Fan, Donghui Chen, Congrui Li, Wenli Ouyang, Mingda Zhu, Junchi Yan. [doi]
• Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with TransformersXiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low. [doi]
• Submodular framework for structured-sparse optimal transportPiyushi Manupriya, Pratik Jawanpuria, Karthik S. Gurumoorthy, Saketha Nath Jagarlapudi, Bamdev Mishra. [doi]
• An Information-Theoretic Analysis of In-Context LearningHong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy. [doi]
• Harmony in Diversity: Merging Neural Networks with Canonical Correlation AnalysisStefan Horoi, Albert Manuel Orozco Camacho, Eugene Belilovsky, Guy Wolf. [doi]
• Hieros: Hierarchical Imagination on Structured State Space Sequence World ModelsPaul Mattes, Rainer Schlosser, Ralf Herbrich. [doi]
• Graph Structure Extrapolation for Out-of-Distribution GeneralizationXiner Li, Shurui Gui, Youzhi Luo, Shuiwang Ji. [doi]
• Graph-based Time Series Clustering for End-to-End Hierarchical ForecastingAndrea Cini, Danilo P. Mandic, Cesare Alippi. [doi]
• Fine-grained Classes and How to Find ThemMatej Grcic, Artyom Gadetsky, Maria Brbic. [doi]
• Proactive Detection of Voice Cloning with Localized WatermarkingRobin San Roman, Pierre Fernandez, Hady ElSahar, Alexandre Défossez, Teddy Furon, Tuan Tran. [doi]
• Diffusion Models Encode the Intrinsic Dimension of Data ManifoldsJan Stanczuk, Georgios Batzolis, Teo Deveney, Carola-Bibiane Schönlieb. [doi]
• On the Generalization of Equivariant Graph Neural NetworksRafal Karczewski, Amauri H. Souza, Vikas Garg 0001. [doi]
• Removing Spurious Concepts from Neural Network Representations via Joint Subspace EstimationFloris Holstege, Bram Wouters, Noud P. A. van Giersbergen, Cees Diks. [doi]
• Scale-Free Image Keypoints Using Differentiable Persistent HomologyGiovanni Barbarani, Francesco Vaccarino, Gabriele Trivigno, Marco Guerra, Gabriele Moreno Berton, Carlo Masone. [doi]
• Variance-reduced Zeroth-Order Methods for Fine-Tuning Language ModelsTanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha. [doi]
• StrWAEs to Invariant RepresentationsHyunjong Lee, Yedarm Seong, Sungdong Lee, Joong-Ho Won. [doi]
• Stability Evaluation through Distributional Perturbation AnalysisJosé H. Blanchet, Peng Cui 0001, Jiajin Li, Jiashuo Liu. [doi]
• Accelerated Speculative Sampling Based on Tree Monte CarloZhengmian Hu, Heng Huang. [doi]
• Learning and Forgetting Unsafe Examples in Large Language ModelsJiachen Zhao, Zhun Deng, David Madras, James Zou 0001, Mengye Ren. [doi]
• Improving Generalization in Offline Reinforcement Learning via Adversarial Data SplittingDa Wang, Lin Li, Wei Wei 0018, Qixian Yu, Jianye Hao, Jiye Liang. [doi]
• Position: Measure Dataset Diversity, Don't Just Claim ItDora Zhao, Jerone T. A. Andrews, Orestis Papakyriakopoulos, Alice Xiang. [doi]
• CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded ModellingJunchao Gong, Lei Bai 0001, Peng Ye, Wanghan Xu, Na Liu, Jianhua Dai, Xiaokang Yang, Wanli Ouyang. [doi]
• Is DPO Superior to PPO for LLM Alignment? A Comprehensive StudyShusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu 0005, Yi Wu 0013. [doi]
• Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric RegularizationJinlu Zhang 0002, Yiyi Zhou, Qiancheng Zheng, Xiaoxiong Du, Gen Luo, Jun Peng, Xiaoshuai Sun, Rongrong Ji. [doi]
• OMPO: A Unified Framework for RL under Policy and Dynamics ShiftsYu Luo, Tianying Ji, Fuchun Sun 0001, Jianwei Zhang 0001, Huazhe Xu, Xianyuan Zhan. [doi]
• Statistical Inference Under Constrained Selection BiasSantiago Cortes-Gomez, Mateo Dulce Rubio, Carlos Miguel Patiño, Bryan Wilder. [doi]
• DsDm: Model-Aware Dataset Selection with DatamodelsLogan Engstrom, Axel Feldmann, Aleksander Madry. [doi]
• TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic TasksZhiruo Wang, Graham Neubig, Daniel Fried. [doi]
• Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based ModelsSongtao Liu, Hanjun Dai, Yue Zhao, Peng Liu. [doi]
• How Language Model Hallucinations Can SnowballMuru Zhang, Ofir Press, William Merrill, Alisa Liu, Noah A. Smith. [doi]
• State-Free Inference of State-Space Models: The *Transfer Function* ApproachRom N. Parnichkun, Stefano Massaroli, Alessandro Moro, Jimmy T. H. Smith, Ramin M. Hasani, Mathias Lechner, Qi An, Christopher Ré, Hajime Asama, Stefano Ermon, Taiji Suzuki, Michael Poli, Atsushi Yamashita. [doi]
• Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many MessagesHilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar, Samson Zhou. [doi]
• Robust and Conjugate Gaussian Process RegressionMatías Altamirano, François-Xavier Briol, Jeremias Knoblauch. [doi]
• Learning Surrogates for Offline Black-Box Optimization via Gradient MatchingMinh Hoang, Azza Fadhel, Aryan Deshwal, Jana Doppa, Trong Nghia Hoang. [doi]
• LIDAO: Towards Limited Interventions for Debiasing (Large) Language ModelsTianci Liu 0003, Haoyu Wang 0004, Shiyang Wang, Yu Cheng, Jing Gao 0004. [doi]
• More Benefits of Being Distributional: Second-Order Bounds for Reinforcement LearningKaiwen Wang, Owen Oertell, Alekh Agarwal, Nathan Kallus, Wen Sun 0002. [doi]
• Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic PromptsZhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, Wei-chen Chiu. [doi]
• Learning to Explore in POMDPs with Informational RewardsAnnie Xie, Logan M. Bhamidipaty, Evan Zheran Liu, Joey Hong, Sergey Levine, Chelsea Finn. [doi]
• Position: AI/ML Influencers Have a Place in the Academic ProcessIain Weissburg, Mehir Arora, Xinyi Wang, Liangming Pan, William Yang Wang. [doi]
• Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized SmoothingYouwei Shu, Xi Xiao, Derui Wang, Yuxin Cao, Siji Chen, Jason Xue, Linyi Li 0001, Bo Li 0026. [doi]
• TimeX++: Learning Time-Series Explanations with Information BottleneckZichuan Liu, Tianchun Wang, Jimeng Shi, Xu Zheng 0003, Zhuomin Chen, Lei Song, Wenqian Dong, Jayantha Obeysekera, Farhad Shirani 0001, Dongsheng Luo. [doi]
• Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free LunchLe Yu, Bowen Yu 0002, Haiyang Yu, Fei Huang 0004, Yongbin Li. [doi]
• GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian SplattingXiaoyu Zhou, Xingjian Ran, Yajiao Xiong, Jinlin He, Zhiwei Lin, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang 0001. [doi]
• DecisionNCE: Embodied Multimodal Representations via Implicit Preference LearningJianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao, Xiao Hu, Sijie Cheng, Haoyi Niu, Jihao Liu, Yu Liu, Jingjing Liu, Ya-Qin Zhang, Xianyuan Zhan. [doi]
• Not all distributional shifts are equal: Fine-grained robust conformal inferenceJiahao Ai, Zhimei Ren. [doi]
• Listwise Reward Estimation for Offline Preference-based Reinforcement LearningHeewoong Choi, Sangwon Jung, Hongjoon Ahn, Taesup Moon. [doi]
• eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction DataBo Peng 0009, Xinyi Ling, Ziru Chen, Huan Sun 0001, Xia Ning. [doi]
• Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference AccelerationZhengyang Zhuge, Peisong Wang, Xingting Yao, Jian Cheng 0001. [doi]
• Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex LossesChangyu Gao, Andrew Lowy, Xingyu Zhou, Stephen J. Wright 0001. [doi]
• Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?Mira Jürgens, Nis Meinert, Viktor Bengs, Eyke Hüllermeier, Willem Waegeman. [doi]
• Embodied CoT Distillation From LLM To Off-the-shelf AgentsWonje Choi 0003, Woo Kyung Kim, Minjong Yoo, Honguk Woo. [doi]
• Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase AlignmentHaokun Gui, Xiucheng Li, Xinyang Chen. [doi]
• Dr. Strategy: Model-Based Generalist Agents with Strategic DreamingHany Hamed, Subin Kim, Dongyeong Kim, Jaesik Yoon, Sungjin Ahn. [doi]
• Sliced Wasserstein with Random-Path Projecting DirectionsKhai Nguyen, Shujian Zhang, Tam Le, Nhat Ho. [doi]
• Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural NetworksLihao Wang, Zhaofei Yu. [doi]
• Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionAaron Lou, Chenlin Meng, Stefano Ermon. [doi]
• Self-Supervised Coarsening of Unstructured Grid with Automatic DifferentiationSergei Shumilin, Alexander Ryabov, Nikolay B. Yavich, Evgeny Burnaev, Vladimir Vanovskiy. [doi]
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RLJiawei Huang, Niao He, Andreas Krause 0001. [doi]
• Rich-Observation Reinforcement Learning with Continuous Latent DynamicsYuda Song 0001, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy. [doi]
• Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masksBjørn Leth Møller, Christian Igel, Kristoffer Knutsen Wickstrøm, Jon Sporring, Robert Jenssen, Bulat Ibragimov. [doi]
• Watermarks in the Sand: Impossibility of Strong Watermarking for Language ModelsHanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi 0001, Giuseppe Ateniese, Boaz Barak. [doi]
• A Single-Loop Robust Policy Gradient Method for Robust Markov Decision ProcessesZhenwei Lin, Chenyu Xue, Qi Deng, Yinyu Ye 0001. [doi]
• FADAS: Towards Federated Adaptive Asynchronous OptimizationYujia Wang, Shiqiang Wang, Songtao Lu, Jinghui Chen. [doi]
• Discovering Multiple Solutions from a Single Task in Offline Reinforcement LearningTakayuki Osa, Tatsuya Harada. [doi]
• Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider BiasBaohong Li, Anpeng Wu, Ruoxuan Xiong, Kun Kuang. [doi]
• OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language ModelsAli AhmadiTeshnizi, Wenzhi Gao, Madeleine Udell. [doi]
• UPOCR: Towards Unified Pixel-Level OCR InterfaceDezhi Peng, Zhenhua Yang, Jiaxin Zhang 0003, Chongyu Liu, Yongxin Shi, Kai Ding 0009, Fengjun Guo, Lianwen Jin. [doi]
• Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for SamplingDenis Blessing, Xiaogang Jia, Johannes Esslinger, Francisco Vargas 0001, Gerhard Neumann. [doi]
• Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image RestorationXiaole Tang, Xin Hu, Xiang Gu 0005, Jian Sun 0009. [doi]
• Practical Performance Guarantees for Pipelined DNN InferenceAaron Archer, Matthew Fahrbach, Kuikui Liu, Prakash Prabhu. [doi]
• Multi-layer Rehearsal Feature Augmentation for Class-Incremental LearningBowen Zheng, Da-Wei Zhou 0001, Han-Jia Ye, De-Chuan Zhan. [doi]
• Image Fusion via Vision-Language ModelZixiang Zhao, Lilun Deng, Haowen Bai, Yukun Cui, Zhipeng Zhang, Yulun Zhang, Haotong Qin, Dongdong Chen, Jiangshe Zhang 0001, Peng Wang, Luc Van Gool. [doi]
• A Dense Reward View on Aligning Text-to-Image Diffusion with PreferenceShentao Yang, TianQi Chen, Mingyuan Zhou. [doi]
• Algorithmic Stability Unleashed: Generalization Bounds with Unbounded LossesShaojie Li, Bowei Zhu, Yong Liu 0018. [doi]
• Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual OptimisationZakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, Carola-Bibiane Schönlieb. [doi]
• Interpretability Illusions in the Generalization of Simplified ModelsDan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen 0001, Asma Ghandeharioun. [doi]
• SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer BlocksJiwon Song, Kyungseok Oh, Taesu Kim, HyungJun Kim, Yulhwa Kim, Jae-Joon Kim. [doi]
• Improving Transformers with Dynamically Composable Multi-Head AttentionDa Xiao, Qingye Meng, Shengping Li, Xingyuan Yuan. [doi]
• Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal SlicesNathaniel Cohen, Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli. [doi]
• Semantically-correlated memories in a dense associative modelThomas F. Burns. [doi]
• Interpreting and Improving Large Language Models in Arithmetic CalculationWei Zhang, Chaoqun Wan, Yonggang Zhang, Yiu-ming Cheung, Xinmei Tian 0001, Xu Shen, Jieping Ye. [doi]
• Mean-field Analysis on Two-layer Neural Networks from a Kernel PerspectiveShokichi Takakura, Taiji Suzuki. [doi]
• NExT-GPT: Any-to-Any Multimodal LLMShengqiong Wu, Hao Fei 0001, Leigang Qu, Wei Ji 0008, Tat-Seng Chua. [doi]
• Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement LearningQiankun Zhang, Aocheng Shen, Boyu Zhang, Hanrui Jiang, Bingqian Du. [doi]
• Q-Probe: A Lightweight Approach to Reward Maximization for Language ModelsKenneth Li 0002, Samy Jelassi, Hugh Zhang, Sham M. Kakade, Martin Wattenberg, David Brandfonbrener. [doi]
• On the Weight Dynamics of Deep Normalized NetworksChristian H. X. Ali Mehmeti-Göpel, Michael Wand 0001. [doi]
• Diffusion Rejection SamplingByeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, Il-Chul Moon. [doi]
• Graph Automorphism Group Equivariant Neural NetworksEdward Pearce-Crump, William J. Knottenbelt. [doi]
• FedBAT: Communication-Efficient Federated Learning via Learnable BinarizationShiwei Li, Wenchao Xu, Haozhao Wang, Xing Tang 0007, Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li 0003, Xiuqiang He, Ruixuan Li 0001. [doi]
• Isometric Representation Learning for Disentangled Latent Space of Diffusion ModelsJaehoon Hahm, Junho Lee, Sunghyun Kim, Joonseok Lee. [doi]
• Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation ModelMikail Khona, Maya Okawa, Jan Hula, Rahul Ramesh, Kento Nishi, Robert P. Dick, Ekdeep Singh Lubana, Hidenori Tanaka. [doi]
• Interpreting and Improving Diffusion Models from an Optimization PerspectiveFrank Permenter, Chenyang Yuan. [doi]
• Delving into Differentially Private TransformerYoulong Ding, Xueyang Wu 0001, Yining Meng, Yonggang Luo, Hao Wang 0014, Weike Pan. [doi]
• Sobolev Space Regularised Pre Density ModelsMark Kozdoba, Binyamin Perets, Shie Mannor. [doi]
• Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial StatesNoam Razin, Yotam Alexander, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen. [doi]
• An Efficient Self-Learning Framework For Interactive Spoken Dialog SystemsHitesh Tulsiani, David M. Chan, Shalini Ghosh, Garima Lalwani, Prabhat Pandey, Ankish Bansal, Sri Garimella, Ariya Rastrow, Björn Hoffmeister. [doi]
• Mixtures of Experts Unlock Parameter Scaling for Deep RLJohan Samir Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Nicolaus Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro. [doi]
• Sampling in Unit Time with Kernel Fisher-Rao FlowAimee Maurais, Youssef M. Marzouk. [doi]
• A General Theory for Softmax Gating Multinomial Logistic Mixture of ExpertsHuy Nguyen, Pedram Akbarian, TrungTin Nguyen, Nhat Ho. [doi]
• Estimating Barycenters of Distributions with Neural Optimal TransportAlexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Evgeny Burnaev, Alexander Korotin. [doi]
• Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity TheoryKai Xu, Hong Ge. [doi]
• Performance Bounds for Active Binary Testing with Information MaximizationAditya Chattopadhyay, Benjamin David Haeffele, René Vidal, Donald Geman. [doi]
• Handling Heterogeneous Curvatures in Bandit LQR ControlYu-Hu Yan, Jing Wang, Peng Zhao 0006. [doi]
• MLI Formula: A Nearly Scale-Invariant Solution with Noise PerturbationBowen Tao, Xin-Chun Li, De-Chuan Zhan. [doi]
• CLLMs: Consistency Large Language ModelsSiqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, Hao Zhang. [doi]
• EvTexture: Event-driven Texture Enhancement for Video Super-ResolutionDachun Kai, Jiayao Lu, Yueyi Zhang, Xiaoyan Sun 0001. [doi]
• Diffusion Model-Augmented Behavioral CloningShang-Fu Chen, Hsiang-Chun Wang, Ming-Hao Hsu, Chun-Mao Lai, Shao-Hua Sun. [doi]
• Efficient Stochastic Approximation of Minimax Excess Risk OptimizationLijun Zhang 0005, Haomin Bai, Wei-Wei Tu, Ping Yang, Yao Hu. [doi]
• KnowFormer: Revisiting Transformers for Knowledge Graph ReasoningJunnan Liu, Qianren Mao, Weifeng Jiang, Jianxin Li 0002. [doi]
• Knowledge-aware Reinforced Language Models for Protein Directed EvolutionYuhao Wang, Qiang Zhang, Ming Qin, Xiang Zhuang, Xiaotong Li, Zhichen Gong, Zeyuan Wang, Yu Zhao 0009, Jianhua Yao 0001, Keyan Ding, Huajun Chen. [doi]
• Fair Federated Learning via the Proportional Veto CoreBhaskar Ray Chaudhury, Aniket Murhekar, Zhuowen Yuan, Bo Li 0026, Ruta Mehta, Ariel D. Procaccia. [doi]
• Efficient Algorithms for Empirical Group Distributionally Robust Optimization and BeyondDingzhi Yu, Yunuo Cai, Wei Jiang, Lijun Zhang. [doi]
• Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERTJon Saad-Falcon, Daniel Y. Fu, Simran Arora, Neel Guha, Christopher Ré. [doi]
• Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and TracingIdan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy 0001. [doi]
• Prompt-tuning Latent Diffusion Models for Inverse ProblemsHyungjin Chung, Jong Chul Ye, Peyman Milanfar, Mauricio Delbracio. [doi]
• Differentiable Mapper for Topological Optimization of Data RepresentationZiyad Oulhaj, Mathieu Carrière, Bertrand Michel. [doi]
• Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous TrainingTehila Dahan, Kfir Yehuda Levy. [doi]
• SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise AttentionRomain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko. [doi]
• Variational Inference with Coverage Guarantees in Simulation-Based InferenceYash P. Patel, Declan McNamara, Jackson Loper, Jeffrey Regier, Ambuj Tewari. [doi]
• Provable Contrastive Continual LearningYichen Wen, Zhiquan Tan, Kaipeng Zheng, Chuanlong Xie, Weiran Huang 0001. [doi]
• Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial ProblemsSiwei Wei, Xudong Zhang, Zhiyang Zhou, Yan Cai 0001. [doi]
• Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen ClientsMengmeng Ma 0002, Tang Li 0005, Xi Peng 0005. [doi]
• Learning-Efficient Yet Generalizable Collaborative Filtering for Item RecommendationYuanhao Pu, Xiaolong Chen, Xu Huang 0008, Jin Chen 0008, Defu Lian, Enhong Chen. [doi]
• PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics ModelingPhong C. H. Nguyen, Xinlun Cheng, Shahab Azarfar, Pradeep K. Seshadri, Yen Thi Nguyen, MunHo Kim, Sanghun Choi, H. S. Udaykumar, Stephen Baek. [doi]
• Mean-field Underdamped Langevin Dynamics and its Spacetime DiscretizationQiang Fu, Ashia Camage Wilson. [doi]
• Graph-Triggered Rising BanditsGianmarco Genalti, Marco Mussi, Nicola Gatti 0001, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli. [doi]
• A Theory of Fault-Tolerant LearningChanglong Wu, Yifan Wang, Ananth Grama. [doi]
• An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic OptimizationEmre Sahinoglu, Shahin Shahrampour. [doi]
• Two-timescale Derivative Free Optimization for Performative Prediction with Markovian DataHaitong Liu, Qiang Li, Hoi-To Wai. [doi]
• Accurate LoRA-Finetuning Quantization of LLMs via Information RetentionHaotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li, Yang Zhang 0088, Shouda Liu, Jie Luo 0004, Xianglong Liu 0001, Michele Magno. [doi]
• Convergence of Some Convex Message Passing Algorithms to a Fixed PointVáclav Vorácek, Tomás Werner. [doi]
• Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable SimulationsFeng Gao, Liangzhi Shi, Shenao Zhang, Zhaoran Wang 0001, Yi Wu. [doi]
• Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random FeaturesChao Wang, Xin Bing, Xin He, Caixing Wang. [doi]
• Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition FunctionsGuneykan Ozgul, Xiantao Li, Mehrdad Mahdavi, Chunhao Wang. [doi]
• No Dimensional Sampling Coresets for ClassificationMeysam Alishahi, Jeff M. Phillips. [doi]
• Standardized Interpretable Fairness Measures for Continuous Risk ScoresAnn-Kristin Becker, Oana Dumitrasc, Klaus Broelemann. [doi]
• Rotational Equilibrium: How Weight Decay Balances Learning Across Neural NetworksAtli Kosson, Bettina Messmer, Martin Jaggi. [doi]
• Exploration and Anti-Exploration with Distributional Random Network DistillationKai Yang, Jian Tao, Jiafei Lyu, Xiu Li 0001. [doi]
• Position: What makes an image realistic?Lucas Theis. [doi]
• RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language ModelsQi Lv, Hao Li, Xiang Deng, Rui Shao, Michael Y. Wang, Liqiang Nie. [doi]
• Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in DisguiseKwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai 0002. [doi]
• Meta Evidential Transformer for Few-Shot Open-Set RecognitionHitesh Sapkota, Krishna Prasad Neupane, Qi Yu 0001. [doi]
• MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-ExpertsGuanjie Chen, Xinyu Zhao, Tianlong Chen, Yu Cheng. [doi]
• Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping CompositionsYongqiang Cai. [doi]
• Adaptive Hierarchical Certification for Segmentation using Randomized SmoothingAlaa Anani, Tobias Lorenz 0002, Bernt Schiele, Mario Fritz. [doi]
• On the Consistency of Kernel Methods with Dependent ObservationsPierre-François Massiani, Sebastian Trimpe, Friedrich Solowjow. [doi]
• Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-TuningHao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion. [doi]
• Towards Scalable and Versatile Weight Space LearningKonstantin Schürholt, Michael W. Mahoney, Damian Borth. [doi]
• The Balanced-Pairwise-Affinities Feature TransformDaniel Shalam, Simon Korman. [doi]
• Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution LearnabilitySepanta Zeighami, Cyrus Shahabi. [doi]
• Sub-token ViT Embedding via Stochastic Resonance TransformersDong Lao, Yangchao Wu, Tian-Yu Liu, Alex Wong 0001, Stefano Soatto. [doi]
• Generalized Smooth Variational Inequalities: Methods with Adaptive StepsizesDaniil Vankov, Angelia Nedich, Lalitha Sankar. [doi]
• ESM All-Atom: Multi-Scale Protein Language Model for Unified Molecular ModelingKangjie Zheng, Siyu Long, Tianyu Lu, Junwei Yang, Xinyu Dai, Ming Zhang 0004, Zaiqing Nie, Wei-Ying Ma, Hao Zhou 0012. [doi]
• Reinformer: Max-Return Sequence Modeling for Offline RLZifeng Zhuang, Dengyun Peng, Jinxin Liu, Ziqi Zhang, Donglin Wang. [doi]
• Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly DetectionYuxin Li, Yaoxuan Feng, Bo Chen 0001, Wenchao Chen, Yubiao Wang, Xinyue Hu, Baolin Sun, Chunhui Qu, Mingyuan Zhou. [doi]
• Model Assessment and Selection under Temporal Distribution ShiftElise Han, Chengpiao Huang, Kaizheng Wang. [doi]
• Learning High-Order Relationships of Brain RegionsWeikang Qiu, Huangrui Chu, Selena Wang, Haolan Zuo, Xiaoxiao Li, Yize Zhao, Rex Ying. [doi]
• Liouville Flow Importance SamplerYifeng Tian, Nishant Panda, Yen-Ting Lin. [doi]
• On the Hardness of Probabilistic Neurosymbolic LearningJaron Maene, Vincent Derkinderen, Luc De Raedt. [doi]
• Adaptive Accompaniment with ReaLchordsYusong Wu, Tim Cooijmans, Kyle Kastner, Adam Roberts, Ian Simon, Alexander Scarlatos, Chris Donahue, Cassie Tarakajian, Shayegan Omidshafiei, Aaron C. Courville, Pablo Samuel Castro, Natasha Jaques, Cheng-Zhi Anna Huang. [doi]
• Scalable Pre-training of Large Autoregressive Image ModelsAlaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Ángel Bautista 0001, Vaishaal Shankar, Alexander T. Toshev, Joshua M. Susskind, Armand Joulin. [doi]
• Offline Inverse RL: New Solution Concepts and Provably Efficient AlgorithmsFilippo Lazzati, Mirco Mutti, Alberto Maria Metelli. [doi]
• Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-DecodingGuangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu 0001, Liping Tang, Yuan Gao, Zhen Li 0026, Shuguang Cui, Julian J. McAuley, Zichao Yang, Eric P. Xing, Zhiting Hu. [doi]
• Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-SquaresLiangzu Peng, Wotao Yin. [doi]
• Toward Adaptive Reasoning in Large Language Models with Thought RollbackSijia Chen, Baochun Li. [doi]
• A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC MaximizationXinwen Zhang, Ali Payani, Myungjin Lee, Richard Souvenir, Hongchang Gao. [doi]
• Long Range Propagation on Continuous-Time Dynamic GraphsAlessio Gravina, Giulio Lovisotto, Claudio Gallicchio, Davide Bacciu, Claas Grohnfeldt. [doi]
• High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference CostJiakui Hu, Man Yao, Xuerui Qiu, Yuhong Chou, Yuxuan Cai, Ning Qiao, Yonghong Tian 0001, Bo Xu 0002, Guoqi Li. [doi]
• Individualized Privacy Accounting via Subsampling with Applications in Combinatorial OptimizationBadih Ghazi, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Adam Sealfon. [doi]
• Balancing Similarity and Complementarity for Federated LearningKunda Yan, Sen Cui, Abudukelimu Wuerkaixi, Jingfeng Zhang, Bo Han 0003, Gang Niu 0001, Masashi Sugiyama, Changshui Zhang. [doi]
• Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order GradientHao Di, Haishan Ye, Yueling Zhang, Xiangyu Chang, Guang Dai, Ivor W. Tsang. [doi]
• Ameliorate Spurious Correlations in Dataset CondensationJustin Cui, Ruochen Wang, Yuanhao Xiong, Cho-Jui Hsieh. [doi]
• Understanding MLP-Mixer as a wide and sparse MLPTomohiro Hayase, Ryo Karakida. [doi]
• Rethinking the Flat Minima Searching in Federated LearningTaehwan Lee, Sung Whan Yoon. [doi]
• Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary DynamicsXinyu Zhang, Wenjie Qiu 0005, Yi-Chen Li 0001, Lei Yuan 0001, Chengxing Jia, Zongzhang Zhang, Yang Yu 0001. [doi]
• Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network ModuleYixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Ashish Sirasao, Emad Barsoum. [doi]
• HexGen: Generative Inference of Large Language Model over Heterogeneous EnvironmentYouhe Jiang, Ran Yan, Xiaozhe Yao, Yang Zhou, Beidi Chen, Binhang Yuan. [doi]
• Taylor Videos for Action RecognitionLei Wang 0001, Xiuyuan Yuan, Tom Gedeon, Liang Zheng 0001. [doi]
• Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain AdaptationDapeng Hu, Jian Liang, Xinchao Wang, Chuan-Sheng Foo. [doi]
• Spider: A Unified Framework for Context-dependent Concept SegmentationXiaoqi Zhao, Youwei Pang, Wei Ji 0011, Baicheng Sheng, Jiaming Zuo, Lihe Zhang, Huchuan Lu. [doi]
• Eluder-based Regret for Stochastic Contextual MDPsOrin Levy, Asaf B. Cassel, Alon Cohen, Yishay Mansour. [doi]
• Prompt-guided Precise Audio Editing with Diffusion ModelsManjie Xu, Chenxing Li, Duzhen Zhang, Dan Su 0002, Wei Liang, Dong Yu 0001. [doi]
• Overcoming Saturation in Density Ratio Estimation by Iterated RegularizationLukas Gruber, Markus Holzleitner, Johannes Lehner, Sepp Hochreiter, Werner Zellinger. [doi]
• Perturb-and-Project: Differentially Private Similarities and MarginalsVincent Cohen-Addad, Tommaso d'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong. [doi]
• Exploring the Benefit of Activation Sparsity in Pre-trainingZhengyan Zhang, Chaojun Xiao, Qiujieli Qin, Yankai Lin, Zhiyuan Zeng, Xu Han 0007, Zhiyuan Liu 0001, Ruobing Xie, Maosong Sun 0001, Jie Zhou 0016. [doi]
• Controlling Behavioral Diversity in Multi-Agent Reinforcement LearningMatteo Bettini, Ryan Kortvelesy, Amanda Prorok. [doi]
• FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement LearningYuwei Fu, Haichao Zhang, Di Wu 0044, Wei Xu, Benoit Boulet. [doi]
• Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed EnvironmentsAntoine Dedieu, Wolfgang Lehrach, Guangyao Zhou, Dileep George, Miguel Lázaro-Gredilla. [doi]
• A Provable Decision Rule for Out-of-Distribution DetectionXinsong Ma, Xin Zou, Weiwei Liu. [doi]
• Exploring Training on Heterogeneous Data with Mixture of Low-rank AdaptersYuhang Zhou, Zihua Zhao, Siyuan Du, Haolin Li, Jiangchao Yao, Ya Zhang 0002, Yanfeng Wang. [doi]
• Non-clairvoyant Scheduling with Partial PredictionsZiyad Benomar, Vianney Perchet. [doi]
• Position: Do Not Explain Vision Models Without ContextPaulina Tomaszewska, Przemyslaw Biecek. [doi]
• HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid PredictionLanxiang Xing, Haixu Wu, Yuezhou Ma, Jianmin Wang 0001, Mingsheng Long. [doi]
• Graph Neural PDE Solvers with Conservation and Similarity-EquivarianceMasanobu Horie, Naoto Mitsume. [doi]
• Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic OptimisationOssi Räisä, Joonas Jälkö, Antti Honkela. [doi]
• On a Neural Implementation of Brenier's Polar FactorizationNina Vesseron, Marco Cuturi. [doi]
• Random features models: a way to study the success of naive imputationAlexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet. [doi]
• Repeat After Me: Transformers are Better than State Space Models at CopyingSamy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach. [doi]
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous SystemsJianliang He, Siyu Chen, Fengzhuo Zhang, Zhuoran Yang. [doi]
• Position: Embracing Negative Results in Machine LearningFlorian Karl, Lukas Malte Kemeter, Gabriel Dax, Paulina Sierak. [doi]
• LongRoPE: Extending LLM Context Window Beyond 2 Million TokensYiran Ding, Li Lyna Zhang, Chengruidong Zhang, Yuanyuan Xu, Ning Shang, Jiahang Xu, Fan Yang 0024, Mao Yang. [doi]
• Decoupling Learning and Decision-Making: Breaking the O(T) Barrier in Online Resource Allocation with First-Order MethodsWenzhi Gao, Chunlin Sun, Chenyu Xue, Yinyu Ye 0001. [doi]
• Rethinking Data Shapley for Data Selection Tasks: Misleads and MeritsJiachen T. Wang, Tianji Yang, James Zou 0001, Yongchan Kwon, Ruoxi Jia 0001. [doi]
• Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift AdaptationYuyang Qian, Peng Zhao 0006, Yu-Jie Zhang, Masashi Sugiyama, Zhi-Hua Zhou. [doi]
• DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep LearningS. Ashwin Hebbar, Sravan Kumar Ankireddy, Hyeji Kim, Sewoong Oh, Pramod Viswanath. [doi]
• One-Shot Strategic Classification Under Unknown CostsElan Rosenfeld, Nir Rosenfeld. [doi]
• Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence RatesRiccardo Grazzi, Massimiliano Pontil, Saverio Salzo. [doi]
• MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data UtilizationYu Zhang 0133, Qi Zhang 0020, Zixuan Gong, Yiwei Shi, Yepeng Liu, Duoqian Miao 0001, Yang Liu, Ke Liu, Kun Yi, Wei Fan 0010, Liang Hu 0004, Changwei Wang. [doi]
• Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code PredicatesAshish Hooda, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha. [doi]
• Asymptotically Optimal and Computationally Efficient Average Treatment Effect Estimation in A/B testingVikas Deep, Achal Bassamboo, Sandeep K. Juneja. [doi]
• Conformalized Survival Distributions: A Generic Post-Process to Increase CalibrationShiang Qi, Yakun Yu, Russell Greiner. [doi]
• Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient DescentKonstantin Donhauser, Javier Abad Martinez, Neha Hulkund, Fanny Yang. [doi]
• Learning Decision Policies with Instrumental Variables through Double Machine LearningDaqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska. [doi]
• Generalist Equivariant Transformer Towards 3D Molecular Interaction LearningXiangzhe Kong, Wenbing Huang 0001, Yang Liu 0005. [doi]
• DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data AugmentationZelin Zang, Hao Luo 0004, Kai Wang 0036, Panpan Zhang, Fan Wang 0019, Stan Z. Li, Yang You 0001. [doi]
• Compositional Curvature Bounds for Deep Neural NetworksTaha Entesari, Sina Sharifi, Mahyar Fazlyab. [doi]
• 3D Geometric Shape Assembly via Efficient Point Cloud MatchingNahyuk Lee, Juhong Min, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, Minsu Cho. [doi]
• Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action RecognitionYuke Li, Guangyi Chen 0002, Ben Abramowitz, Stefano Anzellotti, Donglai Wei 0001. [doi]
• Differentially Private Synthetic Data via Foundation Model APIs 2: TextChulin Xie, Zinan Lin 0001, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A. Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li 0026, Sergey Yekhanin. [doi]
• Equilibrium of Data Markets with ExternalitySafwan Hossain, Yiling Chen 0001. [doi]
• Towards Resource-friendly, Extensible and Stable Incomplete Multi-view ClusteringShengju Yu, Zhibin Dong, Siwei Wang 0001, Xinhang Wan, Yue Liu 0008, Weixuan Liang, Pei Zhang 0008, Wenxuan Tu, Xinwang Liu 0002. [doi]
• Amortized Equation Discovery in Hybrid Dynamical SystemsYongtuo Liu, Sara Magliacane, Miltiadis Kofinas, Stratis Gavves. [doi]
• MS3D: A RG Flow-Based Regularization for GAN Training with Limited DataJian Wang, Xin Lan, Yuxin Tian, Jiancheng Lv 0001. [doi]
• Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule SubstratesZhenqiao Song, Yunlong Zhao, Wenxian Shi, Wengong Jin, Yang Yang, Lei Li 0005. [doi]
• CaPS: Collaborative and Private Synthetic Data Generation from Distributed SourcesSikha Pentyala, Mayana Pereira, Martine De Cock. [doi]
• To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DROZi-Hao Qiu, Siqi Guo, Mao Xu, Tuo Zhao, Lijun Zhang 0005, Tianbao Yang. [doi]
• Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic AnalysisYingying Li, Jing Yu 0010, Lauren Conger, Taylan Kargin, Adam Wierman. [doi]
• Learning from Streaming Data when Users ChooseJinyan Su, Sarah Dean. [doi]
• Mitigating Label Noise on Graphs via Topological Sample SelectionYuhao Wu, Jiangchao Yao, Xiaobo Xia, Jun Yu, Ruxin Wang 0002, Bo Han, Tongliang Liu. [doi]
• Prompting a Pretrained Transformer Can Be a Universal ApproximatorAleksandar Petrov, Philip Torr 0001, Adel Bibi. [doi]
• Online Adaptive Anomaly Thresholding with Confidence SequencesSophia Huiwen Sun, Abishek Sankararaman, Balakrishnan Narayanaswamy. [doi]
• Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural NetworksHaoyu Li, Shichang Zhang, Longwen Tang, Mathieu Bauchy, Yizhou Sun. [doi]
• Provable Representation with Efficient Planning for Partially Observable Reinforcement LearningHongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans, Bo Dai 0001. [doi]
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space DualityTri Dao, Albert Gu. [doi]
• Towards Understanding Inductive Bias in Transformers: A View From InfinityItay Lavie, Guy Gur-Ari, Zohar Ringel. [doi]
• Vanilla Bayesian Optimization Performs Great in High DimensionsCarl Hvarfner, Erik Orm Hellsten, Luigi Nardi. [doi]
• Coactive Learning for Large Language Models using Implicit User FeedbackAaron David Tucker, Kianté Brantley, Adam Cahall, Thorsten Joachims. [doi]
• Privacy Attacks in Decentralized LearningAbdellah El Mrini, Edwige Cyffers, Aurélien Bellet. [doi]
• Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to K-Level Stochastic OptimizationsXiaokang Pan, Xingyu Li, Jin Liu, Tao Sun, Kai Sun, Lixing Chen, Zhe Qu. [doi]
• Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AIYegor Tkachenko. [doi]
• Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain AdaptationWangzi Qi, Wei Wang, Chao Huang 0008, Jie Wen 0001, Cong Wang. [doi]
• MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go ApproximationAlexandre Hayderi, Amin Saberi, Ellen Vitercik, Anders Wikum. [doi]
• Understanding Finetuning for Factual Knowledge ExtractionGaurav Rohit Ghosal, Tatsunori Hashimoto, Aditi Raghunathan. [doi]
• Continuous Treatment Effects with Surrogate OutcomesZhenghao Zeng, David Arbour, Avi Feller, Raghavendra Addanki, Ryan A. Rossi, Ritwik Sinha, Edward H. Kennedy. [doi]
• Federated Neuro-Symbolic LearningPengwei Xing, Songtao Lu, Han Yu 0001. [doi]
• AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual DistractorsYucen Wang, Shenghua Wan, Le Gan, Shuai Feng, De-Chuan Zhan. [doi]
• Highway Value Iteration NetworksYuhui Wang, Weida Li, Francesco Faccio, Qingyuan Wu, Jürgen Schmidhuber. [doi]
• Image Restoration Through Generalized Ornstein-Uhlenbeck BridgeConghan Yue, Zhengwei Peng, Junlong Ma, Shiyan Du, Pengxu Wei, Dongyu Zhang. [doi]
• Perfect Alignment May be Poisonous to Graph Contrastive LearningJingyu Liu, Huayi Tang, Yong Liu 0018. [doi]
• Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level PrivacyBo Li 0001, Wei Wang 0030, Peng Ye. [doi]
• Conditional Language Learning with ContextXiao Zhang, Miao Li, Ji Wu. [doi]
• Multi-Patch Prediction: Adapting Language Models for Time Series Representation LearningYuxuan Bian, Xuan Ju, Jiangtong Li, Zhijian Xu, Dawei Cheng, Qiang Xu 0001. [doi]
• Few-shot Adaptation to Distribution Shifts By Mixing Source and Target EmbeddingsYihao Xue, Ali Payani, Yu Yang 0007, Baharan Mirzasoleiman. [doi]
• FrameQuant: Flexible Low-Bit Quantization for TransformersHarshavardhan Adepu, Zhanpeng Zeng, Li Zhang, Vikas Singh. [doi]
• IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling ConsistencyLinshan Hou, Ruili Feng, Zhongyun Hua, Wei Luo 0001, Leo Yu Zhang, Yiming Li. [doi]
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalMantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang 0001, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li 0026, David A. Forsyth, Dan Hendrycks. [doi]
• Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free InferenceLuca Masserano, Alexander Shen, Michele Doro, Tommaso Dorigo, Rafael Izbicki, Ann B. Lee. [doi]
• CaM: Cache Merging for Memory-efficient LLMs InferenceYuxin Zhang 0002, Yuxuan Du, Gen Luo, Yunshan Zhong, Zhenyu Zhang 0015, Shiwei Liu 0003, Rongrong Ji. [doi]
• Inferring Dynamic Networks from Marginals with Iterative Proportional FittingSerina Chang, Frederic Koehler, Zhaonan Qu, Jure Leskovec, Johan Ugander. [doi]
• Benchmarking Deletion Metrics with the Principled ExplanationsYipei Wang, Xiaoqian Wang. [doi]
• Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical ReexaminationZhiyao Luo, Yangchen Pan, Peter J. Watkinson, Tingting Zhu 0001. [doi]
• See More Details: Efficient Image Super-Resolution by Experts MiningEduard Zamfir, Zongwei Wu, Nancy Mehta, Yulun Zhang, Radu Timofte. [doi]
• Learning 1-Bit Tiny Object Detector with Discriminative Feature RefinementSheng Xu 0007, Mingze Wang, Yanjing Li, Mingbao Lin, Baochang Zhang 0001, David S. Doermann, Xiao Sun. [doi]
• Understanding Stochastic Natural Gradient Variational InferenceKaiwen Wu, Jacob R. Gardner. [doi]
• Probabilistic Constrained Reinforcement Learning with Formal InterpretabilityYanran Wang, Qiuchen Qian, David Boyle 0001. [doi]
• MALIBO: Meta-learning for Likelihood-free Bayesian OptimizationJiarong Pan, Stefan Falkner, Felix Berkenkamp, Joaquin Vanschoren. [doi]
• Robust Stable Spiking Neural NetworksJianhao Ding, Zhiyu Pan, Yujia Liu, Zhaofei Yu, Tiejun Huang 0001. [doi]
• Equivariance via Minimal Frame Averaging for More Symmetries and EfficiencyYuchao Lin, Jacob Helwig, Shurui Gui, Shuiwang Ji. [doi]
• LLaGA: Large Language and Graph AssistantRunjin Chen, Tong Zhao 0003, Ajay Kumar Jaiswal, Neil Shah, Zhangyang Wang. [doi]
• Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution StrategyRisheng Liu, Zhu Liu, Wei Yao 0014, Shangzhi Zeng, Jin Zhang 0002. [doi]
• Improving Neural Additive Models with Bayesian PrinciplesKouroche Bouchiat, Alexander Immer, Hugo Yèche, Gunnar Rätsch, Vincent Fortuin. [doi]
• Et Tu Certifications: Robustness Certificates Yield Better Adversarial ExamplesAndrew C. Cullen, Shijie Liu, Paul Montague, Sarah Monazam Erfani, Benjamin I. P. Rubinstein. [doi]
• Hybrid Neural Representations for Spherical DataHyomin Kim, Yunhui Jang, Jaeho Lee 0001, Sungsoo Ahn. [doi]
• Feature Importance Disparities for Data Bias InvestigationsPeter W. Chang, Leor Fishman, Seth Neel. [doi]
• Matroid Semi-Bandits in Sublinear TimeRuo-Chun Tzeng, Naoto Ohsaka, Kaito Ariu. [doi]
• Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale ModelsZixin Zhang 0004, Fan Qi, Changsheng Xu. [doi]
• Consistent Adversarially Robust Linear Classification: Non-Parametric SettingElvis Dohmatob. [doi]
• Towards Unified Multi-granularity Text Detection with Interactive AttentionXingyu Wan, Chengquan Zhang, Pengyuan Lyu, Sen Fan, Zihan Ni, Kun Yao, Errui Ding, Jingdong Wang 0001. [doi]
• Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-MindMo Yu, Qiujing Wang, Shunchi Zhang, Yisi Sang, Kangsheng Pu, Zekai Wei, Han Wang, Liyan Xu, Jing Li, Yue Yu, Jie Zhou 0016. [doi]
• Evaluating Quantized Large Language ModelsShiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang 0002. [doi]
• Graph Generation with Diffusion MixtureJaehyeong Jo, Dongki Kim, Sung Ju Hwang. [doi]
• Faster Sampling via Stochastic Gradient Proximal SamplerXunpeng Huang, Difan Zou, Hanze Dong, Yian Ma, Tong Zhang 0001. [doi]
• Learning Modality Knowledge Alignment for Cross-Modality TransferWenxuan Ma 0001, Shuang Li 0008, Lincan Cai, Jingxuan Kang. [doi]
• When Representations Align: Universality in Representation Learning DynamicsLoek van Rossem, Andrew M. Saxe. [doi]
• DNCs Require More Planning StepsYara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster. [doi]
• Agent Instructs Large Language Models to be General Zero-Shot ReasonersNicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, Chenguang Wang 0001. [doi]
• Connect Later: Improving Fine-tuning for Robustness with Targeted AugmentationsHelen Qu, Sang Michael Xie. [doi]
• A decoder-only foundation model for time-series forecastingAbhimanyu Das, Weihao Kong, Rajat Sen, Yichen Zhou. [doi]
• SelfVC: Voice Conversion With Iterative Refinement using Self TransformationsPaarth Neekhara, Shehzeen Samarah Hussain, Rafael Valle, Boris Ginsburg, Rishabh Ranjan, Shlomo Dubnov, Farinaz Koushanfar, Julian J. McAuley. [doi]
• On a Combinatorial Problem Arising in Machine TeachingJoakim Sunde, Brigt Arve Toppe Håvardstun, Jan Kratochvíl, Jan Arne Telle. [doi]
• Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked PretrainingQi Zhang, Tianqi Du, Haotian Huang, Yifei Wang, Yisen Wang. [doi]
• Bounded and Uniform Energy-based Out-of-distribution Detection for GraphsShenzhi Yang, Bin Liang, An Liu, Lin Gui, Xingkai Yao, Xiaofang Zhang. [doi]
• Byzantine Resilient and Fast Federated Few-Shot LearningAnkit Pratap Singh, Namrata Vaswani. [doi]
• DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-TrainingZhongkai Hao, Chang Su, Songming Liu, Julius Berner, Chengyang Ying, Hang Su 0006, Anima Anandkumar, Jian Song, Jun Zhu 0001. [doi]
• Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning PerspectiveYajie Bao, Michael Crawshaw, Mingrui Liu. [doi]
• One for All: A Universal Generator for Concept Unlearnability via Multi-Modal AlignmentChaochao Chen, Jiaming Zhang, Yuyuan Li, Zhongxuan Han. [doi]
• Adversarial Attacks on Combinatorial Multi-Armed BanditsRishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao. [doi]
• Neural operators meet conjugate gradients: The FCG-NO method for efficient PDE solvingAlexander Rudikov, Vladimir Fanaskov, Ekaterina A. Muravleva, Yuri M. Laevsky, Ivan V. Oseledets. [doi]
• Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language ModelsJinhao Li 0004, Haopeng Li, Sarah Monazam Erfani, Lei Feng, James Bailey 0001, Feng Liu. [doi]
• Covert Malicious Finetuning: Challenges in Safeguarding LLM AdaptationDanny Halawi, Alexander Wei 0001, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt. [doi]
• Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and InsufficiencyYangfan Liu, Jiaqi Lv, Xin Geng 0001, Ning Xu 0009. [doi]
• Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraintWei Xiong 0015, Hanze Dong, Chenlu Ye, Ziqi Wang, Han Zhong 0001, Heng Ji, Nan Jiang 0008, Tong Zhang 0001. [doi]
• IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality MetricsEkaterina Shumitskaya, Anastasia Antsiferova, Dmitriy S. Vatolin. [doi]
• Quantum Positional Encodings for Graph Neural NetworksSlimane Thabet, Mehdi Djellabi, Igor Olegovich Sokolov, Sachin Kasture, Louis-Paul Henry, Loïc Henriet. [doi]
• Explorations of Self-Repair in Language ModelsCody Rushing, Neel Nanda. [doi]
• Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial TrainingJiacheng Zhang, Feng Liu 0003, Dawei Zhou 0004, Jingfeng Zhang, Tongliang Liu. [doi]
• Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment ProblemZhentao Tan, Yadong Mu. [doi]
• How Flawed Is ECE? An Analysis via Logit SmoothingMuthu Chidambaram, Holden Lee, Colin McSwiggen, Semon Rezchikov. [doi]
• A New Linear Scaling Rule for Private Adaptive Hyperparameter OptimizationAshwinee Panda, Xinyu Tang, Saeed Mahloujifar, Vikash Sehwag, Prateek Mittal. [doi]
• ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane ReflectionsMassimo Bini, Karsten Roth, Zeynep Akata, Anna Khoreva. [doi]
• Reinforcement Learning within Tree Search for Fast Macro PlacementZijie Geng, Jie Wang 0005, Ziyan Liu, Siyuan Xu, Zhentao Tang, Mingxuan Yuan, Jianye Hao, Yongdong Zhang 0001, Feng Wu 0001. [doi]
• Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional ConnectivityAli Behrouz, Parsa Delavari, Farnoosh Hashemi. [doi]
• Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule GenerationZhilin Huang, Ling Yang 0006, Xiangxin Zhou, Chujun Qin, Yijie Yu, Xiawu Zheng, Zikun Zhou, Wentao Zhang, Yu Wang, Wenming Yang. [doi]
• Conformal Predictions under Markovian DataFrédéric Zheng, Alexandre Proutière. [doi]
• Flora: Low-Rank Adapters Are Secretly Gradient CompressorsYongchang Hao, Yanshuai Cao, Lili Mou. [doi]
• AI Alignment with Changing and Influenceable Reward FunctionsMicah Carroll, Davis Foote, Anand Siththaranjan, Stuart Russell 0001, Anca D. Dragan. [doi]
• Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGDYijun Wan, Melih Barsbey, Abdellatif Zaidi, Umut Simsekli. [doi]
• Enhancing Adversarial Robustness in SNNs with Sparse GradientsYujia Liu, Tong Bu, Jianhao Ding, Zecheng Hao, Tiejun Huang 0001, Zhaofei Yu. [doi]
• How Private are DP-SGD Implementations?Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang. [doi]
• KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics DemonstrationsLongxin Kou, Fei Ni, Yan Zheng 0002, Jinyi Liu 0002, Yifu Yuan, Zibin Dong, Jianye Hao. [doi]
• Scalable AI Safety via Doubly-Efficient DebateJonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras. [doi]
• Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman ProblemsYifan Xia, Xianliang Yang, Zichuan Liu, Zhihao Liu, Lei Song, Jiang Bian 0002. [doi]
• Collective Certified Robustness against Graph Injection AttacksYuni Lai, Bailin Pan, Kaihuang Chen, Yancheng Yuan, Kai Zhou 0001. [doi]
• Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEsS. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Andrew Stuart, Michael W. Mahoney, Bernie Wang 0001. [doi]
• Monotone Individual FairnessYahav Bechavod. [doi]
• Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client ParticipationHaibo Yang 0001, Peiwen Qiu, Prashant Khanduri, Minghong Fang, Jia Liu 0002. [doi]
• Efficient Mixture Learning in Black-Box Variational InferenceAlexandra Hotti, Oskar Kviman, Ricky Molén, Víctor Elvira, Jens Lagergren. [doi]
• OSN: Infinite Representations of Dynamic 3D Scenes from Monocular VideosZiyang Song, Jinxi Li,