Table of Contents

• Learning from Sparse Offline Datasets via Conservative Density EstimationZhepeng Cen, Zuxin Liu, Zitong Wang, Yihang Yao, Henry Lam, Ding Zhao. [doi]
• Predictive auxiliary objectives in deep RL mimic learning in the brainChing Fang, Kim Stachenfeld. [doi]
• Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningFuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, Lijuan Wang. [doi]
• Threshold-Consistent Margin Loss for Open-World Deep Metric LearningQin Zhang, Linghan Xu, Jun Fang, Qingming Tang, Ying Nian Wu, Joseph Tighe, Yifan Xing. [doi]
• Generalization error of spectral algorithmsMaksim Velikanov, Maxim Panov, Dmitry Yarotsky. [doi]
• Benchmarking and Improving Generator-Validator Consistency of Language ModelsXiang Lisa Li, Vaishnavi Shrivastava, Siyan Li, Tatsunori Hashimoto, Percy Liang. [doi]
• Time Fairness in Online Knapsack ProblemsAdam Lechowicz, Rik Sengupta, Bo Sun 0004, Shahin Kamali, Mohammad Hajiesmaili. [doi]
• Deep Generative Clustering with Multimodal Diffusion Variational AutoencodersEmanuele Palumbo, Laura Manduchi, Sonia Laguna, Daphné Chopard, Julia E. Vogt. [doi]
• Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play FrameworkEliya Segev, Maya Alroy, Ronen Katsir, Noam Wies, Ayana Shenhav, Yael Ben-Oren, David Zar, Oren Tadmor, Jacob Bitterman, Amnon Shashua, Tal Rosenwein. [doi]
• Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image ClassificationReza Esfandiarpoor, Stephen H. Bach. [doi]
• Self-Consuming Generative Models Go MADSina Alemohammad, Josue Casco-Rodriguez, Lorenzo Luzi, Ahmed Imtiaz Humayun, Hossein Babaei, Daniel LeJeune, Ali Siahkoohi, Richard G. Baraniuk. [doi]
• Continual Momentum Filtering on Parameter Space for Online Test-time AdaptationJae Hong Lee, Joon-Hyuk Chang. [doi]
• Sparse Weight Averaging with Multiple Particles for Iterative Magnitude PruningMoonseok Choi, Hyungi Lee, Giung Nam, Juho Lee 0001. [doi]
• Convolutional Deep Kernel MachinesEdward Milsom, Ben Anson, Laurence Aitchison. [doi]
• CPPO: Continual Learning for Reinforcement Learning with Human FeedbackHan Zhang 0025, Yu Lei, Lin Gui 0003, Min Yang 0007, Yulan He 0001, Hui Wang, Ruifeng Xu. [doi]
• Can Transformers Capture Spatial Relations between Objects?Chuan Wen, Dinesh Jayaraman, Yang Gao 0029. [doi]
• The Consensus Game: Language Model Generation via Equilibrium SearchAthul Paul Jacob, Yikang Shen, Gabriele Farina, Jacob Andreas. [doi]
• Parameter-Efficient Orthogonal Finetuning via Butterfly FactorizationWeiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu 0019, Juyeon Heo, Songyou Peng, YanDong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf. [doi]
• Quantifying the Plausibility of Context Reliance in Neural Machine TranslationGabriele Sarti, Grzegorz Chrupala, Malvina Nissim, Arianna Bisazza. [doi]
• Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMsMiao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, Bryan Hooi. [doi]
• CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making AgentsSiyuan Qi, Shuo Chen, Yexin Li, Xiangyu Kong, Junqi Wang, Bangcheng Yang, Pring Wong, Yifan Zhong, Xiaoyuan Zhang, Zhaowei Zhang, Nian Liu, Yaodong Yang 0001, Song Chun Zhu. [doi]
• Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion ModelsKevin Black, Mitsuhiko Nakamoto, Pranav Atreya, Homer Rich Walke, Chelsea Finn, Aviral Kumar, Sergey Levine. [doi]
• Physics-Regulated Deep Reinforcement Learning: Invariant EmbeddingsHongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo. [doi]
• SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt TuningHongjun Wang, Sagar Vaze, Kai Han 0001. [doi]
• Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent AdaptivityEmmeran Johnson, Ciara Pike-Burke, Patrick Rebeschini. [doi]
• Adversarial Imitation Learning via BoostingJonathan D. Chang, Dhruv Sreenivas, Yingbing Huang, Kianté Brantley, Wen Sun 0002. [doi]
• Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity ViewYujie Mo, Feiping Nie 0001, Ping Hu, Heng Tao Shen, Zheng Zhang 0006, Xinchao Wang, Xiaofeng Zhu 0001. [doi]
• Variance-aware Regret Bounds for Stochastic Contextual Dueling BanditsQiwei Di, Tao Jin 0002, Yue Wu, Heyang Zhao, Farzad Farnoud, Quanquan Gu. [doi]
• Adversarial Feature Map Pruning for BackdoorDong Huang 0005, Qingwen Bu. [doi]
• VQ-TR: Vector Quantized Attention for Time Series ForecastingKashif Rasul, Andrew Bennett, Pablo Vicente, Umang Gupta, Hena Ghonia, Anderson Schneider, Yuriy Nevmyvaka. [doi]
• PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image SynthesisJunsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Zhongdao Wang, James T. Kwok, Ping Luo 0002, Huchuan Lu, Zhenguo Li. [doi]
• Grounding Multimodal Large Language Models to the WorldZhiliang Peng, Wenhui Wang 0003, Li Dong 0004, Yaru Hao, Shaohan Huang, Shuming Ma, Qixiang Ye, Furu Wei. [doi]
• Attention-based Iterative Decomposition for Tensor Product RepresentationTaewon Park, Inchul Choi, Minho Lee 0001. [doi]
• SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output ModelsSeyyede Fatemeh Seyyedsalehi, Mahdieh Soleymani Baghshah, Hamid R. Rabiee. [doi]
• Distributionally Robust Optimization with Bias and Variance ReductionRonak Mehta, Vincent Roulet, Krishna Pillutla, Zaïd Harchaoui. [doi]
• Dynamic Layer Tying for Parameter-Efficient TransformersTamir David Hay, Lior Wolf. [doi]
• YaRN: Efficient Context Window Extension of Large Language ModelsBowen Peng, Jeffrey Quesnelle, Honglu Fan, Enrico Shippole. [doi]
• Beyond Memorization: Violating Privacy via Inference with Large Language ModelsRobin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev. [doi]
• Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problemsGabriel Cardoso 0001, Yazid Janati El Idrissi, Sylvain Le Corff, Eric Moulines. [doi]
• Human Feedback is not Gold StandardTom Hosking, Phil Blunsom, Max Bartolo. [doi]
• TapMo: Shape-aware Motion Generation of Skeleton-free CharactersJiaxu Zhang, Shaoli Huang, Zhigang Tu 0001, Xin Chen 0059, Xiaohang Zhan, Gang Yu, Ying Shan. [doi]
• DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image GenerationHong Chen, Yipeng Zhang, Simin Wu, Xin Wang 0019, Xuguang Duan, Yuwei Zhou, Wenwu Zhu 0001. [doi]
• T-Rep: Representation Learning for Time Series using Time-EmbeddingsArchibald Fraikin, Adrien Bennetot, Stéphanie Allassonnière. [doi]
• Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChainMarcus J. Min, Yangruibo Ding, Luca Buratti, Saurabh Pujar, Gail E. Kaiser, Suman Jana, Baishakhi Ray. [doi]
• Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning PlatformShengyi Huang, Jiayi Weng, Rujikorn Charakorn, Min Lin, Zhongwen Xu, Santiago Ontañón. [doi]
• Evaluating Large Language Models at Evaluating Instruction FollowingZhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng 0001, Tanya Goyal, Danqi Chen 0001. [doi]
• LEGO-Prover: Neural Theorem Proving with Growing LibrariesHaiming Wang, Huajian Xin, Chuanyang Zheng, Zhengying Liu, Qingxing Cao, Yinya Huang, Jing Xiong, Han Shi, Enze Xie, Jian Yin 0001, Zhenguo Li, Xiaodan Liang. [doi]
• Augmented Bayesian Policy SearchMahdi Kallel, Debabrota Basu, Riad Akrour, Carlo D'Eramo. [doi]
• On Stationary Point Convergence of PPO-ClipRuinan Jin, Shuai Li 0010, Baoxiang Wang 0001. [doi]
• Emu: Generative Pretraining in MultimodalityQuan Sun, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Yueze Wang, Hongcheng Gao, Jingjing Liu, Tiejun Huang 0003, Xinlong Wang. [doi]
• CoLiDE: Concomitant Linear DAG EstimationSeyed Saman Saboksayr, Gonzalo Mateos, Mariano Tepper. [doi]
• OctoPack: Instruction Tuning Code Large Language ModelsNiklas Muennighoff, Qian Liu, Armel Randy Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, Shayne Longpre. [doi]
• Kosmos-G: Generating Images in Context with Multimodal Large Language ModelsXichen Pan, Li Dong 0004, Shaohan Huang, Zhiliang Peng, Wenhu Chen, Furu Wei. [doi]
• UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data ScienceYazheng Yang, Yuqi Wang, Guang Liu, Ledell Wu, Qi Liu 0049. [doi]
• KoLA: Carefully Benchmarking World Knowledge of Large Language ModelsJifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-li, Xin Lv, Hao Peng 0015, Zijun Yao 0002, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, Kaifeng Yun, Linlu Gong, Nianyi Lin, Jianhui Chen, Zhili Wu, Yunjia Qi, Weikai Li 0002, Yong Guan, Kaisheng Zeng, Ji Qi, Hailong Jin, Jinxin Liu, Yu Gu 0002, Yuan Yao 0011, Ning Ding 0002, Lei Hou 0001, Zhiyuan Liu 0001, Bin Xu 0001, Jie Tang 0001, Juanzi Li. [doi]
• Shadow Cones: A Generalized Framework for Partial Order EmbeddingsTao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa. [doi]
• On Accelerating Diffusion-Based Sampling Processes via Improved Integration ApproximationGuoqiang Zhang 0003, Kenta Niwa, W. Bastiaan Kleijn. [doi]
• Generalization of Scaled Deep ResNets in the Mean-Field RegimeYihang Chen, Fanghui Liu 0001, Yiping Lu, Grigorios Chrysos 0002, Volkan Cevher. [doi]
• Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD GeneralizationYuhang Zang, Hanlin Goh, Joshua M. Susskind, Chen Huang 0001. [doi]
• A Restoration Network as an Implicit PriorYuyang Hu, Mauricio Delbracio, Peyman Milanfar, Ulugbek Kamilov. [doi]
• Pooling Image Datasets with Multiple Covariate Shift and ImbalanceSotirios Panagiotis Chytas, Vishnu Suresh Lokhande, Vikas Singh. [doi]
• Modulated Phase Diffusor: Content-Oriented Feature Synthesis for Detecting Unknown ObjectsAming Wu, Cheng Deng. [doi]
• FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient DescentZiyao Wang, Jianyu Wang, Ang Li. [doi]
• Porf: Pose residual field for accurate Neural surface ReconstructionJia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr 0001. [doi]
• SPDER: Semiperiodic Damping-Enabled Object RepresentationKathan Shah, Chawin Sitawarin. [doi]
• Achieving Fairness in Multi-Agent MDP Using Reinforcement LearningPeizhong Ju, Arnob Ghosh, Ness B. Shroff. [doi]
• Jointly Training Large Autoregressive Multimodal ModelsEmanuele Aiello, Lili Yu, Yixin Nie, Armen Aghajanyan, Barlas Oguz. [doi]
• Can LLM-Generated Misinformation Be Detected?Canyu Chen, Kai Shu. [doi]
• Traveling Waves Encode The Recent Past and Enhance Sequence LearningT. Anderson Keller, Lyle Muller, Terrence J. Sejnowski, Max Welling. [doi]
• CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide ImagesOlga Fourkioti, Mat De Vries, Chris Bakal. [doi]
• LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model FinetuningHan Guo, Philip Greengard, Eric P. Xing, Yoon Kim. [doi]
• Delphic Offline Reinforcement Learning under Nonidentifiable Hidden ConfoundingAlizée Pace, Hugo Yèche, Bernhard Schölkopf, Gunnar Rätsch, Guy Tennenholtz. [doi]
• PAC Prediction Sets Under Label ShiftWenwen Si, Sangdon Park 0001, Insup Lee 0001, Edgar Dobriban, Osbert Bastani. [doi]
• FOSI: Hybrid First and Second Order OptimizationHadar Sivan, Moshe Gabel, Assaf Schuster. [doi]
• CCIL: Continuity-Based Data Augmentation for Corrective Imitation LearningLiyiming Ke, Yunchu Zhang, Abhay Deshpande, Siddhartha S. Srinivasa, Abhishek Gupta 0004. [doi]
• Improving Non-Transferable Representation Learning by Harnessing Content and StyleZiming Hong, Zhenyi Wang, Li Shen 0008, Yu Yao, Zhuo Huang, Shiming Chen 0002, Chuanwu Yang, Mingming Gong, Tongliang Liu. [doi]
• Sharpness-Aware Minimization Enhances Feature Quality via Balanced LearningJacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan. [doi]
• Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous SourcesXingxuan Li, Ruochen Zhao, Yew Ken Chia, Bosheng Ding, Shafiq Joty, Soujanya Poria, Lidong Bing. [doi]
• Compressed Context Memory for Online Language Model InteractionJang-Hyun Kim, Junyoung Yeom, Sangdoo Yun, Hyun Oh Song. [doi]
• Exploring Weight Balancing on Long-Tailed Recognition ProblemNaoya Hasegawa, Issei Sato. [doi]
• Interpreting Robustness Proofs of Deep Neural NetworksDebangshu Banerjee, Avaljot Singh, Gagandeep Singh 0001. [doi]
• NeuroBack: Improving CDCL SAT Solving using Graph Neural NetworksWenxi Wang, Yang Hu, Mohit Tiwari, Sarfraz Khurshid, Kenneth L. McMillan, Risto Miikkulainen. [doi]
• ResFields: Residual Neural Fields for Spatiotemporal SignalsMarko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang 0001. [doi]
• Training Unbiased Diffusion Models From Biased DatasetYeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, Wanmo Kang, Il-Chul Moon. [doi]
• Soft Contrastive Learning for Time SeriesSeunghan Lee, Taeyoung Park, Kibok Lee. [doi]
• Towards Category Unification of 3D Single Object Tracking on Point CloudsJiahao Nie 0001, Zhiwei He 0001, Xudong Lv, Xueyi Zhou, Dong-Kyu Chae, Fei Xie. [doi]
• Is Self-Repair a Silver Bullet for Code Generation?Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao 0001, Armando Solar-Lezama. [doi]
• Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt EditingXinyu Hu, Pengfei Tang, Simiao Zuo, Zihan Wang, Bowen Song, Qiang Lou, Jian Jiao 0007, Denis Charles. [doi]
• Boosting Vanilla Lightweight Vision Transformers via Re-parameterizationZhentao Tan, Xiaodan Li, Yue Wu, Qi Chu 0001, Le Lu 0001, Nenghai Yu, Jieping Ye. [doi]
• Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic DataThomas T. C. K. Zhang, Leonardo Felipe Toso, James Anderson 0001, Nikolai Matni. [doi]
• Robot Fleet Learning via Policy MergingLirui Wang, Kaiqing Zhang, Allan Zhou, Max Simchowitz, Russ Tedrake. [doi]
• LLM-Assisted Code Cleaning For Training Accurate Code GeneratorsNaman Jain, Tianjun Zhang, Wei-Lin Chiang, Joseph E. Gonzalez, Koushik Sen, Ion Stoica. [doi]
• AGILE3D: Attention Guided Interactive Multi-object 3D SegmentationYuanwen Yue, Sabarinath Mahadevan, Jonas Schult, Francis Engelmann, Bastian Leibe, Konrad Schindler, Theodora Kontogianni. [doi]
• Solving High Frequency and Multi-Scale PDEs with Gaussian ProcessesShikai Fang, Madison Cooley, Da Long, Shibo Li, Mike Kirby, Shandian Zhe. [doi]
• Vision-Language Foundation Models as Effective Robot ImitatorsXinghang Li, Minghuan Liu, Hanbo Zhang, Cunjun Yu, Jie Xu, Hongtao Wu, Chilam Cheang, Ya Jing, Weinan Zhang 0001, Huaping Liu, Hang Li, Tao Kong. [doi]
• Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and BoostingAleksei Ustimenko, Aleksandr Beznosikov. [doi]
• TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time SeriesArjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Nicolas Chapados, Alexandre Drouin. [doi]
• Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability CurvatureGuangsheng Bao, Yanbin Zhao, Zhiyang Teng, Linyi Yang, Yue Zhang 0004. [doi]
• RetroBridge: Modeling Retrosynthesis with Markov BridgesIlia Igashov, Arne Schneuing, Marwin H. S. Segler, Michael M. Bronstein, Bruno E. Correia. [doi]
• Emo: Earth Mover Distance Optimization for Auto-Regressive Language ModelingSiyu Ren, Zhiyong Wu, Kenny Q. Zhu. [doi]
• Graph-based Virtual Sensing from Sparse and Partial Multivariate ObservationsGiovanni de Felice, Andrea Cini, Daniele Zambon, Vladimir V. Gusev, Cesare Alippi. [doi]
• Consistency Models as a Rich and Efficient Policy Class for Reinforcement LearningZihan Ding, Chi Jin 0001. [doi]
• Diffusion Model for Dense MatchingJisu Nam, Gyuseong Lee, Sunwoo Kim, Hyeonsu Kim, Hyoungwon Cho, Seyeon Kim, Seungryong Kim. [doi]
• Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication ChannelXuan Li, Zhanke Zhou, Jiangchao Yao, Yu Rong, Lu Zhang, Bo Han 0003. [doi]
• Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationLinfeng Ye, Shayan Mohajer Hamidi, Renhao Tan, En-Hui Yang. [doi]
• Tangent Transformers for Composition, Privacy and RemovalTian-Yu Liu, Aditya Golatkar, Stefano Soatto. [doi]
• Robust Similarity Learning with Difference Alignment RegularizationShuo Chen 0003, Gang Niu 0001, Chen Gong 0002, Okan Koc, Jian Yang 0003, Masashi Sugiyama. [doi]
• On the Generalization and Approximation Capacities of Neural Controlled Differential EquationsLinus Bleistein, Agathe Guilloux. [doi]
• Forward χ2 Divergence Based Variational Importance SamplingChengrui Li, Yule Wang, Weihan Li, Anqi Wu. [doi]
• On the generalization capacity of neural networks during generic multimodal reasoningTakuya Ito, Soham Dan, Mattia Rigotti, James R. Kozloski, Murray Campbell. [doi]
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual TokenizationYang Jin, Kun Xu 0005, Kun Xu 0005, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chengru Song, Dai Meng, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu. [doi]
• SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI ModelsDingli Yu, Simran Kaur 0001, Arushi Gupta, Jonah Brown-Cohen, Anirudh Goyal, Sanjeev Arora. [doi]
• Spatio-Temporal Few-Shot Learning via Diffusive Neural Network GenerationYuan Yuan 0032, Chenyang Shao, Jingtao Ding, Depeng Jin, Yong Li 0008. [doi]
• Measuring Vision-Language STEM Skills of Neural ModelsJianhao Shen, Ye Yuan 0016, Srbuhi Mirzoyan, Ming Zhang 0004, Chenguang Wang 0001. [doi]
• Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System InstancesMikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar. [doi]
• On the Markov Property of Neural Algorithmic Reasoning: Analyses and MethodsMontgomery Bohde, Meng Liu, Alexandra Saxton, Shuiwang Ji. [doi]
• Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival PredictionYilan Zhang, Yingxue Xu, Jianqi Chen, Fengying Xie, Hao Chen. [doi]
• Energy-based Automated Model EvaluationRu Peng, Heming Zou, Haobo Wang, Yawen Zeng, Zenan Huang, Junbo Zhao 0002. [doi]
• Towards Green AI in Fine-tuning Large Language Models via Adaptive BackpropagationKai Huang 0007, Hanyun Yin, Heng Huang, Wei Gao 0006. [doi]
• SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand CoresZhiyu Mei, Wei Fu, Jiaxuan Gao, Guangju Wang, Huanchen Zhang, Yi Wu 0013. [doi]
• On Representation Complexity of Model-based and Model-free Reinforcement LearningHanlin Zhu, Baihe Huang, Stuart Russell 0001. [doi]
• Accurate Retraining-free Pruning for Pretrained Encoder-based Language ModelsSeungcheol Park, Hojun Choi, U Kang. [doi]
• ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target SimulationBo Zhang 0069, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen 0003, Si Liu 0001, Junchi Yan, Yu Qiao 0001. [doi]
• Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3DHaojie Huang, Owen Howell, Dian Wang 0001, Xupeng Zhu, Robert Platt 0001, Robin Walters 0001. [doi]
• On Bias-Variance Alignment in Deep ModelsLin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar. [doi]
• LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory UnitsZeyu Liu 0003, Gourav Datta, Anni Li, Peter Anthony Beerel. [doi]
• Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample ComplexityRunyu Zhang, Yang Hu, Na Li 0002. [doi]
• Neural Architecture RetrievalXiaohuan Pei, Yanxi Li 0001, Minjing Dong, Chang Xu 0002. [doi]
• Take a Step Back: Evoking Reasoning via Abstraction in Large Language ModelsHuaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng Tze Cheng, Ed H. Chi, Quoc V. Le, Denny Zhou. [doi]
• Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language ModelsErfan Shayegani, Yue Dong 0002, Nael B. Abu-Ghazaleh. [doi]
• Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMsShashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, Tushar Khot. [doi]
• Large-Vocabulary 3D Diffusion Model with TransformerZiang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu 0002. [doi]
• New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity ContradictionsXinzhe Yuan, William de Vazelhes, Bin Gu 0001, Huan Xiong. [doi]
• Confidence-aware Reward Optimization for Fine-tuning Text-to-Image ModelsKyuyoung Kim, Jongheon Jeong, Minyong An, Mohammad Ghavamzadeh, Krishnamurthy Dj Dvijotham, Jinwoo Shin, Kimin Lee. [doi]
• Real-Fake: Effective Training Data Synthesis Through Distribution MatchingJianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr 0001, Bo Zhao. [doi]
• Label-Noise Robust Diffusion ModelsByeonghu Na, Yeongmin Kim, HeeSun Bae, Jung-Hyun Lee, Se Jung Kwon, Wanmo Kang, Il-Chul Moon. [doi]
• CoBIT: A Contrastive Bi-directional Image-Text Generation ModelHaoxuan You, Mandy Guo, Zhecan Wang, Kai-Wei Chang, Jason M. Baldridge, Jiahui Yu. [doi]
• Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical MLRobin Van De Water, Hendrik Schmidt, Paul W. G. Elbers, Patrick Thoral, Bert Arnrich, Patrick Rockenschaub. [doi]
• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Xiangyu Qi, Yi Zeng 0005, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia 0001, Prateek Mittal, Peter Henderson 0002. [doi]
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic ScenesZhilu Zhang, Haoyu Wang, Shuai Liu 0009, Xiaotao Wang, Lei Lei, Wangmeng Zuo. [doi]
• Elucidating the design space of classifier-guided diffusion generationJiaJun Ma, Tianyang Hu, Wenjia Wang, Jiacheng Sun. [doi]
• Mastering Memory Tasks with World ModelsMohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran, Sarath Chandar. [doi]
• Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex ApproachChristian Fabian, Kai Cui 0001, Heinz Koeppl. [doi]
• Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow InstructionsFederico Bianchi 0001, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger, Dan Jurafsky, Tatsunori Hashimoto, James Zou 0001. [doi]
• Vision-Language Models are Zero-Shot Reward Models for Reinforcement LearningJuan Rocamonde, Victoriano Montesinos, Elvis Nava, Ethan Perez, David Lindner. [doi]
• Discovering Temporally-Aware Reinforcement Learning AlgorithmsMatthew Thomas Jackson, Chris Lu 0001, Louis Kirsch, Robert Tjarko Lange, Shimon Whiteson, Jakob Nicolaus Foerster. [doi]
• Supervised Knowledge Makes Large Language Models Better In-context LearnersLinyi Yang, Shuibai Zhang, Zhuohao Yu, Guangsheng Bao, Yidong Wang, Jindong Wang 0001, Ruochen Xu, Wei Ye 0004, Xing Xie 0001, Weizhu Chen, Yue Zhang 0004. [doi]
• Few-shot Hybrid Domain Adaptation of Image GeneratorHengjia Li, Yang Liu 0212, Linxuan Xia, Yuqi Lin, Wenxiao Wang 0001, Tu Zheng, Zheng Yang, Xiaohui Zhong, Xiaobo Ren, Xiaofei He 0001. [doi]
• How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated QuestionsLorenzo Pacchiardi, Alex James Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Markus Brauner. [doi]
• De novo Protein Design Using Geometric Vector Field NetworksWeian Mao, Muzhi Zhu, Zheng Sun, Shuaike Shen, Lin Yuanbo Wu, Hao Chen 0041, Chunhua Shen. [doi]
• Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural NetworksShih-Hsin Wang, Yung-Chang Hsu, Justin M. Baker, Andrea L. Bertozzi, Jack Xin, Bao Wang. [doi]
• Improving equilibrium propagation without weight symmetry through Jacobian homeostasisAxel Laborieux, Friedemann Zenke. [doi]
• JointNet: Extending Text-to-Image Diffusion for Dense Distribution ModelingJingyang Zhang, Shiwei Li, Yuanxun Lu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Yao Yao 0008. [doi]
• Online Continual Learning for Interactive Instruction Following AgentsByeonghwi Kim, Minhyuk Seo, Jonghyun Choi. [doi]
• Evaluating the Zero-shot Robustness of Instruction-tuned Language ModelsJiuding Sun, Chantal Shaib, Byron C. Wallace. [doi]
• Probabilistically Rewired Message-Passing Neural NetworksChendi Qian, Andrei Manolache, Kareem Ahmed, Zhe Zeng, Guy Van den Broeck, Mathias Niepert, Christopher Morris 0001. [doi]
• Efficient ConvBN Blocks for Transfer Learning and BeyondKaichao You, Guo Qin, Anchang Bao, Meng Cao, Ping Huang, Jiulong Shan, Mingsheng Long. [doi]
• The Marginal Value of Momentum for Small Learning Rate SGDRunzhe Wang, Sadhika Malladi, Tianhao Wang 0017, Kaifeng Lyu, Zhiyuan Li 0005. [doi]
• LabelDP-Pro: Learning with Label Differential Privacy via ProjectionsBadih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Chiyuan Zhang. [doi]
• Sparse Autoencoders Find Highly Interpretable Features in Language ModelsRobert Huben, Hoagy Cunningham, Logan Riggs, Aidan Ewart, Lee Sharkey. [doi]
• Zero Bubble (Almost) Pipeline ParallelismPenghui Qi, Xinyi Wan, Guangxing Huang, Min Lin. [doi]
• Optimal Sketching for Residual Error Estimation for Matrix and Vector NormsYi Li 0002, Honghao Lin, David P. Woodruff. [doi]
• Nougat: Neural Optical Understanding for Academic DocumentsLukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic. [doi]
• LLM-grounded Video Diffusion ModelsLong Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li. [doi]
• Aligning Relational Learning with Lipschitz FairnessYaning Jia, Chunhui Zhang, Soroush Vosoughi. [doi]
• Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learningMustafa Shukor, Alexandre Ramé, Corentin Dancette, Matthieu Cord. [doi]
• LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal AcquisitionLingfeng Liu, Dong Ni 0002, Hangjie Yuan. [doi]
• HYPO: Hyperspherical Out-Of-Distribution GeneralizationHaoyue Bai, Yifei Ming, Julian Katz-Samuels, Yixuan Li 0001. [doi]
• Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory GenerationZhilong Zhang, Yihao Sun, Junyin Ye, Tian-Shuo Liu, Jiaji Zhang, Yang Yu 0001. [doi]
• Horizon-Free Regret for Linear Markov Decision ProcessesZihan Zhang, Jason D. Lee, Yuxin Chen 0002, Simon Shaolei Du. [doi]
• Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEsKejun Tang, Jiayu Zhai, Xiaoliang Wan, Chao Yang 0002. [doi]
• MAmmoTH: Building Math Generalist Models through Hybrid Instruction TuningXiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun 0001, Yu Su 0001, Wenhu Chen. [doi]
• Alt-Text with Context: Improving Accessibility for Images on TwitterNikita Srivatsan, Sofía Samaniego, Omar Florez, Taylor Berg-Kirkpatrick. [doi]
• Massively Scalable Inverse Reinforcement Learning in Google MapsMatt Barnes 0001, Matthew Abueg, Oliver F. Lange, Matt Deeds, Jason Trader, Denali Molitor, Markus Wulfmeier, Shawn O'Banion. [doi]
• Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer ControlLongtao Zheng, Rundong Wang, Xinrun Wang, Bo An 0001. [doi]
• Continuous Field Reconstruction from Sparse Observations with Implicit Neural NetworksXihaier Luo, Wei Xu 0020, Balu Nadiga, Yihui Ren 0001, Shinjae Yoo. [doi]
• Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time StepsMingxiao Li, Tingyu Qu, Ruicong Yao, Wei Sun, Marie-Francine Moens. [doi]
• MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object DetectionYuxue Yang, Lue Fan, Zhaoxiang Zhang 0001. [doi]
• iTransformer: Inverted Transformers Are Effective for Time Series ForecastingYong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, Mingsheng Long. [doi]
• Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systemsJacob S. Prince, Gabriel Fajardo, George A. Alvarez, Talia Konkle. [doi]
• Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionZhiyuan Cheng 0010, Hongjun Choi, Shiwei Feng 0002, James Chenhao Liang, Guanhong Tao 0001, Dongfang Liu, Michael Zuzak, Xiangyu Zhang 0001. [doi]
• The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context LearningBill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Raghavi Chandu, Chandra Bhagavatula, Yejin Choi 0001. [doi]
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing PolicyPingzhi Li, Zhenyu Zhang 0015, Prateek Yadav, Yi-Lin Sung, Yu Cheng 0001, Mohit Bansal, Tianlong Chen. [doi]
• Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNsQihan Ren, Jiayang Gao, Wen Shen 0002, Quanshi Zhang. [doi]
• Listen, Think, and UnderstandYuan Gong 0001, Hongyin Luo, Alexander H. Liu, Leonid Karlinsky, James R. Glass. [doi]
• Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance ReductionYichen Wu, Long-Kai Huang, Renzhen Wang, Deyu Meng, Ying Wei 0001. [doi]
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech RecognitionChen Chen 0075, Ruizhe Li 0001, Yuchen Hu, Sabato Marco Siniscalchi, Pin-Yu Chen, Engsiong Chng, Chao-Han Huck Yang. [doi]
• SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step ReasoningNing Miao, Yee Whye Teh, Tom Rainforth. [doi]
• Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed LearningBinwu Wang, Pengkun Wang, Wei Xu, Xu Wang, Yudong Zhang, Kun Wang, Yang Wang. [doi]
• Function-space Parameterization of Neural Networks for Sequential LearningAidan Scannell, Riccardo Mereu, Paul Edmund Chang, Ella Tamir, Joni Pajarinen, Arno Solin. [doi]
• RLCD: Reinforcement Learning from Contrastive Distillation for LM AlignmentKevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian. [doi]
• Learning to Make Adherence-aware AdviceGuanting Chen, Xiaocheng Li, Chunlin Sun, Hanzhao Wang. [doi]
• Skill Machines: Temporal Logic Skill Composition in Reinforcement LearningGeraud Nangue Tasse, Devon Jarvis, Steven James 0001, Benjamin Rosman. [doi]
• Convergence of Bayesian Bilevel OptimizationShi Fu, Fengxiang He, Xinmei Tian 0001, Dacheng Tao. [doi]
• CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?Ibrahim Alabdulmohsin, Xiao Wang 0038, Andreas Peter Steiner, Priya Goyal, Alexander D'Amour, Xiaohua Zhai. [doi]
• Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual SamplingJiayang Liu, Yiming Bu, Daniel Tso, Qinru Qiu. [doi]
• Adaptive Regret for Bandits Made Possible: Two Queries SufficeZhou Lu, Qiuyi Zhang 0001, Xinyi Chen, Fred Zhang, David P. Woodruff, Elad Hazan. [doi]
• Quasi-Monte Carlo for 3D Sliced WassersteinKhai Nguyen, Nicola Bariletto, Nhat Ho. [doi]
• AutoLoRa: An Automated Robust Fine-Tuning FrameworkXilie Xu, Jingfeng Zhang, Mohan S. Kankanhalli. [doi]
• Fixed-Budget Differentially Private Best Arm IdentificationZhirui Chen, P. N. Karthik, Yeow Meng Chee, Vincent Y. F. Tan. [doi]
• Large Language Models as OptimizersChengrun Yang, Xuezhi Wang 0002, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, Xinyun Chen. [doi]
• Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face RecognitionJean-Rémy Conti, Stéphan Clémençon. [doi]
• Symbol as Points: Panoptic Symbol Spotting via Point-based RepresentationWenlong Liu, Tianyu Yang, Yuhan Wang, Qizhi Yu, Lei Zhang. [doi]
• DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain AdaptionNan Yin, Mengzhu Wang, Zhenghan Chen, Li Shen 0008, Huan Xiong, Bin Gu 0001, Xiao Luo 0001. [doi]
• A Characterization Theorem for Equivariant Networks with Point-wise ActivationsMarco Pacini, Xiaowen Dong 0001, Bruno Lepri, Gabriele Santin. [doi]
• Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal LearningXiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li, Tianqing Fang, Mingxi Cheng, Paul Bogdan. [doi]
• Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization ApproachAoqi Zuo, Yiqing Li, Susan Wei, Mingming Gong. [doi]
• COCO-Periph: Bridging the Gap Between Human and Machine Perception in the PeripheryAnne Harrington, Vasha Dutell, Mark Hamilton, Ayush Tewari, Simon Stent, William T. Freeman, Ruth Rosenholtz. [doi]
• Leveraging Optimization for Adaptive Attacks on Image WatermarksNils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum. [doi]
• CARD: Channel Aligned Robust Blend Transformer for Time Series ForecastingXue Wang, Tian Zhou, Qingsong Wen, Jinyang Gao, Bolin Ding, Rong Jin 0001. [doi]
• Sentence-level Prompts Benefit Composed Image RetrievalYang Bai, Xinxing Xu, Yong Liu 0026, Salman Khan 0001, Fahad Shahbaz Khan, Wangmeng Zuo, Rick Siow Mong Goh, Chun-Mei Feng. [doi]
• CompA: Addressing the Gap in Compositional Reasoning in Audio-Language ModelsSreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Reddy Evuru, Ramaneswaran S., Sakshi Singh, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha. [doi]
• Concept Bottleneck Generative ModelsAya Abdelsalam Ismail, Julius Adebayo, Héctor Corrada Bravo, Stephen Ra, KyungHyun Cho. [doi]
• ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified StatesSam Bond-Taylor, Chris G. Willcocks. [doi]
• Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion ModelsZiyu Wang, Lejun Min, Gus Xia. [doi]
• General Graph Random FeaturesIsaac Reid, Krzysztof Marcin Choromanski, Eli Berger, Adrian Weller. [doi]
• On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic ApproximationJeongyeol Kwon, Dohyun Kwon, Stephen Wright, Robert D. Nowak. [doi]
• A unique M-pattern for micro-expression spotting in long videosJinxuan Wang, Shiting Xu, Tong Zhang. [doi]
• VFLAIR: A Research Library and Benchmark for Vertical Federated LearningTianyuan Zou, Zixuan Gu, Yu He, Hideaki Takahashi, Yang Liu 0165, Ya-Qin Zhang. [doi]
• Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?Jianfei Yang, Hanjie Qian, Yuecong Xu, Kai Wang 0036, Lihua Xie. [doi]
• VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language ModelsZihao Zhu, Mingda Zhang, Shaokui Wei, Bingzhe Wu, Baoyuan Wu. [doi]
• Belief-Enriched Pessimistic Q-Learning against Adversarial State PerturbationsXiaolin Sun, Zizhan Zheng. [doi]
• Intriguing Properties of Generative ClassifiersPriyank Jaini, Kevin Clark, Robert Geirhos. [doi]
• What Algorithms can Transformers Learn? A Study in Length GeneralizationHattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Joshua M. Susskind, Samy Bengio, Preetum Nakkiran. [doi]
• Conformal Risk ControlAnastasios Nikolas Angelopoulos, Stephen Bates, Adam Fisch, Lihua Lei, Tal Schuster. [doi]
• Federated Wasserstein DistanceAlain Rakotomamonjy, Kimia Nadjahi, Liva Ralaivola. [doi]
• Fair and Efficient Contribution Valuation for Vertical Federated LearningZhenan Fan, Huang Fang, Xinglu Wang, Zirui Zhou, Jian Pei, Michael P. Friedlander, Yong Zhang. [doi]
• Chain of Log-Concave Markov ChainsSaeed Saremi, Ji-Won Park, Francis R. Bach. [doi]
• Network Memory Footprint Compression Through Jointly Learnable Codebooks and MappingsEdouard Yvinec, Arnaud Dapogny, Kevin Bailly. [doi]
• State Representation Learning Using an Unbalanced AtlasLi Meng, Morten Goodwin, Anis Yazidi, Paal E. Engelstad. [doi]
• A Quadratic Synchronization Rule for Distributed Deep LearningXinran Gu, Kaifeng Lyu, Sanjeev Arora, Jingzhao Zhang, Longbo Huang. [doi]
• Towards Cheaper Inference in Deep Networks with Lower Bit-Width AccumulatorsYaniv Blumenfeld, Itay Hubara, Daniel Soudry. [doi]
• MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical ReasoningKe Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, Hongsheng Li 0001. [doi]
• Contrastive Learning is Spectral Clustering on Similarity GraphZhiquan Tan, Yifan Zhang, Jingqin Yang, Yang Yuan. [doi]
• Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule GenerationTuan Le, Julian Cremer, Frank Noé, Djork-Arné Clevert, Kristof T. Schütt. [doi]
• End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent PhenomenonGuillaume Bono, Leonid Antsfeld, Boris Chidlovskii, Philippe Weinzaepfel, Christian Wolf 0001. [doi]
• Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering PerspectiveZehao Dou, Yang Song. [doi]
• Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-ResolutionYiyang Ma, Huan Yang 0005, Wenhan Yang, Jianlong Fu, Jiaying Liu 0001. [doi]
• Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 WordsYujia Bao, Srinivasan Sivanandan, Theofanis Karaletsos. [doi]
• Towards Cross Domain Generalization of Hamiltonian Representation via Meta LearningYeongwoo Song, Hawoong Jeong. [doi]
• Alice Benchmarks: Connecting Real World Re-Identification with the SyntheticXiaoxiao Sun, Yue Yao, Shengjin Wang, Hongdong Li, Liang Zheng 0001. [doi]
• Generative Adversarial Equilibrium SolversDenizalp Goktas, David C. Parkes, Ian Gemp, Luke Marris, Georgios Piliouras, Romuald Elie, Guy Lever, Andrea Tacchetti. [doi]
• Offline Data Enhanced On-Policy Policy Gradient with Provable GuaranteesYifei Zhou, Ayush Sekhari, Yuda Song 0001, Wen Sun 0002. [doi]
• Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task DatasetsDominique Beaini, Shenyang Huang, Joao Alex Cunha, Zhiyi Li, Gabriela Moisescu-Pareja, Oleksandr Dymov, Samuel Maddrell-Mander, Callum McLean, Frederik Wenkel, Luis Müller, Jama Hussein Mohamud, Ali Parviz, Michael Craig, Michal Koziarski, Jiarui Lu, Zhaocheng Zhu, Cristian Gabellini, Kerstin Klaser 0001, Josef Dean, Cas Wognum, Maciej Sypetkowski, Guillaume Rabusseau, Reihaneh Rabbany, Jian Tang 0005, Christopher Morris 0001, Mirco Ravanelli, Guy Wolf, Prudencio Tossou, Hadrien Mary, Therence Bois, Andrew W. Fitzgibbon, Blazej Banaszewski, Chad Martin, Dominic Masters. [doi]
• Octavius: Mitigating Task Interference in MLLMs via LoRA-MoEZeren Chen, Ziqin Wang, Zhen Wang 0003, Huayang Liu, Zhenfei Yin, Si Liu 0001, Lu Sheng, Wanli Ouyang, Jing Shao. [doi]
• On the Power of the Weisfeiler-Leman Test for Graph Motif ParametersMatthias Lanzinger, Pablo Barceló. [doi]
• The LLM SurgeonTycho F. A. van der Ouderaa, Markus Nagel, Mart van Baalen, Tijmen Blankevoort. [doi]
• Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language TranslationRyan Wong 0003, Necati Cihan Camgöz, Richard Bowden. [doi]
• Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert SpaceHao Xiong 0003, Yehui Tang, Yunlin He, Wei Tan, Junchi Yan. [doi]
• Matrix Manifold Neural Networks++Xuan Son Nguyen, Shuo Yang, Aymeric Histace. [doi]
• Deep Orthogonal Hypersphere Compression for Anomaly DetectionYunhe Zhang, Yan Sun, Jinyu Cai, Jicong Fan 0001. [doi]
• Towards Principled Representation Learning from Videos for Reinforcement LearningDipendra Misra, Akanksha Saran, Tengyang Xie, Alex Lamb, John Langford 0001. [doi]
• Headless Language Models: Learning without Predicting with Contrastive Weight TyingNathan Godey, Éric Villemonte de la Clergerie, Benoît Sagot. [doi]
• ReLU Strikes Back: Exploiting Activation Sparsity in Large Language ModelsSeyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Sachin Mehta, Carlo C. del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar. [doi]
• Revisiting Deep Audio-Text Retrieval Through the Lens of TransportationManh Luong, Khai Nguyen, Nhat Ho, Reza Haf, Dinh Phung 0001, Lizhen Qu. [doi]
• CABINET: Content Relevance-based Noise Reduction for Table Question AnsweringSohan Patnaik, Heril Changwal, Milan Aggarwal, Sumit Bhatia, Yaman Kumar 0001, Balaji Krishnamurthy. [doi]
• ADOPD: A Large-Scale Document Page Decomposition DatasetJiuxiang Gu, Xiangxi Shi, Jason Kuen, Lu Qi, Ruiyi Zhang, Anqi Liu, Ani Nenkova, Tong Sun. [doi]
• NAISR: A 3D Neural Additive Model for Interpretable Shape RepresentationYining Jiao, Carlton J. Zdanski, Julia S. Kimbell, Andrew Prince, Cameron Worden, Samuel Kirse, Christopher Rutter, Benjamin Shields, William Dunn, Jisan Mahmud, Marc Niethammer. [doi]
• DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion ModelsYongchan Kwon, Eric Wu, Kevin Wu, James Zou 0001. [doi]
• FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model HeterogeneityKai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu. [doi]
• Unbalancedness in Neural Monge Maps Improves Unpaired Domain TranslationLuca Eyring, Dominik Klein, Théo Uscidda, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian J. Theis. [doi]
• Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion AttacksLukas Struppek, Dominik Hintersdorf, Kristian Kersting. [doi]
• Learning to Solve Bilevel Programs with Binary TenderBo Zhou, Ruiwei Jiang, Siqian Shen. [doi]
• Causal Fairness under Unobserved Confounding: A Neural Sensitivity FrameworkMaresa Schröder, Dennis Frauen, Stefan Feuerriegel. [doi]
• Denoising Diffusion Step-aware ModelsShuai Yang, Yukang Chen, Luozhou Wang, Shu Liu 0005, Ying-Cong Chen. [doi]
• Constraint-Free Structure Learning with Smooth Acyclic OrientationsRiccardo Massidda, Francesco Landolfi, Martina Cinquini, Davide Bacciu. [doi]
• Universal Jailbreak Backdoors from Poisoned Human FeedbackJavier Rando, Florian Tramèr. [doi]
• Thought Propagation: an Analogical Approach to Complex Reasoning with Large Language ModelsJunchi Yu, Ran He 0001, Zhitao Ying. [doi]
• Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean SpeechSzu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao 0001, Yu-Chiang Frank Wang. [doi]
• Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion PriorsGuocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li 0024, Hsin-Ying Lee 0001, Ivan Skorokhodov, Peter Wonka, Sergey Tulyakov, Bernard Ghanem. [doi]
• In-Context Pretraining: Language Modeling Beyond Document BoundariesWeijia Shi, Sewon Min, Maria Lomeli, Chunting Zhou, Margaret Li, Xi Victoria Lin, Noah A. Smith, Luke Zettlemoyer, Wen-tau Yih, Mike Lewis. [doi]
• ContextRef: Evaluating Referenceless Metrics for Image Description GenerationElisa Kreiss, Eric Zelikman, Christopher Potts, Nick Haber. [doi]
• Leveraging Unpaired Data for Vision-Language Generative Models via Cycle ConsistencyTianhong Li, Sangnie Bhardwaj, Yonglong Tian, Han Zhang 0010, Jarred Barber, Dina Katabi, Guillaume Lajoie, Huiwen Chang, Dilip Krishnan. [doi]
• Decentralized Riemannian Conjugate Gradient Method on the Stiefel ManifoldJun Chen 0023, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong Liu 0007. [doi]
• Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial PatchesLingxuan Wu, Xiao Yang, Yinpeng Dong, Liuwei Xie, Hang Su 0006, Jun Zhu 0001. [doi]
• SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with BacktrackingChris Cundy, Stefano Ermon. [doi]
• Neural Fourier Transform: A General Approach to Equivariant Representation LearningMasanori Koyama, Kenji Fukumizu, Kohei Hayashi, Takeru Miyato. [doi]
• The importance of feature preprocessing for differentially private linear optimizationZiteng Sun, Ananda Theertha Suresh, Aditya Krishna Menon. [doi]
• Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian OptimizationAnthony Bardou, Patrick Thiran, Thomas Begin. [doi]
• Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update CalibrationYujia Wang, Yuanpu Cao, Jingcheng Wu, Ruoyu Chen, Jinghui Chen. [doi]
• Vanishing Gradients in Reinforcement Finetuning of Language ModelsNoam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin. [doi]
• Fine-Tuning Language Models for FactualityKatherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning, Chelsea Finn. [doi]
• How do Language Models Bind Entities in Context?Jiahai Feng, Jacob Steinhardt. [doi]
• Privacy-Preserving In-Context Learning for Large Language ModelsTong Wu, Ashwinee Panda, Jiachen T. Wang, Prateek Mittal. [doi]
• Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned GenerationRuoyu Wang 0034, Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu 0011. [doi]
• VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPsLing Yang 0006, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui 0001, Muhan Zhang, Jure Leskovec. [doi]
• Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial AttacksNguyen Hung-Quang, Yingjie Lao, Tung Pham, Kok Seng Wong, Khoa D. Doan. [doi]
• SaNN: Simple Yet Powerful Simplicial-aware Neural NetworksSravanthi Gurugubelli, Sundeep Prabhakar Chepuri. [doi]
• RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question AnsweringKai-Po Chang, Chi-Pin Huang, Wei-Yuan Cheng, Fu-En Yang, Chien-Yi Wang, Yung-Hsuan Lai, Yu-Chiang Frank Wang. [doi]
• DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model TrainingAochuan Chen, Yimeng Zhang, Jinghan Jia, James Diffenderfer, Konstantinos Parasyris, Jiancheng Liu, Yihua Zhang, Zheng Zhang 0005, Bhavya Kailkhura, Sijia Liu 0001. [doi]
• UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionWenxuan Zhou, Sheng Zhang 0012, Yu Gu 0017, Muhao Chen, Hoifung Poon. [doi]
• Robust Model Based Reinforcement Learning Using L1 Adaptive ControlMinjun Sung, Sambhu H. Karumanchi, Aditya Gahlawat, Naira Hovakimyan. [doi]
• FasterViT: Fast Vision Transformers with Hierarchical AttentionAli Hatamizadeh, Greg Heinrich, Hongxu Yin, Andrew Tao, José M. Álvarez 0004, Jan Kautz, Pavlo Molchanov 0001. [doi]
• MINDE: Mutual Information Neural Diffusion EstimationGiulio Franzese, Mustapha Bounoua, Pietro Michiardi. [doi]
• Gene Regulatory Network Inference in the Presence of Dropouts: a Causal ViewHaoyue Dai, Ignavier Ng, Gongxu Luo, Peter Spirtes, Petar Stojanov, Kun Zhang 0001. [doi]
• Entropy-MCMC: Sampling from Flat Basins with EaseBolian Li, Ruqi Zhang. [doi]
• Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing ValuesXiaodan Chen, Xiucheng Li, Bo Liu, Zhijun Li. [doi]
• Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC BoundsYuxin Dong, Tieliang Gong, Hong Chen 0004, Shujian Yu, Chen Li 0011. [doi]
• Proving Test Set Contamination in Black-Box Language ModelsYonatan Oren, Nicole Meister, Niladri S. Chatterji, Faisal Ladhak, Tatsunori Hashimoto. [doi]
• Feature-aligned N-BEATS with Sinkhorn divergenceJoonhun Lee, Myeongho Jeon, Myungjoo Kang, Kyunghyun Park. [doi]
• CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen ObjectsYoonyoung Cho, Junhyek Han, Yoontae Cho, Beomjoon Kim. [doi]
• CLEX: Continuous Length Extrapolation for Large Language ModelsGuanzheng Chen, Xin Li 0056, Zaiqiao Meng, Shangsong Liang, Lidong Bing. [doi]
• HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion GuidanceJunzhe Zhu, Peiye Zhuang, Sanmi Koyejo. [doi]
• Generative Human Motion Stylization in Latent SpaceChuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng 0001. [doi]
• Optimal robust Memorization with ReLU Neural NetworksLijia Yu, Xiao-Shan Gao, Lijun Zhang. [doi]
• The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank ReductionPratyusha Sharma, Jordan T. Ash, Dipendra Misra. [doi]
• Causal-StoNet: Causal Inference for High-Dimensional Complex DataYaxin Fang, Faming Liang. [doi]
• Contextual Bandits with Online Neural RegressionRohan Deb, Yikun Ban, Shiliang Zuo, Jingrui He, Arindam Banerjee 0001. [doi]
• Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?Megan Richards, Polina Kirichenko, Diane Bouchacourt, Mark Ibrahim. [doi]
• Boosting the Adversarial Robustness of Graph Neural Networks: An OOD PerspectiveKuan Li, Yiwen Chen, Yang Liu 0200, Jin Wang 0007, Qing He 0003, Minhao Cheng, Xiang Ao 0001. [doi]
• A differentiable brain simulator bridging brain simulation and brain-inspired computingChaoming Wang, Tianqiu Zhang, Sichao He, Hongyaoxing Gu, Shangyang Li, Si Wu 0001. [doi]
• MCM: Masked Cell Modeling for Anomaly Detection in Tabular DataJiaxin Yin, Yuanyuan Qiao, Zitang Zhou, Xiangchao Wang, Jie Yang 0002. [doi]
• Two-timescale Extragradient for Finding Local Minimax PointsJiseok Chae, Kyuwon Kim, Donghwan Kim. [doi]
• Feature CollapseThomas Laurent 0001, James von Brecht, Xavier Bresson. [doi]
• SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential EquationsXuan Zhang, Jacob Helwig, Yuchao Lin, Yaochen Xie, Cong Fu 0003, Stephan Wojtowytsch, Shuiwang Ji. [doi]
• LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed PromptsHanan Gani, Shariq Farooq Bhat, Muzammal Naseer, Salman Khan 0001, Peter Wonka. [doi]
• Think before you speak: Training Language Models With Pause TokensSachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan. [doi]
• Enhanced Face Recognition using Intra-class Incoherence ConstraintYuanqing Huang, Yinggui Wang, Le Yang 0001, Lei Wang. [doi]
• Defining Expertise: Applications to Treatment Effect EstimationAlihan Hüyük, Qiyao Wei, Alicia Curth, Mihaela van der Schaar. [doi]
• Bespoke Solvers for Generative Flow ModelsNeta Shaul, Juan C. Pérez, Ricky T. Q. Chen, Ali K. Thabet, Albert Pumarola, Yaron Lipman. [doi]
• Temporal Generalization Estimation in Evolving GraphsBin Lu 0005, Tingyan Ma, Xiaoying Gan, Xinbing Wang, Yunqiang Zhu, Chenghu Zhou, Shiyu Liang. [doi]
• What does the Knowledge Neuron Thesis Have to do with Knowledge?Jingcheng Niu, Andrew Liu, Zining Zhu 0001, Gerald Penn. [doi]
• Hypothesis Search: Inductive Reasoning with Language ModelsRuocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman. [doi]
• The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized SmoothingBlaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen. [doi]
• Representation Deficiency in Masked Language ModelingYu Meng 0001, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han 0001, Luke Zettlemoyer. [doi]
• RLIF: Interactive Imitation Learning as Reinforcement LearningJianlan Luo, Perry Dong, Yuexiang Zhai, Yi Ma 0001, Sergey Levine. [doi]
• Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated LearningKostadin Garov, Dimitar Iliev Dimitrov, Nikola Jovanovic 0001, Martin T. Vechev. [doi]
• Sharpness-Aware Data Poisoning AttackPengfei He, Han Xu 0002, Jie Ren, Yingqian Cui, Shenglai Zeng, Hui Liu 0031, Charu C. Aggarwal, Jiliang Tang. [doi]
• Nearly d-Linear Convergence Bounds for Diffusion Models via Stochastic LocalizationJoe Benton, Valentin De Bortoli, Arnaud Doucet, George Deligiannidis. [doi]
• Stochastic Controlled Averaging for Federated Learning with Communication CompressionXinmeng Huang, Ping Li, Xiaoyun Li. [doi]
• Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy ImagesHannah Kniesel, Leon Sick, Tristan Payer, Tim Bergner, Kavitha Shaga Devan, Clarissa Read, Paul Walther, Timo Ropinski, Pedro Hermosilla. [doi]
• Rethinking Complex Queries on Knowledge Graphs with Neural Link PredictorsHang Yin, Zihao Wang 0001, Yangqiu Song. [doi]
• Lipschitz Singularities in Diffusion ModelsZhantao Yang, Ruili Feng, Han Zhang 0010, Yujun Shen, Kai Zhu 0004, Lianghua Huang, Yifei Zhang, Yu Liu 0063, Deli Zhao, Jingren Zhou, Fan Cheng 0002. [doi]
• RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural RepresentationsJiajun He 0003, Gergely Flamich, Zongyu Guo, José Miguel Hernández-Lobato. [doi]
• MVDream: Multi-view Diffusion for 3D GenerationYichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, Xiao Yang. [doi]
• Eureka: Human-Level Reward Design via Coding Large Language ModelsYecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, Anima Anandkumar. [doi]
• The Trickle-down Impact of Reward Inconsistency on RLHFLingfeng Shen, Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu 0001. [doi]
• PlaSma: Procedural Knowledge Models for Language-based Planning and Re-PlanningFaeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona Jacqueline Arai, Soumya Sanyal 0001, Keisuke Sakaguchi, Xiang Ren 0001, Yejin Choi 0001. [doi]
• QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language ModelsJing Liu, Ruihao Gong, Xiuying Wei, Zhiwei Dong, Jianfei Cai 0001, Bohan Zhuang. [doi]
• MgNO: Efficient Parameterization of Linear Operators via MultigridJuncai He, Xinliang Liu, Jinchao Xu. [doi]
• DrM: Mastering Visual Reinforcement Learning through Dormant Ratio MinimizationGuowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu 0003, Jiaxin Yuan, Pu-Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu. [doi]
• On the Posterior Distribution in Denoising: Application to Uncertainty QuantificationHila Manor, Tomer Michaeli. [doi]
• Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot DesignHeng Dong, Junyu Zhang, Chongjie Zhang. [doi]
• Dissecting learning and forgetting in language model finetuningXiao Zhang, Ji Wu. [doi]
• A Linear Algebraic Framework for Counterfactual GenerationJong-Hoon Ahn, Akshay Vashist. [doi]
• FeatUp: A Model-Agnostic Framework for Features at Any ResolutionStephanie Fu, Mark Hamilton, Laura E. Brandt, Axel Feldmann, Zhoutong Zhang, William T. Freeman. [doi]
• ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic SegmentationKim-Celine Kahl, Carsten T. Lüth, Maximilian Zenk, Klaus H. Maier-Hein, Paul F. Jaeger. [doi]
• Improving Intrinsic Exploration by Creating Stationary ObjectivesRoger Creus Castanyer, Joshua Romoff, Glen Berseth. [doi]
• Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function ApproximationJianliang He, Han Zhong, Zhuoran Yang. [doi]
• GRANDE: Gradient-Based Decision Tree Ensembles for Tabular DataSascha Marton, Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt. [doi]
• On the Stability of Iterative Retraining of Generative Models on their own DataQuentin Bertrand, Avishek Joey Bose, Alexandre Duplessis, Marco Jiralerspong, Gauthier Gidel. [doi]
• Delta-AI: Local objectives for amortized inference in sparse graphical modelsJean-Pierre Falet, Hae Beom Lee, Nikolay Malkin, Chen Sun 0007, Dragos Secrieru, Dinghuai Zhang, Guillaume Lajoie, Yoshua Bengio. [doi]
• Single Motion DiffusionSigal Raab, Inbal Leibovitch, Guy Tevet, Moab Arar, Amit Haim Bermano, Daniel Cohen-Or. [doi]
• Towards Foundation Models for Knowledge Graph ReasoningMikhail Galkin 0001, Xinyu Yuan, Hesham Mostafa, Jian Tang 0005, Zhaocheng Zhu. [doi]
• True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement LearningWeihao Tan, Wentao Zhang, Shanqi Liu, Longtao Zheng, Xinrun Wang, Bo An 0001. [doi]
• DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural RepresentationsDogyun Park, Sihyeon Kim, Sojin Lee, Hyunwoo J. Kim. [doi]
• Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization AnalysisShicheng Liu, Minghui Zhu. [doi]
• Implicit regularization of deep residual networks towards neural ODEsPierre Marion, Yu-Han Wu, Michael Eli Sander, Gérard Biau. [doi]
• FedImpro: Measuring and Improving Client Update in Federated LearningZhenheng Tang, Yonggang Zhang, Shaohuai Shi, Xinmei Tian 0001, Tongliang Liu, Bo Han 0003, Xiaowen Chu 0001. [doi]
• From Sparse to Soft Mixtures of ExpertsJoan Puigcerver, Carlos Riquelme Ruiz, Basil Mustafa, Neil Houlsby. [doi]
• EX-Graph: A Pioneering Dataset Bridging Ethereum and XQian Wang, Zhen Zhang 0023, Zemin Liu, Shengliang Lu, Bingqiao Luo, Bingsheng He. [doi]
• SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation LearningJiacheng Chen, Zeyuan Ma, Hongshu Guo, Yining Ma 0001, Jie Zhang, Yue-jiao Gong. [doi]
• PINNACLE: PINN Adaptive ColLocation and Experimental points selectionGregory Kang Ruey Lau, Apivich Hemachandra, See-Kiong Ng, Bryan Kian Hsiang Low. [doi]
• Learning Hierarchical Polynomials with Three-Layer Neural NetworksZihao Wang, Eshaan Nichani, Jason D. Lee. [doi]
• Image Background Serves as Good Proxy for Out-of-distribution DataSen Pei. [doi]
• Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy DistillationYaofo Chen, Shuaicheng Niu, Yaowei Wang 0001, Shoukai Xu, Hengjie Song, Mingkui Tan. [doi]
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang 0002, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu 0001, Maosong Sun 0001, Jie Zhou 0016. [doi]
• REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision ProcessesDavid Ireland, Giovanni Montana. [doi]
• Learning Hierarchical Image Segmentation For Recognition and By RecognitionTsung-Wei Ke, Sangwoo Mo, Stella X. Yu. [doi]
• Identifying Policy Gradient SubspacesJan Schneider, Pierre Schumacher, Simon Guist, Le Chen, Daniel F. B. Haeufle, Bernhard Schölkopf, Dieter Büchler. [doi]
• Improving Convergence and Generalization Using Parameter SymmetriesBo Zhao, Robert M. Gower, Robin Walters 0001, Rose Yu. [doi]
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill SetsSeonghyeon Ye, Doyoung Kim, Sungdong Kim, Hyeonbin Hwang, Seungone Kim, Yongrae Jo, James Thorne, Juho Kim, Minjoon Seo. [doi]
• Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-EncodersNishant Yadav, Nicholas Monath, Manzil Zaheer, Rob Fergus, Andrew McCallum. [doi]
• Unraveling the Key Components of OOD Generalization via DiversificationHarold Benoit, Liangze Jiang, Andrei Atanov, Oguzhan Fatih Kar, Mattia Rigotti, Amir Zamir. [doi]
• GeoLLM: Extracting Geospatial Knowledge from Large Language ModelsRohin Manvi, Samar Khanna, Gengchen Mai, Marshall Burke, David B. Lobell, Stefano Ermon. [doi]
• MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled ImagesXurui Li, Ziming Huang, Feng Xue, Yu Zhou. [doi]
• NfgTransformer: Equivariant Representation Learning for Normal-form GamesSiqi Liu 0002, Luke Marris, Georgios Piliouras, Ian Gemp, Nicolas Heess. [doi]
• Contrastive Difference Predictive CodingChongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach. [doi]
• DistillSpec: Improving Speculative Decoding via Knowledge DistillationYongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, Rishabh Agarwal. [doi]
• Whittle Index with Multiple Actions and State Constraint for Inventory ManagementChuheng Zhang, Xiangsen Wang, Wei Jiang 0024, Xianliang Yang, Siwei Wang, Lei Song, Jiang Bian 0002. [doi]
• A Variational Framework for Estimating Continuous Treatment Effects with Measurement ErrorErdun Gao, Howard D. Bondell, Wei Huang, Mingming Gong. [doi]
• Training Diffusion Models with Reinforcement LearningKevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, Sergey Levine. [doi]
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language ModelsYan Liu, Yu Liu, Xiaokang Chen, Pin-Yu Chen, Daoguang Zan, Min-Yen Kan, Tsung-Yi Ho. [doi]
• Customizable Combination of Parameter-Efficient Modules for Multi-Task LearningHaowen Wang, Tao Sun, Congyun Jin, Yingbo Wang, Yibo Fan, Yunqi Xu, Yuliang Du, Cong Fan. [doi]
• Transformers can optimally learn regression mixture modelsReese Pathak, Rajat Sen, Weihao Kong, Abhimanyu Das. [doi]
• Set Learning for Accurate and Calibrated ModelsLukas Muttenthaler, Robert A. Vandermeulen, Qiuyi Zhang 0001, Thomas Unterthiner, Klaus-Robert Müller. [doi]
• The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation ModelsCheng Shi, Sibei Yang. [doi]
• SALMONN: Towards Generic Hearing Abilities for Large Language ModelsChangli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan 0019, Wei Li 0119, Lu Lu 0015, Zejun Ma, Chao Zhang 0031. [doi]
• Robust Model-Based Optimization for Challenging Fitness LandscapesSaba Ghaffari, Ehsan Saleh, Alexander G. Schwing, Yu-Xiong Wang, Martin D. Burke, Saurabh Sinha. [doi]
• InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationXingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng 0001, Qiang Liu 0001. [doi]
• A Recipe for Improved Certifiable RobustnessKai Hu, Klas Leino, Zifan Wang, Matt Fredrikson. [doi]
• Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex OptimizationHamidreza Almasi, Harsh Mishra, Balajee Vamanan, Sathya N. Ravi. [doi]
• Experimental Design for Multi-Channel Imaging via Task-Driven Feature SelectionStefano B. Blumberg, Paddy J. Slator, Daniel C. Alexander. [doi]
• NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal ModelingKun Wang, Hao Wu, Yifan Duan, Guibin Zhang, Kai Wang 0036, Xiaojiang Peng, Yu Zheng, Yuxuan Liang, Yang Wang 0015. [doi]
• DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D GenerationYukun Huang, Jianan Wang, Yukai Shi, Boshi Tang, Xianbiao Qi, Lei Zhang 0001. [doi]
• Robust NAS under adversarial training: benchmark, theory, and beyondYongtao Wu, Fanghui Liu 0001, Carl-Johann Simon-Gabriel, Grigorios Chrysos 0002, Volkan Cevher. [doi]
• Combining Axes Preconditioners through Kronecker Approximation for Deep LearningSai Surya Duvvuri, Devvrit, Rohan Anil, Cho-Jui Hsieh, Inderjit S. Dhillon. [doi]
• Towards Eliminating Hard Label Constraints in Gradient Inversion AttacksYanbo Wang, Jian Liang, Ran He 0001. [doi]
• AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context RetrievalQi Yan, Raihan Seraj, Jiawei He, Lili Meng, Tristan Sylvain. [doi]
• Intelligent Switching for Reset-Free RLDarshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar. [doi]
• Label-Focused Inductive Bias over Latent Object Features in Visual ClassificationIlmin Kang, HyounYoung Bae, Kangil Kim. [doi]
• Does Writing with Language Models Reduce Content Diversity?Vishakh Padmakumar, He He 0001. [doi]
• Vision Transformers Need RegistersTimothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski. [doi]
• CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement LearningTianyu Li, Hyunyoung Jung 0002, Matthew C. Gombolay, Yong-Kwon Cho, Sehoon Ha. [doi]
• In-Context Learning Learns Label Relationships but Is Not Conventional LearningJannik Kossen, Yarin Gal, Tom Rainforth. [doi]
• A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge DistillationAyan Sengupta, Shantanu Dixit, Md. Shad Akhtar, Tanmoy Chakraborty 0002. [doi]
• Sparse Model Soups: A Recipe for Improved Pruning via Model AveragingMax Zimmer, Christoph Spiegel 0002, Sebastian Pokutta. [doi]
• FedCDA: Federated Learning with Cross-rounds Divergence-aware AggregationHaozhao Wang, Haoran Xu, Yichen Li, Yuan Xu, Ruixuan Li 0001, Tianwei Zhang 0004. [doi]
• On-Policy Distillation of Language Models: Learning from Self-Generated MistakesRishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, Olivier Bachem. [doi]
• Jointly-Learned Exit and Inference for a Dynamic Neural NetworkFlorence Regol, Joud Chataoui, Mark Coates. [doi]
• Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regimeKeita Suzuki, Taiji Suzuki. [doi]
• Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking OraclesZhiwei Tang, Dmitry Rybin, Tsung-Hui Chang. [doi]
• FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link PredictionYuxing Tian, Yiyan Qi, Fan Guo. [doi]
• DiffusionSat: A Generative Foundation Model for Satellite ImagerySamar Khanna, Patrick Liu, Linqi Zhou, Chenlin Meng, Robin Rombach, Marshall Burke, David B. Lobell, Stefano Ermon. [doi]
• Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation ApproachChangwen Zhang, Wenli Ouyang, Hao Yuan, Liming Gong, Yong Sun, Ziao Guo, Zhichen Dong, Junchi Yan. [doi]
• Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FRONDQiyu Kang, Kai Zhao, Qinxu Ding, Feng Ji, Xuhao Li, Wenfei Liang, Yang Song 0012, Wee-Peng Tay. [doi]
• Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation LearningXiaoxin He, Xavier Bresson, Thomas Laurent 0001, Adam Perold, Yann LeCun, Bryan Hooi. [doi]
• Learning with Language-Guided State AbstractionsAndi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths 0001, Jacob Andreas, Julie Shah. [doi]
• BTR: Binary Token Representations for Efficient Retrieval Augmented Language ModelsQingqing Cao, Sewon Min, Yizhong Wang, Hannaneh Hajishirzi. [doi]
• Variational Bayesian Last LayersJames Harrison, John Willes, Jasper Snoek. [doi]
• Large Language Models Cannot Self-Correct Reasoning YetJie Huang 0009, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, Denny Zhou. [doi]
• STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series PredictionDennis Wu, Jerry Yao-Chieh Hu, Weijian Li, Bo-Yu Chen, Han Liu. [doi]
• Plug-and-Play: An Efficient Post-training Pruning Method for Large Language ModelsYingtao Zhang, Haoli Bai, Haokun Lin, Jialin Zhao 0004, Lu Hou, Carlo Vittorio Cannistraci. [doi]
• Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product NetworksFederico Errica, Mathias Niepert. [doi]
• Fast Updating Truncated SVD for Representation Learning with Sparse MatricesHaoran Deng, Yang Yang 0009, Jiahe Li 0008, Cheng Chen, Weihao Jiang, Shiliang Pu. [doi]
• Masks, Signs, And Learning Rate RewindingAdvait Harshal Gadhikar, Rebekka Burkholz. [doi]
• From Latent Graph to Latent Topology Inference: Differentiable Cell Complex ModuleClaudio Battiloro, Indro Spinelli, Lev Telyatnikov, Michael M. Bronstein, Simone Scardapane, Paolo Di Lorenzo. [doi]
• sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing FlowsDongjin Kim, Donggoo Jung, Sungyong Baik, Tae Hyun Kim 0006. [doi]
• Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake AnalysisKai Chen 0023, Chunwei Wang, Kuo Yang, Jianhua Han, Lanqing Hong, Fei Mi, Hang Xu, Zhengying Liu, Wenyong Huang, Zhenguo Li, Dit-Yan Yeung, Lifeng Shang. [doi]
• Analysis of Learning a Flow-based Generative Model from Limited Sample ComplexityHugo Cui, Florent Krzakala, Eric Vanden-Eijnden, Lenka Zdeborová. [doi]
• TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series ForecastingDefu Cao, Furong Jia, Sercan Ö. Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, Yan Liu 0002. [doi]
• Provable Reward-Agnostic Preference-Based Reinforcement LearningWenhao Zhan, Masatoshi Uehara, Wen Sun 0002, Jason D. Lee. [doi]
• ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion ModelsYingqing He, Shaoshu Yang, Haoxin Chen, Xiaodong Cun, Menghan Xia, Yong Zhang 0034, Xintao Wang, Ran He 0001, Qifeng Chen, Ying Shan. [doi]
• RingAttention with Blockwise Transformers for Near-Infinite ContextHao Liu 0055, Matei Zaharia, Pieter Abbeel. [doi]
• Neural Language of Thought ModelsYi-Fu Wu, Minseung Lee, Sungjin Ahn. [doi]
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language ModelsShuai Zhao 0006, Xiaohan Wang, Linchao Zhu, Yi Yang 0001. [doi]
• Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributionsFrank Cole, Yulong Lu. [doi]
• Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic ChipsMan Yao, Jiakui Hu, Tianxiang Hu, Yifan Xu, Zhaokun Zhou, Yonghong Tian 0001, Bo Xu 0002, Guoqi Li. [doi]
• Diffusion Models for Multi-Task Generative ModelingChangyou Chen, Han Ding 0001, Bunyamin Sisman, Yi Xu, Ouye Xie, Benjamin Z. Yao, Son Dinh Tran, Belinda Zeng. [doi]
• Learning from Label Proportions: Bootstrapping Supervised Learners via Belief PropagationShreyas Havaldar, Navodita Sharma, Shubhi Sareen, Karthikeyan Shanmugam, Aravindan Raghuveer. [doi]
• Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural NetworksPuja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra, Jayaraman J. Thiagarajan. [doi]
• COSA: Concatenated Sample Pretrained Vision-Language Foundation ModelSihan Chen, Xingjian He, Handong Li, Xiaojie Jin, Jiashi Feng, Jing Liu. [doi]
• 3D Reconstruction with Generalizable Neural Fields using Scene PriorsYang Fu, Shalini De Mello, Xueting Li, Amey Kulkarni, Jan Kautz, Xiaolong Wang 0004, Sifei Liu. [doi]
• Demystifying Linear MDPs and Novel Dynamics Aggregation FrameworkJoongkyu Lee, Min-hwan Oh. [doi]
• Adaptive Rational Activations to Boost Deep Reinforcement LearningQuentin Delfosse, Patrick Schramowski, Martin Mundt, Alejandro Molina 0001, Kristian Kersting. [doi]
• FreeNoise: Tuning-Free Longer Video Diffusion via Noise ReschedulingHaonan Qiu, Menghan Xia, Yong Zhang 0034, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu 0002. [doi]
• Gradual Domain Adaptation via Gradient FlowZhan Zhuang, Yu Zhang, Ying Wei. [doi]
• Prometheus: Inducing Fine-Grained Evaluation Capability in Language ModelsSeungone Kim, Jamin Shin, Yejin Choi 0001, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, Minjoon Seo. [doi]
• Lion Secretly Solves a Constrained Optimization: As Lyapunov PredictsLizhang Chen, Bo Liu 0042, Kaizhao Liang, Qiang Liu 0001. [doi]
• A Data-Driven Measure of Relative Uncertainty for Misclassification DetectionEduardo Dadalto Câmara Gomes, Marco Romanelli 0002, Georg Pichler, Pablo Piantanida. [doi]
• Online GNN Evaluation Under Test-time Graph Distribution ShiftsXin Zheng, Dongjin Song, Qingsong Wen, Bo Du 0001, Shirui Pan. [doi]
• EQA-MX: Embodied Question Answering using Multimodal ExpressionMd Mofijul Islam, Alexi Gladstone, Riashat Islam, Tariq Iqbal. [doi]
• PTaRL: Prototype-based Tabular Representation Learning via Space CalibrationHangting Ye, Wei Fan 0010, Xiaozhuang Song, Shun Zheng, He Zhao, Dandan Guo, Yi Chang 0001. [doi]
• Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and BatchingGanesh Ramachandra Kini, Vala Vakilian, Tina Behnia, Jaidev Gill, Christos Thrampoulidis. [doi]
• OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental LearningWei-Cheng Huang, Chun-Fu Richard Chen, Hsiang Hsu. [doi]
• AmortizedPeriod: Attention-based Amortized Inference for Periodicity IdentificationHang Yu 0002, Cong Liao, Ruolan Liu, Jianguo Li, Yun Hu, Xinzhe Wang. [doi]
• Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient NoiseRui Pan, Yuxing Liu, Xiaoyu Wang, Tong Zhang 0001. [doi]
• Meaning Representations from Trajectories in Autoregressive ModelsTian-Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto. [doi]
• Learning semilinear neural operators: A unified recursive framework for prediction and data assimilationAshutosh Singh, Ricardo Augusto Borsoi, Deniz Erdogmus, Tales Imbiriba. [doi]
• Beating Price of Anarchy and Gradient Descent without Regret in Potential GamesIosif Sakos, Stefanos Leonardos, Stelios Andrew Stavroulakis, Will Overman, Ioannis Panageas, Georgios Piliouras. [doi]
• PAE: Reinforcement Learning from External Knowledge for Efficient ExplorationZhe Wu, Haofei Lu, Junliang Xing, You Wu, Renye Yan, Yaozhong Gan, Yuanchun Shi. [doi]
• Language Modeling Is CompressionGrégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness. [doi]
• Multimodal Learning Without Labeled Multimodal Data: Guarantees and ApplicationsPaul Pu Liang, Chun Kai Ling, Yun Cheng, Alexander Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis-Philippe Morency, Russ Salakhutdinov. [doi]
• Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAGJonas Seng, Matej Zecevic, Devendra Singh Dhami, Kristian Kersting. [doi]
• Masked Completion via Structured Diffusion with White-Box TransformersDruv Pai, Sam Buchanan, Ziyang Wu, Yaodong Yu, Yi Ma 0001. [doi]
• Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement LearningYucheng Yang, Tianyi Zhou 0001, Qiang He, Lei Han, Mykola Pechenizkiy, Meng Fang. [doi]
• Neural Active Learning Beyond BanditsYikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu, Kommy Weldemariam, Hanghang Tong, Jingrui He. [doi]
• Graph Generation with K2-treesYunhui Jang, Dongwoo Kim, Sungsoo Ahn. [doi]
• Skeleton-of-Thought: Prompting LLMs for Efficient Parallel GenerationXuefei Ning, Zinan Lin 0001, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang 0002. [doi]
• SemiReward: A General Reward Model for Semi-supervised LearningSiyuan Li, Weiyang Jin, Zedong Wang, Fang Wu, Zicheng Liu 0006, Cheng Tan 0012, Stan Z. Li. [doi]
• The Update-Equivalence Framework for Decision-Time PlanningSamuel Sokota, Gabriele Farina, David J. Wu 0002, Hengyuan Hu, Kevin A. Wang, J. Zico Kolter, Noam Brown. [doi]
• AMAGO: Scalable In-Context Reinforcement Learning for Adaptive AgentsJake Grigsby, Linxi Fan, Yuke Zhu. [doi]
• Repeated Random Sampling for Minimizing the Time-to-Accuracy of LearningPatrik Okanovic, Roger Waleffe, Vasilis Mageirakos, Konstantinos E. Nikolakakis, Amin Karbasi, Dionysios S. Kalogerias, Nezihe Merve Gürel, Theodoros Rekatsinas. [doi]
• FITS: Modeling Time Series with 10k ParametersZhijian Xu, Ailing Zeng, Qiang Xu 0001. [doi]
• Inverse Approximation Theory for Nonlinear Recurrent Neural NetworksShida Wang, Zhong Li, Qianxiao Li. [doi]
• Neural Rate Control for Learned Video CompressionYiWei Zhang, Guo Lu, Yunuo Chen, Shen Wang, Yibo Shi, Jing Wang, Li Song 0001. [doi]
• Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion ModelsGabriele Corso, Yilun Xu, Valentin De Bortoli, Regina Barzilay, Tommi S. Jaakkola. [doi]
• OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel ViewsFrancis Engelmann, Fabian Manhardt, Michael Niemeyer, Keisuke Tateno, Federico Tombari. [doi]
• Look, Remember and Reason: Grounded Reasoning in Videos with Language ModelsApratim Bhattacharyya, Sunny Panchal, Reza Pourreza 0002, Mingu Lee, Pulkit Madan, Roland Memisevic. [doi]
• MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework DesignXiang Fu 0005, Tian Xie, Andrew S. Rosen, Tommi S. Jaakkola, Jake Smith. [doi]
• Tailoring Self-Rationalizers with Multi-Reward DistillationSahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu, Liunian Harold Li, Aaron Chan, Jack Hessel, Yejin Choi 0001, Xiang Ren 0001. [doi]
• Hybrid Sharing for Multi-Label Image ClassificationZihao Yin, Chen Gan, Kelei He, Yang Gao 0001, Junfeng Zhang. [doi]
• LaneSegNet: Map Learning with Lane Segment Perception for Autonomous DrivingTianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li 0001. [doi]
• Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging DataCe Ju, Reinmar J. Kobler, Liyao Tang, Cuntai Guan, Motoaki Kawanabe. [doi]
• TAB: Temporal Accumulated Batch Normalization in Spiking Neural NetworksHaiyan Jiang, Vincent Zoonekynd, Giulia De Masi, Bin Gu 0001, Huan Xiong. [doi]
• FedDA: Faster Adaptive Gradient Methods for Federated Constrained OptimizationJunyi Li, Feihu Huang, Heng Huang. [doi]
• DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform GenerationRoi Benita, Michael Elad, Joseph Keshet. [doi]
• TabR: Tabular Deep Learning Meets Nearest NeighborsYury Gorishniy, Ivan Rubachev, Nikolay Kartashev, Daniil Shlenskii, Akim Kotelnikov, Artem Babenko. [doi]
• TUVF: Learning Generalizable Texture UV Radiance FieldsAn-Chieh Cheng, Xueting Li, Sifei Liu, Xiaolong Wang 0004. [doi]
• Spectrally Transformed Kernel RegressionRuntian Zhai, Rattana Pukdee, Roger Jin, Maria-Florina Balcan, Pradeep Kumar Ravikumar. [doi]
• Lifting Architectural Constraints of Injective FlowsPeter Sorrenson, Felix Draxler, Armand Rousselot, Sander Hummerich, Lea Zimmermann, Ullrich Köthe. [doi]
• Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs BinningHansheng Xue, Vijini Mallawaarachchi, Lexing Xie, Vaibhav Rajan. [doi]
• Local Composite Saddle Point OptimizationSite Bai, Brian Bullins. [doi]
• Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional KernelsZahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu. [doi]
• Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsFred Zhang, Neel Nanda. [doi]
• Cycle Consistency Driven Object DiscoveryAniket Rajiv Didolkar, Anirudh Goyal, Yoshua Bengio. [doi]
• In-context Exploration-Exploitation for Reinforcement LearningZhenwen Dai, Federico Tomasi, Sina Ghiassian. [doi]
• MagicDrive: Street View Generation with Diverse 3D Geometry ControlRuiyuan Gao 0001, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, Qiang Xu 0001. [doi]
• Progressive Fourier Neural Representation for Sequential Video CompilationHaeyong Kang, Jaehong Yoon, DahYun Kim, Sung Ju Hwang, Chang D. Yoo. [doi]
• The Alignment Problem from a Deep Learning PerspectiveRichard Ngo, Lawrence Chan, Sören Mindermann. [doi]
• How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker ComputationJosh Alman, Zhao Song 0002. [doi]
• OmniControl: Control Any Joint at Any Time for Human Motion GenerationYiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, Huaizu Jiang. [doi]
• On the Parameterization of Second-Order Optimization Effective towards the Infinite WidthSatoki Ishikawa, Ryo Karakida. [doi]
• Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal CorrelationDevavrat Tomar, Guillaume Vray, Jean-Philippe Thiran, Behzad Bozorgtabar. [doi]
• Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion ModelsSenmao Li, Joost van de Weijer 0001, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang 0003. [doi]
• Learning Implicit Representation for Reconstructing Articulated ObjectsHao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja. [doi]
• AutoVP: An Automated Visual Prompting Framework and BenchmarkHsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Si Liu 0001, Tsung-Yi Ho. [doi]
• Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory MatchingZiyao Guo, Kai Wang 0036, George Cazenavette, Hui Li, Kaipeng Zhang, Yang You 0001. [doi]
• Towards the Fundamental Limits of Knowledge Transfer over Finite DomainsQingyue Zhao, Banghua Zhu. [doi]
• How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular DataMihaela C. Stoian, Salijona Dyrmishi, Maxime Cordy, Thomas Lukasiewicz, Eleonora Giunchiglia. [doi]
• Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated PoliciesXiangyu Liu, Chenghao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang. [doi]
• Multi-Resolution Diffusion Models for Time Series ForecastingLifeng Shen, Weiyu Chen, James T. Kwok. [doi]
• Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge DistillationChengming Hu, Haolun Wu, Xuan Li, Chen Ma 0001, Xi Chen 0009, Boyu Wang, Jun Yan 0007, Xue Liu 0001. [doi]
• Views Can Be Deceiving: Improved SSL Through Feature Space AugmentationKimia Hamidieh, Haoran Zhang 0003, Swami Sankaranarayanan, Marzyeh Ghassemi. [doi]
• AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZJonas Belouadi, Anne Lauscher, Steffen Eger. [doi]
• ImplicitSLIM and How it Improves Embedding-based Collaborative FilteringIlya Shenbin, Sergey I. Nikolenko. [doi]
• Blending Imitation and Reinforcement Learning for Robust Policy ImprovementXuefeng Liu, Takuma Yoneda, Rick Stevens, Matthew R. Walter, Yuxin Chen 0001. [doi]
• VDT: General-purpose Video Diffusion Transformers via Mask ModelingHaoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu 0001, Ping Luo 0002, Mingyu Ding. [doi]
• Pose Modulated Avatars from VideoChunjin Song, Bastian Wandt, Helge Rhodin. [doi]
• InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data PruningZiheng Qin, Kai Wang 0036, Zangwei Zheng, Jianyang Gu, Xiangyu Peng, Zhaopan Xu, Daquan Zhou, Lei Shang, Baigui Sun, Xuansong Xie, Yang You 0001. [doi]
• Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFaceXinyu Yang, Weixin Liang, James Zou 0001. [doi]
• Pre-training with Synthetic Data Helps Offline Reinforcement LearningZecheng Wang, Che Wang, Zixuan Dong, Keith W. Ross. [doi]
• SliceGPT: Compress Large Language Models by Deleting Rows and ColumnsSaleh Ashkboos, Maximilian L. Croci, Marcelo Gennari Do Nascimento, Torsten Hoefler, James Hensman. [doi]
• Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable SpacingsIlyass Hammouamri, Ismail Khalfaoui Hassani, Timothée Masquelier. [doi]
• DAM: Towards a Foundation Model for ForecastingLuke Nicholas Darlow, Qiwen Deng, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Artjom Joosen, Adam Barker, Amos J. Storkey. [doi]
• Explaining Kernel Clustering via Decision TreesMaximilian Fleissner, Leena Chennuru Vankadara, Debarghya Ghoshdastidar. [doi]
• T-MARS: Improving Visual Representations by Circumventing Text Feature LearningPratyush Maini, Sachin Goyal, Zachary Chase Lipton, J. Zico Kolter, Aditi Raghunathan. [doi]
• On the Provable Advantage of Unsupervised PretrainingJiawei Ge, Shange Tang, Jianqing Fan, Chi Jin 0001. [doi]
• Discovering Failure Modes of Text-guided Diffusion Models via Adversarial SearchQihao Liu, Adam Kortylewski, Yutong Bai, Song Bai, Alan L. Yuille. [doi]
• ODEFormer: Symbolic Regression of Dynamical Systems with TransformersStéphane d'Ascoli, Sören Becker, Philippe Schwaller, Alexander Mathis, Niki Kilbertus. [doi]
• Unbiased Watermark for Large Language ModelsZhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, Heng Huang. [doi]
• Generative Modeling with Phase Stochastic BridgeTianrong Chen, Jiatao Gu, Laurent Dinh, Evangelos A. Theodorou, Joshua M. Susskind, Shuangfei Zhai. [doi]
• Efficient Sharpness-Aware Minimization for Molecular Graph Transformer ModelsYili Wang, Kaixiong Zhou, Ninghao Liu, Ying Wang, Xin Wang. [doi]
• BrainLM: A foundation model for brain activity recordingsJosue Ortega Caro, Antonio Henrique de Oliveira Fonseca, Syed Asad Rizvi, Matteo Rosati, Christopher L. Averill, James Cross, Prateek Mittal, Emanuele Zappala, Rahul Madhav Dhodapkar, Chadi Abdallah, David van Dijk. [doi]
• General Stability Analysis for Zeroth-Order Optimization AlgorithmsXinyue Liu, Hualin Zhang, Bin Gu 0001, Hong Chen 0004. [doi]
• CAS: A Probability-Based Approach for Universal Condition Alignment ScoreChunsan Hong, Byunghee Cha, Tae Hyun Oh. [doi]
• Clifford Group Equivariant Simplicial Message Passing NetworksCong Liu, David Ruhe, Floor Eijkelboom, Patrick Forré. [doi]
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language ModelsArchiki Prasad, Elias Stengel-Eskin, Mohit Bansal. [doi]
• Improved Analysis of Sparse Linear Regression in Local Differential Privacy ModelLiyang Zhu, Meng Ding, Vaneet Aggarwal, Jinhui Xu 0001, Di Wang 0015. [doi]
• The Expressive Power of Low-Rank AdaptationYuchen Zeng, Kangwook Lee 0001. [doi]
• Learning in reverse causal strategic environments with ramifications on two sided marketsSeamus Somerstep, Yuekai Sun, Yaacov Ritov. [doi]
• Linear attention is (maybe) all you need (to understand Transformer optimization)Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra. [doi]
• Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio LearnersSarthak Yadav, Sergios Theodoridis, Lars Kai Hansen, Zheng-Hua Tan. [doi]
• SpeechTokenizer: Unified Speech Tokenizer for Speech Language ModelsXin Zhang, Dong Zhang, Shimin Li, Yaqian Zhou, Xipeng Qiu. [doi]
• Gradual Optimization Learning for Conformational Energy MinimizationArtem Tsypin, Leonid Ugadiarov, Kuzma Khrabrov, Alexander Telepov, Egor Rumiantsev, Alexey Skrynnik, Aleksandr Panov, Dmitry P. Vetrov, Elena Tutubalina, Artur Kadurin. [doi]
• PerceptionCLIP: Visual Classification by Inferring and Conditioning on ContextsBang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang. [doi]
• Rethinking the Power of Graph Canonization in Graph Representation Learning with StabilityZehao Dong, Muhan Zhang, Philip R. O. Payne, Michael A. Province, Carlos Cruchaga, Tianyu Zhao, Fuhai Li, Yixin Chen 0001. [doi]
• Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNNBiswadeep Chakraborty, Beomseok Kang, Harshit Kumar, Saibal Mukhopadhyay. [doi]
• Harnessing Density Ratios for Online Reinforcement LearningPhilip Amortila, Dylan J. Foster, Nan Jiang 0008, Ayush Sekhari, Tengyang Xie. [doi]
• I-PHYRE: Interactive Physical ReasoningShiqian Li, Kewen Wu 0004, Chi Zhang 0017, Yixin Zhu 0001. [doi]
• Contrastive Preference Learning: Learning from Human Feedback without Reinforcement LearningJoey Hejna, Rafael Rafailov, Harshit Sikchi, Chelsea Finn, Scott Niekum, W. Bradley Knox, Dorsa Sadigh. [doi]
• Bandits Meet Mechanism Design to Combat Clickbait in Online RecommendationThomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu. [doi]
• Towards Robust Out-of-Distribution Generalization Bounds via SharpnessYingtian Zou, Kenji Kawaguchi, Yingnan Liu, Jiashuo Liu, Mong-Li Lee, Wynne Hsu. [doi]
• FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound ScalingYu Tian 0001, Min Shi 0001, Yan Luo, Ava Kouhana, Tobias Elze, Mengyu Wang 0001. [doi]
• Implicit Maximum a Posteriori Filtering via Adaptive OptimizationGianluca M. Bencomo, Jake Snell, Thomas L. Griffiths 0001. [doi]
• Sliced Wasserstein Estimation with Control VariatesKhai Nguyen, Nhat Ho. [doi]
• Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained ModelsPeiyan Zhang, Haoyang Liu, Chaozhuo Li 0001, Xing Xie 0001, Sunghun Kim 0001, Haohan Wang. [doi]
• SpaCE: The Spatial Confounding EnvironmentMauricio Tec, Ana Trisovic, Michelle Audirac, Sophie Woodward, Jie Kate Hu, Naeem Khoshnevis, Francesca Dominici. [doi]
• Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language ModelsHritik Bansal, John Dang, Aditya Grover. [doi]
• A Simple and Scalable Representation for Graph GenerationYunhui Jang, Seul Lee, Sungsoo Ahn. [doi]
• An Efficient Membership Inference Attack for the Diffusion Model by Proximal InitializationFei Kong, Jinhao Duan, Ruipeng Ma, Heng Tao Shen, Xiaoshuang Shi, Xiaofeng Zhu 0001, Kaidi Xu. [doi]
• Towards Offline Opponent Modeling with In-context LearningYuheng Jing, Kai Li 0022, Bingyun Liu, Yifan Zang 0001, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng 0001. [doi]
• Denevil: towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction LearningShitong Duan, Xiaoyuan Yi, Peng Zhang 0060, Tun Lu, Xing Xie 0001, Ning Gu. [doi]
• One For All: Towards Training One Graph Model For All Classification TasksHao Liu 0057, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen 0001, Muhan Zhang. [doi]
• MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding MethodsMara Finkelstein, Markus Freitag. [doi]
• Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency AdaptationZhiyu Zhu, Xinyi Wang 0005, Zhibo Jin, Jiayu Zhang, Huaming Chen. [doi]
• Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation ModelsTianjian Li, Haoran Xu, Philipp Koehn, Daniel Khashabi, Kenton Murray. [doi]
• Let's do the time-warp-attend: Learning topological invariants of dynamical systemsNoa Moriel, Matthew Ricci, Mor Nitzan. [doi]
• Language Model Beats Diffusion - Tokenizer is key to visual generationLijun Yu, José Lezama, Nitesh Bharadwaj Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang 0001, Irfan Essa, David A. Ross, Lu Jiang 0004. [doi]
• Zero and Few-shot Semantic Parsing with Ambiguous InputsElias Stengel-Eskin, Kyle Rawlins, Benjamin Van Durme. [doi]
• Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised LearningJames Chapman 0006, Lennie Wells, Ana Lawry Aguila. [doi]
• OMNI: Open-endedness via Models of human Notions of InterestingnessJenny Zhang, Joel Lehman, Kenneth O. Stanley, Jeff Clune. [doi]
• Linearity of Relation Decoding in Transformer Language ModelsEvan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau. [doi]
• Large Language Models as Analogical ReasonersMichihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat, Jure Leskovec, Percy Liang, Ed H. Chi, Denny Zhou. [doi]
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-SupervisionJiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng, Seung Wook Kim 0001, Boyi Li, Tong Che, Danfei Xu, Sanja Fidler, Marco Pavone 0001, Yue Wang 0036. [doi]
• Unleashing Large-Scale Video Generative Pre-training for Visual Robot ManipulationHongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, Tao Kong. [doi]
• Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation LearningYouhan Lee, Hasun Yu, Jaemyung Lee 0004, Jaehoon Kim. [doi]
• ConjNorm: Tractable Density Estimation for Out-of-Distribution DetectionBo Peng, Yadan Luo, Yonggang Zhang, Yixuan Li 0001, Zhen Fang 0001. [doi]
• DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species GenomesZhihan Zhou 0001, Yanrong Ji, Weijian Li, Pratik Dutta, Ramana V. Davuluri, Han Liu. [doi]
• DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language ModelsLicheng Wen, Daocheng Fu, Xin Li 0110, Xinyu Cai, Tao Ma 0002, Pinlong Cai, Min Dou, Botian Shi, Liang He 0001, Yu Qiao 0001. [doi]
• CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense PredictionSize Wu, Wenwei Zhang, Lumin Xu, Sheng Jin 0007, Xiangtai Li, Wentao Liu 0002, Chen Change Loy. [doi]
• Neural Optimal Transport with General Cost FunctionalsArip Asadulaev, Alexander Korotin, Vage Egiazarian, Petr Mokrov, Evgeny Burnaev. [doi]
• Threaten Spiking Neural Networks through Combining Rate and Temporal InformationZecheng Hao, Tong Bu, Xinyu Shi, Zihan Huang, Zhaofei Yu, Tiejun Huang 0001. [doi]
• Revisiting Data Augmentation in Deep Reinforcement LearningJianshu Hu, Yunpeng Jiang, Paul Weng. [doi]
• Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingMelanie Sclar, Yejin Choi 0001, Yulia Tsvetkov, Alane Suhr. [doi]
• UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous DrivingKai Cheng, Xiaoxiao Long, Wei Yin 0006, Jin Wang, Zhiqiang Wu, Yuexin Ma, Kaixuan Wang, Xiaozhi Chen, Xuejin Chen. [doi]
• CausalLM is not optimal for in-context learningNan Ding 0002, Tomer Levinboim, Jialin Wu, Sebastian Goodman, Radu Soricut. [doi]
• InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph PriorChenguo Lin, Yadong Mu. [doi]
• Optimal transport based adversarial patch to leverage large scale attack transferabilityPol Labarbarie, Adrien Chan-Hon-Tong, Stéphane Herbin, Milad Leyli-Abadi. [doi]
• Curiosity-driven Red-teaming for Large Language ModelsZhang-Wei Hong, Idan Shenfeld, Tsun-Hsuan Wang, Yung-Sung Chuang, Aldo Pareja, James R. Glass, Akash Srivastava, Pulkit Agrawal 0001. [doi]
• A Black-box Approach for Non-stationary Multi-agent Reinforcement LearningHaozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon Shaolei Du. [doi]
• Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?Gourav Datta, Zeyu Liu 0003, Peter Anthony Beerel. [doi]
• Data-independent Module-aware Pruning for Hierarchical Vision TransformersYang He 0002, Joey Tianyi Zhou. [doi]
• Multi-Source Diffusion Models for Simultaneous Music Generation and SeparationGiorgio Mariani, Irene Tallini, Emilian Postolache, Michele Mancusi, Luca Cosmo, Emanuele Rodolà. [doi]
• InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision GeneralistsYulu Gan, Sungwoo Park, Alexander Schubert, Anthony Philippakis, Ahmed M. Alaa. [doi]
• Enhancing One-Shot Federated Learning Through Data and Ensemble Co-BoostingRong Dai, Yonggang Zhang, Ang Li, Tongliang Liu, Xun Yang, Bo Han 0003. [doi]
• On the Stability of Expressive Positional Encodings for GraphsYinan Huang, William Lu, Joshua Robinson 0001, Yu Yang, Muhan Zhang, Stefanie Jegelka, Pan Li 0005. [doi]
• InstructDET: Diversifying Referring Object Detection with Generalized InstructionsRonghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu 0006, Rui Zhao 0001, Yibing Song. [doi]
• SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach. [doi]
• AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning InferenceXuanlei Zhao, Shenggan Cheng, Guangyang Lu, Haotian Zhou, Bin Jia, Yang You 0001. [doi]
• AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion ModelZibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng 0002, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu. [doi]
• Efficient Continual Finite-Sum MinimizationIoannis Mavrothalassitis, Stratis Skoulakis, Leello Tadesse Dadi, Volkan Cevher. [doi]
• Structured Video-Language Modeling with Temporal Grouping and Spatial GroundingYuanhao Xiong, Long Zhao 0003, Boqing Gong, Ming-Hsuan Yang 0001, Florian Schroff, Ting Liu 0005, Cho-Jui Hsieh, Liangzhe Yuan. [doi]
• A Semantic Invariant Robust Watermark for Large Language ModelsAiwei Liu, Leyi Pan, Xuming Hu, Shiao Meng, Lijie Wen 0001. [doi]
• Polynormer: Polynomial-Expressive Graph Transformer in Linear TimeChenhui Deng, Zichao Yue, Zhiru Zhang. [doi]
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi. [doi]
• Human Motion Diffusion as a Generative PriorYoni Shafir, Guy Tevet, Roy Kapon, Amit Haim Bermano. [doi]
• A Precise Characterization of SGD Stability Using Loss Surface GeometryGregory Dexter, Borja Ocejo, S. Sathiya Keerthi, Aman Gupta, Ayan Acharya, Rajiv Khanna. [doi]
• R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image GenerationJiayu Xiao, Henglei Lv, Liang Li 0003, Shuhui Wang, Qingming Huang. [doi]
• Augmenting Transformers with Recursively Composed Multi-grained RepresentationsXiang Hu, Qingyang Zhu, Kewei Tu, Wei Wu. [doi]
• Enhancing Small Medical Learners with Privacy-preserving Contextual PromptingXinlu Zhang, Shiyang Li, Xianjun Yang, Chenxin Tian, Yao Qin 0001, Linda Ruth Petzold. [doi]
• Adaptive Window Pruning for Efficient Local Motion DeblurringHaoying Li, Jixin Zhao, Shangchen Zhou, Huajun Feng, Chongyi Li, Chen Change Loy. [doi]
• Object centric architectures enable efficient causal representation learningAmin Mansouri, Jason S. Hartford, Yan Zhang, Yoshua Bengio. [doi]
• Generalized Schrödinger Bridge MatchingGuan-Horng Liu, Yaron Lipman, Maximilian Nickel, Brian Karrer, Evangelos A. Theodorou, Ricky T. Q. Chen. [doi]
• Learning to Act without ActionsDominik Schmidt, Minqi Jiang. [doi]
• Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential GamesBrian Hu Zhang, Gabriele Farina, Tuomas Sandholm. [doi]
• Interpretable Meta-Learning of Physical SystemsMatthieu Blanke, Marc Lelarge. [doi]
• Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training DatasetHuigen Ye, Hua Xu, Hongyan Wang. [doi]
• AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?Qi Zhao, Shijie Wang, Ce Zhang 0010, Changcheng Fu, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun 0002. [doi]
• DreamLLM: Synergistic Multimodal Comprehension and CreationRunpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang 0005, Kaisheng Ma, Li Yi. [doi]
• Pre-training with Random Orthogonal Projection Image ModelingMaryam Haghighat, Peyman Moghadam, Shaheer Mohamed, Piotr Koniusz. [doi]
• LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster InferenceYifan Feng, Yihe Luo, Shihui Ying, Yue Gao 0002. [doi]
• Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous DatasetsYihuan Mao, Chengjie Wu, Xi Chen, Hao Hu 0006, Ji-jiang, Tianze Zhou, Tangjie Lv, Changjie Fan, Zhipeng Hu, Yi Wu 0013, Yujing Hu, Chongjie Zhang. [doi]
• One Forward is Enough for Neural Network Training via Likelihood Ratio MethodJinyang Jiang 0001, Zeliang Zhang, Chenliang Xu, Zhaofei Yu, Yijie Peng. [doi]
• f-FERM: A Scalable Framework for Robust Fair Empirical Risk MinimizationSina Baharlouei, Shivam Patel, Meisam Razaviyayn. [doi]
• Text2Reward: Reward Shaping with Language Models for Reinforcement LearningTianbao Xie, Siheng Zhao, Chen Henry Wu, Yitao Liu, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu 0009. [doi]
• BatchPrompt: Accomplish more with lessJianzhe Lin, Maurice Diesendruck, Liang Du, Robin Abraham. [doi]
• Learning the greatest common divisor: explaining transformer predictionsFrançois Charton. [doi]
• Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy InstructionsTaehyeon Kim, Joonkee Kim, Gihun Lee, Se-Young Yun. [doi]
• CO2: Efficient Distributed Training with Full Communication-Computation OverlapWeigao Sun, Zhen Qin, Weixuan Sun, Shidi Li, Dong Li 0033, Xuyang Shen, Yu Qiao, Yiran Zhong. [doi]
• Leave-one-out Distinguishability in Machine LearningJiayuan Ye 0001, Anastasia Borovykh, Soufiane Hayou, Reza Shokri. [doi]
• Plug-and-Play Policy Planner for Large Language Model Powered Dialogue AgentsYang Deng 0002, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua. [doi]
• Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear SolversOren Mangoubi, Nisheeth K. Vishnoi. [doi]
• Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving MapsHenry Li, Ronen Basri, Yuval Kluger. [doi]
• $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power DivergenceJuno Kim, Jaehyuk Kwon, Mincheol Cho, Hyunjong Lee, Joong-Ho Won. [doi]
• On the Joint Interaction of Models, Data, and FeaturesYiding Jiang, Christina Baek, J. Zico Kolter. [doi]
• Leveraging Generative Models for Unsupervised Alignment of Neural Time Series DataAyesha Vermani, Il Memming Park, Josue Nassar. [doi]
• SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and GenerationChongyu Fan, Jiancheng Liu, Yihua Zhang, Eric Wong 0001, Dennis Wei, Sijia Liu 0001. [doi]
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningYuwei Guo 0002, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang 0001, Yu Qiao 0001, Maneesh Agrawala, Dahua Lin, Bo Dai 0002. [doi]
• Modulate Your Spectrum in Self-Supervised LearningXi Weng, Yunhao Ni, Tengwei Song, Jie Luo 0004, Rao Muhammad Anwer, Salman Khan 0001, Fahad Shahbaz Khan, Lei Huang 0015. [doi]
• Multimodal Molecular Pretraining via Modality BlendingQiying Yu, Yudi Zhang 0008, Yuyan Ni, Shikun Feng, Yanyan Lan, Hao Zhou, Jingjing Liu. [doi]
• DiffEnc: Variational Diffusion with a Learned EncoderBeatrix Miranda Ginn Nielsen, Anders Christensen, Andrea Dittadi, Ole Winther. [doi]
• Dynamic Neighborhood Construction for Structured Large Discrete Action SpacesFabian Akkerman, Julius Luy, Wouter van Heeswijk, Maximilian Schiffer. [doi]
• Learning Optimal Contracts: How to Exploit Small Action SpacesFrancesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi 0001, Nicola Gatti 0001. [doi]
• Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource LanguagesWanru Zhao, Yihong Chen, Royson Lee, Xinchi Qiu, Yan Gao, Hongxiang Fan, Nicholas Donald Lane. [doi]
• Understanding Convergence and Generalization in Federated Learning through Feature Learning TheoryWei Huang, Ye Shi 0001, Zhongyi Cai, Taiji Suzuki. [doi]
• Task structure and nonlinearity jointly determine learned representational geometryMatteo Alleman, Jack W. Lindsey, Stefano Fusi. [doi]
• Skill or Luck? Return Decomposition via Advantage FunctionsHsiao-Ru Pan, Bernhard Schölkopf. [doi]
• Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient MethodsSara Klein, Simon Weissmann, Leif Döring. [doi]
• Addressing Loss of Plasticity and Catastrophic Forgetting in Continual LearningMohamed Elsayed 0003, A. Rupam Mahmood. [doi]
• Idempotent Generative NetworkAssaf Shocher, Amil Dravid, Yossi Gandelsman, Inbar Mosseri, Michael Rubinstein, Alexei A. Efros. [doi]
• GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial PerturbationsZaishuo Xia, Han Yang, Binghui Wang, Jinyuan Jia. [doi]
• Bounds on Representation-Induced Confounding Bias for Treatment Effect EstimationValentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel. [doi]
• Point2SSM: Learning Morphological Variations of Anatomies from Point CloudsJadie Adams, Shireen Y. Elhabian. [doi]
• Neural Spectral Methods: Self-supervised learning in the spectral domainYiheng Du, Nithin Chalapathi, Aditi S. Krishnapriyan. [doi]
• Scaling Convex Neural Networks with Burer-Monteiro FactorizationArda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci. [doi]
• Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch ImportanceYuyao Zhang, Lan Wei, Nikolaos M. Freris. [doi]
• Debiased Collaborative Filtering with Kernel-Based Causal BalancingHaoxuan Li, Chunyuan Zheng, Yanghao Xiao, Peng Wu 0012, Zhi Geng, Xu Chen, Peng Cui 0001. [doi]
• A Mutual Information Perspective on Federated Contrastive LearningChristos Louizos, Matthias Reisser, Denis Korzhenkov. [doi]
• Deep Confident Steps to New Pockets: Strategies for Docking GeneralizationGabriele Corso, Arthur Deng, Nicholas Polizzi, Regina Barzilay, Tommi S. Jaakkola. [doi]
• Lewis's Signaling Game as beta-VAE For Natural Word Lengths and SegmentsRyo Ueda, Tadahiro Taniguchi. [doi]
• On the Learnability of Watermarks for Language ModelsChenChen Gu, Xiang Lisa Li, Percy Liang, Tatsunori Hashimoto. [doi]
• Decoupling regularization from the action spaceSobhan Mohammadpour, Emma Frejinger, Pierre-Luc Bacon. [doi]
• Reclaiming the Source of Programmatic Policies: Programmatic versus Latent SpacesTales Henrique Carvalho, Kenneth Tjhia, Levi Lelis. [doi]
• Graph Transformers on EHRs: Better Representation Improves Downstream PerformanceRaphael Poulain, Rahmatollah Beheshti. [doi]
• Generating Images with 3D Annotations Using Diffusion ModelsWufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang 0099, Zihao Xiao, Guofeng Zhang 0020, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu 0001, Alan L. Yuille. [doi]
• Function Vectors in Large Language ModelsEric Todd, Millicent L. Li, Arnab Sen Sharma, Aaron Mueller, Byron C. Wallace, David Bau. [doi]
• What does automatic differentiation compute for neural networks?Sejun Park, Sanghyuk Chun, Wonyeol Lee 0001. [doi]
• Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature AttacksYassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström. [doi]
• Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair GraphsXiong Zhou, Xianming Liu, Feilong Zhang 0002, Gang Wu 0010, Deming Zhai, Junjun Jiang, Xiangyang Ji. [doi]
• Lemur: Harmonizing Natural Language and Code for Language AgentsYiheng Xu, Hongjin Su, Chen Xing, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, Zhoujun Cheng, Siheng Zhao, Lingpeng Kong, Bailin Wang, Caiming Xiong, Tao Yu 0009. [doi]
• How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion ModelsPascal Chang, Jingwei Tang, Markus Gross 0001, Vinicius C. Azevedo. [doi]
• Graph-constrained diffusion for End-to-End Path PlanningDingyuan Shi, Yongxin Tong, Zimu Zhou, Ke Xu 0001, Zheng Wang, Jieping Ye. [doi]
• On the Fairness ROAD: Robust Optimization for Adversarial DebiasingVincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki. [doi]
• What's in a Prior? Learned Proximal Networks for Inverse ProblemsZhenghan Fang, Sam Buchanan, Jeremias Sulam. [doi]
• Learning to Compose: Improving Object Centric Learning by Injecting CompositionalityWhie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong. [doi]
• Ins-DetCLIP: Aligning Detection Model to Follow Human-Language InstructionRenjie Pi, Lewei Yao, Jianhua Han, Xiaodan Liang, Wei Zhang 0196, Hang Xu. [doi]
• Interpretable Diffusion via Information DecompositionXianghao Kong, Ollie Liu, Han Li, Dani Yogatama, Greg Ver Steeg. [doi]
• VeRA: Vector-based Random Matrix AdaptationDawid Jan Kopiczko, Tijmen Blankevoort, Yuki M. Asano. [doi]
• Improved Regret Bounds for Non-Convex Online-Within-Online Meta LearningJiechao Guan, Hui Xiong 0001. [doi]
• Understanding Transferable Representation Learning and Zero-shot Transfer in CLIPZixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu. [doi]
• Noisy Interpolation Learning with Shallow Univariate ReLU NetworksNirmit Joshi, Gal Vardi, Nathan Srebro. [doi]
• Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt OptimizersQingyan Guo, Rui Wang 0028, Junliang Guo, Bei Li, Kaitao Song, Xu Tan 0003, Guoqing Liu, Jiang Bian 0002, Yujiu Yang. [doi]
• A Hierarchical Bayesian Model for Few-Shot Meta LearningMinyoung Kim, Timothy M. Hospedales. [doi]
• On the Hardness of Online Nonconvex Optimization with Single Oracle FeedbackZiwei Guan, Yi Zhou 0017, Yingbin Liang. [doi]
• Latent Representation and Simulation of Markov Processes via Time-Lagged Information BottleneckMarco Federici, Patrick Forré, Ryota Tomioka, Bastiaan S. Veeling. [doi]
• DAFA: Distance-Aware Fair Adversarial TrainingHyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park, Ho Bae, Sungroh Yoon. [doi]
• Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and HowSebastian Pineda-Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter, Josif Grabocka. [doi]
• Scale-Adaptive Diffusion Model for Complex Sketch SynthesisJijin Hu, Ke Li 0004, Yonggang Qi, Yi-Zhe Song. [doi]
• A Variational Perspective on Solving Inverse Problems with Diffusion ModelsMorteza Mardani, Jiaming Song, Jan Kautz, Arash Vahdat. [doi]
• IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language ModelsShaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu. [doi]
• FedWon: Triumphing Multi-domain Federated Learning Without NormalizationWeiming Zhuang, Lingjuan Lyu. [doi]
• PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function ApproximationZhuqing Liu, Xin Zhang, Jia Liu 0002, Zhengyuan Zhu, Songtao Lu. [doi]
• Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion ModelingHuangjie Zheng, Zhendong Wang, Jianbo Yuan, Guanghan Ning, Pengcheng He, Quanzeng You, Hongxia Yang, Mingyuan Zhou. [doi]
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsPan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu 0010, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng 0002, Kai-Wei Chang, Michel Galley, Jianfeng Gao 0001. [doi]
• The Human-AI Substitution game: active learning from a strategic labelerTom Yan, Chicheng Zhang. [doi]
• Investigating the Benefits of Projection Head for Representation LearningYihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman. [doi]
• Time-Efficient Reinforcement Learning with Stochastic Stateful PoliciesFiras Al-Hafez, Guoping Zhao, Jan Peters 0001, Davide Tateo. [doi]
• Boosting Graph Anomaly Detection with Adaptive Message PassingJingyan Chen, Guanghui Zhu, Chunfeng Yuan, Yihua Huang 0001. [doi]
• MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning ProcessXinyao Fan, Yueying Wu, Chang Xu 0008, Yuhao Huang, Weiqing Liu, Jiang Bian 0002. [doi]
• MUSTARD: Mastering Uniform Synthesis of Theorem and Proof DataYinya Huang, Xiaohan Lin, Zhengying Liu, Qingxing Cao, Huajian Xin, Haiming Wang, Zhenguo Li, Linqi Song, Xiaodan Liang. [doi]
• Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMsYuxin Zhang 0002, Lirui Zhao, Mingbao Lin, Yunyun Sun, Yiwu Yao, Xingjia Han, Jared Tanner, Shiwei Liu 0003, Rongrong Ji. [doi]
• Continuous Invariance LearningLin Yong, Fan Zhou, Lu Tan, Lintao Ma, Jianmeng Liu, Yansu He, Yuan Yuan, Yu Liu 0071, James Y. Zhang, Yujiu Yang, Hao Wang. [doi]
• On Diffusion Modeling for Anomaly DetectionVictor Livernoche, Vineet Jain, Yashar Hezaveh, Siamak Ravanbakhsh. [doi]
• MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction FollowingRenze Lou, Kai Zhang 0033, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su 0001, Wenpeng Yin 0001. [doi]
• Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation SpaceErik J. Bekkers, Sharvaree P. Vadgama, Rob Hesselink, Putri A. van der Linden, David W. Romero. [doi]
• P2Seg: Pointly-supervised Segmentation via Mutual DistillationZipeng Wang, Xuehui Yu, Xumeng Han, Wenwen Yu, Zhixun Huang, Jianbin Jiao, Zhenjun Han. [doi]
• Conditional Variational Diffusion ModelsGabriel della Maggiora, Luis Alberto Croquevielle, Nikita Deshpande, Harry Horsley, Thomas Heinis, Artur Yakimovich. [doi]
• Improving Domain Generalization with Domain RelationsHuaxiu Yao, Xinyu Yang, Xinyi Pan, Shengchao Liu, Pang Wei Koh, Chelsea Finn. [doi]
• The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical ModelDaniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry, Paul Hand. [doi]
• Are Models Biased on Text without Gender-related Language?Catarina G. Belém, Preethi Seshadri, Yasaman Razeghi, Sameer Singh 0001. [doi]
• Analyzing and Improving Optimal-Transport-based Adversarial NetworksJaemoo Choi, Jaewoong Choi, Myungjoo Kang. [doi]
• SE(3)-Stochastic Flow Matching for Protein Backbone GenerationAvishek Joey Bose, Tara Akhound-Sadegh, Guillaume Huguet, Kilian Fatras, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael M. Bronstein, Alexander Tong 0001. [doi]
• Adversarial Causal Bayesian OptimizationScott Sussex, Pier Giuseppe Sessa, Anastasia Makarova, Andreas Krause 0001. [doi]
• Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via GroupingYining Li, Peizhong Ju, Ness B. Shroff. [doi]
• Mechanistically analyzing the effects of fine-tuning on procedurally defined tasksSamyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tim Rocktäschel, Edward Grefenstette, David Scott Krueger. [doi]
• Tree Cross AttentionLeo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed. [doi]
• PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality ImagesJinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong 0001, Dongeun Lee 0001, Kookjin Lee, Noseong Park. [doi]
• Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training TasksTianyu Fan, Lirong Wu, Yufei Huang 0002, Haitao Lin, Cheng Tan 0012, Zhangyang Gao, Stan Z. Li. [doi]
• TimeMixer: Decomposable Multiscale Mixing for Time Series ForecastingShiyu Wang 0001, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y. Zhang, Jun Zhou 0011. [doi]
• WildFusion: Learning 3D-Aware Latent Diffusion Models in View SpaceKatja Schwarz, Seung Wook Kim 0001, Jun Gao 0004, Sanja Fidler, Andreas Geiger 0001, Karsten Kreis. [doi]
• QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language ModelsYuhui Xu, Lingxi Xie, Xiaotao Gu, Xin Chen 0060, Heng Chang, Hengheng Zhang, Zhengsu Chen, Xiaopeng Zhang 0008, Qi Tian 0001. [doi]
• RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with AnomaliesHao Cheng 0005, Qingsong Wen, Yang Liu, Liang Sun. [doi]
• Adaptive Federated Learning with Auto-Tuned ClientsJunhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis. [doi]
• A Branching Decoder for Set GenerationZixian Huang, Gengyang Xiao, Yu Gu 0016, Gong Cheng 0001. [doi]
• Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface PredictionZiyang Yu, Wenbing Huang 0001, Yang Liu 0005. [doi]
• Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and TuningPratik Patil, Daniel LeJeune. [doi]
• RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalParth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning. [doi]
• Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-MakingAliyah R. Hsu, Yeshwanth Cherapanamjeri, Briton Park, Tristan Naumann, Anobel Y. Odisho, Bin Yu 0001. [doi]
• The Hidden Language of Diffusion ModelsHila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf. [doi]
• Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXClément Bonnet, Daniel Luo, Donal Byrne, Shikha Surana, Sasha Abramowitz, Paul Duckworth, Vincent Coyette, Laurence Illing Midgley, Elshadai Tegegn, Tristan Kalloniatis, Omayma Mahjoub, Matthew Macfarlane, Andries P. Smit, Nathan Grinsztajn, Raphaël Boige, Cemlyn N. Waters, Mohamed A. Mimouni, Ulrich A. Mbou Sob, Ruan de Kock, Siddarth Singh, Daniel Furelos-Blanco, Victor Le, Arnu Pretorius, Alexandre Laterre. [doi]
• Chain-of-Experts: When LLMs Meet Complex Operations Research ProblemsZiyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu, Yuan Jessica Wang, Xiongwei Han, Xiaojin Fu, Tao Zhong, Jia Zeng, Mingli Song, Gang Chen 0001. [doi]
• Matryoshka Diffusion ModelsJiatao Gu, Shuangfei Zhai, Yizhe Zhang 0002, Joshua M. Susskind, Navdeep Jaitly. [doi]
• Quantifying and Enhancing Multi-modal Robustness with Modality PreferenceZequn Yang, Yake Wei, Ce Liang, Di Hu 0001. [doi]
• Accelerating Distributed Stochastic Optimization via Self-Repellent Random WalksJie Hu, Vishwaraj Doshi, Do Young Eun. [doi]
• Probabilistic Adaptation of Black-Box Text-to-Video ModelsSherry Yang, Yilun Du, Bo Dai 0001, Dale Schuurmans, Joshua B. Tenenbaum, Pieter Abbeel. [doi]
• MAMBA: an Effective World Model Approach for Meta-Reinforcement LearningZohar Rimon, Tom Jurgenson, Orr Krupnik, Gilad Adler, Aviv Tamar. [doi]
• DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content CreationJiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu 0002, Gang Zeng. [doi]
• A General Framework for User-Guided Bayesian OptimizationCarl Hvarfner, Frank Hutter, Luigi Nardi. [doi]
• Conformal Inductive Graph Neural NetworksSoroush H. Zargarbashi, Aleksandar Bojchevski. [doi]
• Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language ModelsSheng Shen, Le Hou, Yanqi Zhou, Nan Du 0002, Shayne Longpre, Jason Wei, Hyung Won Chung, Barret Zoph, William Fedus, Xinyun Chen, Tu Vu, Yuexin Wu, Wuyang Chen, Albert Webson, Yunxuan Li, Vincent Y. Zhao, Hongkun Yu 0001, Kurt Keutzer, Trevor Darrell, Denny Zhou. [doi]
• Object-Centric Learning with Slot Mixture ModuleDaniil E. Kirilenko, Vitaliy Vorobyov, Alexey K. Kovalev, Aleksandr Panov. [doi]
• DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated TextXianjun Yang, Wei Cheng 0002, Yue Wu, Linda Ruth Petzold, William Yang Wang, Haifeng Chen. [doi]
• Understanding In-Context Learning from RepetitionsJianhao Yan, Jin Xu, Chiyu Song, Chenming Wu, Yafu Li, Yue Zhang 0004. [doi]
• Diffusion Sampling with Momentum for Mitigating Divergence ArtifactsSuttisak Wizadwongsa, Worameth Chinchuthakun, Pramook Khungurn, Amit Raj, Supasorn Suwajanakorn. [doi]
• Constrained Decoding for Cross-lingual Label ProjectionDuong Minh Le, Yang Chen, Alan Ritter, Wei Xu 0004. [doi]
• Model Merging by Uncertainty-Based Gradient MatchingNico Daheim, Thomas Möllenhoff, Edoardo M. Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan. [doi]
• One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep ModelsSheng-Jun Huang, Yi Li, Yiming Sun, Ying-Peng Tang. [doi]
• MEND: Meta Demonstration Distillation for Efficient and Effective In-Context LearningYichuan Li 0001, Xiyao Ma, Sixing Lu, Kyumin Lee, Xiaohu Liu, Chenlei Guo. [doi]
• Chain of Hindsight aligns Language Models with FeedbackHao Liu 0055, Carmelo Sferrazza, Pieter Abbeel. [doi]
• SILO Language Models: Isolating Legal Risk In a Nonparametric DatastoreSewon Min, Suchin Gururangan, Eric Wallace, Weijia Shi, Hannaneh Hajishirzi, Noah A. Smith, Luke Zettlemoyer. [doi]
• Scaling Laws for Associative MemoriesVivien Cabannes, Elvis Dohmatob, Alberto Bietti. [doi]
• Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation NetworksMarc Rußwurm, Konstantin Klemmer, Esther Rolf, Robin Zbinden, Devis Tuia. [doi]
• Relay Diffusion: Unifying diffusion process across resolutions for image synthesisJiayan Teng, Wendi Zheng, Ming Ding 0004, Wenyi Hong, Jianqiao Wangni, Zhuoyi Yang, Jie Tang 0001. [doi]
• Only Pay for What Is Uncertain: Variance-Adaptive Thompson SamplingAadirupa Saha, Branislav Kveton. [doi]
• Learning Thresholds with Latent Values and Censored FeedbackJiahao Zhang, Tao Lin, Weiqiang Zheng, Zhe Feng 0004, Yifeng Teng, Xiaotie Deng. [doi]
• A Differentially Private Clustering Algorithm for Well-Clustered GraphsWeiqiang He, Hendrik Fichtenberger, Pan Peng 0001. [doi]
• Improving the Convergence of Dynamic NeRFs via Optimal TransportSameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Hisham Husain, Anton van den Hengel. [doi]
• Quantifying the Sensitivity of Inverse Reinforcement Learning to MisspecificationJoar Max Viktor Skalse, Alessandro Abate. [doi]
• Manifold Preserving Guided DiffusionYutong He, Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Dongjun Kim, Wei-Hsiang Liao, Yuki Mitsufuji, J. Zico Kolter, Ruslan Salakhutdinov, Stefano Ermon. [doi]
• Teach LLMs to Phish: Stealing Private Information from Language ModelsAshwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal. [doi]
• Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential ExecutionShanqi Liu, Dong Xing, Pengjie Gu, Xinrun Wang, Bo An 0001, Yong Liu. [doi]
• Understanding prompt engineering may not require rethinking generalizationVictor Akinwande, Yiding Jiang, Dylan Sam, J. Zico Kolter. [doi]
• On the Variance of Neural Network Training with respect to Test Sets and DistributionsKeller Jordan. [doi]
• Amortizing intractable inference in large language modelsEdward J. Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar, Guillaume Lajoie, Yoshua Bengio, Nikolay Malkin. [doi]
• Multi-View Causal Representation Learning with Partial ObservabilityDingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello. [doi]
• Logical Languages Accepted by Transformer Encoders with Hard AttentionPablo Barceló, Alexander Kozachinskiy, Anthony Widjaja Lin, Vladimir V. Podolskii. [doi]
• Enhancing Tail Performance in Extreme Classifiers by Label Variance ReductionAnirudh Buvanesh, Rahul Chand, Jatin Prakash, Bhawna Paliwal, Mudit Dhawan, Neelabh Madan, Deepesh Hada, Vidit Jain, Sonu Mehta, Yashoteja Prabhu, Manish Gupta, Ramachandran Ramjee, Manik Varma. [doi]
• Early Neuron Alignment in Two-layer ReLU Networks with Small InitializationHancheng Min, Enrique Mallada, René Vidal. [doi]
• Self-Supervised Dataset Distillation for Transfer LearningDong-Bok Lee, Seanie Lee, Joonho Ko, Kenji Kawaguchi, Juho Lee 0001, Sung Ju Hwang. [doi]
• SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NASYameng Peng, Andy Song, Haytham M. Fayek, Vic Ciesielski, Xiaojun Chang. [doi]
• ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language ModelsYi-Lin Sung, Jaehong Yoon, Mohit Bansal. [doi]
• Federated Recommendation with Additive PersonalizationZhiwei Li, Guodong Long, Tianyi Zhou 0001. [doi]
• NetInfoF Framework: Measuring and Exploiting Network Usable InformationMeng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang Song 0003, Soji Adeshina, Da Zheng, Christos Faloutsos. [doi]
• Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and MitigationNiels Mündler, Jingxuan He, Slobodan Jenko, Martin T. Vechev. [doi]
• Towards Robust Multi-Modal Reasoning via Model SelectionXiangyan Liu, Rongxue Li, Wei Ji, Tao Lin. [doi]
• Multi-Task Reinforcement Learning with Mixture of Orthogonal ExpertsAhmed Hendawy, Jan Peters 0001, Carlo D'Eramo. [doi]
• Stochastic Modified Equations and Dynamics of Dropout AlgorithmZhongwang Zhang, Yuqing Li, Tao Luo, Zhi-Qin John Xu. [doi]
• The Generalization Gap in Offline Reinforcement LearningIshita Mediratta, Qingfei You, Minqi Jiang, Roberta Raileanu. [doi]
• Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D GenerationJunyoung Seo, Wooseok Jang, Minseop Kwak, Inès Hyeonsu Kim, Jaehoon Ko, Junho Kim, Jin-Hwa Kim, Jiyoung Lee, Seungryong Kim. [doi]
• Structural Fairness-aware Active Learning for Graph Neural NetworksHaoyu Han, Xiaorui Liu, Li Ma, MohamadAli Torkamani, Hui Liu 0031, Jiliang Tang, Makoto Yamada. [doi]
• Efficient Integrators for Diffusion Generative ModelsKushagra Pandey, Maja Rudolph, Stephan Mandt. [doi]
• Consistent algorithms for multi-label classification with macro-at-k metricsErik Schultheis, Wojciech Kotlowski, Marek Wydmuch, Rohit Babbar, Strom Borman, Krzysztof Dembczynski. [doi]
• Treatment Effects Estimation By Uniform TransformerRuoqi Yu, Shulei Wang. [doi]
• Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchySimon Ging, María Alejandra Bravo, Thomas Brox. [doi]
• Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Reza Haf, Shirui Pan. [doi]
• Implicit Gaussian process representation of vector fields over arbitrary latent manifoldsRobert L. Peach, Matteo Vinao-Carl, Nir Grossman, Michael David, Emma Mallas, David J. Sharp, Paresh A. Malhotra, Pierre Vandergheynst, Adam Gosztolai. [doi]
• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans. [doi]
• DFormer: Rethinking RGBD Representation Learning for Semantic SegmentationBowen Yin, Xuying Zhang, Zhong-Yu Li, Li Liu, Ming-Ming Cheng, Qibin Hou. [doi]
• Generalized Policy Iteration using Tensor Approximation for Hybrid ControlSuhan Shetty, Teng Xue, Sylvain Calinon. [doi]
• Towards image compression with perfect realism at ultra-low bitratesMarlène Careil, Matthew J. Muckley, Jakob Verbeek, Stéphane Lathuilière. [doi]
• Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical FlowHanyu Zhou, Yi Chang 0002, Haoyue Liu, Wending Yan, Yuxing Duan, Zhiwei Shi, Luxin Yan. [doi]
• LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language ModelsZecheng Tang, Chenfei Wu, Juntao Li, Nan Duan. [doi]
• Confronting Reward Model Overoptimization with Constrained RLHFTed Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen Marcus McAleer. [doi]
• Zoology: Measuring and Improving Recall in Efficient Language ModelsSimran Arora, Sabri Eyuboglu, Aman Timalsina, Isys Johnson, Michael Poli, James Zou 0001, Atri Rudra, Christopher Ré. [doi]
• Time-Varying Propensity Score to Bridge the Gap between the Past and PresentRasool Fakoor, Jonas Mueller 0001, Zachary Chase Lipton, Pratik Chaudhari, Alex Smola. [doi]
• You Only Query Once: An Efficient Label-Only Membership Inference AttackYutong Wu 0009, Han Qiu 0001, Shangwei Guo, Jiwei Li 0001, Tianwei Zhang 0004. [doi]
• Online Information Acquisition: Hiring Multiple AgentsFederico Cacciamani, Matteo Castiglioni, Nicola Gatti 0001. [doi]
• Object-Aware Inversion and Reassembly for Image EditingZhen Yang 0009, Ganggui Ding, Wen Wang, Hao Chen 0041, Bohan Zhuang, Chunhua Shen. [doi]
• A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional DataSaptarshi Chakraborty, Peter L. Bartlett. [doi]
• GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionOscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle, German Rigau, Eneko Agirre. [doi]
• Neural Neighborhood Search for Multi-agent Path FindingZhongxia Yan 0001, Cathy Wu 0002. [doi]
• DOS: Diverse Outlier Sampling for Out-of-Distribution DetectionWenyu Jiang, Hao Cheng 0014, Mingcai Chen, Chongjun Wang, Hongxin Wei. [doi]
• BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex SelectivityAndrew F. Luo, Margaret M. Henderson, Michael J. Tarr, Leila Wehbe. [doi]
• One-shot Empirical Privacy Estimation for Federated LearningGalen Andrew, Peter Kairouz, Sewoong Oh, Alina Oprea, Hugh Brendan McMahan, Vinith Menon Suriyakumar. [doi]
• The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax MimicryMichael Zhang, Kush Bhatia, Hermann Kumbong, Christopher Ré. [doi]
• Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance KernelPaul Hagemann, Johannes Hertrich, Fabian Altekrüger, Robert Beinert, Jannis Chemseddine, Gabriele Steidl. [doi]
• Retroformer: Retrospective Large Language Agents with Policy Gradient OptimizationWeiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh R. N., Zeyuan Chen, Jianguo Zhang 0005, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese. [doi]
• Provable Compositional Generalization for Object-Centric LearningThaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel. [doi]
• Latent 3D Graph DiffusionYuning You, Ruida Zhou, Jiwoong Park, Haotian Xu, Chao Tian, Zhangyang Wang, Yang Shen 0001. [doi]
• Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized SmoothingSong Xia, Yi Yu, Xudong Jiang 0001, Henghui Ding. [doi]
• The Unreasonable Effectiveness of Linear Prediction as a Perceptual MetricDaniel Severo 0001, Lucas Theis, Johannes Ballé. [doi]
• Learning Conditional Invariances through Non-CommutativityAbhra Chaudhuri, Serban Georgescu, Anjan Dutta 0001. [doi]
• Kernelised Normalising FlowsEshant English, Matthias Kirchler, Christoph Lippert. [doi]
• 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose EstimationChen Zhao, Tong Zhang 0023, Mathieu Salzmann. [doi]
• Improved Techniques for Training Consistency ModelsYang Song, Prafulla Dhariwal. [doi]
• Spurious Feature Diversification Improves Out-of-distribution GeneralizationYong Lin, Lu Tan, Yifan Hao, Honam Wong, Hanze Dong, Weizhong Zhang, Yujiu Yang, Tong Zhang 0001. [doi]
• Federated Text-driven Prompt Generation for Vision-Language ModelsChen Qiu, Xingyu Li, Chaithanya Kumar Mummadi, Madan Ravi Ganesh, Zhenzhen Li, Lu Peng, Wan-Yi Lin. [doi]
• Parallelizing non-linear sequential models over the sequence lengthYi Heng Lim, Qi Zhu, Joshua Selfridge, Muhammad Firmansyah Kasim. [doi]
• Towards Characterizing Domain Counterfactuals for Invertible Latent Causal ModelsZeyu Zhou, Ruqi Bai, Sean Kulinski, Murat Kocaoglu, David I. Inouye. [doi]
• Bridging Vision and Language Spaces with Assignment PredictionJungin Park, Jiyoung Lee, Kwanghoon Sohn. [doi]
• RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective AugmentationFangyuan Xu, Weijia Shi, Eunsol Choi. [doi]
• SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous ManipulationQianxu Wang, Haotong Zhang 0005, Congyue Deng, Yang You, Hao Dong 0003, Yixin Zhu 0001, Leonidas J. Guibas. [doi]
• MixSATGEN: Learning Graph Mixing for SAT Instance GenerationXinyan Chen, Yang Li, Runzhong Wang, Junchi Yan. [doi]
• SALMON: Self-Alignment with Instructable Reward ModelsZhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Daniel Cox, Yiming Yang, Chuang Gan. [doi]
• Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent DynamicsChristian Gumbsch, Noor Sajid, Georg Martius, Martin V. Butz. [doi]
• GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization PriorsLi Yang, Ruizheng Wu, Jiyong Li, Ying-Cong Chen. [doi]
• Rethinking CNN's Generalization to Backdoor Attack from Frequency DomainQuanrui Rao, Lin Wang, Wuying Liu. [doi]
• GIO: Gradient Information Optimization for Training Dataset SelectionDante Everaert, Christopher Potts. [doi]
• Training-free Multi-objective Diffusion Model for 3D Molecule GenerationXu Han, Caihua Shan, Yifei Shen, Can Xu, Han Yang, Xiang Li 0067, Dongsheng Li 0002. [doi]
• Test-Time Training on Nearest Neighbors for Large Language ModelsMoritz Hardt, Yu Sun 0020. [doi]
• ExeDec: Execution Decomposition for Compositional Generalization in Neural Program SynthesisKensen Shi, Joey Hong, Yinlin Deng, Pengcheng Yin, Manzil Zaheer, Charles Sutton. [doi]
• Exploring Target Representations for Masked AutoencodersXingbin Liu, Jinghao Zhou, Tao Kong, Xianming Lin, Rongrong Ji. [doi]
• Combinatorial Bandits for Maximum Value Reward Function under Value-Index FeedbackYiliu Wang, Wei Chen, Milan Vojnovic. [doi]
• Identifiable Latent Polynomial Causal Models through the Lens of ChangeYuhang Liu, Zhen Zhang 0008, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang 0001, Javen Qinfeng Shi. [doi]
• Language Models Represent Space and TimeWes Gurnee, Max Tegmark. [doi]
• RepoBench: Benchmarking Repository-Level Code Auto-Completion SystemsTianyang Liu 0003, Canwen Xu, Julian J. McAuley. [doi]
• CAMBranch: Contrastive Learning with Augmented MILPs for BranchingJiacheng Lin, Meng Xu, Zhihua Xiong, Huangang Wang. [doi]
• Learning 3D Particle-based Simulators from RGB-D VideosWilliam F. Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kim Stachenfeld, Kelsey R. Allen. [doi]
• Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian ProcessesQuoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet. [doi]
• Label-free Node Classification on Graphs with Large Language Models (LLMs)Zhikai Chen, Haitao Mao, Hongzhi Wen, Haoyu Han, Wei Jin 0009, Haiyang Zhang, Hui Liu 0031, Jiliang Tang. [doi]
• Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational InferenceKhalid Oublal, Saïd Ladjal, David Benhaiem, Emmanuel Le-borgne, François Roueff. [doi]
• Retrieval-Guided Reinforcement Learning for Boolean Circuit MinimizationAnimesh Basak Chowdhury, Marco Romanelli 0002, Benjamin Tan 0001, Ramesh Karri, Siddharth Garg. [doi]
• An Unforgeable Publicly Verifiable Watermark for Large Language ModelsAiwei Liu, Leyi Pan, Xuming Hu, Shuang Li 0015, Lijie Wen 0001, Irwin King, Philip S. Yu. [doi]
• Graphical Multioutput Gaussian Process with AttentionYijue Dai, Wenzhong Yan, Feng Yin. [doi]
• Uncertainty Quantification via Stable Distribution PropagationFelix Petersen, Aashwin Ananda Mishra, Hilde Kuehne, Christian Borgelt, Oliver Deussen, Mikhail Yurochkin. [doi]
• Estimating Conditional Mutual Information for Dynamic Feature SelectionSoham Gadgil, Ian Connick Covert, Su-In Lee. [doi]
• Generative Learning for Financial Time Series with Irregular and Scale-Invariant PatternsHongbin Huang, Minghua Chen, Xiao Qiao. [doi]
• Optimal Sample Complexity of Contrastive LearningNoga Alon, Dmitrii Avdiukhin, Dor Elboim, Orr Fischer, Grigory Yaroslavtsev. [doi]
• Variance Reduced Halpern Iteration for Finite-Sum Monotone InclusionsXufeng Cai, Ahmet Alacaoglu, Jelena Diakonikolas. [doi]
• Perceptual Scales Predicted by Fisher Information MetricsJonathan Vacher, Pascal Mamassian. [doi]
• Beyond Imitation: Leveraging Fine-grained Quality Signals for AlignmentGeyang Guo, Ranchi Zhao, Tianyi Tang, Xin Zhao 0018, Ji-Rong Wen. [doi]
• Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised LearningCongpei Qiu, Tong Zhang 0023, Yanhao Wu, Wei Ke 0003, Mathieu Salzmann, Sabine Süsstrunk. [doi]
• Forward Learning of Graph Neural NetworksNamyong Park, Xing Wang, Antoine Simoulin, Shuai Yang, Grey Yang, Ryan A. Rossi, Puja Trivedi, Nesreen K. Ahmed. [doi]
• DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified RobustnessShoumik Saha, Wenxiao Wang 0002, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras. [doi]
• Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose EstimationPrakhar Kaushik, Aayush Mishra, Adam Kortylewski, Alan L. Yuille. [doi]
• Identifying the Risks of LM Agents with an LM-Emulated SandboxYangjun Ruan, Honghua Dong, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto. [doi]
• Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement TasksBen Eisner, Yi Yang 0007, Todor Davchev, Mel Vecerík, Jonathan Scholz, David Held. [doi]
• Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source SeparationShahar Lutati, Eliya Nachmani, Lior Wolf. [doi]
• Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity EstimationHsiang Hsu, Guihong Li, Shaohan Hu, Chun-Fu Chen 0001. [doi]
• Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of ElectrocardiogramYeongYeon Na, Minje Park, Yunwon Tae, Sunghoon Joo. [doi]
• An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant NetworksDongwon Son, Jaehyung Kim, Sanghyeon Son, Beomjoon Kim. [doi]
• FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image AnalysisRaman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy M. Hospedales. [doi]
• Masked Structural Growth for 2x Faster Language Model Pre-trainingYiqun Yao, Zheng Zhang, Jing Li, Yequan Wang. [doi]
• Thin-Shell Object Manipulations With Differentiable Physics SimulationsYian Wang, Juntian Zheng, Zhehuan Chen, Zhou Xian, Gu Zhang, Chao Liu, Chuang Gan. [doi]
• The mechanistic basis of data dependence and abrupt learning in an in-context classification taskGautam Reddy. [doi]
• Estimating Shape Distances on Neural Representations with Limited SamplesDean A. Pospisil, Brett W. Larsen, Sarah E. Harvey, Alex H. Williams. [doi]
• Neuroformer: Multimodal and Multitask Generative Pretraining for Brain DataAntonis Antoniades, Yiyi Yu, Joseph Canzano, William Yang Wang, Spencer L. Smith. [doi]
• Magnushammer: A Transformer-Based Approach to Premise SelectionMaciej Mikula, Szymon Tworkowski, Szymon Antoniak, Bartosz Piotrowski, Albert Q. Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu. [doi]
• Bayesian Coreset Optimization for Personalized Federated LearningPrateek Chanda, Shrey Modi, Ganesh Ramakrishnan. [doi]
• EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy ModelHuaijin Wu, Wei Liu 0005, Yatao Bian, Jiaxiang Wu 0001, Nianzu Yang, Junchi Yan. [doi]
• ZeroFlow: Scalable Scene Flow via DistillationKyle Vedder, Neehar Peri, Nathaniel Chodosh, Ishan Khatri, Eric Eaton, Dinesh Jayaraman, Yang Liu, Deva Ramanan, James Hays. [doi]
• GraphChef: Decision-Tree Recipes to Explain Graph Neural NetworksPeter Müller, Lukas Faber, Karolis Martinkus, Roger Wattenhofer. [doi]
• Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated LearningYun-Hin Chan, Rui Zhou, Running Zhao, Zhihan Jiang, Edith C. H. Ngai. [doi]
• A Real-World WebAgent with Planning, Long Context Understanding, and Program SynthesisIzzeddin Gur, Hiroki Furuta, Austin V. Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, Aleksandra Faust. [doi]
• Outliers with Opposing Signals Have an Outsized Effect on Neural Network OptimizationElan Rosenfeld, Andrej Risteski. [doi]
• Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop SchedulingCong Zhang, Zhiguang Cao, Wen Song, Yaoxin Wu, Jie Zhang 0002. [doi]
• SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional VideosYulei Niu, WenLiang Guo, Long Chen 0016, Xudong Lin 0003, Shih-Fu Chang. [doi]
• Towards Meta-Pruning via Optimal TransportAlexander Theus, Olin Geimer, Friedrich Wicke, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh. [doi]
• Noise Map Guidance: Inversion with Spatial Context for Real Image EditingHansam Cho, Jonghyun Lee, Seoung Bum Kim, Tae Hyun Oh, Yonghyun Jeong. [doi]
• LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionSifan Zhou, Liang Li 0003, Xinyu Zhang 0015, Bo Zhang 0046, Shipeng Bai, Miao Sun, Ziyu Zhao, Xiaobo Lu, Xiangxiang Chu. [doi]
• Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless CompressionYufeng Zhang, Hang Yu, Jianguo Li, Weiyao Lin. [doi]
• αTC-VAE: On the relationship between Disentanglement and DiversityCristian Meo, Louis Mahon, Anirudh Goyal, Justin Dauwels. [doi]
• Structural Inference with Dynamics Encoding and Partial Correlation CoefficientsAoran Wang, Jun Pang 0001. [doi]
• Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular DesignJeff Guo, Philippe Schwaller. [doi]
• DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view RepresentationYueru Luo, Shuguang Cui, Zhen Li 0026. [doi]
• Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and SelectionFan Shi, Bin Li 0015, Xiangyang Xue. [doi]
• Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian GameSimin Li, Jun Guo, Jingqiao Xiu, Ruixiao Xu, Xin Yu 0009, Jiakai Wang, Aishan Liu, Yaodong Yang 0001, Xianglong Liu 0001. [doi]
• CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNsFlorian Grötschla, Joël Mathys, Robert Veres, Roger Wattenhofer. [doi]
• InstructPix2NeRF: Instructed 3D Portrait Editing from a Single ImageJianhui Li, Shilong Liu, Zidong Liu, Yikai Wang, Kaiwen Zheng, Jinghui Xu, Jianmin Li, Jun Zhu 0001. [doi]
• Finite Scalar Quantization: VQ-VAE Made SimpleFabian Mentzer, David Minnen, Eirikur Agustsson, Michael Tschannen. [doi]
• Provably Robust Conformal Prediction with Improved EfficiencyGe Yan, Yaniv Romano, Tsui-Wei Weng. [doi]
• Course Correcting Koopman RepresentationsMahan Fathi, Clement Gehring, Jonathan Pilault, David Kanaa, Pierre-Luc Bacon, Ross Goroshin. [doi]
• SEA: Sparse Linear Attention with Estimated Attention MaskHeejun Lee, Jina Kim, Jeffrey Willette, Sung Ju Hwang. [doi]
• A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksJintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Baokun Wang, Changhua Meng, Zibin Zheng, Liang Chen 0001. [doi]
• Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMsFeiyang Kang, Hoang Anh Just, Yifan Sun, Himanshu Jahagirdar, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, Ruoxi Jia 0001. [doi]
• Safe Collaborative FilteringRiku Togashi, Tatsushi Oka, Naoto Ohsaka, Tetsuro Morimura. [doi]
• SafeDreamer: Safe Reinforcement Learning with World ModelsWeidong Huang 0008, Jiaming Ji, Chunhe Xia, Borong Zhang, Yaodong Yang 0001. [doi]
• Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language ModelsSijia Chen, Baochun Li, Di Niu. [doi]
• Neural Fine-Tuning Search for Few-Shot LearningPanagiotis Eustratiadis, Lukasz Dudziak, Da Li 0001, Timothy M. Hospedales. [doi]
• Multi-View Representation is What You Need for Point-Cloud Pre-TrainingSiming Yan, Chen Song, YouKang Kong, Qixing Huang. [doi]
• DreamClean: Restoring Clean Image Using Deep Diffusion PriorJie Xiao 0002, Ruili Feng, Han Zhang 0010, Zhiheng Liu, Zhantao Yang, Yurui Zhu, Xueyang Fu, Kai Zhu 0004, Yu Liu 0063, Zheng-Jun Zha. [doi]
• Language Model Self-improvement by Reinforcement Learning ContemplationJing-Cheng Pang, Pengyuan Wang, Kaiyuan Li, Xiong-Hui Chen, Jiacheng Xu 0003, Zongzhang Zhang, Yang Yu 0001. [doi]
• Guiding Instruction-based Image Editing via Multimodal Large Language ModelsTsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, Zhe Gan. [doi]
• Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal DataYongsheng Mei, Mahdi Imani, Tian Lan. [doi]
• CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulesHung Le, Hailin Chen, Amrita Saha, Akash Gokul, Doyen Sahoo, Shafiq Joty. [doi]
• Adapting to Distribution Shift by Visual Domain Prompt GenerationZhixiang Chi, Li Gu, Tao Zhong, Huan Liu, Yuanhao Yu, Konstantinos N. Plataniotis, Yang Wang 0003. [doi]
• HyperAttention: Long-context Attention in Near-Linear TimeInsu Han, Rajesh Jayaram, Amin Karbasi, Vahab Mirrokni, David P. Woodruff, Amir Zandieh. [doi]
• Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading IndicatorsLifan Zhao, Yanyan Shen. [doi]
• Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion ModelsYangming Li, Boris van Breugel, Mihaela van der Schaar. [doi]
• Grokking as the transition from lazy to rich training dynamicsTanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan. [doi]
• Selective Visual Representations Improve Convergence and Generalization for Embodied AIAinaz Eftekhar, Kuo-Hao Zeng, Jiafei Duan, Ali Farhadi, Aniruddha Kembhavi, Ranjay Krishna. [doi]
• Detecting Pretraining Data from Large Language ModelsWeijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen 0001, Luke Zettlemoyer. [doi]
• Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty RegularizationYiyang Chen, Zhedong Zheng, Wei Ji 0008, Leigang Qu, Tat-Seng Chua. [doi]
• Reverse Forward Curriculum Learning for Extreme Sample and Demo EfficiencyStone Tao, Arth Shukla, Tse-kai Chan, Hao Su 0001. [doi]
• Deep Neural Networks Tend To Extrapolate PredictablyKatie Kang, Amrith Setlur, Claire J. Tomlin, Sergey Levine. [doi]
• Scalable Modular Network: A Framework for Adaptive Learning via Agreement RoutingMinyang Hu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen 0001. [doi]
• Defining and extracting generalizable interaction primitives from DNNsLu Chen, Siyu Lou, Benhao Huang, Quanshi Zhang. [doi]
• DreamFlow: High-quality text-to-3D generation by Approximating Probability FlowKyungmin Lee, Kihyuk Sohn, Jinwoo Shin. [doi]
• Efficient Score Matching with Deep Equilibrium LayersYuhao Huang, Qingsong Wang, Akwum Onwunta, Bao Wang. [doi]
• Self-supervised Representation Learning from Random Data ProjectorsYi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs. [doi]
• GTMGC: Using Graph Transformer to Predict Molecule's Ground-State ConformationGuikun Xu, Yongquan Jiang, PengChuan Lei, Yan Yang, Jim Chen. [doi]
• FedTrans: Client-Transparent Utility Estimation for Robust Federated LearningMingkun Yang, Ran Zhu, Qing Wang 0007, Jie Yang 0028. [doi]
• DP-SGD Without Clipping: The Lipschitz Neural Network WayLouis Béthune, Thomas Massena, Thibaut Boissin, Aurélien Bellet, Franck Mamalet, Yannick Prudent, Corentin Friedrich, Mathieu Serrurier, David Vigouroux. [doi]
• HiGen: Hierarchical Graph Generative NetworksMahdi Karami. [doi]
• GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision BoundariesXiaoqi Wang, Han-Wei Shen. [doi]
• Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion ModelsPablo Pernias, Dominic Rampas, Mats L. Richter, Christopher Pal, Marc Aubreville. [doi]
• How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with RepresentationsTianyu Guo 0004, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai 0017. [doi]
• Statistically Optimal K-means Clustering via Nonnegative Low-rank Semidefinite ProgrammingYubo Zhuang, Xiaohui Chen, Yun Yang, Richard Y. Zhang. [doi]
• Fair Classifiers that Abstain without HarmTongxin Yin, Jean-Francois Ton, Ruocheng Guo, Yuanshun Yao, Mingyan Liu, Yang Liu. [doi]
• Imitation Learning from Observation with Automatic Discount SchedulingYuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao 0029. [doi]
• Policy Rehearsing: Training Generalizable Policies for Reinforcement LearningChengxing Jia, Chenxiao Gao, Hao Yin, Fuxiang Zhang, Xiong-Hui Chen, Tian Xu, Lei Yuan, Zongzhang Zhang, Zhi-Hua Zhou, Yang Yu 0001. [doi]
• Efficient Video Diffusion Models via Content-Frame Motion-Latent DecompositionSihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin, Anima Anandkumar. [doi]
• CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization AnalysisXiaoxiao Sun, Xingjian Leng, Zijian Wang 0009, Yang Yang 0002, Zi Huang, Liang Zheng 0001. [doi]
• Empirical Likelihood for Fair ClassificationPangpang Liu, Yichuan Zhao. [doi]
• MetaMath: Bootstrap Your Own Mathematical Questions for Large Language ModelsLonghui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu. [doi]
• A Simple and Effective Pruning Approach for Large Language ModelsMingjie Sun, Zhuang Liu 0003, Anna Bair, J. Zico Kolter. [doi]
• SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time SeriesJunyan Cheng, Peter Chin 0001. [doi]
• Exploring the cloud of feature interaction scores in a Rashomon setSichao Li, Rong Wang, Quanling Deng, Amanda S. Barnard. [doi]
• Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective LearningFeiyang Ye, Yueming Lyu, Xuehao Wang, Yu Zhang, Ivor W. Tsang. [doi]
• Patched Denoising Diffusion Models For High-Resolution Image SynthesisZheng-ding, Mengqi Zhang, Jiajun Wu 0001, Zhuowen Tu. [doi]
• Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction ModelJiahao Li, Hao Tan 0002, Kai Zhang 0045, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, Sai Bi. [doi]
• Robust Training of Federated Models with Extremely Label DeficiencyYonggang Zhang, Zhiqin Yang, Xinmei Tian 0001, Nannan Wang 0001, Tongliang Liu, Bo Han 0003. [doi]
• Hybrid Distillation: Connecting Masked Autoencoders with Contrastive LearnersBowen Shi, Xiaopeng Zhang 0008, Yaoming Wang, Jin Li, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian 0001. [doi]
• DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion ModelsZhenting Wang, Chen Chen 0043, Lingjuan Lyu, Dimitris N. Metaxas, ShiQing Ma. [doi]
• Let Models Speak Ciphers: Multiagent Debate through EmbeddingsChau Pham 0001, Boyi Liu, Yingxiang Yang, Zhengyu Chen 0001, Tianyi Liu, Jianbo Yuan, Bryan A. Plummer, Zhaoran Wang 0001, Hongxia Yang. [doi]
• A Lightweight Method for Tackling Unknown Participation Statistics in Federated AveragingShiqiang Wang 0001, Mingyue Ji. [doi]
• ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion ProcessChangyao Tian, Chenxin Tao, Jifeng Dai, Hao Li 0069, Ziheng Li, Lewei Lu, Xiaogang Wang 0001, Hongsheng Li 0001, Gao Huang, Xizhou Zhu. [doi]
• ZeRO++: Extremely Efficient Collective Communication for Large Model TrainingGuanhua Wang, Heyang Qin, Sam Ade Jacobs, Xiaoxia Wu, Connor Holmes, Zhewei Yao, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan 0001, Lei Yang 0001, Yuxiong He. [doi]
• Scalable and Effective Implicit Graph Neural Networks on Large GraphsJuncheng Liu, Bryan Hooi, Kenji Kawaguchi, Yiwei Wang 0001, Chaosheng Dong, Xiaokui Xiao. [doi]
• Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled PerturbationsYongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Benjamin Eysenbach, Tuomas Sandholm, Furong Huang, Stephen Marcus McAleer. [doi]
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of DiffusionDongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon. [doi]
• Fusing Models with Complementary ExpertiseHongyi Wang 0001, Felipe Maia Polo, Yuekai Sun, Souvik Kundu 0009, Eric P. Xing, Mikhail Yurochkin. [doi]
• Sparse MoE with Language Guided Routing for Multilingual Machine TranslationXinyu Zhao, Xuxi Chen, Yu Cheng 0001, Tianlong Chen. [doi]
• ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target ShiftHwanwoo Kim, Xin Zhang, Jiwei Zhao, Qinglong Tian. [doi]
• Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear TimeYuzhou Gu, Zhao Song 0002, Junze Yin, Lichen Zhang 0003. [doi]
• Improved algorithm and bounds for successive projectionJiashun Jin, Zheng Tracy Ke, Gabriel Moryoussef, Jiajun Tang, Jingming Wang. [doi]
• Select to Perfect: Imitating desired behavior from large multi-agent dataTim Franzmeyer, Edith Elkind, Philip Torr 0001, Jakob Nicolaus Foerster, João F. Henriques. [doi]
• Post-hoc bias scoring is optimal for fair classificationWenlong Chen, Yegor Klochkov, Yang Liu. [doi]
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight CompressionTim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, Dan Alistarh. [doi]
• GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising DiffusionXueyi Liu, Li Yi. [doi]
• Talk like a Graph: Encoding Graphs for Large Language ModelsBahare Fatemi, Jonathan Halcrow, Bryan Perozzi. [doi]
• Self-Supervised Contrastive Learning for Long-term ForecastingJunwoo Park, Daehoon Gwak, Jaegul Choo, Edward Choi. [doi]
• MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance FieldKaizhi Yang, Xiaoshuai Zhang, Zhiao Huang, Xuejin Chen, Zexiang Xu, Hao Su 0001. [doi]
• Learning Multi-Agent Communication from Graph Modeling PerspectiveShengchao Hu, Li Shen 0008, Ya Zhang 0002, Dacheng Tao. [doi]
• Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One DayYifan Jiang 0001, Hao Tang 0005, Jen-Hao Rick Chang, Liangchen Song, Zhangyang Wang, Liangliang Cao. [doi]
• InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test NodesJiawei Sun, Kailai Li, Ruoxin Chen, Jie Li 0002, Chentao Wu, Yue Ding 0001, Junchi Yan. [doi]
• GAFormer: Enhancing Timeseries Transformers Through Group-Aware EmbeddingsJingyun Xiao, Ran Liu, Eva L. Dyer. [doi]
• Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics SimulationYunyang Li, Yusong Wang, Lin Huang, Han Yang, Xinran Wei, Jia Zhang, Tong Wang, Zun Wang, Bin Shao, Tie-Yan Liu. [doi]
• PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise TrainingDawei Zhu, Nan Yang 0002, Liang Wang 0046, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li. [doi]
• Near-Optimal Solutions of Constrained Learning ProblemsJuan Elenter, Luiz F. O. Chamon, Alejandro Ribeiro. [doi]
• Adaptive Instrument Design for Indirect ExperimentsYash Chandak, Shiv Shankar, Vasilis Syrgkanis, Emma Brunskill. [doi]
• Theoretical Understanding of Learning from Adversarial PerturbationsSoichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki. [doi]
• Neural Common Neighbor with Completion for Link PredictionXiyuan Wang, Haotong Yang, Muhan Zhang. [doi]
• Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AINabeel Seedat, Fergus Imrie, Mihaela van der Schaar. [doi]
• Predictive, scalable and interpretable knowledge tracing on structured domainsHanqi Zhou, Robert Bamler, Charley M. Wu, Álvaro Tejero-Cantero. [doi]
• Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMsQingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu, Bin Yu 0001, Jianfeng Gao 0001, Tuo Zhao. [doi]
• From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property PredictionNima Shoghi, Adeesh Kolluru, John R. Kitchin, Zachary W. Ulissi, C. Lawrence Zitnick, Brandon M. Wood. [doi]
• Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe. [doi]
• Reconciling Spatial and Temporal Abstractions for Goal RepresentationMehdi Zadem, Sergio Mover, Sao Mai Nguyen. [doi]
• Video Decomposition Prior: Editing Videos Layer by LayerGaurav Shrivastava, Ser-Nam Lim, Abhinav Shrivastava. [doi]
• AffineQuant: Affine Transformation Quantization for Large Language ModelsYuexiao Ma, Huixia Li, Xiawu Zheng, Feng Ling, XueFeng Xiao, Rui Wang 0089, Shilei Wen, Fei Chao 0001, Rongrong Ji. [doi]
• Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior ModelsMarien Renaud, Jiaming Liu 0001, Valentin De Bortoli, Andrés Almansa, Ulugbek Kamilov. [doi]
• Towards Poisoning Fair RepresentationsTianci Liu 0003, Haoyu Wang 0004, Feijie Wu, Hengtong Zhang, Pan Li 0005, Lu Su, Jing Gao 0004. [doi]
• Expected flow networks in stochastic environments and two-player zero-sum gamesMarco Jiralerspong, Bilun Sun, Danilo Vucetic, Tianyu Zhang, Yoshua Bengio, Gauthier Gidel, Nikolay Malkin. [doi]
• Lemur: Integrating Large Language Models in Automated Program VerificationHaoze Wu 0001, Clark W. Barrett, Nina Narodytska. [doi]
• DrS: Learning Reusable Dense Rewards for Multi-Stage TasksTongzhou Mu, Minghua Liu, Hao Su 0001. [doi]
• Selective Mixup Fine-Tuning for Optimizing Non-Decomposable ObjectivesShrinivas Ramasubramanian, Harsh Rangwani, Sho Takemori, Kunal Samanta, Yuhei Umeda, Venkatesh Babu Radhakrishnan. [doi]
• Why is SAM Robust to Label Noise?Christina Baek, J. Zico Kolter, Aditi Raghunathan. [doi]
• Incentivized Truthful Communication for Federated BanditsZhepei Wei, Chuanhao Li, Tianze Ren, Haifeng Xu, Hongning Wang. [doi]
• The Effective Horizon Explains Deep RL Performance in Stochastic EnvironmentsCassidy Laidlaw, Banghua Zhu, Stuart Russell 0001, Anca D. Dragan. [doi]
• WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex InstructionsCan Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao 0004, Jiazhan Feng, Chongyang Tao, Qingwei Lin, Daxin Jiang. [doi]
• Making Pre-trained Language Models Great on Tabular PredictionJiahuan Yan, Bo Zheng, Hongxia Xu, Yiheng Zhu, Danny Z. Chen, Jimeng Sun 0001, Jian Wu 0001, Jintai Chen. [doi]
• Cascading Reinforcement LearningYihan Du, R. Srikant 0001, Wei Chen. [doi]
• Compositional Conservatism: A Transductive Approach in Offline Reinforcement LearningYeda Song, Dongwook Lee, Gunhee Kim. [doi]
• Mixture of Weak and Strong Experts on GraphsHanqing Zeng, Hanjia Lyu, Diyi Hu, Yinglong Xia, Jiebo Luo. [doi]
• Bayesian Neural Controlled Differential Equations for Treatment Effect EstimationKonstantin Hess, Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel. [doi]
• Towards Faithful XAI Evaluation via Generalization-Limited Backdoor WatermarkMengxi Ya, Yiming Li 0004, Tao Dai 0001, Bin Wang, Yong Jiang 0001, Shu-Tao Xia. [doi]
• Towards domain-invariant Self-Supervised Learning with Batch Styles StandardizationMarin Scalbert, Maria Vakalopoulou, Florent Couzinie-Devy. [doi]
• Rethinking the symmetry-preserving circuits for constrained variational quantum algorithmsGe Yan 0001, Hongxu Chen, Kaisen Pan, Junchi Yan. [doi]
• GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherYouliang Yuan, Wenxiang Jiao, Wenxuan Wang 0001, Jen-tse Huang 0001, Pinjia He, Shuming Shi 0001, Zhaopeng Tu. [doi]
• Behaviour DistillationAndrei Lupu, Chris Lu 0001, Jarek Liesen, Robert Tjarko Lange, Jakob Nicolaus Foerster. [doi]
• Tractable MCMC for Private Learning with Pure and Gaussian Differential PrivacyYingyu Lin, Yian Ma, Yu-Xiang Wang 0003, Rachel Redberg, Zhiqi Bu. [doi]
• Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy OptimizationKun Lei, Zhengmao He, Chenhao Lu, Kaizhe Hu, Yang Gao 0029, Huazhe Xu. [doi]
• SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik R. Narasimhan. [doi]
• DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuningZhengxiang Shi, Aldo Lipani. [doi]
• Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor ProductsShengjie Luo, Tianlang Chen, Aditi S. Krishnapriyan. [doi]
• Benign Oscillation of Stochastic Gradient Descent with Large Learning RateMiao Lu, Beining Wu, Xiaodong Yang, Difan Zou. [doi]
• Sliced Denoising: A Physics-Informed Molecular Pre-Training MethodYuyan Ni, Shikun Feng, Wei-Ying Ma, Zhi-Ming Ma, Yanyan Lan. [doi]
• Efficient Subgraph GNNs by Learning Effective Selection PoliciesBeatrice Bevilacqua, Moshe Eliasof, Eli A. Meirom, Bruno Ribeiro 0001, Haggai Maron. [doi]
• Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series ForecastingPeng Chen 0038, Yingying Zhang, Yunyao Cheng 0001, Yang Shu, Yihang Wang, Qingsong Wen, Bin Yang 0016, Chenjuan Guo. [doi]
• Towards Understanding Sycophancy in Language ModelsMrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, Ethan Perez. [doi]
• CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed SamplingSeyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber. [doi]
• TOSS: High-quality Text-guided Novel View Synthesis from a Single ImageYukai Shi, Jianan Wang, He Cao, Boshi Tang, Xianbiao Qi, Tianyu Yang, Yukun Huang, Shilong Liu, Lei Zhang 0001, Heung-Yeung Shum. [doi]
• Learning Decentralized Partially Observable Mean Field Control for Artificial Collective BehaviorKai Cui 0001, Sascha Hauck, Christian Fabian, Heinz Koeppl. [doi]
• Understanding Expressivity of GNN in Rule LearningHaiquan Qiu, Yongqi Zhang, Yong Li 0008, Quanming Yao. [doi]
• Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement LearningMaxime Wabartha, Joelle Pineau. [doi]
• One-hot Generalized Linear Model for Switching Brain State DiscoveryChengrui Li, Soon-Ho Kim, Chris Rodgers, Hannah Choi, Anqi Wu. [doi]
• Weaker MVI Condition: Extragradient Methods with Multi-Step ExplorationYifeng Fan, Yongqiang Li, Bo Chen. [doi]
• Generating Pragmatic Examples to Train Neural Program SynthesizersSaujas Vaduguru, Daniel Fried, Yewen Pu. [doi]
• A Foundation Model for Error Correction CodesYoni Choukroun, Lior Wolf. [doi]
• Symmetric Mean-field Langevin Dynamics for Distributional Minimax ProblemsJuno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki. [doi]
• Unpaired Image-to-Image Translation via Neural Schrödinger BridgeBeomsu Kim, Gihyun Kwon, Kwanyoung Kim, Jong Chul Ye. [doi]
• A Sublinear Adversarial Training AlgorithmYeqi Gao, Lianke Qin, Zhao Song 0002, Yitan Wang. [doi]
• PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial FiltersJingyu Chen, Runlin Lei, Zhewei Wei. [doi]
• LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentBin Zhu, Bin Lin, Munan Ning, Yang Yan, Jiaxi Cui, Hongfa Wang, Yatian Pang, Wenhao Jiang, Junwu Zhang, Zongwei Li, Caiwan Zhang, Zhifeng Li 0001, Wei Liu 0005, Li Yuan 0007. [doi]
• Information Retention via Learning Supplemental FeaturesZhipeng Xie, Yahe Li. [doi]
• GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data GenerationKai Chen, Enze Xie, Zhe Chen, Yibo Wang, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung. [doi]
• A Poincaré Inequality and Consistency Results for Signal Sampling on Large GraphsThien Le, Luana Ruiz, Stefanie Jegelka. [doi]
• Grokking in Linear Estimators - A Solvable Model that Groks without UnderstandingNoam Levi, Alon Beck, Yohai Bar-Sinai. [doi]
• Polynomial Width is Sufficient for Set Representation with High-dimensional FeaturesPeihao Wang, Shenghao Yang 0002, Shu Li, Zhangyang Wang, Pan Li 0005. [doi]
• Maximum Likelihood Estimation is All You Need for Well-Specified Covariate ShiftJiawei Ge, Shange Tang, Jianqing Fan, Cong Ma, Chi Jin 0001. [doi]
• Trajeglish: Traffic Modeling as Next-Token PredictionJonah Philion, Xue Bin Peng, Sanja Fidler. [doi]
• Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery DetectionJiawei Liang, Siyuan Liang, Aishan Liu, Xiaojun Jia, Junhao Kuang, Xiaochun Cao. [doi]
• Data Debugging with Shapley Importance over Machine Learning PipelinesBojan Karlas, David Dao, Matteo Interlandi, Sebastian Schelter, Wentao Wu 0001, Ce Zhang 0001. [doi]
• Brain decoding: toward real-time reconstruction of visual perceptionYohann Benchetrit, Hubert J. Banville, Jean-Remi King. [doi]
• Oracle Efficient Algorithms for Groupwise RegretKrishna Acharya, Eshwar Ram Arunachaleswaran, Sampath Kannan, Aaron Roth 0001, Juba Ziani. [doi]
• SaProt: Protein Language Modeling with Structure-aware VocabularyJin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, Fajie Yuan. [doi]
• Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label DescriptionsSachin Kumar 0009, Chan Young Park, Yulia Tsvetkov. [doi]
• GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction BenchmarksRenat Sergazinov, Elizabeth Chun, Valeriya Rogovchenko, Nathaniel J. Fernandes, Nicholas Kasman, Irina Gaynanova. [doi]
• Compressing Latent Space via Least VolumeQiuyi Chen, Mark D. Fuge. [doi]
• METRA: Scalable Unsupervised RL with Metric-Aware AbstractionSeohong Park, Oleh Rybkin, Sergey Levine. [doi]
• Communication-Efficient Federated Non-Linear Bandit OptimizationChuanhao Li, Chong Liu, Yu-Xiang Wang. [doi]
• Predicting Emergent Abilities with Infinite Resolution EvaluationShengding Hu, Xin Liu, Xu Han 0007, Xinrong Zhang, Chaoqun He, Weilin Zhao, Yankai Lin, Ning Ding 0002, Zebin Ou, Guoyang Zeng, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Fine-Tuned Language Models Generate Stable Inorganic Materials as TextNate Gruver, Anuroop Sriram, Andrea Madotto, Andrew Gordon Wilson, C. Lawrence Zitnick, Zachary W. Ulissi. [doi]
• Unified Projection-Free Algorithms for Adversarial DR-Submodular OptimizationMohammad Pedramfar, Yididiya Y. Nadew, Christopher John Quinn, Vaneet Aggarwal. [doi]
• Learning to Reject Meets Long-tail LearningHarikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Neha Gupta, Sanjiv Kumar. [doi]
• Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural NetworksKesen Zhao, Liang Zhang. [doi]
• Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted ActivationsPatricia Pauli, Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu 0002. [doi]
• SLiMe: Segment Like MeAliasghar Khani, Saeid Asgari Taghanaki, Aditya Sanghi, Ali Mahdavi-Amiri, Ghassan Hamarneh. [doi]
• Demonstration-Regularized RLDaniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard. [doi]
• Non-negative Contrastive LearningYifei Wang 0001, Qi Zhang, Yaoyu Guo, Yisen Wang 0001. [doi]
• High-dimensional SGD aligns with emerging outlier eigenspacesGérard Ben Arous, Reza Gheissari, Jiaoyang Huang, Aukosh Jagannath. [doi]
• Unified Generative Modeling of 3D Molecules with Bayesian Flow NetworksYuxuan Song, Jingjing Gong, Hao Zhou, Mingyue Zheng, Jingjing Liu, Wei-Ying Ma. [doi]
• Conditional Information Bottleneck Approach for Time Series ImputationMinGyu Choi, ChangHee Lee. [doi]
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLHao Sun, Alihan Hüyük, Mihaela van der Schaar. [doi]
• Adversarial Attacks on Fairness of Graph Neural NetworksBinchi Zhang, Yushun Dong, Chen Chen 0022, Yada Zhu, Minnan Luo, Jundong Li. [doi]
• Directly Fine-Tuning Diffusion Models on Differentiable RewardsKevin Clark, Paul Vicol, Kevin Swersky, David J. Fleet. [doi]
• MetaCoCo: A New Few-Shot Classification Benchmark with Spurious CorrelationMin Zhang, Haoxuan Li, Fei Wu 0001, Kun Kuang. [doi]
• Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning FrameworkXinyu Shi, Jianhao Ding, Zecheng Hao, Zhaofei Yu. [doi]
• Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised PretrainingLicong Lin, Yu Bai 0017, Song Mei. [doi]
• Approximating Nash Equilibria in Normal-Form Games via Stochastic OptimizationIan Gemp, Luke Marris, Georgios Piliouras. [doi]
• On Harmonizing Implicit SubpopulationsFeng Hong 0004, Jiangchao Yao, Yueming Lyu, Zhihan Zhou 0002, Ivor W. Tsang, Ya Zhang 0002, Yanfeng Wang. [doi]
• LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL ArchitecturesVimal Thilak, Chen Huang 0001, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin. [doi]
• Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and EditingLing Yang 0006, Zhilong Zhang, Zhaochen Yu, Jingwei Liu, Minkai Xu, Stefano Ermon, Bin Cui 0001. [doi]
• DreamSmooth: Improving Model-based Reinforcement Learning via Reward SmoothingVint Lee, Pieter Abbeel, Youngwoon Lee. [doi]
• Online Stabilization of Spiking Neural NetworksYaoyu Zhu, Jianhao Ding, Tiejun Huang 0001, Xiaodong Xie, Zhaofei Yu. [doi]
• M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and ClusteringJiaxin Lu, Zetian Jiang, Tianzhe Wang, Junchi Yan. [doi]
• Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient ReasoningMurong Yue, Jie Zhao, Min Zhang, Liang Du, Ziyu Yao. [doi]
• Large Language Models as Automated Aligners for benchmarking Vision-Language ModelsYuanfeng Ji, Chongjian Ge, Weikai Kong, Enze Xie, Zhengying Liu, Zhenguo Li, Ping Luo 0002. [doi]
• Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series PredictionXiaoyi Liu, Duxin Chen, Wenjia Wei, Xia Zhu, Wenwu Yu. [doi]
• The Curse of Diversity in Ensemble-Based ExplorationZhixuan Lin, Pierluca D'Oro, Evgenii Nikishin, Aaron C. Courville. [doi]
• Privileged Sensing Scaffolds Reinforcement LearningEdward S. Hu, James Springer, Oleh Rybkin, Dinesh Jayaraman. [doi]
• Inducing High Energy-Latency of Large Vision-Language Models with Verbose ImagesKuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr 0001, Zhifeng Li 0001, Wei Liu 0005. [doi]
• Probabilistic Self-supervised Representation Learning via Scoring Rules MinimizationAmirhossein Vahidi, Simon Schoßer, Lisa Wimmer, Yawei Li, Bernd Bischl, Eyke Hüllermeier, Mina Rezaei. [doi]
• Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of ViewRaj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach. [doi]
• Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte CarloHaque Ishfaq, Qingfeng Lan, Pan Xu 0002, A. Rupam Mahmood, Doina Precup, Anima Anandkumar, Kamyar Azizzadenesheli. [doi]
• An Agnostic View on the Cost of Overfitting in (Kernel) Ridge RegressionLijia Zhou, James B. Simon, Gal Vardi, Nathan Srebro. [doi]
• Parametric Augmentation for Time Series Contrastive LearningXu Zheng, Tianchun Wang, Wei Cheng 0002, Aitian Ma, Haifeng Chen, Mo Sha 0001, Dongsheng Luo. [doi]
• When should we prefer Decision Transformers for Offline Reinforcement Learning?Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang 0001. [doi]
• VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAEHaonan Yu, Wei Xu 0017. [doi]
• Principled Federated Domain Adaptation: Gradient Projection and Auto-WeightingEnyi Jiang, Yibo Jacky Zhang, Sanmi Koyejo. [doi]
• Dual RL: Unification and New Methods for Reinforcement and Imitation LearningHarshit Sikchi, Qinqing Zheng, Amy Zhang 0001, Scott Niekum. [doi]
• Decodable and Sample Invariant Continuous Object EncoderDehao Yuan, Furong Huang, Cornelia Fermüller, Yiannis Aloimonos. [doi]
• Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataChongyi Zheng, Benjamin Eysenbach, Homer Rich Walke, Patrick Yin, Kuan Fang, Ruslan Salakhutdinov, Sergey Levine. [doi]
• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human FeedbackSouradip Chakraborty, Amrit S. Bedi, Alec Koppel, Huazheng Wang, Dinesh Manocha, Mengdi Wang, Furong Huang. [doi]
• Memory-Consistent Neural Networks for Imitation LearningKaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman, James Weimer, Insup Lee 0001. [doi]
• Language Model Detectors Are Easily Optimized AgainstCharlotte Nicks, Eric Mitchell, Rafael Rafailov, Archit Sharma, Christopher D. Manning, Chelsea Finn, Stefano Ermon. [doi]
• LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language ModelsYixiao Li, Yifan Yu 0003, Chen Liang 0006, Nikos Karampatziakis, Pengcheng He, Weizhu Chen, Tuo Zhao. [doi]
• DyST: Towards Dynamic Neural Scene Representations on Real-World VideosMaximilian Seitzer, Sjoerd van Steenkiste, Thomas Kipf, Klaus Greff, Mehdi S. M. Sajjadi. [doi]
• Improving LoRA in Privacy-preserving Federated LearningYoubang Sun, Zitao Li, Yaliang Li, Bolin Ding. [doi]
• Compositional Preference Models for Aligning LMsDongyoung Go, Tomasz Korbak, Germán Kruszewski, Jos Rozen, Marc Dymetman. [doi]
• ImagenHub: Standardizing the evaluation of conditional image generation modelsMax Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen. [doi]
• Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methodsYuto Nishimura, Taiji Suzuki. [doi]
• Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery FrameworkYufei Kuang, Jie Wang 0005, Haoyang Liu, Fangzhou Zhu, Xijun Li, Jia Zeng, Jianye Hao, Bin Li 0025, Feng Wu 0001. [doi]
• Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information DecompositionFaisal Hamman, Sanghamitra Dutta. [doi]
• AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei Xiao. [doi]
• AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality PredictionKethmi Hirushini Hettige, Jiahao Ji, Shili Xiang, Cheng Long, Gao Cong, Jingyuan Wang. [doi]
• OpenChat: Advancing Open-source Language Models with Mixed-Quality DataGuan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, Yang Liu 0165. [doi]
• Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary NetworksSuhwan Choi, Myeongho Jeon, Yeonjung Hwang, Jeonglyul Oh, Sungjun Lim, Joonseok Lee, Myungjoo Kang. [doi]
• Controlled Text Generation via Language Model ArithmeticJasper Dekoninck, Marc Fischer 0002, Luca Beurer-Kellner, Martin T. Vechev. [doi]
• Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised LearningZhaoyi Zhou, Chuning Zhu, Runlong Zhou, Qiwen Cui, Abhishek Gupta 0004, Simon Shaolei Du. [doi]
• Large-scale Training of Foundation Models for Wearable BiosignalsSalar Abbaspourazad, Oussama Elachqar, Andrew C. Miller, Saba Emrani, Udhyakumar Nallasamy, Ian Shapiro. [doi]
• Matcher: Segment Anything with One Shot Using All-Purpose Feature MatchingYang Liu, Muzhi Zhu, Hengtao Li, Hao Chen 0041, Xinlong Wang, Chunhua Shen. [doi]
• FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth EstimatorsHaiping Wang 0004, Yuan Liu 0025, Bing Wang 0013, Yujing Sun, Zhen Dong 0005, Wenping Wang, Bisheng Yang. [doi]
• Uncertainty-aware Graph-based Hyperspectral Image ClassificationLinlin Yu, Yifei Lou, Feng Chen 0001. [doi]
• Knowledge Fusion of Large Language ModelsFanqi Wan, Xinting Huang, Deng Cai 0002, Xiaojun Quan, Wei Bi, Shuming Shi 0001. [doi]
• IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUsYuzhen Mao, Martin Ester, Ke Li. [doi]
• The Expressive Power of Transformers with Chain of ThoughtWilliam Merrill, Ashish Sabharwal. [doi]
• S2AC: Energy-Based Reinforcement Learning with Stein Soft Actor CriticSafa Messaoud, Billel Mokeddem, Zhenghai Xue, Linsey Pang, Bo An 0001, Haipeng Chen 0001, Sanjay Chawla. [doi]
• Manifold Diffusion FieldsAhmed A. Elhag, Yuyang Wang, Joshua M. Susskind, Miguel Ángel Bautista 0001. [doi]
• Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNsAakash Lahoti, Stefani Karp, Ezra Winston, Aarti Singh, Yuanzhi Li. [doi]
• Transformer-VQ: Linear-Time Transformers via Vector QuantizationLucas D. Lingle. [doi]
• How connectivity structure shapes rich and lazy learning in neural circuitsYuhan Helena Liu, Aristide Baratin, Jonathan Cornford, Stefan Mihalas, Eric Shea-Brown, Guillaume Lajoie. [doi]
• Provably Efficient CVaR RL in Low-rank MDPsYulai Zhao 0002, Wenhao Zhan, Xiaoyan Hu, Ho-Fung Leung, Farzan Farnia, Wen Sun 0002, Jason D. Lee. [doi]
• Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsJian Xie, Kai Zhang 0033, Jiangjie Chen, Renze Lou, Yu Su 0001. [doi]
• STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative ModelsPum Jun Kim, Seojun Kim, Jaejun Yoo. [doi]
• ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual LearningJiecheng Lu, Xu Han, Shihao Yang. [doi]
• Light Schrödinger BridgeAlexander Korotin, Nikita Gushchin, Evgeny Burnaev. [doi]
• ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation FusionShangyu Wu, Ying Xiong, Yufei Cui, Xue Liu 0001, Buzhou Tang, Tei-Wei Kuo, Chun Jason Xue. [doi]
• Tool-Augmented Reward ModelingLei Li 0040, Yekun Chai, Shuohuan Wang, Yu Sun 0004, Hao Tian, Ningyu Zhang 0001, Hua Wu 0003. [doi]
• Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision MakingJeonghye Kim, Suyoung Lee, Woojun Kim, Youngchul Sung. [doi]
• DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion ModelsSohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang. [doi]
• Koopman-based generalization bound: New aspect for full-rank weightsYuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki. [doi]
• Test-time Adaptation against Multi-modal Reliability BiasMouxing Yang, Yunfan Li 0003, Changqing Zhang, Peng Hu 0002, Xi Peng 0001. [doi]
• What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine SimilarityGabryel Mason-Williams, Fredrik Dahlqvist. [doi]
• Multisize Dataset CondensationYang He 0002, Lingao Xiao, Joey Tianyi Zhou, Ivor W. Tsang. [doi]
• One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-AttentionArvind V. Mahankali, Tatsunori Hashimoto, Tengyu Ma 0001. [doi]
• BECLR: Batch Enhanced Contrastive Few-Shot LearningStylianos Poulakakis-Daktylidis, Hadi Jamali Rad. [doi]
• Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local UpdatesSiqi Zhang, Sayantan Choudhury, Sebastian U. Stich, Nicolas Loizou. [doi]
• Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics TasksMurtaza Dalal, Tarun Chiruvolu, Devendra Singh Chaplot, Ruslan Salakhutdinov. [doi]
• HyperHuman: Hyper-Realistic Human Generation with Latent Structural DiffusionXian Liu, Jian Ren, Aliaksandr Siarohin, Ivan Skorokhodov, Yanyu Li, Dahua Lin, Xihui Liu, Ziwei Liu 0002, Sergey Tulyakov. [doi]
• Domain-Agnostic Molecular Generation with Chemical FeedbackYin Fang, Ningyu Zhang 0001, Zhuo Chen 0007, Lingbing Guo, Xiaohui Fan, Huajun Chen. [doi]
• Don't Play Favorites: Minority Guidance for Diffusion ModelsSoobin Um, Suhyeon Lee 0004, Jong Chul Ye. [doi]
• Teaching Language Models to Hallucinate Less with Synthetic TasksErik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Hassan Awadallah, Ece Kamar. [doi]
• Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote AlignmentUtkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu, Carl Vondrick, Bharath Hariharan, Kavita Bala. [doi]
• Faithful Explanations of Black-box NLP Models Using LLM-generated CounterfactualsYair Ori Gat, Nitay Calderon, Amir Feder, Alexander Chapanin, Amit Sharma, Roi Reichart. [doi]
• Rethinking Model Ensemble in Transfer-based Adversarial AttacksHuanran Chen, Yichi Zhang, Yinpeng Dong, Xiao Yang, Hang Su 0006, Jun Zhu 0001. [doi]
• Fake It Till Make It: Federated Learning with Consensus-Oriented GenerationRui Ye, Yaxin Du, Zhenyang Ni, Yanfeng Wang, Siheng Chen. [doi]
• Multi-granularity Correspondence Learning from Long-term Noisy VideosYijie Lin 0001, Jie Zhang, Zhenyu Huang 0005, Jia Liu, Zujie Wen, Xi Peng 0001. [doi]
• Flat Minima in Linear Estimation and an Extended Gauss Markov TheoremSimon N. Segert. [doi]
• Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge GraphsZhanke Zhou, Yongqi Zhang, Jiangchao Yao, Quanming Yao, Bo Han 0003. [doi]
• RETSim: Resilient and Efficient Text SimilarityMarina Zhang, Owen S. Vallis, Aysegul Bumin, Tanay Vakharia, Elie Bursztein. [doi]
• Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence AnalysisJie Hao, Xiaochuan Gong, Mingrui Liu. [doi]
• Achieving Human Parity in Content-Grounded Datasets GenerationAsaf Yehudai, Boaz Carmeli, Yosi Mass, Ofir Arviv, Nathaniel Mills, Eyal Shnarch, Leshem Choshen. [doi]
• Making LLaMA SEE and Draw with SEED TokenizerYuying Ge, Sijie Zhao, Ziyun Zeng, Yixiao Ge, Chen Li, Xintao Wang, Ying Shan. [doi]
• Tag2Text: Guiding Vision-Language Model via Image TaggingXinyu Huang, Youcai Zhang, Jinyu Ma, Weiwei Tian, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, Lei Zhang 0001. [doi]
• Code Representation Learning at ScaleDejiao Zhang, Wasi Uddin Ahmad, Ming Tan, Hantian Ding, Ramesh Nallapati, Dan Roth, Xiaofei Ma 0001, Bing Xiang. [doi]
• When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and LimitationsAleksandar Petrov, Philip Torr 0001, Adel Bibi. [doi]
• Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanismTingting Jiang, Qi Xu, Xuming Ran, Jiangrong Shen, Pan Lv, Qiang Zhang, Gang Pan 0001. [doi]
• Subtractive Mixture Models via Squaring: Representation and LearningLorenzo Loconte, Aleksanteri M. Sladek, Stefan Mengel, Martin Trapp 0001, Arno Solin, Nicolas Gillis, Antonio Vergari. [doi]
• Language-Informed Visual Concept LearningSharon Lee, Yunzhi Zhang, Shangzhe Wu, Jiajun Wu 0001. [doi]
• A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making TasksHaruo Hosoya. [doi]
• Fast Ensembling with Diffusion Schrödinger BridgeHyunsu Kim, Jongmin Yoon, Juho Lee 0001. [doi]
• Chain of Thought Empowers Transformers to Solve Inherently Serial ProblemsZhiyuan Liu 0001, Hong Liu, Denny Zhou, Tengyu Ma 0001. [doi]
• Robust Adversarial Reinforcement Learning via Bounded Rationality CurriculaAryaman Reddi, Maximilian Tölle, Jan Peters 0001, Georgia Chalvatzaki, Carlo D'Eramo. [doi]
• Learning Interactive Real-World SimulatorsSherry Yang, Yilun Du, Seyed Kamyar Seyed Ghasemipour, Jonathan Tompson, Leslie Pack Kaelbling, Dale Schuurmans, Pieter Abbeel. [doi]
• Solving Inverse Problems with Latent Diffusion Models via Hard Data ConsistencyBowen Song, Soo Min Kwon, Zecheng Zhang, Xinyu Hu, Qing Qu 0001, Liyue Shen. [doi]
• Near-Optimal Quantum Algorithm for Minimizing the Maximal LossHao Wang, Chenyi Zhang, Tongyang Li. [doi]
• ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer ModelsSunghyeon Woo, SunWoo Lee, Dongsuk Jeon. [doi]
• Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven PriorsIdo Amos, Jonathan Berant, Ankit Gupta 0001. [doi]
• Learning Multi-Faceted Prototypical User InterestsNhu-Thuat Tran, Hady W. Lauw. [doi]
• Simple Hierarchical Planning with DiffusionChang Chen, Fei Deng, Kenji Kawaguchi, Caglar Gulcehre, Sungjin Ahn. [doi]
• Learning Polynomial Problems with SL(2, R)-EquivarianceHannah Lawrence, Mitchell Tong Harris. [doi]
• Mirage: Model-agnostic Graph Distillation for Graph ClassificationMridul Gupta, Sahil Manchanda, Hariprasad Kodamana, Sayan Ranu. [doi]
• Motif: Intrinsic Motivation from Artificial Intelligence FeedbackMartin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang 0001, Mikael Henaff. [doi]
• HoloNets: Spectral Convolutions do extend to Directed GraphsChristian Koke, Daniel Cremers. [doi]
• Entity-Centric Reinforcement Learning for Object Manipulation from PixelsDan Haramati, Tal Daniel, Aviv Tamar. [doi]
• In defense of parameter sharing for model-compressionAditya Desai, Anshumali Shrivastava. [doi]
• Do Generated Data Always Help Contrastive Learning?Yifei Wang 0001, Jizhe Zhang, Yisen Wang 0001. [doi]
• Democratizing Fine-grained Visual Recognition with Large Language ModelsMingxuan Liu, Subhankar Roy, Wenjing Li, Zhun Zhong, Nicu Sebe, Elisa Ricci 0001. [doi]
• More is Better: when Infinite Overparameterization is Optimal and Overfitting is ObligatoryJames B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin. [doi]
• Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK ApproachShaopeng Fu, Di Wang 0015. [doi]
• TokenFlow: Consistent Diffusion Features for Consistent Video EditingMichal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel. [doi]
• Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and AutoregressionAdam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang. [doi]
• Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational AutoencodersHien Dang 0003, Tho Tran Huu, Tan Minh Nguyen, Nhat Ho. [doi]
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsDeyao Zhu, Jun Chen 0021, Xiaoqian Shen, Xiang Li, Mohamed Elhoseiny. [doi]
• Improving protein optimization with smoothed fitness landscapesAndrew Kirjner, Jason Yim, Raman Samusevich, Shahar Bracha, Tommi S. Jaakkola, Regina Barzilay, Ila R. Fiete. [doi]
• Language Model Cascades: Token-Level Uncertainty And BeyondNeha Gupta, Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar. [doi]
• Reward Model Ensembles Help Mitigate OveroptimizationThomas Coste, Usman Anwar, Robert Kirk, David Krueger 0001. [doi]
• LEMON: Lossless model expansionYite Wang, Jiahao Su, Hanlin Lu, Cong Xie, Tianyi Liu, Jianbo Yuan, Haibin Lin, Ruoyu Sun 0001, Hongxia Yang. [doi]
• Curriculum reinforcement learning for quantum architecture search under hardware errorsYash J. Patel, Akash Kundu, Mateusz Ostaszewski, Xavier Bonet-Monroig, Vedran Dunjko, Onur Danaci. [doi]
• BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian DynamicsSuresh Bishnoi, Jayadeva, Sayan Ranu, N. M. Anoop Krishnan. [doi]
• AttEXplore: Attribution for Explanation with model parameters eXplorationZhiyu Zhu, Huaming Chen, Jiayu Zhang, Xinyi Wang 0005, Zhibo Jin, Jason Xue, Flora D. Salim. [doi]
• Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited SupervisionNan Chen, Zemin Liu, Bryan Hooi, Bingsheng He, Rizal Fathony, Jun Hu, Jia Chen. [doi]
• Deep Temporal Graph ClusteringMeng Liu 0014, Yue Liu 0008, Ke Liang 0006, Wenxuan Tu, Siwei Wang 0001, Sihang Zhou 0001, Xinwang Liu 0002. [doi]
• Submodular Reinforcement LearningManish Prajapat, Mojmir Mutny, Melanie N. Zeilinger, Andreas Krause 0001. [doi]
• Scaling Laws for Sparsely-Connected Foundation ModelsElias Frantar, Carlos Riquelme Ruiz, Neil Houlsby, Dan Alistarh, Utku Evci. [doi]
• Exploring Diffusion Time-steps for Unsupervised Representation LearningZhongqi Yue, Jiankun Wang 0010, Qianru Sun, Lei Ji 0001, Eric I-Chao Chang, Hanwang Zhang. [doi]
• Revisiting Link Prediction: a data perspectiveHaitao Mao, Juanhui Li, Harry Shomer, Bingheng Li, Wenqi Fan, Yao Ma 0001, Tong Zhao 0003, Neil Shah, Jiliang Tang. [doi]
• Bayesian Bi-clustering of Neural Spiking Activity with Latent StructuresGanchao Wei. [doi]
• Conversational Drug Editing Using Retrieval and Domain FeedbackShengchao Liu, Jiongxiao Wang, Yijin Yang, Chengpeng Wang, Ling Liu 0001, Hongyu Guo, Chaowei Xiao. [doi]
• Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language ModelsYin Fang, Xiaozhuan Liang, Ningyu Zhang 0001, Kangwei Liu, Rui Huang, Zhuo Chen 0007, Xiaohui Fan, Huajun Chen. [doi]
• Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language ModelsAshutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras 0001, Maarten Sap, Mark O. Riedl. [doi]
• Diverse Projection Ensembles for Distributional Reinforcement LearningMoritz Akiya Zanger, Wendelin Boehmer, Matthijs T. J. Spaan. [doi]
• The Reasonableness Behind Unreasonable Translation Capability of Large Language ModelTingchen Fu, Lemao Liu, Deng Cai 0002, Guoping Huang, Shuming Shi 0001, Rui Yan 0001. [doi]
• Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular VideosFengrui Tian, Yueqi Duan, Angtian Wang, Jianfei Guo, Shaoyi Du. [doi]
• Zipformer: A faster and better encoder for automatic speech recognitionZengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang 0006, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey. [doi]
• DORSal: Diffusion for Object-centric Representations of Scenes et alAllan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom, Mehdi S. M. Sajjadi, Thomas Kipf. [doi]
• Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisHubert Siuzdak. [doi]
• Risk Bounds of Accelerated SGD for Overparameterized Linear RegressionXuheng Li, Yihe Deng, Jingfeng Wu, Dongruo Zhou, Quanquan Gu. [doi]
• MT-Ranker: Reference-free machine translation evaluation by inter-system rankingIbraheem Muhammad Moosa, Rui Zhang 0037, Wenpeng Yin 0001. [doi]
• Context is EnvironmentSharut Gupta, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja. [doi]
• A Hard-to-Beat Baseline for Training-free CLIP-based AdaptationZhengbo Wang, Jian Liang, Lijun Sheng, Ran He 0001, Zilei Wang, Tieniu Tan. [doi]
• Denoising Diffusion Bridge ModelsLinqi Zhou, Aaron Lou, Samar Khanna, Stefano Ermon. [doi]
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized ToolsetsLifan Yuan, Yangyi Chen, Xingyao Wang 0002, Yi Fung 0001, Hao Peng 0009, Heng Ji. [doi]
• Accurate Forgetting for Heterogeneous Federated Continual LearningAbudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang, Kunda Yan, Bo Han 0003, Gang Niu 0001, Lei Fang, Changshui Zhang, Masashi Sugiyama. [doi]
• Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data AugmentationJiyang Zheng, Yu Yao, Bo Han 0003, Dadong Wang, Tongliang Liu. [doi]
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon TasksAaron Spieler, Nasim Rahaman, Georg Martius, Bernhard Schölkopf, Anna Levina. [doi]
• Neuron Activation Coverage: Rethinking Out-of-distribution Detection and GeneralizationYibing Liu, Chris Xing Tian, Haoliang Li, Lei Ma, Shiqi Wang 0001. [doi]
• Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric LearningLi Ren, Chen Chen 0001, Liqiang Wang, Kien A. Hua. [doi]
• Cameras as Rays: Pose Estimation via Ray DiffusionJason Y. Zhang 0001, Amy Lin, Moneish Kumar, Tzu-Hsuan Yang, Deva Ramanan, Shubham Tulsiani. [doi]
• fairret: a Framework for Differentiable Fairness Regularization TermsMaarten Buyl, MaryBeth Defrance, Tijl De Bie. [doi]
• In-Context Learning through the Bayesian PrismMadhur Panwar, Kabir Ahuja, Navin Goyal. [doi]
• Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementKai Xu, Rongyu Chen, Gianni Franchi, Angela Yao. [doi]
• Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learningAntoine Bambade, Fabian Schramm, Adrien B. Taylor, Justin Carpentier. [doi]
• Generative Pre-training for Speech with Flow MatchingAlexander H. Liu, Matthew Le 0001, Apoorv Vyas, Bowen Shi, Andros Tjandra, Wei-Ning Hsu. [doi]
• EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsYefei He, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang. [doi]
• Learning to Jointly Understand Visual and Tactile SignalsYichen Li, Yilun Du, Chao Liu 0064, Chao Liu 0064, Francis Williams, Michael Foshey, Benjamin Eckart, Jan Kautz, Joshua B. Tenenbaum, Antonio Torralba 0001, Wojciech Matusik. [doi]
• Memory-Assisted Sub-Prototype Mining for Universal Domain AdaptationYuxiang Lai, Yi Zhou 0007, Xinghong Liu, Tao Zhou 0002. [doi]
• Neural Contractive Dynamical SystemsHadi Beik Mohammadi, Søren Hauberg, Georgios Arvanitidis, Nadia Figueroa, Gerhard Neumann, Leonel Rozo. [doi]
• Learning Nash Equilibria in Rank-1 GamesNikolas Patris, Ioannis Panageas. [doi]
• lpNTK: Better Generalisation with Less Data via Sample Interaction During LearningShangmin Guo, Yi Ren, Stefano V. Albrecht, Kenny Smith. [doi]
• Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching ApproachSagar Shrestha, Xiao Fu 0001. [doi]
• Learning to Reject with a Fixed Predictor: Application to DecontextualizationChristopher Mohri, Daniel Andor, Eunsol Choi, Michael Collins 0001, Anqi Mao, Yutao Zhong 0002. [doi]
• Adversarial Training on Purification (AToP): Advancing Both Robustness and GeneralizationGuang Lin, Chao Li, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao. [doi]
• TorchRL: A data-driven decision-making library for PyTorchAlbert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang, Gianni De Fabritiis, Vincent Moens. [doi]
• Prediction without Preclusion: Recourse Verification with Reachable SetsAvni Kothari, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun. [doi]
• Fast and unified path gradient estimators for normalizing flowsLorenz Vaitl, Ludwig Winkler, Lorenz Richter, Pan Kessel. [doi]
• Skip-Attention: Improving Vision Transformers by Paying Less AttentionShashanka Venkataramanan, Amir Ghodrati, Yuki M. Asano, Fatih Porikli, AmirHossein Habibian. [doi]
• Masked Audio Generation using a Single Non-Autoregressive TransformerAlon Ziv, Itai Gat, Gaël Le Lan, Tal Remez, Felix Kreuk, Jade Copet, Alexandre Défossez, Gabriel Synnaeve, Yossi Adi. [doi]
• Effective pruning of web-scale datasets based on complexity of concept clustersAmro Abbas, Evgenia Rusak, Kushal Tirumala, Wieland Brendel, Kamalika Chaudhuri, Ari S. Morcos. [doi]
• Universal Humanoid Motion Representations for Physics-Based ControlZhengyi Luo 0002, Jinkun Cao, Josh Merel, Alexander Winkler, Jing Huang, Kris M. Kitani, WeiPeng Xu. [doi]
• AdaMerging: Adaptive Model Merging for Multi-Task LearningEnneng Yang, Zhenyi Wang, Li Shen 0008, Shiwei Liu 0003, Guibing Guo, Xingwei Wang 0001, Dacheng Tao. [doi]
• Pre-Training and Fine-Tuning Generative Flow NetworksLing Pan, Moksh Jain, Kanika Madan, Yoshua Bengio. [doi]
• SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problemMargalit Glasgow. [doi]
• EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion ModelsKoichi Namekata, Amirmojtaba Sabour, Sanja Fidler, Seung Wook Kim 0001. [doi]
• When can transformers reason with abstract symbols?Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind. [doi]
• Neural-Symbolic Recursive Machine for Systematic GeneralizationQing Li 0003, Yixin Zhu 0001, Yitao Liang, Ying Nian Wu, Song Chun Zhu, Siyuan Huang 0001. [doi]
• StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive LearningShengzhong Zhang, Wenjie Yang 0006, Xinyuan Cao, Hongwei Zhang, Zengfeng Huang. [doi]
• Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional NetworkTianze Luo, Zhanfeng Mo, Sinno Jialin Pan. [doi]
• Consistency-guided Prompt Learning for Vision-Language ModelsShuvendu Roy, Ali Etemad. [doi]
• CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic DecodingQiongyi Zhou, Changde Du, Shengpei Wang, Huiguang He. [doi]
• Enhancing Transfer Learning with Flexible Nonparametric Posterior SamplingHyungi Lee, Giung Nam, Edwin Fong, Juho Lee 0001. [doi]
• Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement LearningChenyu Zhang, Han Wang 0016, Aritra Mitra, James Anderson 0001. [doi]
• Optimistic Bayesian Optimization with Unknown ConstraintsQuoc Phong Nguyen, Wan Theng Ruth Chew, Le Song, Bryan Kian Hsiang Low, Patrick Jaillet. [doi]
• Modelling complex vector drawings with stroke-cloudsAlexander Ashcroft, Ayan Das 0003, Yulia Gryaditskaya, Zhiyu Qu, Yi-Zhe Song. [doi]
• Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphJiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin 0001, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, Jian Guo. [doi]
• Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed BanditDuanyi Yao, Songze Li, Ye Xue, Jin Liu. [doi]
• BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian InferenceSiqi Kou, Lei Gan, Dequan Wang, Chongxuan Li, Zhijie Deng. [doi]
• Task Planning for Visual Room Rearrangement under Partial ObservabilityKaran Mirakhor, Sourav Ghosh, Dipanjan Das 0003, Brojeshwar Bhowmick. [doi]
• Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task SubstructuresJung-Chun Liu, Chi-Hsien Chang, Shao-Hua Sun, Tian-Li Yu 0001. [doi]
• Future Language Modeling from Temporal Document HistoryChangmao Li, Jeffrey Flanigan. [doi]
• ODE Discovery for Longitudinal Heterogeneous Treatment Effects InferenceKrzysztof Kacprzyk, Samuel Holt, Jeroen Berrevoets, Zhaozhi Qian, Mihaela van der Schaar. [doi]
• Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic PromptsXinhua Cheng, Tianyu Yang, Jianan Wang, Yu Li, Lei Zhang 0001, Jian Zhang 0018, Li Yuan 0007. [doi]
• Text-to-3D with Classifier Score DistillationXin Yu 0004, Yuan-Chen Guo, Yangguang Li, Ding Liang, Song-Hai Zhang, Xiaojuan Qi 0001. [doi]
• Rethinking and Extending the Probabilistic Inference Capacity of GNNsTuo Xu, Lei Zou. [doi]
• Initializing Models with Larger OnesZhiqiu Xu, Yanjie Chen, Kirill Vishniakov, Yida Yin, Zhiqiang Shen, Trevor Darrell, Lingjie Liu, Zhuang Liu 0003. [doi]
• Embarrassingly Simple Dataset DistillationYunzhen Feng, Shanmukha Ramakrishna Vedantam, Julia Kempe. [doi]
• InsertNeRF: Instilling Generalizability into NeRF with HyperNet ModulesYanqi Bao, Tianyu Ding, Jing Huo, Wenbin Li 0006, Yuxin Li, Yang Gao 0001. [doi]
• Enhancing Neural Subset Selection: Integrating Background Information into Set RepresentationsBinghui Xie, Yatao Bian, Kaiwen Zhou, Yongqiang Chen 0002, Peilin Zhao, Bo Han 0003, Wei Meng 0001, James Cheng. [doi]
• Small-scale proxies for large-scale Transformer training instabilitiesMitchell Wortsman, Peter J. Liu, Lechao Xiao, Katie E. Everett, Alexander A. Alemi, Ben Adlam, John D. Co-Reyes, Izzeddin Gur, Abhishek Kumar, Roman Novak, Jeffrey Pennington, Jascha Sohl-Dickstein, Kelvin Xu, Jaehoon Lee 0001, Justin Gilmer, Simon Kornblith. [doi]
• Fast-ELECTRA for Efficient Pre-trainingChengyu Dong, Liyuan Liu, Hao Cheng 0002, Jingbo Shang, Jianfeng Gao 0001, Xiaodong Liu 0003. [doi]
• Sin3DM: Learning a Diffusion Model from a Single 3D Textured ShapeRundi Wu, Ruoshi Liu, Carl Vondrick, Changxi Zheng. [doi]
• Dropout Enhanced Bilevel TrainingPeiran Yu, Junyi Li, Heng Huang. [doi]
• Doubly Robust Instance-Reweighted Adversarial TrainingDaouda Sow, Sen Lin 0001, Zhangyang Wang, Yingbin Liang. [doi]
• Learning to Act from Actionless Videos through Dense CorrespondencesPo-Chen Ko, Jiayuan Mao, Yilun Du, Shao-Hua Sun, Joshua B. Tenenbaum. [doi]
• Understanding and Mitigating the Label Noise in Pre-training on Downstream TasksHao Chen 0102, Jindong Wang 0001, Ankit Shah 0001, Ran Tao 0013, Hongxin Wei, Xing Xie 0001, Masashi Sugiyama, Bhiksha Raj. [doi]
• Neural Network-Based Score Estimation in Diffusion Models: Optimization and GeneralizationYinbin Han, Meisam Razaviyayn, Renyuan Xu. [doi]
• LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized AttentionRenrui Zhang, Jiaming Han, Chris Liu, Aojun Zhou, Pan Lu, Yu Qiao 0001, Hongsheng Li 0001, Peng Gao 0007. [doi]
• Symmetric Basis Convolutions for Learning Lagrangian Fluid MechanicsRene Winchenbach, Nils Thuerey. [doi]
• Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement LearningHarry Zhao 0001, Safa Alver, Harm van Seijen, Romain Laroche, Doina Precup, Yoshua Bengio. [doi]
• Certified Adversarial Robustness for Rate Encoded Spiking Neural NetworksBhaskar Mukhoty, Hilal AlQuabeh, Giulia De Masi, Huan Xiong, Bin Gu 0001. [doi]
• SEABO: A Simple Search-Based Method for Offline Imitation LearningJiafei Lyu, Xiaoteng Ma, Le Wan, Runze Liu, Li Xiu 0001, Zongqing Lu. [doi]
• A Flexible Generative Model for Heterogeneous Tabular EHR with Missing ModalityHuan He, William Hao, Yuanzhe Xi, Yong Chen 0016, Bradley A. Malin, Joyce C. Ho. [doi]
• Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language ModelsShuai Fu, Xiequn Wang, Qiushi Huang, Yu Zhang 0006. [doi]
• An improved analysis of per-sample and per-update clipping in federated learningBo Li 0119, Xiaowen Jiang, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Sebastian U. Stich. [doi]
• Don't Judge by the Look: Towards Motion Coherent Video RepresentationYitian Zhang, Yue Bai, Huan Wang 0014, Yizhou Wang 0006, Yun Fu 0001. [doi]
• SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear LayerYuhta Takida, Masaaki Imaizumi, Takashi Shibuya 0001, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji. [doi]
• Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational AutoencoderZiqi Xu, Debo Cheng, Jiuyong Li, Jixue Liu, Lin Liu 0003, Kui Yu. [doi]
• Language Control Diffusion: Efficiently Scaling through Space, Time, and TasksEdwin Zhang, Yujie Lu, Shinda Huang, William Yang Wang, Amy Zhang 0001. [doi]
• Window Attention is Bugged: How not to Interpolate Position EmbeddingsDaniel Bolya, Chaitanya Ryali, Judy Hoffman, Christoph Feichtenhofer. [doi]
• Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmShurui Gui, Xiner Li, Shuiwang Ji. [doi]
• Global Optimality for Non-linear Constrained Restoration Problems via InvexitySamuel Pinilla, Jeyan Thiyagalingam. [doi]
• First-order ANIL provably learns representations despite overparametrisationOguz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion. [doi]
• MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language FeedbackXingyao Wang 0002, Zihan Wang 0001, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, Heng Ji. [doi]
• Copula Conformal prediction for multi-step time series predictionSophia Huiwen Sun, Rose Yu. [doi]
• Some Fundamental Aspects about Lipschitz Continuity of Neural NetworksGrigory Khromov, Sidak Pal Singh. [doi]
• TiC-CLIP: Continual Training of CLIP ModelsSaurabh Garg, Mehrdad Farajtabar, Hadi Pouransari, Raviteja Vemulapalli, Sachin Mehta, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri. [doi]
• From Bricks to Bridges: Product of Invariances to Enhance Latent Space CommunicationIrene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, Emanuele Rodolà. [doi]
• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion ModelsHyeonho Jeong, Jong Chul Ye. [doi]
• Pre-training LiDAR-based 3D Object Detectors through ColorizationTai-Yu Pan, Chenyang Ma, Tianle Chen, Cheng Perng Phoo, Katie Z. Luo, Yurong You, Mark Campbell 0001, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao. [doi]
• Learning dynamic representations of the functional connectome in neurobiological networksLuciano Dyballa, Samuel Lang, Alexandra Haslund-Gourley, Eviatar Yemini, Steven W. Zucker. [doi]
• MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine LearningS. Chandra Mouli, Muhammad Ashraful Alam, Bruno Ribeiro 0001. [doi]
• Perceptual Group Tokenizer: Building Perception with Iterative GroupingZhiwei Deng, Ting Chen, Yang Li. [doi]
• Robustifying State-space Models for Long Sequences via Approximate DiagonalizationAnnan Yu, Arnur Nigmetov, Dmitriy Morozov, Michael W. Mahoney, N. Benjamin Erichson. [doi]
• MuSR: Testing the Limits of Chain-of-thought with Multistep Soft ReasoningZayne Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett. [doi]
• Data Distillation Can Be Like Vodka: Distilling More Times For Better QualityXuxi Chen, Yu Yang 0007, Zhangyang Wang, Baharan Mirzasoleiman. [doi]
• BadChain: Backdoor Chain-of-Thought Prompting for Large Language ModelsZhen Xiang, Fengqing Jiang, Zidi Xiong, Bhaskar Ramasubramanian, Radha Poovendran, Bo Li 0026. [doi]
• Massive Editing for Large Language Models via Meta LearningChenmien Tan, Ge Zhang, Jie Fu. [doi]
• What Matters to You? Towards Visual Representation Alignment for Robot LearningThomas Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy. [doi]
• Are Bert Family Good Instruction Followers? A Study on Their Potential And LimitationsYisheng Xiao, Juntao Li, Zechen Sun, Zechang Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Min Zhang 0005. [doi]
• PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural NetworksLeo Zhiyuan Zhao, Xueying Ding, B. Aditya Prakash. [doi]
• EasyTPP: Towards Open Benchmarking Temporal Point ProcessesSiqiao Xue, Xiaoming Shi, Zhixuan Chu, Yan Wang 0002, Hongyan Hao, Fan Zhou 0012, Caigao Jiang, Chen Pan, James Y. Zhang, Qingsong Wen, Jun Zhou 0011, Hongyuan Mei. [doi]
• On the Limitations of Temperature Scaling for Distributions with OverlapsMuthu Chidambaram, Rong Ge 0001. [doi]
• Accelerated Sampling with Stacked Restricted Boltzmann MachinesJorge Fernandez-de-Cossío-Diaz, Clément Roussel, Simona Cocco, Rémi Monasson. [doi]
• Backdoor Federated Learning by Poisoning Backdoor-Critical LayersHaomin Zhuang, Mingxian Yu, Hao Wang 0022, Yang Hua, Jian Li 0008, Xu Yuan 0001. [doi]
• Statistical Rejection Sampling Improves Preference OptimizationTianqi Liu 0002, Yao Zhao, Rishabh Joshi, Misha Khalman, Mohammad Saleh, Peter J. Liu, Jialu Liu. [doi]
• Separating common from salient patterns with Contrastive Representation LearningRobin Louiset, Edouard Duchesnay, Antoine Grigis, Pietro Gori. [doi]
• Order-Preserving GFlowNetsYihang Chen, Lukas Mauch. [doi]
• Learning From Simplicial Data Based on Random Walks and 1D ConvolutionsFlorian Frantzen, Michael T. Schaub. [doi]
• Training Socially Aligned Language Models on Simulated Social InteractionsRuibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang, Diyi Yang, Soroush Vosoughi. [doi]
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, Weizhu Chen. [doi]
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular OptimizationXiangxin Zhou, Xiwei Cheng, Yuwei Yang, Yu Bao, Liang Wang 0001, Quanquan Gu. [doi]
• Improved statistical and computational complexity of the mean-field Langevin dynamics under structured dataAtsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu. [doi]
• Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationYangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, Danqi Chen 0001. [doi]
• Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image GenerationJaemin Cho 0001, Yushi Hu, Jason M. Baldridge, Roopal Garg, Peter Anderson, Ranjay Krishna, Mohit Bansal, Jordi Pont-Tuset, Su Wang 0001. [doi]
• Sheared LLaMA: Accelerating Language Model Pre-training via Structured PruningMengzhou Xia, Tianyu Gao, Zhiyuan Zeng, Danqi Chen 0001. [doi]
• DittoGym: Learning to Control Soft Shape-Shifting RobotsSuning Huang, Boyuan Chen 0003, Huazhe Xu, Vincent Sitzmann. [doi]
• AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic ModelsJiachun Pan, Jun Hao Liew, Vincent Y. F. Tan, Jiashi Feng, Hanshu Yan. [doi]
• Invariance-based Learning of Latent DynamicsKai Lagemann, Christian Lagemann, Sach Mukherjee. [doi]
• Sample-Efficient Quality-Diversity by Cooperative CoevolutionKe Xue 0001, Ren-Jian Wang, Pengyi Li, Dong Li, Jianye Hao, Chao Qian 0001. [doi]
• GROOT: Learning to Follow Instructions by Watching Gameplay VideosShaofei Cai, Bowei Zhang, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang. [doi]
• Universal Guidance for Diffusion ModelsArpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein. [doi]
• Exploring the Promise and Limits of Real-Time Recurrent LearningKazuki Irie, Anand Gopalakrishnan, Jürgen Schmidhuber. [doi]
• To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data ContaminationManley Roberts, Himanshu Thakur, Christine Herlihy, Colin White, Samuel Dooley. [doi]
• VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video GenerationJinxi Xiang, Ricong Huang, Jun Zhang 0018, Guanbin Li, Xiao Han 0011, Yang Wei. [doi]
• An Extensible Framework for Open Heterogeneous Collaborative PerceptionYifan Lu, Yue Hu, Yiqi Zhong, Dequan Wang, Yanfeng Wang, Siheng Chen. [doi]
• Frozen Transformers in Language Models Are Effective Visual Encoder LayersZiqi Pang, Ziyang Xie, Yunze Man, Yu-Xiong Wang. [doi]
• Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human FeedbackYu Chen, Yihan Du, Pihe Hu, Siwei Wang 0002, Desheng Wu, Longbo Huang. [doi]
• Efficient Dynamics Modeling in Interactive Environments with Koopman TheoryArnab Kumar Mondal, Siba Smarak Panigrahi, Sai Rajeswar, Kaleem Siddiqi, Siamak Ravanbakhsh. [doi]
• Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental LearningSimone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer 0001, Andrew D. Bagdanov. [doi]
• Bayesian Low-rank Adaptation for Large Language ModelsAdam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison. [doi]
• Active Retrosynthetic Planning Aware of Route QualityLuotian Yuan, Yemin Yu, Ying Wei 0001, Yongwei Wang, Zhihua Wang 0008, Fei Wu 0001. [doi]
• Fast Equilibrium of SGD in Generic SituationsZhiyuan Liu, Yi Wang, Zhiren Wang. [doi]
• Prediction Error-based Classification for Class-Incremental LearningMichal Zajac 0005, Tinne Tuytelaars, Gido M. van de Ven. [doi]
• Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text GuidanceGiung Nam, Byeongho Heo, Juho Lee 0001. [doi]
• Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image SynthesisJonghyun Lee, Hansam Cho, Young Joon Yoo, Seoung Bum Kim, Yonghyun Jeong. [doi]
• Proper Laplacian Representation LearningDiego Gomez, Michael Bowling, Marlos C. Machado. [doi]
• Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language ModelsZhaowei Zhu, Jialu Wang, Hao Cheng, Yang Liu 0018. [doi]
• Visual Data-Type Understanding does not emerge from scaling Vision-Language ModelsVishaal Udandarao, Max F. Burg, Samuel Albanie, Matthias Bethge. [doi]
• Batch normalization is sufficient for universal function approximation in CNNsRebekka Burkholz. [doi]
• From Posterior Sampling to Meaningful Diversity in Image RestorationNoa Cohen, Hila Manor, Yuval Bahat, Tomer Michaeli. [doi]
• Adaptive Sharpness-Aware Pruning for Robust Sparse NetworksAnna Bair, Hongxu Yin, Maying Shen, Pavlo Molchanov 0001, José M. Álvarez 0004. [doi]
• Score Regularized Policy Optimization through Diffusion BehaviorHuayu Chen, Cheng Lu 0011, Zhengyi Wang, Hang Su 0006, Jun Zhu 0001. [doi]
• SetCSE: Set Operations using Contrastive Learning of Sentence EmbeddingsKang Liu. [doi]
• Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural NetworksYixuan Weng, Minjun Zhu, Fei Xia, Bin Li 0083, Shizhu He, Kang Liu 0001, Jun Zhao 0001. [doi]
• Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural NetworksChangwoo Lee, Hun-Seok Kim. [doi]
• ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEsYogesh Verma, Markus Heinonen, Vikas Garg 0001. [doi]
• Towards Few-Shot Adaptation of Foundation Models via Multitask FinetuningZhuoyan Xu, Zhenmei Shi, Junyi Wei, Fangzhou Mu, Yin Li 0003, Yingyu Liang. [doi]
• A Probabilistic Framework for Modular Continual LearningLazar Valkov, Akash Srivastava, Swarat Chaudhuri, Charles Sutton. [doi]
• AnyText: Multilingual Visual Text Generation and EditingYuxiang Tuo, Wangmeng Xiang, Jun-Yan He, Yifeng Geng, Xuansong Xie. [doi]
• Prioritized Soft Q-Decomposition for Lexicographic Reinforcement LearningFinn Rietz, Erik Schaffernicht, Stefan Heinrich, Johannes A. Stork. [doi]
• PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape PredictionPeng Wang 0099, Hao Tan 0002, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, Kai Zhang 0045. [doi]
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained ModelKarsten Roth, Lukas Thede, A. Sophia Koepke, Oriol Vinyals, Olivier J. Hénaff, Zeynep Akata. [doi]
• Guess & Sketch: Language Model Guided TranspilationCeline Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni, David Brooks 0001, Stephen Chong, Gu-Yeon Wei, Alexander M. Rush. [doi]
• SparseFormer: Sparse Visual Recognition via Limited Latent TokensZiteng Gao, Zhan Tong, Limin Wang 0002, Mike Zheng Shou. [doi]
• INSIDE: LLMs' Internal States Retain the Power of Hallucination DetectionChao Chen 0026, Kai Liu, Ze Chen 0001, Yi Gu, Yue Wu, Mingyuan Tao, Zhihang Fu, Jieping Ye. [doi]
• Domain Randomization via Entropy MaximizationGabriele Tiboni, Pascal Klink, Jan Peters 0001, Tatiana Tommasi, Carlo D'Eramo, Georgia Chalvatzaki. [doi]
• Learning Grounded Action Abstractions from LanguageLionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, Jacob Andreas. [doi]
• Mitigating Emergent Robustness Degradation while Scaling Graph LearningXiangchi Yuan, Chunhui Zhang, Yijun Tian 0001, Yanfang Ye 0001, Chuxu Zhang. [doi]
• Masked Distillation Advances Self-Supervised Transformer Architecture SearchCaixia Yan, Xiaojun Chang, Zhihui Li 0001, Lina Yao 0001, Minnan Luo, Qinghua Zheng. [doi]
• Goodhart's Law in Reinforcement LearningJacek Karwowski, Oliver Hayman, Xingjian Bai, Klaus Kiendlhofer, Charlie Griffin, Joar Max Viktor Skalse. [doi]
• Fast Hyperboloid Decision Tree AlgorithmsPhilippe Chlenski, Ethan Turok, Antonio Khalil Moretti, Itsik Pe'er. [doi]
• A Neural Framework for Generalized Causal Sensitivity AnalysisDennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar. [doi]
• Idempotence and Perceptual Image CompressionTongda Xu, Ziran Zhu, Dailan He, Yanghao Li, Lina Guo, Yuanyuan Wang, Zhe Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang. [doi]
• π2vec: Policy Representation with Successor FeaturesGianluca Scarpellini, Ksenia Konyushkova, Claudio Fantacci, Thomas Paine, Yutian Chen 0001, Misha Denil. [doi]
• Recursive Generalization Transformer for Image Super-ResolutionZheng Chen 0014, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang. [doi]
• Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction TuningTed Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermis, Acyr Locatelli, Sara Hooker. [doi]
• Learning with Mixture of Prototypes for Out-of-Distribution DetectionHaodong Lu 0002, Dong Gong, Shuo Wang 0012, Jason Xue, Lina Yao 0001, Kristen Moore. [doi]
• Meta-Learning Priors Using Unrolled Proximal NetworksYilang Zhang, Georgios B. Giannakis. [doi]
• EControl: Fast Distributed Optimization with Compression and Error ControlYuan Gao, Rustem Islamov, Sebastian U. Stich. [doi]
• Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression TasksSung Moon Ko, Sumin Lee, Dae-Woong Jeong, Woohyung Lim, Sehui Han. [doi]
• Safe RLHF: Safe Reinforcement Learning from Human FeedbackJosef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang 0001, Yaodong Yang 0001. [doi]
• Decongestion by Representation: Learning to Improve Economic Welfare in MarketplacesOmer Nahum, Gali Noti, David C. Parkes, Nir Rosenfeld. [doi]
• Learning Planning Abstractions from LanguageWeiyu Liu, Geng Chen, Joy Hsu, Jiayuan Mao, Jiajun Wu 0001. [doi]
• Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete DiffusionLunjun Zhang, Yuwen Xiong, Ze Yang 0003, Sergio Casas 0002, Rui Hu 0001, Raquel Urtasun. [doi]
• A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding NetworksTommaso Salvatori, Yuhang Song 0001, Yordan Yordanov, Beren Millidge, Lei Sha, Cornelius Emde, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz. [doi]
• Towards Faithful Explanations: Boosting Rationalization with Shortcuts DiscoveryLinan Yue, Qi Liu 0003, Yichao Du, Li Wang 0014, Weibo Gao, Yanqing An. [doi]
• NEFTune: Noisy Embeddings Improve Instruction FinetuningNeel Jain, Ping-Yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein. [doi]
• Topological data analysis on noisy quantum computersIsmail Yunus Akhalwaya, Shashanka Ubaru, Kenneth L. Clarkson, Mark S. Squillante, Vishnu Jejjala, Yang-Hui He, Kugendran Naidoo, Vasileios Kalantzis, Lior Horesh. [doi]
• Efficient Planning with Latent DiffusionWenhao Li. [doi]
• Deceptive Fairness Attacks on Graphs via Meta LearningJian Kang, Yinglong Xia, Ross Maciejewski, Jiebo Luo, Hanghang Tong. [doi]
• Image Clustering via the Principle of Rate Reduction in the Age of Pretrained ModelsTianzhe Chu, Shengbang Tong, Tianjiao Ding, Xili Dai, Benjamin David Haeffele, René Vidal, Yi Ma 0001. [doi]
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEsIlan Naiman, N. Benjamin Erichson, Pu Ren, Michael W. Mahoney, Omri Azencot. [doi]
• PanoDiffusion: 360-degree Panorama Outpainting via DiffusionTianhao Wu, Chuanxia Zheng, Tat-Jen Cham. [doi]
• HypeBoy: Generative Self-Supervised Representation Learning on HypergraphsSunwoo Kim, Shinhwan Kang, Fanchen Bu, Soo Yong Lee, Jaemin Yoo, Kijung Shin. [doi]
• Learning Personalized Causally Invariant Representations for Heterogeneous Federated ClientsXueyang Tang, Song Guo 0001, Jie Zhang 0076, Jingcai Guo. [doi]
• Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh TransformerYoun-Yeol Yu, Jeongwhan Choi 0002, Woojin Cho, Kookjin Lee, Nayong Kim, Kiseok Chang, ChangSeung Woo, Ilho Kim, Seokwoo Lee, Joon-Young Yang, Sooyoung Yoon, Noseong Park. [doi]
• Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit PredictionJiatong Shi, Hirofumi Inaguma, Xutai Ma, Ilia Kulikov, Anna Y. Sun. [doi]
• Tight Rates in Supervised Outlier Transfer LearningMohammadreza M. Kalan, Samory Kpotufe. [doi]
• Analyzing and Mitigating Object Hallucination in Large Vision-Language ModelsYiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, Huaxiu Yao. [doi]
• Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate RainsWu Ran, Peirong Ma, Zhiquan He, Hao Ren 0002, Hong Lu 0001. [doi]
• Scalable Diffusion for Materials GenerationSherry Yang, KwangHwan Cho, Amil Merchant, Pieter Abbeel, Dale Schuurmans, Igor Mordatch, Ekin Dogus Cubuk. [doi]
• Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and RegressionRuntian Zhai, Bingbin Liu, Andrej Risteski, J. Zico Kolter, Pradeep Kumar Ravikumar. [doi]
• CrIBo: Self-Supervised Learning via Cross-Image Object-Level BootstrappingTim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars. [doi]
• Enabling Lanuguage Models to Implicitly Learn Self-ImprovementZiqi Wang 0003, Le Hou, Tianjian Lu, Yuexin Wu, Yunxuan Li, Hongkun Yu 0001, Heng Ji. [doi]
• PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt OptimizationXinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai 0006, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu. [doi]
• L2MAC: Large Language Model Automatic Computer for Extensive Code GenerationSamuel Holt, Max Ruiz Luyten, Mihaela van der Schaar. [doi]
• MOTOR: A Time-to-Event Foundation Model For Structured Medical RecordsEthan Steinberg, Jason Alan Fries, Yizhe Xu, Nigam Shah. [doi]
• Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?Cheng Han, Qifan Wang, Yiming Cui, Wenguan Wang, Lifu Huang, Siyuan Qi, Dongfang Liu. [doi]
• InfoCon: Concept Discovery with Generative and Discriminative InformativenessRuizhe Liu, Qian Luo, Yanchao Yang. [doi]
• Hybrid LLM: Cost-Efficient and Quality-Aware Query RoutingDujian Ding, Ankur Mallick, Chi Wang 0001, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah. [doi]
• Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement LearningMirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi. [doi]
• AlpaGasus: Training a Better Alpaca with Fewer DataLichang Chen, Shiyang Li, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou 0001, Heng Huang, Hongxia Jin. [doi]
• Effective Structural Encodings via Local Curvature ProfilesLukas Fesser, Melanie Weber 0001. [doi]
• SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3DWeiyu Li, Rui Chen, Xuelin Chen, Ping Tan. [doi]
• Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion ModelsShikun Sun, Longhui Wei, Zhicai Wang, Zixuan Wang, Junliang Xing, Jia Jia 0001, Qi Tian 0001. [doi]
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural NetworksMingqing Xiao 0002, Qingyan Meng, Zongpeng Zhang, Di He 0001, Zhouchen Lin. [doi]
• Unlocking the Power of Representations in Long-term Novelty-based ExplorationAlaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra, Oliver Groth, Michal Valko, Bilal Piot. [doi]
• Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman EquationQiang He, Tianyi Zhou 0001, Meng Fang, Setareh Maghsudi. [doi]
• SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-trainingKazem Meidani, Parshin Shojaee, Chandan K. Reddy, Amir Barati Farimani. [doi]
• Decoupled Marked Temporal Point Process using Neural Ordinary Differential EquationsYujee Song, Donghyun Lee, Rui Meng, Won Hwa Kim. [doi]
• Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface ReconstructionThanh Tung Le, Khai Nguyen, Shanlin Sun, Kun Han, Nhat Ho, Xiaohui Xie. [doi]
• Fiber Monte CarloNick Richardson, Deniz Oktay, Yaniv Ovadia, James C. Bowden, Ryan P. Adams. [doi]
• A Plug-and-Play Image Registration NetworkJunhao Hu, Weijie Gan, Zhixin Sun, Hongyu An, Ulugbek Kamilov. [doi]
• ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary PredictorTong Zhou 0002, Shaolei Ren, Xiaolin Xu. [doi]
• Decoding Natural Images from EEG for Object RecognitionYonghao Song, Bingchuan Liu, Xiang Li, Nanlin Shi, Yijun Wang 0001, Xiaorong Gao. [doi]
• Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal DataYuhui Zhang, Elaine Sui, Serena Yeung. [doi]
• Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged ObjectsChunming He, Kai Li, Yachao Zhang, Yulun Zhang, Chenyu You, Zhenhua Guo 0001, Xiu Li, Martin Danelljan, Fisher Yu 0001. [doi]
• Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean DiscrepancyShuhai Zhang, Yiliao Song, Jiahao Yang, Yuanqing Li 0001, Bo Han 0003, Mingkui Tan. [doi]
• IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion ModelsZhaoyuan Yang, Zhengyang Yu, Zhiwei Xu, Jaskirat Singh, Jing Zhang 0052, Dylan Campbell, Peter H. Tu, Richard Hartley 0001. [doi]
• Grounded Object-Centric LearningAvinash Kori, Francesco Locatello, Fabio De Sousa Ribeiro, Francesca Toni, Ben Glocker. [doi]
• Localizing and Editing Knowledge In Text-to-Image Generative ModelsSamyadeep Basu, Nanxuan Zhao, Vlad I. Morariu, Soheil Feizi, Varun Manjunatha. [doi]
• Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to InexactnessArtem Agafonov, Dmitry Kamzolov, Alexander V. Gasnikov, Ali Kavis, Kimon Antonakopoulos, Volkan Cevher, Martin Takác 0001. [doi]
• Explaining Time Series via Contrastive and Locally Sparse PerturbationsZichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang 0022, Chunlin Chen, Lunting Fan, Qingsong Wen. [doi]
• A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisDipanjyoti Paul, Arpita Chowdhury, Xinqi Xiong, Feng-Ju Chang, David Edward Carlyn, Samuel Stevens, Kaiya Provost, Anuj Karpatne, Bryan Carstens, Daniel I. Rubenstein, Charles V. Stewart, Tanya Y. Berger-Wolf, Yu Su 0001, Wei-Lun Chao. [doi]
• SOHES: Self-supervised Open-world Hierarchical Entity SegmentationShengcao Cao, Jiuxiang Gu, Jason Kuen, Hao Tan 0002, Ruiyi Zhang, Handong Zhao, Ani Nenkova, Liangyan Gui, Tong Sun, Yu-Xiong Wang. [doi]
• Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral DataRabia Gondur, Usama Bin Sikandar, Evan Schaffer, Mikio Christian Aoi, Stephen L. Keeley. [doi]
• Transport meets Variational Inference: Controlled Monte Carlo DiffusionsFrancisco Vargas 0001, Shreyas Padhy, Denis Blessing, Nikolas Nüsken. [doi]
• Conditional Instrumental Variable Regression with Representation Learning for Causal InferenceDebo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu 0003, Jixue Liu, Thuc Duy Le. [doi]
• Doubly Robust Proximal Causal Learning for Continuous TreatmentsYong Wu, Yanwei Fu 0001, Shouyan Wang, Xinwei Sun 0001. [doi]
• Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-AuthenticationJune Yong Yang, Geondo Park, Joowon Kim, Hyeongwon Jang, Eunho Yang. [doi]
• Geometry-Aware Projective Mapping for Unbounded Neural Radiance FieldsJunoh Lee, Hyunjun Jung, Jin-Hwi Park, Inhwan Bae, Hae-Gon Jeon. [doi]
• COLLIE: Systematic Construction of Constrained Text Generation TasksShunyu Yao, Howard Chen 0003, Austin W. Hanjie, Runzhe Yang, Karthik R. Narasimhan. [doi]
• Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention MapsGoro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui. [doi]
• Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label LearningShuo He 0001, Chaojie Wang, Guowu Yang, Lei Feng 0006. [doi]
• Influencer Backdoor Attack on Semantic SegmentationHaoheng Lan, Jindong Gu, Philip Torr, Hengshuang Zhao. [doi]
• TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text FieldsTianyu Huang, Yihan Zeng, Bowen Dong, Hang Xu, Songcen Xu, Rynson W. H. Lau, Wangmeng Zuo. [doi]
• LCOT: Linear Circular Optimal TransportRocio Diaz Martin, Ivan Vladimir Medri, Yikun Bai, Xinran Liu, Kangbai Yan, Gustavo K. Rohde, Soheil Kolouri. [doi]
• Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network InterferenceChencheng Cai, Xu Zhang, Edoardo M. Airoldi. [doi]
• Improved sampling via learned diffusionsLorenz Richter, Julius Berner. [doi]
• B-Coder: Value-Based Deep Reinforcement Learning for Program SynthesisZishun Yu, Yunzhe Tao, Liyu Chen, Tao Sun, Hongxia Yang. [doi]
• Incentive-Aware Federated Learning with Training-Time Model RewardsZhaoxuan Wu, Mohammad Mohammadi Amiri, Ramesh Raskar, Bryan Kian Hsiang Low. [doi]
• Entropy Coding of Unordered Data StructuresJulius Kunze, Daniel Severo 0001, Giulio Zani, Jan-Willem van de Meent, James Townsend. [doi]
• Bellman Optimal Stepsize Straightening of Flow-Matching ModelsBao Nguyen, Binh Nguyen, Viet Anh Nguyen. [doi]
• Protein-ligand binding representation learning from fine-grained interactionsShikun Feng, Minghao Li, Yinjun Jia, Wei-Ying Ma, Yanyan Lan. [doi]
• Towards a statistical theory of data selection under weak supervisionGermain Kolossov, Andrea Montanari, Pulkit Tandon. [doi]
• Reward-Free Curricula for Training Robust World ModelsMarc Rigter, Minqi Jiang, Ingmar Posner. [doi]
• From Zero to Turbulence: Generative Modeling for 3D Flow SimulationMarten Lienen, David Lüdke, Jan Hansen-Palmus, Stephan Günnemann. [doi]
• CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV PerceptionJiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash 0001, Zhuoqing Mao 0001, Chaowei Xiao. [doi]
• Inherently Interpretable Time Series Classification via Multiple Instance LearningJoseph Early, Gavin K. C. Cheung, Kurt Cutajar, Hanting Xie, Jas Kandola, Niall Twomey. [doi]
• PromptTTS 2: Describing and Generating Voices with Text PromptYichong Leng, Zhifang Guo, Kai Shen, Zeqian Ju, Xu Tan 0003, Eric Liu, Yufei Liu, Dongchao Yang, Leying Zhang, Kaitao Song, Lei He 0005, Xiangyang Li 0001, Sheng Zhao, Tao Qin 0001, Jiang Bian 0002. [doi]
• CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design EnvironmentXun Jiang, Zhuomin Chai, Yuxiang Zhao, Yibo Lin, Runsheng Wang, Ru Huang 0001. [doi]
• SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive BiasesYang Liu, Jiashun Cheng, Haihong Zhao, Tingyang Xu, Peilin Zhao, Fugee Tsung, Jia Li 0009, Yu Rong. [doi]
• Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based ApproachShaofeng Zhang, Jinfa Huang, Qiang Zhou, Zhibin Wang, Fan Wang 0019, Jiebo Luo, Junchi Yan. [doi]
• Federated Causal Discovery from Heterogeneous DataLongkang Li, Ignavier Ng, Gongxu Luo, Biwei Huang, Guangyi Chen 0002, Tongliang Liu, Bin Gu 0001, Kun Zhang 0001. [doi]
• Understanding Domain Generalization: A Noise Robustness PerspectiveRui Qiao 0006, Bryan Kian Hsiang Low. [doi]
• Teaching Arithmetic to Small TransformersNayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee 0001, Dimitris Papailiopoulos. [doi]
• Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsXue Jiang, Feng Liu 0003, Zhen Fang 0001, Hong Chen 0004, Tongliang Liu, Feng Zheng, Bo Han 0003. [doi]
• MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in ConversationsHanlei Zhang, Xin Wang, Hua Xu 0003, Qianrui Zhou, Kai Gao, Jianhua Su, Jinyue Zhao, Wenrui Li, Yanting Chen. [doi]
• Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series ForecastingYuxin Li, Wenchao Chen, Xinyue Hu, Bo Chen 0001, Baolin Sun, Mingyuan Zhou. [doi]
• Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label LearningHeeSun Bae, SeungJae Shin, Byeonghu Na, Il-Chul Moon. [doi]
• Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis DataYoung Jae Park, Minseok Seo, Doyi Kim, Hyeri Kim, Sanghoon Choi, Beomkyu Choi, Jeongwon Ryu, Sohee Son, Hae-Gon Jeon, Yeji Choi. [doi]
• Amortized Network Intervention to Steer the Excitatory Point ProcessesZitao Song, Wendi Ren, Shuang Li. [doi]
• Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial TrainingShruthi Gowda, Bahram Zonooz, Elahe Arani. [doi]
• Multiscale Positive-Unlabeled Detection of AI-Generated TextsYuchuan Tian, Hanting Chen, Xutao Wang, Zheyuan Bai, Qinghua Zhang, Ruifeng Li, Chao Xu 0006, Yunhe Wang 0001. [doi]
• DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD EstimationDriton Salihu, Adam Misik, Yuankai Wu, Constantin Patsch, Fabián Seguel, Eckehard G. Steinbach. [doi]
• Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning AbilityIvan Lee, Nan Jiang, Taylor Berg-Kirkpatrick. [doi]
• The Effectiveness of Random Forgetting for Robust GeneralizationVijaya Raghavan T. Ramkumar, Bahram Zonooz, Elahe Arani. [doi]
• Pseudo-Generalized Dynamic View Synthesis from a VideoXiaoming Zhao 0001, Alex Colburn, Fangchang Ma, Miguel Ángel Bautista 0001, Joshua M. Susskind, Alexander G. Schwing. [doi]
• ARGS: Alignment as Reward-Guided SearchMaxim Khanov, Jirayu Burapacheep, Yixuan Li. [doi]
• Making Retrieval-Augmented Language Models Robust to Irrelevant ContextOri Yoran, Tomer Wolfson, Ori Ram, Jonathan Berant. [doi]
• Training Bayesian Neural Networks with Sparse Subspace Variational InferenceJunbo Li, Zichen Miao, Qiang Qiu, Ruqi Zhang. [doi]
• Towards Understanding Factual Knowledge of Large Language ModelsXuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, Philip S. Yu, Zhijiang Guo. [doi]
• Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)Diyang Li, Charles Ling 0001, Zhiqiang Xu, Huan Xiong, Bin Gu 0001. [doi]
• Consistent4D: Consistent 360° Dynamic Object Generation from Monocular VideoYanqin Jiang, Li Zhang 0040, Jin Gao, Weiming Hu, Yao Yao. [doi]
• A Fast and Provable Algorithm for Sparse Phase RetrievalJian-Feng Cai 0001, Yu Long, Ruixue Wen, Jiaxi Ying. [doi]
• Learning from Aggregate responses: Instance Level versus Bag Level Loss FunctionsAdel Javanmard, Lin Chen, Vahab Mirrokni, Ashwinkumar Badanidiyuru, Gang Fu. [doi]
• Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse ProblemsHyungjin Chung, Suhyeon Lee 0004, Jong Chul Ye. [doi]
• Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep LearningPanagiotis Dimitrakopoulos, Giorgos Sfikas, Christophoros Nikou. [doi]
• Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion ModelsZhilin Huang, Ling Yang 0006, Xiangxin Zhou, Zhilong Zhang, Wentao Zhang, Xiawu Zheng, Jie Chen, Yu Wang, Bin Cui 0001, Wenming Yang. [doi]
• Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis RefinementLinlu Qiu, Liwei Jiang, Ximing Lu, Melanie Sclar, Valentina Pyatkin, Chandra Bhagavatula, Bailin Wang, Yoon Kim, Yejin Choi 0001, Nouha Dziri, Xiang Ren 0001. [doi]
• Out-of-Distribution Detection by Leveraging Between-Layer Transformation SmoothnessFran Jelenic, Josip Jukic, Martin Tutek, Mate Puljiz, Jan Snajder. [doi]
• LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied AgentsJaewoo Choi, Youngwoo Yoon, Hyobin Ong, Jaehong Kim 0001, Minsu Jang. [doi]
• Quality-Diversity through AI FeedbackHerbie Bradley, Andrew Dai 0001, Hannah Benita Teufel, Jenny Zhang, Koen Oostermeijer, Marco Bellagente, Jeff Clune, Kenneth O. Stanley, Grégory Schott, Joel Lehman. [doi]
• Identifying Representations for Intervention ExtrapolationSorawit Saengkyongam, Elan Rosenfeld, Pradeep Kumar Ravikumar, Niklas Pfister, Jonas Peters. [doi]
• A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and MachinesManju Garimella, Denizhan Pak, Justin N. Wood, Samantha Marie Waters Wood. [doi]
• Graph Metanetworks for Processing Diverse Neural ArchitecturesDerek Lim, Haggai Maron, Marc T. Law, Jonathan Lorraine, James Lucas. [doi]
• Statistical Perspective of Top-K Sparse Softmax Gating Mixture of ExpertsHuy Nguyen, Pedram Akbarian, Fanqi Yan, Nhat Ho. [doi]
• Large Language Models as Tool MakersTianle Cai, Xuezhi Wang 0002, Tengyu Ma 0001, Xinyun Chen, Denny Zhou. [doi]
• Bridging State and History Representations: Understanding Self-Predictive RLTianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi, Michel Ma, Clement Gehring, Aditya Mahajan, Pierre-Luc Bacon. [doi]
• FlashAttention-2: Faster Attention with Better Parallelism and Work PartitioningTri Dao. [doi]
• An Analytical Solution to Gauss-Newton Loss for Direct Image AlignmentSergei Solonets, Daniil Sinitsyn, Lukas von Stumberg, Nikita Araslanov, Daniel Cremers. [doi]
• Knowledge Distillation Based on Transformed Teacher MatchingKaixiang Zheng, En-Hui Yang. [doi]
• On the Expressivity of Objective-Specification Formalisms in Reinforcement LearningRohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm, Charlie Griffin, Joar Max Viktor Skalse. [doi]
• Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension SeparationHoyong Kim, Kangil Kim. [doi]
• MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean DiscrepancyYan Sun, Jicong Fan 0001. [doi]
• Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven ReasoningAhmed Abdulaal, Adamos Hadjivasiliou, Nina Montaña Brown, Tiantian He, Ayodeji Ijishakin, Ivana Drobnjak, Daniel C. Castro, Daniel C. Alexander. [doi]
• The Generative AI Paradox: "What It Can Create, It May Not Understand"Peter West, Ximing Lu, Nouha Dziri, Faeze Brahman, Linjie Li, Jena D. Hwang, Liwei Jiang, Jillian Fisher, Abhilasha Ravichander, Khyathi Raghavi Chandu, Benjamin Newman, Pang Wei Koh, Allyson Ettinger, Yejin Choi 0001. [doi]
• Faster Approximation of Probabilistic and Distributional Values via Least SquaresWeida Li, Yaoliang Yu. [doi]
• Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor ModelHugo Lebeau, Mohamed-El-Amine Seddik, José Henrique de Morais Goulart. [doi]
• BioBridge: Bridging Biomedical Foundation Models via Knowledge GraphsZifeng Wang 0010, Zichen Wang, Balasubramaniam Srinivasan, Vassilis N. Ioannidis, Huzefa Rangwala, Rishita Anubhai. [doi]
• Space Group Constrained Crystal GenerationRui Jiao, Wenbing Huang 0001, Yu Liu, Deli Zhao, Yang Liu 0005. [doi]
• Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMEliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, R. J. Skerry-Ryan, Michelle Tadmor Ramanovich. [doi]
• Machine Unlearning for Image-to-Image Generative ModelsGuihong Li, Hsiang Hsu, Chun-Fu Chen 0001, Radu Marculescu. [doi]
• Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in TransformersAwni Altabaa, Taylor Whittington Webb, Jonathan D. Cohen 0003, John Lafferty. [doi]
• LDReg: Local Dimensionality Regularized Self-Supervised LearningHanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E. Houle, James Bailey 0001. [doi]
• Learning to design protein-protein interactions with enhanced generalizationAnton Bushuiev, Roman Bushuiev, Petr Kouba, Anatolii Filkin, Marketa Gabrielova, Michal Gabriel, Jirí Sedlár, Tomás Pluskal, Jirí Damborský, Stanislav Mazurenko, Josef Sivic. [doi]
• A Policy Gradient Method for Confounded POMDPsMao Hong, Zhengling Qi, Yanxun Xu. [doi]
• A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language ModelsHaoran Xu, Young-Jin Kim 0001, Amr Sharaf, Hany Hassan Awadalla. [doi]
• Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep ModelsShaofei Shen 0001, Chenhao Zhang 0004, Yawen Zhao 0002, Alina Bialkowski, Tony Weitong Chen, Miao Xu. [doi]
• Coordinate-Aware Modulation for Neural FieldsJoo Chan Lee, Daniel Rho, Seungtae Nam, Jong Hwan Ko, Eunbyung Park. [doi]
• ModernTCN: A Modern Pure Convolution Structure for General Time Series AnalysisDonghao Luo, Xue Wang. [doi]
• LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation DatasetLianmin Zheng, Wei-Lin Chiang, Ying Sheng 0007, Tianle Li, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang 0001, Zhuohan Li 0001, Zi Lin, Eric P. Xing, Joseph E. Gonzalez, Ion Stoica, Hao Zhang 0108. [doi]
• Toward effective protection against diffusion-based mimicry through score distillationHaotian Xue, Chumeng Liang, Xiaoyu Wu, Yongxin Chen. [doi]
• Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution MappingEnming Liang, Minghua Chen 0001. [doi]
• Provable Offline Preference-Based Reinforcement LearningWenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun 0002. [doi]
• Local Graph Clustering with Noisy LabelsArtur Back de Luca, Kimon Fountoulakis, Shenghao Yang 0002. [doi]
• ZipIt! Merging Models from Different Tasks without TrainingGeorge Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman. [doi]
• OpenTab: Advancing Large Language Models as Open-domain Table ReasonersKezhi Kong, Jiani Zhang 0003, Zhengyuan Shen, Balasubramaniam Srinivasan, Chuan Lei, Christos Faloutsos, Huzefa Rangwala, George Karypis. [doi]
• How to Fine-Tune Vision Models with SGDAnanya Kumar, Ruoqi Shen, Sébastien Bubeck, Suriya Gunasekar. [doi]
• Locality Sensitive Sparse Encoding for Learning World Models OnlineZichen Liu, Chao Du, Wee Sun Lee, Min Lin. [doi]
• Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingZeyu Yang, Hongye Yang, Zijie Pan, Li Zhang 0040. [doi]
• Improved Active Learning via Dependent Leverage Score SamplingAtsushi Shimizu, Xiaoou Cheng, Christopher Musco, Jonathan Weare. [doi]
• Impact of Computation in Integral Reinforcement Learning for Continuous-Time ControlWenhan Cao, Wei Pan. [doi]
• Complex priors and flexible inference in recurrent circuits with dendritic nonlinearitiesBenjamin Lyo, Cristina Savin. [doi]
• Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion EstimatorsDaniel Geng, Andrew Owens. [doi]
• LitCab: Lightweight Language Model Calibration over Short- and Long-form ResponsesXin Liu, Muhammad Khalifa, Lu Wang 0008. [doi]
• Provable Robust Watermarking for AI-Generated TextXuandong Zhao, Prabhanjan Vijendra Ananth, Lei Li 0005, Yu-Xiang Wang 0003. [doi]
• Mathematical Justification of Hard Negative Mining via Isometric Approximation TheoremAlbert Xu, Jhih-Yi Hsieh, Bhaskar Vundurthy, Nithya Kemp, Eliana Cohen, Lu Li, Howie Choset. [doi]
• Group Preference Optimization: Few-Shot Alignment of Large Language ModelsSiyan Zhao, John Dang, Aditya Grover. [doi]
• Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly DetectionXiangyu Dong, Xingyi Zhang 0003, Sibo Wang 0001. [doi]
• WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu 0011, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon 0002, Graham Neubig. [doi]
• Win-Win: Training High-Resolution Vision Transformers from Two WindowsVincent Leroy 0003, Jérôme Revaud, Thomas Lucas 0002, Philippe Weinzaepfel. [doi]
• Seer: Language Instructed Video Prediction with Latent Diffusion ModelsXianfan Gu, Chuan Wen, Weirui Ye, Jiaming Song, Yang Gao 0029. [doi]
• Towards Optimal Regret in Adversarial Linear MDPs with Bandit FeedbackHaolin Liu, Chen-Yu Wei, Julian Zimmert. [doi]
• Weakly-supervised Audio Separation via Bi-modal Semantic SimilarityTanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu. [doi]
• Bounding Box Stability against Feature Dropout Reflects Detector Generalization across EnvironmentsYang Yang, Wenhai Wang, Zhe Chen, Jifeng Dai, Liang Zheng 0001. [doi]
• Deep Neural Network Initialization with Sparsity Inducing activationsIlan Price, Nicholas Daultry Ball, Adam C. Jones, Samuel C. H. Lam, Jared Tanner. [doi]
• Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training StagesGuozheng Ma, Lu Li, Sen Zhang 0006, Zixuan Liu, Zhen Wang 0030, Yixin Chen 0001, Li Shen 0008, Xueqian Wang 0001, Dacheng Tao. [doi]
• Tensor Trust: Interpretable Prompt Injection Attacks from an Online GameSam Toyer, Olivia Watkins, Ethan Adrian Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, Alan Ritter, Stuart Russell 0001. [doi]
• Towards Establishing Guaranteed Error for Learned Database OperationsSepanta Zeighami, Cyrus Shahabi. [doi]
• A Dynamical View of the Question of WhyMehdi Fatemi, Sindhu C. M. Gowda. [doi]
• Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisZhenhui Ye, Tianyun Zhong, Yi Ren 0006, Jiaqi Yang, Weichuang Li, Jiawei Huang, Ziyue Jiang 0001, Jinzheng He, Rongjie Huang, Jinglin Liu, Chen Zhang 0020, Xiang Yin 0006, Zejun Ma, Zhou Zhao. [doi]
• VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion RecognitionChenyu Liu, Xinliang Zhou, Zhengri Zhu, Liming Zhai, Ziyu Jia, Yang Liu 0003. [doi]
• Dynamic Discounted Counterfactual Regret MinimizationHang Xu, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. [doi]
• Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical AssumptionsXiu-Chuan Li, Kun Zhang 0001, Tongliang Liu. [doi]
• Closing the Curious Case of Neural Text DegenerationMatthew Finlayson, John Hewitt, Alexander Koller, Swabha Swayamdipta, Ashish Sabharwal. [doi]
• Mayfly: a Neural Data Structure for Graph Stream SummarizationYuan Feng, Yukun Cao, Hairu Wang, Xike Xie, S. Kevin Zhou. [doi]
• Non-Exchangeable Conformal Risk ControlAntónio Farinhas, Chrysoula Zerva, Dennis Ulmer, André F. T. Martins. [doi]
• Expressive Losses for Verified Robustness via Convex CombinationsAlessandro De Palma, Rudy Bunel, Krishnamurthy (Dj) Dvijotham, M. Pawan Kumar, Robert Stanforth, Alessio Lomuscio. [doi]
• TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time SeriesChenxi Sun, Hongyan Li 0002, Yaliang Li, Shenda Hong. [doi]
• Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model EvaluationShih-Ying Yeh, Yu-Guan Hsieh, Zhidong Gao, Bernard B. W. Yang, Giyeong Oh, Yanmin Gong 0001. [doi]
• Neural structure learning with stochastic differential equationsBenjie Wang, Joel Jennings, Wenbo Gong 0001. [doi]
• GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative ModelsHaitao Yang 0005, Xiangru Huang, Bo Sun, Chandrajit L. Bajaj, Qixing Huang. [doi]
• Mean Field Theory in Deep Metric LearningTakuya Furusawa. [doi]
• Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHFAnand Siththaranjan, Cassidy Laidlaw, Dylan Hadfield-Menell. [doi]
• Universal Backdoor AttacksBenjamin Schneider, Nils Lukas, Florian Kerschbaum. [doi]
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement LearningRuizhe Shi, Yuyao Liu, Yanjie Ze, Simon Shaolei Du, Huazhe Xu. [doi]
• Empirical Analysis of Model Selection for Heterogeneous Causal Effect EstimationDivyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis. [doi]
• Space and time continuous physics simulation from partial observationsSteeven Janny, Madiha Nadri, Julie Digne, Christian Wolf 0001. [doi]
• Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point RepresentationJiaxu Wang, Ziyi Zhang, Renjing Xu. [doi]
• Scalable Monotonic Neural NetworksHyunho Kim, Jong-Seok Lee. [doi]
• Tensor Programs VI: Feature Learning in Infinite Depth Neural NetworksGreg Yang, Dingli Yu, Chen Zhu, Soufiane Hayou. [doi]
• Class Probability Matching with Calibrated Networks for Label Shift AdaptionHongwei Wen, Annika Betken, Hanyuan Hang. [doi]
• Hindsight PRIORs for Reward Learning from Human PreferencesMudit Verma, Katherine Metcalf. [doi]
• Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCIWei-Bang Jiang, Li-Ming Zhao, Bao-Liang Lu. [doi]
• On the Reliability of Watermarks for Large Language ModelsJohn Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein. [doi]
• Unveiling Options with Neural Network DecompositionMahdi Alikhasi, Levi Lelis. [doi]
• Image Inpainting via Iteratively Decoupled Probabilistic ModelingWenbo Li 0002, Xin Yu 0004, Kun Zhou 0001, Yibing Song, Zhe Lin 0001. [doi]
• Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingHong Liu, Zhiyuan Li 0005, David Leo Wright Hall, Percy Liang, Tengyu Ma 0001. [doi]
• Image Translation as Diffusion Visual ProgrammersCheng Han, James Chenhao Liang, Qifan Wang, Majid Rabbani, Sohail A. Dianat, Raghuveer Rao, Ying Nian Wu, Dongfang Liu. [doi]
• Forward Learning with Top-Down Feedback: Empirical and Analytical CharacterizationRavi Francesco Srinivasan, Francesca Mignacco, Martino Sorbaro 0001, Maria Refinetti, Avi Cooper, Gabriel Kreiman, Giorgia Dellaferrera. [doi]
• Batched Low-Rank Adaptation of Foundation ModelsYeming Wen, Swarat Chaudhuri. [doi]
• Towards Codable Watermarking for Injecting Multi-Bits Information to LLMsLean Wang, Wenkai Yang, Deli Chen, Hao Zhou 0012, Yankai Lin, Fandong Meng, Jie Zhou 0016, Xu Sun 0001. [doi]
• Query-Policy Misalignment in Preference-Based Reinforcement LearningXiao Hu, Jianxiong Li, Xianyuan Zhan, Qing-Shan Jia, Ya-Qin Zhang. [doi]
• Neural SDF Flow for 3D Reconstruction of Dynamic ScenesWei Mao 0001, Richard Hartley 0001, Mathieu Salzmann, Miaomiao Liu 0001. [doi]
• Illusory Attacks: Information-theoretic detectability matters in adversarial attacksTim Franzmeyer, Stephen Marcus McAleer, João F. Henriques, Jakob Nicolaus Foerster, Philip Torr 0001, Adel Bibi, Christian Schröder de Witt. [doi]
• Realistic Evaluation of Semi-supervised Learning Algorithms in Open EnvironmentsLin-Han Jia, Lan-Zhe Guo, Zhi Zhou 0007, Yu-Feng Li. [doi]
• Adaptive Self-training Framework for Fine-grained Scene Graph GenerationKibum Kim, Kanghoon Yoon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park. [doi]
• A Study of Bayesian Neural Network Surrogates for Bayesian OptimizationYucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson. [doi]
• Class Incremental Learning via Likelihood Ratio Based Task PredictionHaowei Lin, Yijia Shao, Weinan Qian, Ningxin Pan, Yiduo Guo, Bing Liu 0001. [doi]
• ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient InferenceJason Chun Lok Li, Steven Tin Sui Luo, Le Xu, Ngai Wong. [doi]
• Image Inpainting via Tractable Steering of Diffusion ModelsAnji Liu, Mathias Niepert, Guy Van den Broeck. [doi]
• Efficiently Computing Similarities to Private DatasetsArturs Backurs, Zinan Lin 0001, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski. [doi]
• Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMsAngelica Chen, Ravid Shwartz-Ziv, KyungHyun Cho, Matthew L. Leavitt, Naomi Saphra. [doi]
• Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learningYingtao Zhang, Jialin Zhao 0004, Wenjing Wu, Alessandro Muscoloni, Carlo Vittorio Cannistraci. [doi]
• A Symmetry-Aware Exploration of Bayesian Neural Network PosteriorsOlivier Laurent 0002, Emanuel Aldea, Gianni Franchi. [doi]
• Magnitude Invariant Parametrizations Improve Hypernetwork LearningJose Javier Gonzalez Ortiz, John V. Guttag, Adrian V. Dalca. [doi]
• Making RL with Preference-based Feedback Efficient via RandomizationRunzhe Wu, Wen Sun 0002. [doi]
• Cauchy-Schwarz Divergence Information Bottleneck for RegressionShujian Yu, Xi Yu, Sigurd Løkse, Robert Jenssen, José C. Príncipe. [doi]
• Evaluating Representation Learning on the Protein Structure UniverseArian Rokkum Jamasb, Alex Morehead, Chaitanya K. Joshi, Zuobai Zhang, Kieran Didi, Simon V. Mathis, Charles Harris, Jian Tang 0005, Jianlin Cheng, Pietro Lio, Tom L. Blundell. [doi]
• Retrieval-Enhanced Contrastive Vision-Text ModelsAhmet Iscen, Mathilde Caron, Alireza Fathi, Cordelia Schmid. [doi]
• ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection AlgorithmsWilliam Yang, Byron Zhang, Olga Russakovsky. [doi]
• Language Model Decoding as Direct Metrics OptimizationHaozhe Ji, Pei Ke, Hongning Wang, Minlie Huang. [doi]
• Language Model InversionJohn X. Morris, Wenting Zhao, Justin T. Chiu, Vitaly Shmatikov, Alexander M. Rush. [doi]
• Energy-guided Entropic Neural Optimal TransportPetr Mokrov, Alexander Korotin, Alexander Kolesov, Nikita Gushchin, Evgeny Burnaev. [doi]
• Branch-GAN: Improving Text Generation with (not so) Large Language ModelsFredrik Carlsson, Johan Broberg, Erik Hillbom, Magnus Sahlgren, Joakim Nivre. [doi]
• Extending Power of Nature from Binary to Real-Valued Graph Learning in Real WorldChunshu Wu, Ruibing Song, Chuan Liu 0001, Yunan Yang, Ang Li 0006, Michael C. Huang 0001, Tong Geng. [doi]
• Mask-Based Modeling for Neural Radiance FieldsGanlin Yang, Guoqiang Wei, Zhizheng Zhang 0004, Yan Lu, Dong Liu. [doi]
• On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion modelsChristian Horvat, Jean-Pascal Pfister. [doi]
• SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action RecognitionHongwei Ren, Yue Zhou, Xiaopeng Lin, Yulong Huang, Haotian Fu, Jie Song, Bojun Cheng. [doi]
• On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural NetworksZi Wang, Bin Hu 0002, Aaron J. Havens, Alexandre Araujo, Yang Zheng, Yudong Chen, Somesh Jha. [doi]
• Benchmarking Algorithms for Federated Domain GeneralizationRuqi Bai, Saurabh Bagchi, David I. Inouye. [doi]
• Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement LearningSheng Xu, Guiliang Liu. [doi]
• Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset DistillationNoel Loo, Ramin M. Hasani, Mathias Lechner, Alexander Amini, Daniela Rus. [doi]
• D2 Pruning: Message Passing for Balancing Diversity & Difficulty in Data PruningAdyasha Maharana, Prateek Yadav, Mohit Bansal. [doi]
• Out-of-Variable Generalisation for Discriminative ModelsSiyuan Guo, Jonas Bernhard Wildberger, Bernhard Schölkopf. [doi]
• Transformer Fusion with Optimal TransportMoritz Imfeld, Jacopo Graldi, Marco Giordano, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh. [doi]
• Towards Training Without Depth Limits: Batch Normalization Without Gradient ExplosionAlexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand. [doi]
• A Discretization Framework for Robust Contextual Stochastic OptimizationRares Cristian, Georgia Perakis. [doi]
• Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian ProcessesThiziri Nait Saada, Alireza Naderi, Jared Tanner. [doi]
• Plugin estimators for selective classification with out-of-distribution detectionHarikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Sanjiv Kumar. [doi]
• RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory SketchesJiayuan Gu, Sean Kirmani, Paul Wohlhart, Yao Lu 0006, Montserrat Gonzalez Arenas, Kanishka Rao, Wenhao Yu 0003, Chuyuan Fu, Keerthana Gopalakrishnan, Zhuo Xu, Priya Sundaresan, Peng Xu, Hao Su 0001, Karol Hausman, Chelsea Finn, Quan Vuong, Ted Xiao. [doi]
• TEDDY: Trimming Edges with Degree-based Discrimination StrategyHyunjin Seo, Jihun Yun, Eunho Yang. [doi]
• FFB: A Fair Fairness Benchmark for In-Processing Group Fairness MethodsXiaotian Han, Jianfeng Chi, Yu Chen, Qifan Wang, Han Zhao 0002, Na Zou, Xia Hu 0001. [doi]
• Kalman Filter for Online Classification of Non-Stationary DataMichalis K. Titsias, Alexandre Galashov, Amal Rannen Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein. [doi]
• Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language ModelsThomas P. Zollo, Todd Morrill, Zhun Deng, Jake Snell, Toniann Pitassi, Richard S. Zemel. [doi]
• Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement LearningZican Hu, Zongzhang Zhang, Huaxiong Li, Chunlin Chen, Hongyu Ding, Zhi Wang. [doi]
• Large Language Models as Generalizable Policies for Embodied TasksAndrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure, Rin Metcalf, Walter Talbott, Natalie Mackraz, R. Devon Hjelm, Alexander T. Toshev. [doi]
• GAIA: a benchmark for General AI AssistantsGrégoire Mialon, Clémentine Fourrier, Thomas Wolf 0008, Yann LeCun, Thomas Scialom. [doi]
• Dynamic Sparse Training with Structured SparsityMike Lasby, Anna Golubeva, Utku Evci, Mihai Nica, Yani Ioannou. [doi]
• Enhancing Human-AI Collaboration Through Logic-Guided ReasoningChengzhi Cao, Yinghao Fu, Sheng Xu, Ruimao Zhang, Shuang Li 0002. [doi]
• Enhancing Instance-Level Image Classification with Set-Level LabelsRenyu Zhang, Aly A. Khan, Yuxin Chen 0001, Robert L. Grossman. [doi]
• Generative Judge for Evaluating AlignmentJunlong Li, Shichao Sun, Weizhe Yuan, Run-Ze Fan, Hai Zhao 0001, Pengfei Liu 0003. [doi]
• Implicit Neural Representations and the Algebra of Complex WaveletsT. Mitchell Roddenberry, Vishwanath Saragadam, Maarten V. De Hoop, Richard G. Baraniuk. [doi]
• Large Language Models to Enhance Bayesian OptimizationTennison Liu, Nicolás Astorga, Nabeel Seedat, Mihaela van der Schaar. [doi]
• Efficient Inverse Multiagent LearningDenizalp Goktas, Amy Greenwald, Sadie Zhao, Alec Koppel, Sumitra Ganesh. [doi]
• GTA: A Geometry-Aware Attention Mechanism for Multi-View TransformersTakeru Miyato, Bernhard Jaeger, Max Welling, Andreas Geiger 0001. [doi]
• A Simple Romance Between Multi-Exit Vision Transformer and Token ReductionDongyang Liu, Meina Kan, Shiguang Shan, Xilin Chen 0001. [doi]
• Teaching Large Language Models to Self-DebugXinyun Chen, Maxwell Lin, Nathanael Schärli, Denny Zhou. [doi]
• Debiasing Algorithm through Model AdaptationTomasz Limisiewicz, David Marecek, Tomás Musil. [doi]
• Out-Of-Domain Unlabeled Data Improves GeneralizationSeyed Amir Hossein Saberi, Amir Najafi 0002, Alireza Heidari, Mohammad Hosein Movasaghinia, Abolfazl S. Motahari, Babak H. Khalaj. [doi]
• Retrieval-based Disentangled Representation Learning with Natural Language SupervisionJiawei Zhou, Xiaoguang Li, Lifeng Shang, Xin Jiang 0002, Qun Liu 0001, Lei Chen 0002. [doi]
• On the Over-Memorization During Natural, Robust and Catastrophic OverfittingRunqi Lin, Chaojian Yu, Bo Han 0003, Tongliang Liu. [doi]
• Reasoning with Latent Diffusion in Offline Reinforcement LearningSiddarth Venkatraman, Shivesh Khaitan, Ravi Tej Akella, John Dolan, Jeff Schneider 0001, Glen Berseth. [doi]
• PRES: Toward Scalable Memory-Based Dynamic Graph Neural NetworksJunwei Su, Difan Zou, Chuan Wu 0001. [doi]
• USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance FieldsMoyang Li, Peng Wang, Lingzhe Zhao, Bangyan Liao, Peidong Liu. [doi]
• Path Choice Matters for Clear Attributions in Path MethodsBorui Zhang, Wenzhao Zheng, Jie Zhou 0001, Jiwen Lu. [doi]
• MetaGPT: Meta Programming for A Multi-Agent Collaborative FrameworkSirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber. [doi]
• Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion ModelsFei Shen, Hu Ye, Jun Zhang 0018, Cong Wang, Xiao Han 0011, Yang Wei. [doi]
• Differentially Private SGD Without Clipping Bias: An Error-Feedback ApproachXinwei Zhang, Zhiqi Bu, Steven Wu 0001, Mingyi Hong. [doi]
• WizardCoder: Empowering Code Large Language Models with Evol-InstructZiyang Luo, Can Xu, Pu Zhao 0004, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma 0004, Qingwei Lin, Daxin Jiang. [doi]
• Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule GenerationAmeya Daigavane, Song Kim, Mario Geiger, Tess E. Smidt. [doi]
• Str2Str: A Score-based Framework for Zero-shot Protein Conformation SamplingJiarui Lu, Bozitao Zhong, Zuobai Zhang, Jian Tang 0005. [doi]
• Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement LearningQiwei Di, Heyang Zhao, Jiafan He, Quanquan Gu. [doi]
• A Primal-Dual Approach to Solving Variational Inequalities with General ConstraintsTatjana Chavdarova, Tong Yang, Matteo Pagliardini, Michael I. Jordan. [doi]
• REFACTOR: Learning to Extract Theorems from ProofsJin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger Baker Grosse. [doi]
• Towards Robust Offline Reinforcement Learning under Diverse Data CorruptionRui Yang 0010, Han Zhong 0001, Jiawei Xu, Amy Zhang, Chongjie Zhang, Lei Han 0001, Tong Zhang 0001. [doi]
• Prompt Learning with Quaternion NetworksBoya Shi, Zhengqin Xu, Shuai Jia, Chao Ma 0004. [doi]
• Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningYiwei Li, Peiwen Yuan, Shaoxiong Feng, Boyuan Pan, Xinglin Wang, Bin Sun 0004, Heda Wang, Kan Li 0001. [doi]
• Efficient local linearity regularization to overcome catastrophic overfittingElías Abad-Rocamora, Fanghui Liu 0001, Grigorios Chrysos 0002, Pablo M. Olmos, Volkan Cevher. [doi]
• Discovering modular solutions that generalize compositionallySimon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger. [doi]
• Optimal Sample Complexity for Average Reward Markov Decision ProcessesShengbo Wang, José H. Blanchet, Peter W. Glynn. [doi]
• Backdoor Contrastive Learning via Bi-level Trigger OptimizationWeiyu Sun, Xinyu Zhang, Hao Lu 0009, Ying-Cong Chen, Ting Wang, Jinghui Chen, Lu Lin 0001. [doi]
• Exposing Text-Image Inconsistency Using Diffusion ModelsMingzhen Huang, Shan Jia, Zhou Zhou 0009, Yan Ju, Jialing Cai, Siwei Lyu. [doi]
• SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionXinyuan Chen, Yaohui Wang 0004, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang 0001, Dahua Lin, Yu Qiao 0001, Ziwei Liu 0002. [doi]
• On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise InjectionChaohua Shi, Kexin Huang, Lu Gan 0005, Hongqing Liu, Mingrui Zhu, Nannan Wang 0001, Xinbo Gao 0001. [doi]
• Efficient and Scalable Graph Generation through Iterative Local ExpansionAndreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin, Roger Wattenhofer. [doi]
• Overthinking the Truth: Understanding how Language Models Process False DemonstrationsDanny Halawi, Jean-Stanislas Denain, Jacob Steinhardt. [doi]
• At Which Training Stage Does Code Data Help LLMs Reasoning?Yingwei Ma, Yue Liu, Yue Yu 0001, Yuanliang Zhang, Yu Jiang 0001, Changjian Wang, Shanshan Li 0001. [doi]
• FedLoGe: Joint Local and Generic Federated Learning under Long-tailed DataZikai Xiao, Zihan Chen, Liyinglan Liu, Yang Feng, Joey Tianyi Zhou, Jian Wu 0001, Wanlu Liu, Howard Hao Yang, Zuozhu Liu. [doi]
• Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human FeedbackYifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu 0002, Zhixin Feng, Kai Zhao, Yan Zheng 0002. [doi]
• Removing Biases from Molecular Representations via Information MaximizationChenyu Wang, Sharut Gupta, Caroline Uhler, Tommi S. Jaakkola. [doi]
• Layer-wise linear mode connectivityLinara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi. [doi]
• An Emulator for Fine-tuning Large Language Models using Small Language ModelsEric Mitchell, Rafael Rafailov, Archit Sharma, Chelsea Finn, Christopher D. Manning. [doi]
• Algorithms for Caching and MTS with reduced number of predictionsKarim Abdel Sadek, Marek Eliás 0001. [doi]
• Reinforcement Symbolic Regression MachineYilong Xu, Yang Liu, Hao Sun 0002. [doi]
• Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networksDavid A. R. Robin, Kevin Scaman, Marc Lelarge. [doi]
• LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language ModelsAhmad Faiz, Sotaro Kaneda, Ruhan Wang, Rita Chukwunyere Osi, Prateek Sharma, Fan Chen 0001, Lei Jiang 0001. [doi]
• "What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data SelectionAnshuman Chhabra, Peizhao Li, Prasant Mohapatra, Hongfu Liu 0001. [doi]
• Compressing LLMs: The Truth is Rarely Pure and Never SimpleAjay Kumar Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, Yinfei Yang. [doi]
• Stable Anisotropic RegularizationWilliam Rudman, Carsten Eickhoff. [doi]
• Replay across Experiments: A Natural Extension of Off-Policy RLDhruva Tirumala, Thomas Lampe, José Enrique Chen, Tuomas Haarnoja, Sandy H. Huang, Guy Lever, Ben Moran, Tim Hertweck, Leonard Hasenclever, Martin A. Riedmiller, Nicolas Heess, Markus Wulfmeier. [doi]
• Counterfactual Density Estimation using Kernel Stein DiscrepanciesDiego Martinez-Taboada, Edward Kennedy. [doi]
• Fantastic Generalization Measures are Nowhere to be FoundMichael Gastpar, Ido Nachum, Jonathan Shafer, Thomas Weinberger. [doi]
• The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical ImagesNicholas Konz, Maciej A. Mazurowski. [doi]
• Designing Skill-Compatible AI: Methodologies and Frameworks in ChessKarim Hamade, Reid McIlroy-Young, Siddhartha Sen 0001, Jon M. Kleinberg, Ashton Anderson. [doi]
• NECO: NEural Collapse Based Out-of-distribution detectionMouïn Ben Ammar, Nacim Belkhir, Sebastian Popescu, Antoine Manzanera, Gianni Franchi. [doi]
• Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness ConstantsPeter Richtárik, Elnur Gasanov, Konstantin Burlachenko. [doi]
• Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic InterpretationsXinyue Xu, Yi Qin, Lu Mi, Hao Wang, Xiaomeng Li. [doi]
• Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop ControlNeehal Tumma, Mathias Lechner, Noel Loo, Ramin M. Hasani, Daniela Rus. [doi]
• L2P-MIP: Learning to Presolve for Mixed Integer ProgrammingChang Liu 0021, Zhichen Dong, Haobo Ma, Weilin Luo, Xijun Li, Bowen Pang, Jia Zeng, Junchi Yan. [doi]
• Federated Q-Learning: Linear Regret Speedup with Low Communication CostZhong Zheng, Fengyu Gao, Lingzhou Xue, Jing Yang. [doi]
• Efficient Multi-agent Reinforcement Learning by PlanningQihan Liu, Jianing Ye, Xiaoteng Ma, Jun Yang 0028, Bin Liang 0001, Chongjie Zhang. [doi]
• Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A BenchmarkYehui Tang, Hao Xiong 0003, Nianzu Yang, Tailong Xiao, Junchi Yan. [doi]
• Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level VisionHaoning Wu 0001, Zicheng Zhang, Erli Zhang 0001, Chaofeng Chen, Liang Liao, Annan Wang, Chunyi Li, Wenxiu Sun, Qiong Yan, Guangtao Zhai, Weisi Lin. [doi]
• What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction TuningWei Liu 0131, Weihao Zeng, Keqing He 0001, Yong Jiang 0001, Junxian He. [doi]
• ReLoRA: High-Rank Training Through Low-Rank UpdatesVladislav Lialin, Sherin Muckatira, Namrata Shivagunde, Anna Rumshisky. [doi]
• LOQA: Learning with Opponent Q-Learning AwarenessMilad Aghajohari, Juan Agustin Duque, Tim Cooijmans, Aaron C. Courville. [doi]
• Domain constraints improve risk prediction when outcome data is missingSidhika Balachandar, Nikhil Garg 0001, Emma Pierson. [doi]
• MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View StereoChenjie Cao, Xinlin Ren, Yanwei Fu 0001. [doi]
• Diving Segmentation Model into PixelsChen Gan, Zihao Yin, Kelei He, Yang Gao 0001, Junfeng Zhang. [doi]
• Maximum Entropy Model Correction in Reinforcement LearningAmin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh, Amir Massoud Farahmand. [doi]
• Effective Data Augmentation With Diffusion ModelsBrandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov. [doi]
• LRM: Large Reconstruction Model for Single Image to 3DYicong Hong, Kai Zhang 0045, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, Hao Tan 0002. [doi]
• Coeditor: Leveraging Repo-level Diffs for Code Auto-editingJiayi Wei, Greg Durrett, Isil Dillig. [doi]
• CLAP: Collaborative Adaptation for Patchwork LearningSen Cui, Abudukelimu Wuerkaixi, Weishen Pan, Jian Liang, Lei Fang, Changshui Zhang, Fei Wang 0001. [doi]
• Counting Graph Substructures with Graph Neural NetworksCharilaos I. Kanatsoulis, Alejandro Ribeiro. [doi]
• Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent SpaceHengrui Zhang, Jiani Zhang 0003, Zhengyuan Shen, Balasubramaniam Srinivasan, Xiao Qin, Christos Faloutsos, Huzefa Rangwala, George Karypis. [doi]
• Enhancing Group Fairness in Online Settings Using Oblique Decision ForestsSomnath Basu Roy Chowdhury, Nicholas Monath, Ahmad Beirami, Rahul Kidambi, Kumar Avinava Dubey, Amr Ahmed 0001, Snigdha Chaturvedi. [doi]
• A Benchmark for Learning to Translate a New Language from One Grammar BookGarrett Tanzer, Mirac Suzgun, Eline Visser, Dan Jurafsky, Luke Melas-Kyriazi. [doi]
• Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature SpaceYufei Gu, Xiaoqing Zheng, Tomaso Aste. [doi]
• Smooth ECE: Principled Reliability Diagrams via Kernel SmoothingJaroslaw Blasiok, Preetum Nakkiran. [doi]
• TRAM: Bridging Trust Regions and Sharpness Aware MinimizationTom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng 0009. [doi]
• Faithful Rule Extraction for Differentiable Rule Learning ModelsXiaxia Wang 0001, David Jaime Tena Cucala, Bernardo Cuenca Grau, Ian Horrocks 0001. [doi]
• Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured GraphsMilan Papez, Martin Rektoris, Václav Smídl, Tomás Pevný. [doi]
• On the Role of General Function Approximation in Offline Reinforcement LearningChenjie Mao, Qiaosheng Zhang, Zhen Wang 0004, Xuelong Li. [doi]
• DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context LearningJing Xiong, Zixuan Li, Chuanyang Zheng, Zhijiang Guo, Yichun Yin, Enze Xie, Zhicheng Yang, Qingxing Cao, Haiming Wang, Xiongwei Han, Jing Tang, Chengming Li, Xiaodan Liang. [doi]
• VCR-Graphormer: A Mini-batch Graph Transformer via Virtual ConnectionsDongqi Fu, Zhigang Hua, Yan Xie, Jin Fang, Si Zhang, Kaan Sancak, Hao Wu, Andrey Malevich, Jingrui He, Bo Long. [doi]
• Unveiling the Pitfalls of Knowledge Editing for Large Language ModelsZhoubo Li, Ningyu Zhang 0001, Yunzhi Yao, Mengru Wang, Xi Chen 0003, Huajun Chen. [doi]
• Parsing neural dynamics with infinite recurrent switching linear dynamical systemsVictor Geadah, International Brain Laboratory, Jonathan W. Pillow. [doi]
• The optimality of kernel classifiers in Sobolev spaceJianfa Lai, Zhifan Li, Dongming Huang, Qian Lin. [doi]
• LILO: Learning Interpretable Libraries by Compressing and Documenting CodeGabriel Grand, Lionel Wong, Matthew Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas. [doi]
• Turning large language models into cognitive modelsMarcel Binz, Eric Schulz. [doi]
• Mixture of LoRA ExpertsXun Wu, Shaohan Huang, Furu Wei. [doi]
• ConR: Contrastive Regularizer for Deep Imbalanced RegressionMahsa Keramati, Lili Meng, R. David Evans. [doi]
• PeFLL: Personalized Federated Learning by Learning to LearnJonathan Scott, Hossein Zakerinia, Christoph H. Lampert. [doi]
• Neural Field Classifiers via Target Encoding and Classification LossXindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun. [doi]
• Graph Lottery Ticket AutomatedGuibin Zhang, Kun Wang, Wei Huang 0034, Yanwei Yue, Yang Wang 0015, Roger Zimmermann, Aojun Zhou, Dawei Cheng, Jin Zeng, Yuxuan Liang. [doi]
• Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language ModelsShangbin Feng, Weijia Shi, Yuyang Bai, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov. [doi]
• Faithful Vision-Language Interpretation via Concept Bottleneck ModelsSongning Lai, Lijie Hu, Junxiao Wang, Laure Berti-Équille, Di Wang 0015. [doi]
• Deep Reinforcement Learning for Modelling Protein ComplexesZiqi Gao, Tao Feng, Jiaxuan You, Chenyi Zi, Yan Zhou, Chen Zhang, Jia Li. [doi]
• ReMasker: Imputing Tabular Data with Masked AutoencodingTianyu Du, Luca Melis, Ting Wang 0006. [doi]
• Retrieval meets Long Context Large Language ModelsPeng Xu 0008, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu 0001, Zihan Liu 0001, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, Bryan Catanzaro. [doi]
• Poly-View Contrastive LearningAmitis Shidani, R. Devon Hjelm, Jason Ramapuram, Russell Webb, Eeshan Gunesh Dhekane, Dan Busbridge. [doi]
• Understanding Certified Training with Interval Bound PropagationYuhao Mao, Mark Niklas Müller, Marc Fischer 0002, Martin T. Vechev. [doi]
• Enhancing High-Resolution 3D Generation through Pixel-wise Gradient ClippingZijie Pan, Jiachen Lu, Xiatian Zhu, Li Zhang 0040. [doi]
• FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware SchedulerZilinghan Li, Pranshu Chaturvedi, Shilan He, Han Chen, Gagandeep Singh, Volodymyr V. Kindratenko, Eliu A. Huerta, Kibaek Kim, Ravi K. Madduri. [doi]
• Annealing Self-Distillation Rectification Improves Adversarial TrainingYu-Yu Wu, Hung-Jui Wang, Shang-Tse Chen. [doi]
• Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised LearningJohnathan Xie, Yoonho Lee 0001, Annie S. Chen, Chelsea Finn. [doi]
• Large Language Models Are Not Robust Multiple Choice SelectorsChujie Zheng, Hao Zhou 0012, Fandong Meng, Jie Zhou 0016, Minlie Huang. [doi]
• Brusleattack: a Query-Efficient Score- based Black-Box Sparse Adversarial AttackViet Quoc Vo, Ehsan Abbasnejad, Damith Ranasinghe. [doi]
• SEPT: Towards Efficient Scene Representation Learning for Motion PredictionZhiqian Lan, Yuxuan Jiang 0011, Yao Mu, Chen Chen 0068, Shengbo Eben Li. [doi]
• Towards Aligned Layout Generation via Diffusion Model with Aesthetic ConstraintsJian Chen, Ruiyi Zhang, Yufan Zhou, Changyou Chen. [doi]
• Personalize Segment Anything Model with One ShotRenrui Zhang, Zhengkai Jiang 0001, Ziyu Guo, Shilin Yan, Junting Pan, Hao Dong 0003, Yu Qiao 0001, Peng Gao 0007, Hongsheng Li 0001. [doi]
• In-context Autoencoder for Context Compression in a Large Language ModelTao Ge 0001, Jing Hu 0001, Lei Wang, Xun Wang, Si-Qing Chen, Furu Wei. [doi]
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and GenerationYi Wang, Yinan He, Yizhuo Li 0001, Kunchang Li 0002, Jiashuo Yu, Xin Ma, Xinhao Li, Guo Chen 0006, Xinyuan Chen, Yaohui Wang 0004, Ping Luo 0002, Ziwei Liu 0002, Yali Wang 0001, Limin Wang 0002, Yu Qiao 0001. [doi]
• On the Foundations of Shortcut LearningKatherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer. [doi]
• Graph Neural Networks for Learning Equivariant Representations of Neural NetworksMiltiadis Kofinas, Boris Knyazev, Yan Zhang, Yunlu Chen, Gertjan J. Burghouts, Efstratios Gavves, Cees G. M. Snoek, David W. Zhang. [doi]
• GraphPulse: Topological representations for temporal graph property predictionKiarash Shamsi, Farimah Poursafaei, Shenyang Huang, Tran Gia Bao Ngo, Baris Coskunuzer, Cuneyt Gurcan Akcora. [doi]
• UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal ModelingHaoyu Lu, Yuqi Huo, Guoxing Yang, Zhiwu Lu 0001, Wei Zhan, Masayoshi Tomizuka, Mingyu Ding. [doi]
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou 0016, Mark Gerstein, Dahai Li, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• Dynamics-Informed Protein Design with Structure ConditioningUrszula Julia Komorowska, Simon V. Mathis, Kieran Didi, Francisco Vargas 0001, Pietro Lio, Mateja Jamnik. [doi]
• TopoMLP: A Simple yet Strong Pipeline for Driving Topology ReasoningDongming Wu, Jiahao Chang, Fan Jia, Yingfei Liu, Tiancai Wang, Jianbing Shen. [doi]
• Demystifying CLIP DataHu Xu 0001, Saining Xie, Xiaoqing Ellen Tan, Po-Yao Huang 0001, Russell Howes, Vasu Sharma, Shang-wen Li 0001, Gargi Ghosh, Luke Zettlemoyer, Christoph Feichtenhofer. [doi]
• Time Travel in LLMs: Tracing Data Contamination in Large Language ModelsShahriar Golchin, Mihai Surdeanu. [doi]
• The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open WorldWeiyun Wang, Min Shi 0004, Qingyun Li, Wenhai Wang, Zhenhang Huang, Linjie Xing, Zhe Chen, Hao Li 0069, Xizhou Zhu, Zhiguo Cao 0001, Yushi Chen, Tong Lu, Jifeng Dai, Yu Qiao 0001. [doi]
• Can Large Language Models Infer Causation from Correlation?Zhijing Jin, Jiarui Liu 0004, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona T. Diab, Bernhard Schölkopf. [doi]
• Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal GraphsAnson Bastos, Kuldeep Singh 0001, Abhishek Nadgeri, Manish Singh 0002, Toyotaro Suzumura. [doi]
• Frequency-Aware Transformer for Learned Image CompressionHan Li, Shaohui Li, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong. [doi]
• ACRF: Compressing Explicit Neural Radiance Fields via Attribute CompressionGuangchi Fang, Qingyong Hu, Longguang Wang, Yulan Guo. [doi]
• Robustness of AI-Image Detectors: Fundamental Limits and Practical AttacksMehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang 0002, Soheil Feizi. [doi]
• Input-gradient space particle inference for neural network ensemblesTrung Q. Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski. [doi]
• Transferring Labels to Solve Annotation Mismatches Across Object Detection DatasetsYuan-Hong Liao, David Acuna, Rafid Mahmood, James Lucas, Viraj Prabhu, Sanja Fidler. [doi]
• On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMsJen-tse Huang 0001, Wenxuan Wang, Eric John Li, Man Ho Lam, Shujie Ren, Youliang Yuan, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu. [doi]
• Scaling physics-informed hard constraints with mixture-of-expertsNithin Chalapathi, Yiheng Du, Aditi S. Krishnapriyan. [doi]
• What's In My Big Data?Yanai Elazar, Akshita Bhagia, Ian Magnusson, Abhilasha Ravichander, Dustin Schwenk, Alane Suhr, Evan Pete Walsh, Dirk Groeneveld, Luca Soldaini, Sameer Singh 0001, Hannaneh Hajishirzi, Noah A. Smith, Jesse Dodge. [doi]
• Divide and not forget: Ensemble of selectively trained experts in Continual LearningGrzegorz Rypesc, Sebastian Cygert, Valeriya Khan, Tomasz Trzcinski, Bartosz Zielinski 0001, Bartlomiej Twardowski. [doi]
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence ConstraintsChaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, Yuxin Chen. [doi]
• Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything ModelZihan Zhong, ZhiQiang Tang, Tong He, Haoyang Fang, Chun Yuan. [doi]
• A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical ModelZecheng Hao, Xinyu Shi, Zihan Huang, Tong Bu, Zhaofei Yu, Tiejun Huang 0001. [doi]
• LLM Augmented LLMs: Expanding Capabilities through CompositionRachit Bansal, Bidisha Samanta, Siddharth Dalmia, Nitish Gupta, Sriram Ganapathy, Abhishek Bapna, Prateek Jain, Partha Talukdar. [doi]
• Effective and Efficient Federated Tree Learning on Hybrid DataQinbin Li, Chulin Xie, Xiaojun Xu, Xiaoyuan Liu, Ce Zhang 0001, Bo Li 0026, Bingsheng He, Dawn Song. [doi]
• A Framework for Inference Inspired by Human Memory MechanismsXiangyu Zeng, Jie Lin, Piao Hu, Ruizheng Huang, Zhicheng Zhang. [doi]
• GenSim: Generating Robotic Simulation Tasks via Large Language ModelsLirui Wang, Yiyang Ling, Zhecheng Yuan, Mohit Shridhar, Chen Bao, Yuzhe Qin, Bailin Wang, Huazhe Xu, Xiaolong Wang 0004. [doi]
• Circumventing Concept Erasure Methods For Text-To-Image Generative ModelsMinh Pham 0005, Kelly O. Marshall, Niv Cohen, Govind Mittal, Chinmay Hegde. [doi]
• On the Vulnerability of Adversarially Trained Models Against Two-faced AttacksShengjie Zhou, Lue Tao, Yuzhou Cao, Tao Xiang 0001, Bo An 0001, Lei Feng 0006. [doi]
• H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface FieldsMinyoung Park, Mirae Do, Yeonjae Shin, Jaeseok Yoo, Jongkwang Hong, Joongrock Kim, Chul Lee. [doi]
• Finetuning Text-to-Image Diffusion Models for FairnessXudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan S. Kankanhalli. [doi]
• Dynamic Neural Response TuningTian Qiu, Wenxiang Xu, Lin Chen, Linyun Zhou, Zunlei Feng, Mingli Song. [doi]
• A path-norm toolkit for modern networks: consequences, promises and challengesAntoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval. [doi]
• An LLM can Fool Itself: A Prompt-Based Adversarial AttackXilie Xu, Keyi Kong, Ning Liu, LiZhen Cui, Di Wang 0015, Jingfeng Zhang, Mohan S. Kankanhalli. [doi]
• Orbit-Equivariant Graph Neural NetworksMatthew Morris, Bernardo Cuenca Grau, Ian Horrocks 0001. [doi]
• BarLeRIa: An Efficient Tuning Framework for Referring Image SegmentationYaoming Wang, Jin Li, Xiaopeng Zhang 0008, Bowen Shi, Chenglin Li, Wenrui Dai, Hongkai Xiong, Qi Tian 0001. [doi]
• Dual-Encoders for Extreme Multi-label ClassificationNilesh Gupta, Devvrit, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain 0002, Inderjit S. Dhillon. [doi]
• Multimodal Web Navigation with Instruction-Finetuned Foundation ModelsHiroki Furuta, Kuang-Huei Lee, Ofir Nachum, Yutaka Matsuo, Aleksandra Faust, Shixiang Shane Gu, Izzeddin Gur. [doi]
• Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image ClassificationAditya Chattopadhyay, Kwan Ho Ryan Chan, René Vidal. [doi]
• LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking AttacksJianlang Chen, Xuhong Ren, Qing Guo 0005, Felix Juefei-Xu, Di Lin 0002, Wei Feng 0005, Lei Ma 0003, Jianjun Zhao 0001. [doi]
• PBADet: A One-Stage Anchor-Free Approach for Part-Body AssociationZhongpai Gao, Huayi Zhou 0001, Abhishek Sharma, Meng Zheng, Benjamin Planche, Terrence Chen, Ziyan Wu. [doi]
• Maximum Entropy Heterogeneous-Agent Reinforcement LearningJiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu, Qiang Fu, Xiaojun Chang, Yaodong Yang 0001. [doi]
• VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning BenchmarksZhaomin Wu, Junyi Hou, Bingsheng He. [doi]
• On Adversarial Training without Perturbing all ExamplesMax Maria Losch, Mohamed Omran, David Stutz, Mario Fritz, Bernt Schiele. [doi]
• Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder ModelHanni Cheng, Ya Cong, Weihao Jiang, Shiliang Pu. [doi]
• Learning to Embed Time Series Patches IndependentlySeunghan Lee, Taeyoung Park, Kibok Lee. [doi]
• Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor DataShikai Fang, Xin Yu 0003, Zheng Wang 0042, Shibo Li, Mike Kirby, Shandian Zhe. [doi]
• Image2Sentence based Asymmetrical Zero-shot Composed Image RetrievalYongchao Du, Min Wang 0019, Wengang Zhou, Shuping Hui, Houqiang Li. [doi]
• PhyloGFN: Phylogenetic inference with generative flow networksMing Yang Zhou, Zichao Yan, Elliot Layne, Nikolay Malkin, Dinghuai Zhang, Moksh Jain, Mathieu Blanchette, Yoshua Bengio. [doi]
• Guaranteed Approximation Bounds for Mixed-Precision Neural OperatorsRenbo Tu, Colin White, Jean Kossaifi, Boris Bonev, Gennady Pekhimenko, Kamyar Azizzadenesheli, Anima Anandkumar. [doi]
• FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action RecognitionXiaohu Huang, Hao Zhou, Kun Yao, Kai Han. [doi]
• DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbationsZhihe Yang, Yunjian Xu. [doi]
• GOAt: Explaining Graph Neural Networks via Graph Output AttributionShengyao Lu, Keith G. Mills, Jiao He, Bang Liu, Di Niu. [doi]
• Crystalformer: Infinitely Connected Attention for Periodic Structure EncodingTatsunori Taniai, Ryo Igarashi 0002, Yuta Suzuki, Naoya Chiba, Kotaro Saito, Yoshitaka Ushiku, Kanta Ono. [doi]
• LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language ModelsGunho Park, Baeseong Park, Minsub Kim, Sungjae Lee, Jeonghoon Kim, Beomseok Kwon, Se Jung Kwon, Byeongwook Kim, Youngjoo Lee, Dongsoo Lee. [doi]
• UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning ModelsHyunju Kang, Geonhee Han, Hogun Park. [doi]
• Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series DataYongKyung Oh, Dongyoung Lim, Sungil Kim. [doi]
• Multi-task Learning with 3D-Aware RegularizationWei-Hong Li, Steven McDonagh, Ales Leonardis, Hakan Bilen. [doi]
• A Benchmark Study on CalibrationLinwei Tao, Younan Zhu, Haolan Guo, Minjing Dong, Chang Xu 0002. [doi]
• Multi-Scale Representations by Varying Window Attention for Semantic SegmentationHaotian Yan, Ming Wu 0001, Chuang Zhang. [doi]
• Reward Design for Justifiable Sequential Decision-MakingAleksa Sukovic, Goran Radanovic. [doi]
• LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and GenerationSuhyeon Lee 0004, Won Jun Kim, Jinho Chang, Jong Chul Ye. [doi]
• LEAP: Liberate Sparse-View 3D Modeling from Camera PosesHanwen Jiang, Zhenyu Jiang 0002, Yue Zhao, Qixing Huang. [doi]
• Don't Trust: Verify - Grounding LLM Quantitative Reasoning with AutoformalizationJin Peng Zhou, Charles Staats, Wenda Li, Christian Szegedy, Kilian Q. Weinberger, Yuhuai Wu. [doi]
• Spatio-Temporal Approximation: A Training-Free SNN Conversion for TransformersYizhou Jiang, Kunlin Hu, Tianren Zhang, Haichuan Gao, Yuqian Liu, Ying Fang, Feng Chen 0007. [doi]
• Towards Seamless Adaptation of Pre-trained Models for Visual Place RecognitionFeng Lu, Lijun Zhang, Xiangyuan Lan, Shuting Dong, Yaowei Wang, Chun Yuan. [doi]
• DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural NetworksMaryam Toloubidokhti, Yubo Ye, Ryan Missel, Xiajun Jiang, Nilesh Kumar, Ruby Shrestha, Linwei Wang. [doi]
• Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete FunctionsSatwik Bhattamishra, Arkil Patel, Phil Blunsom, Varun Kanade. [doi]
• Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction ConsistencySoumyadeep Pal, Yuguang Yao, Ren Wang 0008, Bingquan Shen, Sijia Liu 0001. [doi]
• Controlling Vision-Language Models for Multi-Task Image RestorationZiwei Luo, Fredrik K. Gustafsson, Zheng Zhao 0004, Jens Sjölund, Thomas B. Schön. [doi]
• Private Zeroth-Order Nonsmooth Nonconvex OptimizationQinzi Zhang, Hoang Tran, Ashok Cutkosky. [doi]
• The False Promise of Imitating Proprietary Language ModelsArnav Gudibande, Eric Wallace, Charlie Snell, Xinyang Geng, Hao Liu 0055, Pieter Abbeel, Sergey Levine, Dawn Song. [doi]
• Compositional Generative Inverse DesignTailin Wu, Takashi Maruyama, Long Wei, Tao Zhang, Yilun Du, Gianluca Iaccarino, Jure Leskovec. [doi]
• When Semantic Segmentation Meets Frequency AliasingLinwei Chen, Lin Gu, Ying Fu 0001. [doi]
• Querying Easily Flip-flopped Samples for Deep Active LearningSeong Jin Cho, GwangSu Kim, Junghyun Lee, Jinwoo Shin, Chang D. Yoo. [doi]
• Adversarial Supervision Makes Layout-to-Image Diffusion Models ThriveYumeng Li, Margret Keuper, Dan Zhang 0003, Anna Khoreva. [doi]
• Principled Architecture-aware Scaling of HyperparametersWuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin. [doi]
• How Does Unlabeled Data Provably Help Out-of-Distribution Detection?Xuefeng Du, Zhen Fang 0001, Ilias Diakonikolas, Yixuan Li 0001. [doi]
• Conformal Language ModelingVictor Quach, Adam Fisch, Tal Schuster, Adam Yala, Jae Ho Sohn, Tommi S. Jaakkola, Regina Barzilay. [doi]
• A Versatile Causal Discovery Framework to Allow Causally-Related Hidden VariablesXinshuai Dong, Biwei Huang, Ignavier Ng, Xiangchen Song, Yujia Zheng, Songyao Jin, Roberto Legaspi, Peter Spirtes, Kun Zhang 0001. [doi]
• Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language ModelsZijun Wu, Yongkang Wu, Lili Mou. [doi]
• ControlVideo: Training-free Controllable Text-to-video GenerationYabo Zhang, Yuxiang Wei 0001, Dongsheng Jiang, Xiaopeng Zhang 0008, Wangmeng Zuo, Qi Tian 0001. [doi]
• The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context LearningTian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite. [doi]
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationDinghuai Zhang, Ricky T. Q. Chen, Cheng-Hao Liu, Aaron C. Courville, Yoshua Bengio. [doi]
• FLD: Fourier Latent Dynamics for Structured Motion Representation and LearningChenhao Li, Elijah Stanger-Jones, Steve Heim, Sangbae Kim. [doi]
• WildChat: 1M ChatGPT Interaction Logs in the WildWenting Zhao, Xiang Ren 0001, Jack Hessel, Claire Cardie, Yejin Choi 0001, Yuntian Deng. [doi]
• An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language ModelsHaochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr 0001. [doi]
• Simplifying Transformer BlocksBobby He, Thomas Hofmann. [doi]
• When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning MethodBiao Zhang 0006, Zhongtao Liu, Colin Cherry, Orhan Firat. [doi]
• Intriguing Properties of Data Attribution on Diffusion ModelsXiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang 0001, Min Lin. [doi]
• Unknown Domain Inconsistency Minimization for Domain GeneralizationSeungJae Shin, HeeSun Bae, Byeonghu Na, Yoon-Yeong Kim, Il-Chul Moon. [doi]
• MOFI: Learning Image Representations from Noisy Entity Annotated ImagesWentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathon Shlens, Xianzhi Du, Yinfei Yang. [doi]
• Learning Performance-Improving Code EditsAlexander Shypula, Aman Madaan, Yimeng Zeng, Uri Alon 0002, Jacob R. Gardner, Yiming Yang, Milad Hashemi, Graham Neubig, Parthasarathy Ranganathan, Osbert Bastani, Amir Yazdanbakhsh. [doi]
• #InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language ModelsKeming Lu, Hongyi Yuan, Zheng Yuan 0002, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, Jingren Zhou. [doi]
• DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt EngineerJunyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li 0026, Zhangyang Wang. [doi]
• Expressivity of ReLU-Networks under Convex RelaxationsMaximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev. [doi]
• SyncDreamer: Generating Multiview-consistent Images from a Single-view ImageYuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, Wenping Wang. [doi]
• CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual GroundingEslam Mohamed Bakr, Mohamed Ayman, Mahmoud Ahmed, Habib Slim, Mohamed Elhoseiny. [doi]
• Vision-by-Language for Training-Free Compositional Image RetrievalShyamgopal Karthik, Karsten Roth, Massimiliano Mancini, Zeynep Akata. [doi]
• Generative Sliced MMD Flows with Riesz KernelsJohannes Hertrich, Christian Wald, Fabian Altekrüger, Paul Hagemann. [doi]
• Equivariant Scalar Fields for Molecular Docking with Fast Fourier TransformsBowen Jing, Tommi S. Jaakkola, Bonnie Berger. [doi]
• BENO: Boundary-embedded Neural Operators for Elliptic PDEsHaixin Wang, Jiaxin Li, Anubhav Dwivedi, Kentaro Hara, Tailin Wu. [doi]
• Automatic Functional Differentiation in JAXMin Lin. [doi]
• Unveiling and Manipulating Prompt Influence in Large Language ModelsZijian Feng, Hanzhang Zhou, Zixiao Zhu, Junlang Qian, Kezhi Mao. [doi]
• Looped Transformers are Better at Learning Learning AlgorithmsLiu Yang, Kangwook Lee 0001, Robert D. Nowak, Dimitris Papailiopoulos. [doi]
• On Double Descent in Reinforcement Learning with LSTD and Random FeaturesDavid Brellmann, Eloïse Berthier, David Filliat, Goran Frehse. [doi]
• Balancing Act: Constraining Disparate Impact in Sparse ModelsMeraj Hashemizadeh, Juan Ramirez, Rohan Sukumaran, Golnoosh Farnadi, Simon Lacoste-Julien, Jose Gallego-Posada. [doi]
• Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement LearningFan-Ming Luo, Tian Xu, Xingchen Cao, Yang Yu 0001. [doi]
• Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and BeyondTianxin Wei, Bowen Jin, Ruirui Li 0002, Hansi Zeng, Zhengyang Wang, Jianhui Sun, Qingyu Yin, Hanqing Lu, Suhang Wang, Jingrui He, Xianfeng Tang. [doi]
• Multimodal Patient Representation Learning with Missing Modalities and LabelsZhenbang Wu, Anant Dadu, Nicholas J. Tustison, Brian B. Avants, Mike A. Nalls, Jimeng Sun 0001, Faraz Faghri. [doi]
• Local Search GFlowNetsMinsu Kim, Taeyoung Yun, Emmanuel Bengio, Dinghuai Zhang, Yoshua Bengio, Sungsoo Ahn, Jinkyoo Park. [doi]
• Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with IdentifiabilitySongyao Jin, Feng Xie 0002, Guangyi Chen 0002, Biwei Huang, Zhengming Chen, Xinshuai Dong, Kun Zhang 0001. [doi]
• Be Aware of the Neighborhood Effect: Modeling Selection Bias under InterferenceHaoxuan Li, Chunyuan Zheng, Sihao Ding 0003, Peng Wu 0012, Zhi Geng, Fuli Feng, Xiangnan He 0001. [doi]
• RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech SeparationSamuel Pegg, Kai Li, Xiaolin Hu 0001. [doi]
• MogaNet: Multi-order Gated Aggregation NetworkSiyuan Li, Zedong Wang, Zicheng Liu 0006, Cheng Tan 0012, Haitao Lin, Di Wu 0057, Zhiyuan Chen 0008, Jiangbin Zheng, Stan Z. Li. [doi]
• Image Clustering Conditioned on Text CriteriaSehyun Kwon, JaeSeung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee 0001. [doi]
• Synaptic Weight Distributions Depend on the Geometry of PlasticityRoman Pogodin, Jonathan Cornford, Arna Ghosh, Gauthier Gidel, Guillaume Lajoie, Blake Aaron Richards. [doi]
• Circuit Component Reuse Across Tasks in Transformer Language ModelsJack Merullo, Carsten Eickhoff, Ellie Pavlick. [doi]
• ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRFJangho Park, Gihyun Kwon, Jong Chul Ye. [doi]
• Complete and Efficient Graph Transformers for Crystal Material Property PredictionKeqiang Yan, Cong Fu 0003, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji. [doi]
• Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled FactorsJonghyun Lee 0004, Dahuin Jung, Saehyung Lee, Junsung Park, Juhyeon Shin, Uiwon Hwang, Sungroh Yoon. [doi]
• Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMsWoomin Song, Seunghyuk Oh, Sangwoo Mo, Jaehyung Kim, Sukmin Yun, Jung-Woo Ha 0001, Jinwoo Shin. [doi]
• Differentiable Euler Characteristic Transforms for Shape ClassificationErnst Röell, Bastian Rieck. [doi]
• On Error Propagation of Diffusion ModelsYangming Li, Mihaela van der Schaar. [doi]
• Toward Student-oriented Teacher Network Training for Knowledge DistillationChengyu Dong, Liyuan Liu, Jingbo Shang. [doi]
• On the hardness of learning under symmetriesBobak T. Kiani, Thien Le, Hannah Lawrence, Stefanie Jegelka, Melanie Weber 0001. [doi]
• LipVoicer: Generating Speech from Silent Videos Guided by Lip ReadingYochai Yemini, Aviv Shamsian, Lior Bracha, Sharon Gannot, Ethan Fetaya. [doi]
• Flow Matching on General GeometriesRicky T. Q. Chen, Yaron Lipman. [doi]
• Large Content And Behavior Models To Understand, Simulate, And Optimize Content And BehaviorAshmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman Kumar 0001, Somesh Singh 0003, Uttaran Bhattacharya, Ishita Dasgupta 0002, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy. [doi]
• ASID: Active Exploration for System Identification in Robotic ManipulationMarius Memmel, Andrew Wagenmaker, Chuning Zhu, Dieter Fox, Abhishek Gupta 0004. [doi]
• Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling LimitBlake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan. [doi]
• Boundary Denoising for Video Activity LocalizationMengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel Pérez-Rúa, Bernard Ghanem. [doi]
• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsSuyu Ge, Yunan Zhang 0001, Liyuan Liu, Minjia Zhang, Jiawei Han 0001, Jianfeng Gao 0001. [doi]
• Consistent Multi-Class Classification from Multiple Unlabeled DatasetsZixi Wei, Senlin Shu, Yuzhou Cao, Hongxin Wei, Bo An 0001, Lei Feng 0006. [doi]
• Parameter-Efficient Multi-Task Model Fusion with Partial LinearizationAnke Tang, Li Shen 0008, Yong Luo 0002, Yibing Zhan, Han Hu 0003, Bo Du 0001, Yixin Chen 0001, Dacheng Tao. [doi]
• Ensemble Distillation for Unsupervised Constituency ParsingBehzad Shayegh, Yanshuai Cao, Xiaodan Zhu 0001, Jackie CK Cheung, Lili Mou. [doi]
• PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationYidong Wang, Zhuohao Yu, Wenjin Yao, Zhengran Zeng, Linyi Yang, Cunxiang Wang, Hao Chen 0102, Chaoya Jiang, Rui Xie 0003, Jindong Wang 0001, Xing Xie 0001, Wei Ye 0004, Shikun Zhang, Yue Zhang 0004. [doi]
• Privately Aligning Language Models with Reinforcement LearningFan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim. [doi]
• GPAvatar: Generalizable and Precise Head Avatar from Image(s)Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, Tatsuya Harada. [doi]
• LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic ConstraintsWeidi Xu, Jingwei Wang, Lele Xie, Jianshan He, Hongting Zhou, Taifeng Wang, Xiaopei Wan, Jingdong Chen, Chao Qu, Wei Chu. [doi]
• Uni3D: Exploring Unified 3D Representation at ScaleJunsheng Zhou, Jinsheng Wang, Baorui Ma, Yu-Shen Liu, Tiejun Huang 0003, Xinlong Wang. [doi]
• STARC: A General Framework For Quantifying Differences Between Reward FunctionsJoar Max Viktor Skalse, Lucy Farnik, Sumeet Ramesh Motwani, Erik Jenner, Adam Gleave, Alessandro Abate. [doi]
• Robust Classification via Regression for Learning with Noisy LabelsErik Englesson, Hossein Azizpour. [doi]
• Functional Interpolation for Relative Positions improves Long Context TransformersShanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli. [doi]
• PB-LLM: Partially Binarized Large Language ModelsZhihang Yuan, Yuzhang Shang, Zhen Dong. [doi]
• DSPy: Compiling Declarative Language Model Calls into State-of-the-Art PipelinesOmar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, Christopher Potts. [doi]
• On the Role of Discrete Tokenization in Visual Representation LearningTianqi Du, Yifei Wang 0001, Yisen Wang 0001. [doi]
• CNN Kernels Can Be the Best ShapeletsEric Qu, Yansen Wang, Xufang Luo, Wenqiang He, Kan Ren, Dongsheng Li 0002. [doi]
• MAP IT to Visualize RepresentationsRobert Jenssen. [doi]
• Efficient Backpropagation with Variance Controlled Adaptive SamplingZiteng Wang, Jianfei Chen, Jun Zhu. [doi]
• Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative CommunityArman Isajanyan, Artur Shatveryan, David Kocharian, Zhangyang Wang, Humphrey Shi. [doi]
• Improved Probabilistic Image-Text RepresentationsSanghyuk Chun. [doi]
• Latent Trajectory Learning for Limited Timestamps under Distribution Shift over TimeQiuhao Zeng, Changjian Shui, Long-Kai Huang, Peng Liu, Xi Chen, Charles Ling 0001, Boyu Wang. [doi]
• Ferret: Refer and Ground Anything Anywhere at Any GranularityHaoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, Yinfei Yang. [doi]
• Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric PerspectiveMing Zhong 0005, Chenxin An, Weizhu Chen, Jiawei Han 0001, Pengcheng He. [doi]
• Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open WorldsSipeng Zheng, Jiazheng Liu, Yicheng Feng, Zongqing Lu. [doi]
• NeurRev: Train Better Sparse Neural Network Practically via Neuron RevitalizationGen Li, Lu Yin 0006, Jie Ji, Wei Niu 0002, Minghai Qin, Bin Ren, Linke Guo, Shiwei Liu 0003, Xiaolong Ma. [doi]
• Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate ModelsAndrew Engel, Zhichao Wang, Natalie Frank, Ioana Dumitriu, Sutanay Choudhury, Anand D. Sarwate, Tony Chiang. [doi]
• Critical Learning Periods Emerge Even in Deep Linear NetworksMichael Kleinman, Alessandro Achille, Stefano Soatto. [doi]
• REBAR: Retrieval-Based Reconstruction for Time-series Contrastive LearningMaxwell A. Xu, Alexander Moreno, Hui Wei, Benjamin M. Marlin, James Matthew Rehg. [doi]
• Towards Non-Asymptotic Convergence for Diffusion-Based Generative ModelsGen Li 0005, Yuting Wei, Yuxin Chen 0002, Yuejie Chi. [doi]
• AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly DetectionQihang Zhou, Guansong Pang, Yu Tian 0001, Shibo He, Jiming Chen 0001. [doi]
• Chain-of-Table: Evolving Tables in the Reasoning Chain for Table UnderstandingZilong Wang 0002, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang 0002, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, Tomas Pfister. [doi]
• Pushing Boundaries: Mixup's Influence on Neural CollapseQuinn LeBlanc Fisher, Haoming Meng, Vardan Papyan. [doi]
• A Lie Group Approach to Riemannian Batch NormalizationZiheng Chen, Yue Song, Yunmei Liu, Nicu Sebe. [doi]
• Privacy Amplification for Matrix MechanismsChristopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke 0002, Abhradeep Guha Thakurta. [doi]
• COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RLXiyao Wang, Ruijie Zheng, Yanchao Sun, Ruonan Jia, Wichayaporn Wongkamjan, Huazhe Xu, Furong Huang. [doi]
• MaGIC: Multi-modality Guided Image CompletionHao Wang 0093, Yongsheng Yu, Tiejian Luo, Heng Fan 0001, Libo Zhang 0001. [doi]
• Prompt Gradient Projection for Continual LearningJingyang Qiao, Zhizhong Zhang, Xin Tan, Chengwei Chen, Yanyun Qu, Yong Peng, Yuan Xie 0001. [doi]
• Periodicity Decoupling Framework for Long-term Series ForecastingTao Dai 0001, Beiliang Wu, Peiyuan Liu, Naiqi Li, Jigang Bao, Yong Jiang 0001, Shu-Tao Xia. [doi]
• Revisiting the Last-Iterate Convergence of Stochastic Gradient MethodsZijian Liu, Zhengyuan Zhou. [doi]
• PubDef: Defending Against Transfer Attacks From Public ModelsChawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David A. Wagner 0001. [doi]
• Accelerating Sinkhorn algorithm with sparse Newton iterationsXun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying. [doi]
• GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge GraphsPengcheng Jiang, Cao Xiao, Adam Cross, Jimeng Sun 0001. [doi]
• An Investigation of Representation and Allocation Harms in Contrastive LearningSubha Maity, Mayank Agarwal, Mikhail Yurochkin, Yuekai Sun. [doi]
• PolyVoice: Language Models for Speech to Speech TranslationQianqian Dong, Zhiying Huang, Qi Tian 0001, Chen Xu 0008, Tom Ko, Yunlong Zhao, Siyuan Feng, Tang Li 0001, Kexin Wang, Xuxin Cheng, Fengpeng Yue, Ye Bai, Xi Chen, Lu Lu 0015, Zejun Ma, Yuping Wang, Mingxuan Wang, Yuxuan Wang 0002. [doi]
• Pre-Training Goal-based Models for Sample-Efficient Reinforcement LearningHaoqi Yuan, Zhancun Mu, Feiyang Xie, Zongqing Lu. [doi]
• Raidar: geneRative AI Detection viA RewritingChengzhi Mao, Carl Vondrick, Hao Wang 0014, Junfeng Yang. [doi]
• Better Neural PDE Solvers Through Data-Free Mesh MoversPeiyan Hu, Yue Wang 0017, Zhi-Ming Ma. [doi]
• Neural Auto-designer for Enhanced Quantum KernelsCong Lei, Yuxuan Du, Peng Mi, Jun Yu 0001, Tongliang Liu. [doi]
• iGraphMix: Input Graph Mixup Method for Node ClassificationJongwon Jeong, Hoyeop Lee, Hyui Geon Yoon, Beomyoung Lee, Junhee Heo, Geonsoo Kim, Kim Jin Seon. [doi]
• Approximately Piecewise E(3) Equivariant Point NetworksMatan Atzmon, Jiahui Huang, Francis Williams, Or Litany. [doi]
• Benign Overfitting and Grokking in ReLU Networks for XOR Cluster DataZhiwei Xu, Yutong Wang, Spencer Frei, Gal Vardi, Wei Hu. [doi]
• Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion ModelYinan Zheng, Jianxiong Li, Dongjie Yu, Yujie Yang, Shengbo Eben Li, Xianyuan Zhan, Jingjing Liu. [doi]
• Causally Aligned Curriculum LearningMingxuan Li, Junzhe Zhang, Elias Bareinboim. [doi]
• Demystifying Poisoning Backdoor Attacks from a Statistical PerspectiveGanghua Wang, Xun Xian, Ashish Kundu, Jayanth Srinivasa, Xuan Bi, Mingyi Hong, Jie Ding 0002. [doi]
• P2OT: Progressive Partial Optimal Transport for Deep Imbalanced ClusteringChuyu Zhang, Hui Ren 0003, Xuming He 0001. [doi]
• Off-Policy Primal-Dual Safe Reinforcement LearningZifan Wu, Bo Tang, Qian Lin, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, Dong Wang 0022. [doi]
• Robust Angular Synchronization via Directed Graph Neural NetworksYixuan He, Gesine Reinert, David Wipf, Mihai Cucuringu. [doi]
• LLCP: Learning Latent Causal Processes for Reasoning-based Video Question AnswerGuangyi Chen 0002, Yuke Li, Xiao Liu, Zijian Li 0001, Eman Al Suradi, Donglai Wei 0001, Kun Zhang 0001. [doi]
• Stabilizing Backpropagation Through Time to Learn Complex PhysicsPatrick Schnell, Nils Thuerey. [doi]
• Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN ExpressivenessBohang Zhang, Jingchu Gai, Yiheng Du, Qiwei Ye, Di He 0001, Liwei Wang 0001. [doi]
• Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human GainYiming Gao 0007, Feiyu Liu, Liang Wang 0015, Dehua Zheng, Zhenjie Lian, Weixuan Wang, Wenjin Yang, Siqin Li, Xianliang Wang, Wenhui Chen, Jing Dai, Qiang Fu, Yang Wei, Lanxiao Huang, Wei Liu 0005. [doi]
• Correlated Noise Provably Beats Independent Noise for Differentially Private LearningChristopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke 0002, Abhradeep Guha Thakurta. [doi]
• INViTE: INterpret and Control Vision-Language Models with Text ExplanationsHaozhe Chen, Junfeng Yang, Carl Vondrick, Chengzhi Mao. [doi]
• OWL: A Large Language Model for IT OperationsHongcheng Guo, Jian Yang 0030, Jiaheng Liu, Liqun Yang, Linzheng Chai, Jiaqi Bai, Junran Peng, Xiaorong Hu, Chao Chen, Dongfeng Zhang, Xu Shi, Tieqiao Zheng, Liangfan Zheng, Bo Zhang 0096, Ke Xu 0001, Zhoujun Li 0001. [doi]
• Improving Generalization of Alignment with Human Preferences through Group Invariant LearningRui Zheng, Wei Shen, Yuan Hua, Wenbin Lai, Shihan Dou, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Haoran Huang, Tao Gui, Qi Zhang 0001, Xuanjing Huang 0001. [doi]
• Retro-fallback: retrosynthetic planning in an uncertain worldAustin Tripp, Krzysztof Maziarz, Sarah Lewis, Marwin H. S. Segler, José Miguel Hernández-Lobato. [doi]
• GIM: Learning Generalizable Image Matcher From Internet VideosXuelun Shen, Zhipeng Cai, Wei Yin 0006, Matthias Müller 0011, Zijun Li 0006, Kaixuan Wang, Xiaozhi Chen, Cheng Wang 0003. [doi]
• ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Minlie Huang, Nan Duan, Weizhu Chen. [doi]
• Sample-Efficient Learning of POMDPs with Multiple Observations In HindsightJiacheng Guo, Minshuo Chen, Huan Wang 0014, Caiming Xiong, Mengdi Wang, Yu Bai 0017. [doi]
• Equivariant Matrix Function Neural NetworksIlyes Batatia, Lars L. Schaaf, Gábor Csányi, Christoph Ortner, Felix A. Faber. [doi]
• Unprocessing Seven Years of Algorithmic FairnessAndré F. Cruz, Moritz Hardt. [doi]
• DragonDiffusion: Enabling Drag-style Manipulation on Diffusion ModelsChong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang. [doi]
• Minimum width for universal approximation using ReLU networks on compact domainNamjun Kim, Chanho Min, Sejun Park. [doi]
• Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient HeterogeneityTomoya Murata, Kenta Niwa, Takumi Fukami, Iifan Tyou. [doi]
• Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse TasksZiping Xu, Zifan Xu, Runxuan Jiang, Peter Stone, Ambuj Tewari. [doi]
• Memorization in Self-Supervised Learning Improves Downstream GeneralizationWenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes 0001, Nicolas Papernot, Franziska Boenisch. [doi]
• TD-MPC2: Scalable, Robust World Models for Continuous ControlNicklas Hansen 0001, Hao Su 0001, Xiaolong Wang 0004. [doi]
• From Graphs to Hypergraphs: Hypergraph Projection and its ReconstructionYanbang Wang, Jon M. Kleinberg. [doi]
• AgentBench: Evaluating LLMs as AgentsXiao Liu 0036, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu 0016, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng 0001, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su 0001, Huan Sun 0001, Minlie Huang, Yuxiao Dong, Jie Tang 0001. [doi]
• Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference CostYuan Gao 0015, Weizhong Zhang, Wenhan Luo, Lin Ma 0002, Jin-Gang Yu, Gui-Song Xia, Jiayi Ma 0001. [doi]
• PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of CodeXuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, Qiang Xu 0001. [doi]
• Spatially-Aware Transformers for Embodied AgentsJunmo Cho, Jaesik Yoon, Sungjin Ahn. [doi]
• Respect the model: Fine-grained and Robust Explanation with Sharing Ratio DecompositionSangyu Han, Yearim Kim, Nojun Kwak. [doi]
• Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex OptimizationHanmin Li, Avetik G. Karagulyan, Peter Richtárik. [doi]
• Hybrid Directional Graph Neural Network for MoleculesJunyi An, Chao Qu, Zhipeng Zhou, Fenglei Cao, Yinghui Xu, Yuan Qi, Furao Shen. [doi]
• Toward Optimal Policy Population Growth in Two-Player Zero-Sum GamesStephen Marcus McAleer, JB Lanier, Kevin A. Wang, Pierre Baldi, Tuomas Sandholm, Roy Fox. [doi]
• Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance AccompanimentLi Siyao, Tianpei Gu, Zhitao Yang, Zhengyu Lin, Ziwei Liu 0002, Henghui Ding, Lei Yang 0059, Chen Change Loy. [doi]
• RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA DesignCheng Tan 0012, Yijie Zhang, Zhangyang Gao, Bozhen Hu, Siyuan Li, Zicheng Liu 0006, Stan Z. Li. [doi]
• Context-Aware Meta-LearningChristopher Fifty, Dennis Duan, Ronald G. Junkins, Ehsan Amid, Jure Leskovec, Christopher Ré, Sebastian Thrun. [doi]
• SEAL: A Framework for Systematic Evaluation of Real-World Super-ResolutionWenlong Zhang, Xiaohui Li, Xiangyu Chen, Xiaoyun Zhang, Yu Qiao 0001, Xiao-Ming Wu 0003, Chao Dong. [doi]
• Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasksSina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis, Tim Jakob Schäfer, Georg Martius, Anna Levina. [doi]
• ToolChain*: Efficient Action Space Navigation in Large Language Models with A* SearchYuchen Zhuang, Xiang Chen, Tong Yu 0001, Saayan Mitra, Victor Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, Chao Zhang 0014. [doi]
• Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple BaselineDonggyu Lee, Sangwon Jung, Taesup Moon. [doi]
• Efficient Modulation for Vision NetworksXu Ma 0005, Xiyang Dai, Jianwei Yang, Bin Xiao 0004, Yinpeng Chen, Yun Fu 0001, Lu Yuan. [doi]
• Learning Energy Decompositions for Partial Inference in GFlowNetsHyosoon Jang, Minsu Kim, Sungsoo Ahn. [doi]
• How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?Wenxuan Li, Alan L. Yuille, Zongwei Zhou. [doi]
• Habitat 3.0: A Co-Habitat for Humans, Avatars, and RobotsXavier Puig, Eric Undersander, Andrew Szot, Mikael Dallaire-Cote, Tsung-Yen Yang, Ruslan Partsey, Ruta Desai, Alexander Clegg, Michal Hlavac, So Yeon Min, Vladimir Vondrus, Théophile Gervet, Vincent-Pierre Berges, John M. Turner, Oleksandr Maksymets, Zsolt Kira, Mrinal Kalakrishnan, Jitendra Malik, Devendra Singh Chaplot, Unnat Jain, Dhruv Batra, Akshara Rai, Roozbeh Mottaghi. [doi]
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time AdaptationJiaming Liu, Senqiao Yang, Peidong Jia, Renrui Zhang, Ming Lu, Yandong Guo, Wei Xue, Shanghang Zhang. [doi]
• Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative InstructionsJuncheng Li 0006, Kaihang Pan, Zhiqi Ge, Minghe Gao, Wei Ji 0008, Wenqiao Zhang, Tat-Seng Chua, Siliang Tang, Hanwang Zhang, Yueting Zhuang. [doi]
• Leveraging Uncertainty Estimates To Improve Classifier PerformanceGundeep Arora, Srujana Merugu, Anoop Saladi, Rajeev Rastogi. [doi]
• Adapting Large Language Models via Reading ComprehensionDaixuan Cheng, Shaohan Huang, Furu Wei. [doi]
• Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category TheoryYiting Chen 0003, Zhanpeng Zhou, Junchi Yan. [doi]
• Score Models for Offline Goal-Conditioned Reinforcement LearningHarshit Sikchi, Rohan Chitnis, Ahmed Touati, Alborz Geramifard, Amy Zhang 0001, Scott Niekum. [doi]
• ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient UpdateLiyuan Mao, Haoran Xu, Weinan Zhang 0001, Xianyuan Zhan. [doi]
• Locality-Aware Graph Rewiring in GNNsFederico Barbero, Ameya Velingker, Amin Saberi, Michael M. Bronstein, Francesco Di Giovanni. [doi]
• Feature emergence via margin maximization: case studies in algebraic tasksDepen Morwani, Benjamin L. Edelman, Costin-Andrei Oncescu, Rosie Zhao, Sham M. Kakade. [doi]
• Topic Modeling as Multi-Objective Contrastive OptimizationThong Thanh Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T. Nguyen, See-Kiong Ng, Anh Tuan Luu. [doi]
• Sufficient conditions for offline reactivation in recurrent neural networksNanda H. Krishna, Colin Bredenberg, Daniel Levenstein, Blake Aaron Richards, Guillaume Lajoie. [doi]
• Multimarginal Generative Modeling with Stochastic InterpolantsMichael S. Albergo, Nicholas Matthew Boffi, Michael Lindsey, Eric Vanden-Eijnden. [doi]
• The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image EditingShen Nie, Hanzhong Allan Guo, Cheng Lu 0011, Yuhao Zhou, Chenyu Zheng, Chongxuan Li. [doi]
• Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation PatchingAleksandar Makelov, Georg Lange, Atticus Geiger, Neel Nanda. [doi]
• Accelerating Data Generation for Neural Operators via Krylov Subspace RecyclingHong Wang, Zhongkai Hao, Jie Wang 0005, Zijie Geng, Zhen Wang, Bin Li, Feng Wu 0001. [doi]
• Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual CorrespondenceSunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin 0001. [doi]
• Provable Benefits of Multi-task RL under Non-Markovian Decision Making ProcessesRuiquan Huang, Yuan Cheng, Jing Yang, Vincent Tan, Yingbin Liang. [doi]
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity TheoryNiloofar Mireshghallah, Hyunwoo Kim 0002, Xuhui Zhou, Yulia Tsvetkov, Maarten Sap, Reza Shokri, Yejin Choi 0001. [doi]
• Training Graph Transformers via Curriculum-Enhanced Attention DistillationYisong Huang 0002, Jin Li 0032, Xinlong Chen, Yang-Geng Fu. [doi]
• Offline RL with Observation Histories: Analyzing and Improving Sample ComplexityJoey Hong, Anca D. Dragan, Sergey Levine. [doi]
• MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein EmbeddingLirong Wu, Yijun Tian 0001, Yufei Huang 0002, Siyuan Li, Haitao Lin, Nitesh V. Chawla, Stan Z. Li. [doi]
• SWAP: Sparse Entropic Wasserstein Regression for Robust Network PruningLei You, Hei Victor Cheng. [doi]
• Adversarial Training Should Be Cast as a Non-Zero-Sum GameAlexander Robey, Fabian Latorre, George J. Pappas, Hamed Hassani, Volkan Cevher. [doi]
• Ghost on the Shell: An Expressive Representation of General 3D ShapesZhen Liu, Yao Feng, Yuliang Xiu, Weiyang Liu, Liam Paull, Michael J. Black, Bernhard Schölkopf. [doi]
• RA-DIT: Retrieval-Augmented Dual Instruction TuningXi Victoria Lin, Xilun Chen 0002, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James 0001, Pedro Rodriguez 0001, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih. [doi]
• Procedural Fairness Through Decoupling Objectionable Data Generating ComponentsZeyu Tang, Jialu Wang, Yang Liu, Peter Spirtes, Kun Zhang 0001. [doi]
• Confidential-DPproof: Confidential Proof of Differentially Private TrainingAli Shahin Shamsabadi, Gefei Tan, Tudor Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang 0012, Adrian Weller. [doi]
• GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing ModulesZhenfang Chen, Rui Sun, Wenjun Liu, Yining Hong, Chuang Gan. [doi]
• Learning Over Molecular Conformer Ensembles: Datasets and BenchmarksYanqiao Zhu 0001, JeeHyun Hwang, Keir Adams, Zhen Liu, Bozhao Nan, Brock Stenfors, Yuanqi Du, Jatin Chauhan, Olaf Wiest, Olexandr Isayev, Connor W. Coley, Yizhou Sun, Wei Wang 0010. [doi]
• Neural Processing of Tri-Plane Hybrid Neural FieldsAdriano Cardace, Pierluigi Zama Ramirez, Francesco Ballerini, Allan Zhou, Samuele Salti, Luigi di Stefano. [doi]
• Pareto Deep Long-Tailed Recognition: A Conflict-Averse SolutionZhipeng Zhou, Liu Liu 0014, Peilin Zhao, Wei Gong 0001. [doi]
• Exploring Effective Stimulus Encoding via Vision System Modeling for Visual ProsthesesChuanqing Wang, Di Wu 0057, Chaoming Fang, Jie Yang 0033, Mohamad Sawan. [doi]
• An operator preconditioning perspective on training in physics-informed machine learningTim De Ryck, Florent Bonnet, Siddhartha Mishra, Emmanuel de Bézenac. [doi]
• Rethinking the Uniformity Metric in Self-Supervised LearningXianghong Fang, Jian Li 0054, Qiang Sun, Benyou Wang. [doi]
• A Multi-Level Framework for Accelerating Training Transformer ModelsLongwei Zou, Han Zhang, Yangdong Deng. [doi]
• MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingYizhi Li, Ruibin Yuan, Ge Zhang, Yinghao Ma, Xingran Chen, Hanzhi Yin, Chenghao Xiao, Chenghua Lin, Anton Ragni, Emmanouil Benetos, Norbert Gyenge, Roger B. Dannenberg, Ruibo Liu, Wenhu Chen, Gus Xia, Yemin Shi 0001, Wenhao Huang, Zili Wang, Yike Guo, Jie Fu. [doi]
• Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLXiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang. [doi]
• Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language ModelsMert Yüksekgönül, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi. [doi]
• Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisitedLu Yu, Avetik G. Karagulyan, Arnak S. Dalalyan. [doi]
• PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time AdaptationHaopeng Sun, Lumin Xu, Sheng Jin 0007, Ping Luo 0002, Chen Qian 0006, Wentao Liu 0002. [doi]
• HAZARD Challenge: Embodied Decision Making in Dynamically Changing EnvironmentsQinhong Zhou, Sunli Chen, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan. [doi]
• Retrieval is Accurate GenerationBowen Cao, Deng Cai 0002, Leyang Cui, Xuxin Cheng, Wei Bi, Yuexian Zou, Shuming Shi 0001. [doi]
• Chameleon: Increasing Label-Only Membership Leakage with Adaptive PoisoningHarsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan R. Ullman. [doi]
• Most discriminative stimuli for functional cell type clusteringMax F. Burg, Thomas Zenkel, Michaela Vystrcilová, Jonathan Oesterle, Larissa Höfling, Konstantin F. Willeke, Jan Lause, Sarah Müller, Paul G. Fahey, Zhiwei Ding, Kelli Restivo, Shashwat Sridhar, Tim Gollisch, Philipp Berens, Andreas S. Tolias, Thomas Euler, Matthias Bethge, Alexander S. Ecker. [doi]
• V-DETR: DETR with Vertex Relative Position Encoding for 3D Object DetectionYichao Shen 0001, Zigang Geng, Yuhui Yuan, Yutong Lin, Ze Liu, Chunyu Wang, Han Hu 0001, Nanning Zheng 0001, Baining Guo. [doi]
• Generalization in diffusion models arises from geometry-adaptive harmonic representationsZahra Kadkhodaie, Florentin Guth, Eero P. Simoncelli, Stéphane Mallat. [doi]
• FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editingYuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Pérez-Rúa, Bodo Rosenhahn, Tao Xiang 0002, Sen He 0001. [doi]
• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebateChi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, Zhiyuan Liu 0001. [doi]
• Less is More: Fewer Interpretable Region via Submodular Subset SelectionRuoyu Chen 0001, Hua Zhang 0008, Siyuan Liang, Jingzhi Li 0002, Xiaochun Cao. [doi]
• Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level GenerationZiqi Wang 0005, Chengpeng Hu, Jialin Liu 0001, Xin Yao 0001. [doi]
• C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature DispersionHee Suk Yoon, Eunseop Yoon, Joshua Tian Jin Tee, Mark A. Hasegawa-Johnson, Yingzhen Li, Chang D. Yoo. [doi]
• Hyper Evidential Deep Learning to Quantify Composite Classification UncertaintyChangbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan, Audun Jøsang, Jin-Hee Cho, Dong Hyun Jeong, Feng Chen 0001. [doi]
• Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained ComputationWenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip Torr 0001, Adel Bibi, Mohamed Elhoseiny. [doi]
• Energy-conserving equivariant GNN for elasticity of lattice architected metamaterialsIvan Grega, Ilyes Batatia, Gábor Csányi, Sri Karlapati, Vikram S. Deshpande. [doi]
• AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation LearningRohan Sharma, Kaiyi Ji, Zhiqiang Xu, Changyou Chen. [doi]
• Weatherproofing Retrieval for Localization with Generative AI and Geometric ConsistencyYannis Kalantidis, Mert Bülent Sariyildiz, Rafael S. Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka. [doi]
• An Efficient Tester-Learner for HalfspacesAravind Gollakota, Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan. [doi]
• Structuring Representation Geometry with Rotationally Equivariant Contrastive LearningSharut Gupta, Joshua Robinson 0001, Derek Lim, Soledad Villar, Stefanie Jegelka. [doi]
• Data Filtering NetworksAlex Fang, Albin Madappally Jose, Amit Jain, Ludwig Schmidt, Alexander T. Toshev, Vaishaal Shankar. [doi]
• GAIA: Zero-shot Talking Avatar GenerationTianyu He, Junliang Guo, Runyi Yu 0002, YuChi Wang, Jialiang Zhu, Kaikai An, Leyi Li, Xu Tan 0003, Chunyu Wang, Han Hu 0001, HsiangTao Wu, Sheng Zhao, Jiang Bian 0002. [doi]
• Diffusion-TS: Interpretable Diffusion for General Time Series GenerationXinyu Yuan, Yan Qiao. [doi]
• Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt EngineeringHan Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine A. Heller, Subhrajit Roy. [doi]
• SmartPlay : A Benchmark for LLMs as Intelligent AgentsYue Wu 0001, Xuan Tang, Tom M. Mitchell, Yuanzhi Li. [doi]
• Tree Search-Based Policy Optimization under Stochastic Execution DelayDavid Valensi, Esther Derman, Shie Mannor, Gal Dalal. [doi]
• Understanding the Effects of RLHF on LLM Generalisation and DiversityRobert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, Roberta Raileanu. [doi]
• G2N2 : Weisfeiler and Lehman go grammaticalJason Piquenot, Aldo Moscatelli, Maxime Berar, Pierre Héroux, Romain Raveaux, Jean-Yves Ramel, Sébastien Adam. [doi]
• Does CLIP's generalization performance mainly stem from high train-test similarity?Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel. [doi]
• DyVal: Dynamic Evaluation of Large Language Models for Reasoning TasksKaijie Zhu, Jiaao Chen, Jindong Wang 0001, Neil Zhenqiang Gong, Diyi Yang, Xing Xie 0001. [doi]
• Learning invariant representations of time-homogeneous stochastic dynamical systemsVladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil. [doi]
• How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett. [doi]
• CellPLM: Pre-training of Cell Language Model Beyond Single CellsHongzhi Wen, Wenzhuo Tang, Xinnan Dai, Jiayuan Ding, Wei Jin 0009, Yuying Xie, Jiliang Tang. [doi]
• Lie Group Decompositions for Equivariant Neural NetworksMircea Mironenco, Patrick Forré. [doi]
• A Unified Framework for Bayesian Optimization under Contextual UncertaintySebastian Shenghong Tay, Chuan-Sheng Foo, Daisuke Urano, Richalynn Leong, Bryan Kian Hsiang Low. [doi]
• Two-stage LLM Fine-tuning with Less Specialization and More GeneralizationYihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix Yu, Cho-Jui Hsieh, Inderjit S. Dhillon, Sanjiv Kumar. [doi]
• Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language ModelsJung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee. [doi]
• Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot ResponseJunfeng Long, Zirui Wang, Quanyi Li, Liu Cao, Jiawei Gao 0004, Jiangmiao Pang. [doi]
• Variational Inference for SDEs Driven by Fractional NoiseRembert Daems, Manfred Opper, Guillaume Crevecoeur, Tolga Birdal. [doi]
• Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled DataXiong Zhou, Xianming Liu, Hao Yu, Jialiang Wang, Zeke Xie, Junjun Jiang, Xiangyang Ji. [doi]
• Zero-Shot Robustification of Zero-Shot ModelsDyah Adila, Changho Shin, Linrong Cai, Frederic Sala. [doi]
• Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and PracticeJicong Fan 0001, Rui Chen, Zhao Zhang 0001, Chris Ding. [doi]
• Long-tailed Diffusion Models with Oriented CalibrationTianjiao Zhang, Huangjie Zheng, Jiangchao Yao, Xiangfeng Wang, Mingyuan Zhou, Ya Zhang 0002, Yanfeng Wang. [doi]
• A Topological Perspective on Demystifying GNN-Based Link Prediction PerformanceYu Wang 0160, Tong Zhao 0003, Yuying Zhao, Yunchao Liu, Xueqi Cheng, Neil Shah, Tyler Derr. [doi]
• Incremental Randomized Smoothing CertificationShubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh 0001, Sasa Misailovic. [doi]
• Scalable Language Model with Generalized Continual LearningBohao Peng, Zhuotao Tian, Shu Liu 0005, Ming-Chang Yang, Jiaya Jia. [doi]
• Towards Robust Fidelity for Evaluating Explainability of Graph Neural NetworksXu Zheng, Farhad Shirani 0001, Tianchun Wang, Wei Cheng 0002, Zhuomin Chen, Haifeng Chen, Hua Wei 0001, Dongsheng Luo. [doi]
• Domain-Inspired Sharpness-Aware Minimization Under Domain ShiftsRuipeng Zhang, Ziqing Fan, Jiangchao Yao, Ya Zhang 0002, Yanfeng Wang. [doi]
• Multilingual Jailbreak Challenges in Large Language ModelsYue Deng 0010, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing. [doi]
• Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction AttacksVaidehi Patil, Peter Hase, Mohit Bansal. [doi]
• Rethinking Label Poisoning for GNNs: Pitfalls and AttacksVijay Lingam, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski. [doi]
• Towards 3D Molecule-Text Interpretation in Language ModelsSihang Li, Zhiyuan Liu 0001, Yanchen Luo, Xiang Wang 0010, Xiangnan He 0001, Kenji Kawaguchi, Tat-Seng Chua, Qi Tian 0001. [doi]
• Modeling state-dependent communication between brain regions with switching nonlinear dynamical systemsOrren Karniol-Tambour, David M. Zoltowski, E. Mika Diamanti, Lucas Pinto, Carlos D. Brody, David W. Tank, Jonathan W. Pillow. [doi]
• KW-Design: Pushing the Limit of Protein Design via Knowledge RefinementZhangyang Gao, Cheng Tan 0012, Xingran Chen, Yijie Zhang, Jun Xia, Siyuan Li, Stan Z. Li. [doi]
• Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement LearningNa Li, Yuchen Jiao, Hangguan Shan, Shefeng Yan. [doi]
• Time-LLM: Time Series Forecasting by Reprogramming Large Language ModelsMing Jin 0005, Shiyu Wang 0001, Lintao Ma, Zhixuan Chu, James Y. Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, Qingsong Wen. [doi]
• Denoising Diffusion via Image-Based RenderingTitas Anciukevicius, Fabian Manhardt, Federico Tombari, Paul Henderson. [doi]
• Llemma: An Open Language Model for MathematicsZhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen Marcus McAleer, Albert Q. Jiang, Jia Deng, Stella Biderman, Sean Welleck. [doi]
• Sparsistency for inverse optimal transportFrancisco Andrade 0005, Gabriel Peyré, Clarice Poon. [doi]
• JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and AttentionYuandong Tian, Yiping Wang, Zhenyu Zhang 0015, Beidi Chen, Simon Shaolei Du. [doi]
• Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-VerificationAojun Zhou, Ke Wang, Zimu Lu, Weikang Shi, Sichun Luo, Zipeng Qin, Shaoqing Lu, Anya Jia, Linqi Song, Mingjie Zhan, Hongsheng Li 0001. [doi]
• Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign FeaturesXiong Xu, Kunzhe Huang, Yiming Li 0004, Zhan Qin, Kui Ren 0001. [doi]
• On Differentially Private Federated Linear Contextual BanditsXingyu Zhou 0001, Sayak Ray Chowdhury. [doi]
• Efficient Backdoor Attacks for Deep Neural Networks in Real-world ScenariosZiqiang Li 0001, Hong Sun, Pengfei Xia, Heng Li 0008, Beihao Xia, Yi Wu 0018, Bin Li 0025. [doi]
• CausalTime: Realistically Generated Time-series for Benchmarking of Causal DiscoveryYuxiao Cheng, Ziqian Wang, Tingxiong Xiao, Qin Zhong, Jinli Suo, Kunlun He. [doi]
• EventRPG: Event Data Augmentation with Relevance Propagation GuidanceMingyuan Sun, Donghao Zhang, ZongYuan Ge, Jiaxu Wang, Jia Li, Zheng Fang 0001, Renjing Xu. [doi]
• Towards Optimal Feature-Shaping Methods for Out-of-Distribution DetectionQinyu Zhao, Ming Xu, Kartik Gupta, Akshay Asthana, Liang Zheng 0001, Stephen Gould. [doi]
• Revisit and Outstrip Entity Alignment: A Perspective of Generative ModelsLingbing Guo, Zhuo Chen 0007, Jiaoyan Chen 0001, Yin Fang, Wen Zhang 0015, Huajun Chen. [doi]
• Stack Attention: Improving the Ability of Transformers to Model Hierarchical PatternsBrian DuSell, David Chiang 0001. [doi]
• A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic ModelsEnshu Liu, Xuefei Ning, Huazhong Yang, Yu Wang 0002. [doi]
• Neurosymbolic Grounding for Compositional World ModelsAtharva Sehgal, Arya Grayeli, Jennifer J. Sun, Swarat Chaudhuri. [doi]
• The Need for Speed: Pruning Transformers with One RecipeSamir Khaki, Konstantinos N. Plataniotis. [doi]
• Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based InitializationFrederic Koehler, Thuy Duong Vuong. [doi]
• COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic CircuitsMintong Kang, Nezihe Merve Gürel, Linyi Li, Bo Li 0026. [doi]
• GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth BenchmarkingMert Kosan, Samidha Verma, Burouj Armgaan, Khushbu Pahwa, Ambuj K. Singh, Sourav Medya, Sayan Ranu. [doi]
• Large Multilingual Models Pivot Zero-Shot Multimodal Learning across LanguagesJinyi Hu, Yuan Yao 0013, Chongyi Wang, Shan Wang, Yinxu Pan, Qianyu Chen, Tianyu Yu, Hanghao Wu, Yue Zhao, Haoye Zhang, Xu Han 0007, Yankai Lin, Jiao Xue, Dahai Li, Zhiyuan Liu 0001, Maosong Sun 0001. [doi]
• LongLoRA: Efficient Fine-tuning of Long-Context Large Language ModelsYukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han 0003, Jiaya Jia. [doi]
• BEND: Benchmarking DNA Language Models on Biologically Meaningful TasksFrederikke Isa Marin, Felix Teufel, Marc Horlacher, Dennis Madsen, Dennis Pultz, Ole Winther, Wouter Boomsma. [doi]
• Differentially Private Synthetic Data via Foundation Model APIs 1: ImagesZinan Lin 0001, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, Sergey Yekhanin. [doi]
• Noise-free Score DistillationOren Katzir, Or Patashnik, Daniel Cohen-Or, Dani Lischinski. [doi]
• Interpreting CLIP's Image Representation via Text-Based DecompositionYossi Gandelsman, Alexei A. Efros, Jacob Steinhardt. [doi]
• BatteryML: An Open-source Platform for Machine Learning on Battery DegradationHan Zhang, Xiaofan Gui, Shun Zheng, Ziheng Lu, Yuqi Li, Jiang Bian 0002. [doi]
• Out-of-Distribution Detection with Negative PromptsJun Nie, Yonggang Zhang, Zhen Fang 0001, Tongliang Liu, Bo Han 0003, Xinmei Tian 0001. [doi]
• FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor CoresDaniel Y. Fu, Hermann Kumbong, Eric Nguyen, Christopher Ré. [doi]
• BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationPeng Xu, Wenqi Shao, Mengzhao Chen, Shitao Tang, Kaipeng Zhang, Peng Gao 0007, Fengwei An, Yu Qiao 0001, Ping Luo 0002. [doi]
• Generalized Neural Sorting Networks with Error-Free Differentiable Swap FunctionsJungtaek Kim 0001, Jeongbeen Yoon, Minsu Cho. [doi]
• Bidirectional Temporal Diffusion Model for Temporally Consistent Human AnimationTserendorj Adiya, Jae Shin Yoon, Jungeun Lee, Sanghun Kim, Hwasup Lim. [doi]
• LipSim: A Provably Robust Perceptual Similarity MetricSara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg. [doi]
• Symmetric Single Index LearningAaron Zweig, Joan Bruna. [doi]
• Emergent Communication with Conversational RepairMitja Nikolaus. [doi]
• MiniLLM: Knowledge Distillation of Large Language ModelsYuxian Gu, Li Dong 0004, Furu Wei, Minlie Huang. [doi]
• Social-Transmotion: Promptable Human Trajectory PredictionSaeed Saadatnejad, Yang Gao, Kaouther Messaoud, Alexandre Alahi. [doi]
• BooookScore: A systematic exploration of book-length summarization in the era of LLMsYapei Chang, Kyle Lo, Tanya Goyal, Mohit Iyyer. [doi]
• OpenWebMath: An Open Dataset of High-Quality Mathematical Web TextKeiran Paster, Marco Dos Santos, Zhangir Azerbayev, Jimmy Ba. [doi]
• Multilinear Operator NetworksYixin Cheng, Grigorios Chrysos 0002, Markos Georgopoulos, Volkan Cevher. [doi]
• Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin, Jia-You Chen, Bo Li 0026, Pin-Yu Chen, Chia-Mu Yu, Chun-Ying Huang. [doi]
• DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion PriorJingxiang Sun, Bo Zhang, Ruizhi Shao, Lizhen Wang 0002, Wen Liu, Zhenda Xie, Yebin Liu. [doi]
• Enhancing Neural Training via a Correlated Dynamics ModelJonathan Brokman, Roy Betser, Rotem Turjeman, Tom Berkov, Ido Cohen, Guy Gilboa. [doi]
• Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free AlgorithmWei Yao, Chengming Yu, Shangzhi Zeng, Jin Zhang. [doi]
• Few-Shot Detection of Machine-Generated Text using Style RepresentationsRafael A. Rivera Soto, Kailin Koch, Aleem Khan, Barry Y. Chen, Marcus Bishop, Nicholas Andrews. [doi]
• KITAB: Evaluating LLMs on Constraint Satisfaction for Information RetrievalMarah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yüksekgönül, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi. [doi]
• Early Stopping Against Label Noise Without Validation DataSuqin Yuan, Lei Feng 0006, Tongliang Liu. [doi]
• Large Language Models are Efficient Learners of Noise-Robust Speech RecognitionYuchen Hu, Chen Chen 0075, Chao-Han Huck Yang, Ruizhe Li 0001, Chao Zhang 0031, Pin-Yu Chen, Engsiong Chng. [doi]
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree RepresentationsYi-Lun Liao, Brandon M. Wood, Abhishek Das, Tess E. Smidt. [doi]
• Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce GrokkingKaifeng Lyu, Jikai Jin, Zhiyuan Li 0005, Simon Shaolei Du, Jason D. Lee, Wei Hu 0014. [doi]
• The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space ModelsRaphaël Avalos, Florent Delgrange, Ann Nowé, Guillermo A. Pérez 0001, Diederik M. Roijers. [doi]
• Memorization Capacity of Multi-Head Attention in TransformersSadegh Mahdavi, Renjie Liao, Christos Thrampoulidis. [doi]
• FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSsSepehr Dehdashtian, Lan Wang, Vishnu Boddeti. [doi]
• Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPsKaixuan Ji, Qingyue Zhao, Jiafan He, Weitong Zhang, Quanquan Gu. [doi]
• Fast Value Tracking for Deep Reinforcement LearningFrank Shih, Faming Liang. [doi]
• TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of ExpertsHyunwook Lee, Sungahn Ko. [doi]
• FedInverse: Evaluating Privacy Leakage in Federated LearningDi Wu 0050, Jun Bai, Yiliao Song, Junjun Chen, Wei Zhou, Yong Xiang 0001, Atul Sajjanhar. [doi]
• Grounding Language Plans in Demonstrations Through Counterfactual PerturbationsYanwei Wang, Tsun-Hsuan Wang, Jiayuan Mao, Michael Hagenow, Julie Shah. [doi]
• Video Language PlanningYilun Du, Sherry Yang, Pete Florence, Fei Xia, Ayzaan Wahid, Brian Ichter, Pierre Sermanet, Tianhe Yu, Pieter Abbeel, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Andy Zeng, Jonathan Tompson. [doi]
• RAIN: Your Language Models Can Align Themselves without FinetuningYuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang 0001, Hongyang Zhang 0001. [doi]
• Protein Discovery with Discrete Walk-Jump SamplingNathan C. Frey, Daniel Berenberg, Karina Zadorozhny, Joseph Kleinhenz, Julien Lafrance-Vanasse, Isidro Hötzel, Yan Wu, Stephen Ra, Richard Bonneau, KyungHyun Cho, Andreas Loukas, Vladimir Gligorijevic, Saeed Saremi. [doi]
• Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D VideoXiangming Zhu 0002, Huayu Deng, Haochen Yuan, Yunbo Wang, Xiaokang Yang. [doi]
• Learning Multi-Agent Communication with Contrastive LearningYat Long Lo, Biswa Sengupta, Jakob Nicolaus Foerster, Michael Noukhovitch. [doi]
• Safe and Robust Watermark Injection with a Single OoD ImageShuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou. [doi]
• Classification with Conceptual SafeguardsHailey Joren, Charles T. Marx, Berk Ustun. [doi]
• CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and SimplicityAditya Bhatt 0001, Daniel Palenicek, Boris Belousov, Max Argus, Artemij Amiranashvili, Thomas Brox, Jan Peters 0001. [doi]
• Detecting, Explaining, and Mitigating Memorization in Diffusion ModelsYuxin Wen, Yuchen Liu, Chen Chen 0043, Lingjuan Lyu. [doi]
• Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?Tokio Kajitsuka, Issei Sato. [doi]
• TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained ModelsZuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu 0009, Ding Zhao, Shoham Sabach, Rasool Fakoor. [doi]
• Adversarial AutoMixupHuafeng Qin, Xin Jin, Yun Jiang, Mounîm A. El-Yacoubi, Xinbo Gao 0001. [doi]
• Building Cooperative Embodied Agents Modularly with Large Language ModelsHongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu, Chuang Gan. [doi]
• How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and InitializationNuoya Xiong, Lijun Ding, Simon Shaolei Du. [doi]
• Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning UpdatesNicholas Corrado, Josiah P. Hanna. [doi]
• Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method PerspectiveMing-Yu Chung, Sheng-Yen Chou, Chia-Mu Yu, Pin-Yu Chen, Sy-Yen Kuo, Tsung-Yi Ho. [doi]
• Dual Associated Encoder for Face RestorationYu-Ju Tsai, Yu-Lun Liu 0001, Lu Qi, Kelvin C. K. Chan, Ming-Hsuan Yang 0001. [doi]
• CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative DecodingJunyan Li, Delin Chen, Yining Hong, Zhenfang Chen, Peihao Chen, Yikang Shen, Chuang Gan. [doi]
• Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement LearningHyungho Na, Yunkyeong Seo, Il-Chul Moon. [doi]
• Consistent Video-to-Video Transfer Using Synthetic DatasetJiaxin Cheng, Tianjun Xiao, Tong He 0002. [doi]
• Learning model uncertainty as variance-minimizing instance weightsNishant Jain, Karthikeyan Shanmugam, Pradeep Shenoy. [doi]
• Provably Efficient UCB-type Algorithms For Learning Predictive State RepresentationsRuiquan Huang, Yingbin Liang, Jing Yang 0002. [doi]
• Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuningHaobo Song, Hao Zhao, Soumajit Majumder, Tao Lin. [doi]
• AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge DistillationZihao Tang, Zheqi Lv, Shengyu Zhang 0001, Yifan Zhou, Xinyu Duan, Fei Wu 0001, Kun Kuang. [doi]
• Reverse Diffusion Monte CarloXunpeng Huang, Hanze Dong, Yifan Hao, Yian Ma, Tong Zhang 0001. [doi]
• Evaluating Language Model Agency Through NegotiationsTim R. Davidson, Veniamin Veselovsky, Michal Kosinski, Robert West 0001. [doi]
• Stochastic Gradient Descent for Gaussian Processes Done RightJihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz. [doi]
• Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM FinetuningBingchen Zhao, Haoqin Tu, Chen Wei 0005, Jieru Mei, Cihang Xie. [doi]
• Fully Hyperbolic Convolutional Neural Networks for Computer VisionAhmad Bdeir, Kristian Schwethelm, Niels Landwehr. [doi]
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language ModelsYung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James R. Glass, Pengcheng He. [doi]
• Towards Transparent Time Series ForecastingKrzysztof Kacprzyk, Tennison Liu, Mihaela van der Schaar. [doi]
• Scaling Supervised Local Learning with Augmented Auxiliary NetworksChenxiang Ma, Jibin Wu, Chenyang Si, K. C. Tan. [doi]
• Neur2RO: Neural Two-Stage Robust OptimizationJustin Dumouchelle, Esther Julien, Jannis Kurtz, Elias Boutros Khalil. [doi]
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsXuhui Zhou, Hao Zhu 0011, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, Maarten Sap. [doi]
• Robustifying and Boosting Training-Free Neural Architecture SearchZhenfeng He, Yao Shu, Zhongxiang Dai, Bryan Kian Hsiang Low. [doi]
• Bandits with Replenishable Knapsacks: the Best of both WorldsMartino Bernasconi, Matteo Castiglioni, Andrea Celli, Federico Fusco. [doi]
• DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic ManipulationZilin Si, Gu Zhang, Qingwei Ben, Branden Romero, Zhou Xian, Chao Liu, Chuang Gan. [doi]
• Neural Polynomial Gabor Fields for Macro Motion AnalysisChen Geng 0001, Hong-Xing Yu, Sida Peng, Xiaowei Zhou, Jiajun Wu 0001. [doi]
• A representation-learning game for classes of prediction tasksNeria Uzan, Nir Weinberger. [doi]
• R-EDL: Relaxing Nonessential Settings of Evidential Deep LearningMengyuan Chen, Junyu Gao 0002, Changsheng Xu. [doi]
• Fast Imitation via Behavior Foundation ModelsMatteo Pirotta, Andrea Tirinzoni, Ahmed Touati, Alessandro Lazaric, Yann Ollivier. [doi]
• Are Human-generated Demonstrations Necessary for In-context Learning?Rui Li, Guoyin Wang 0002, Jiwei Li 0001. [doi]
• Simplicial Representation Learning with Neural k-FormsKelly Maggs, Celia Hacker, Bastian Rieck. [doi]
• Unsupervised Order LearningSeon-Ho Lee, Nyeong-Ho Shin, Chang-Su Kim 0001. [doi]
• NeRM: Learning Neural Representations for High-Framerate Human Motion SynthesisDong Wei, HuaiJiang Sun, Bin Li 0084, Xiaoning Sun, Shengxiang Hu 0001, Weiqing Li, Jianfeng Lu. [doi]
• Efficient Streaming Language Models with Attention SinksGuangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis. [doi]
• Unsupervised Pretraining for Fact Verification by Language Model DistillationAdrián Bazaga, Pietro Lio, Gos Micklem. [doi]
• Conformal Prediction via Regression-as-ClassificationEtash Kumar Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugène Ndiaye. [doi]
• Scalable Neural Network KernelsArijit Sehanobish, Krzysztof Marcin Choromanski, Yunfan Zhao, Kumar Avinava Dubey, Valerii Likhosherstov. [doi]
• Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal FeaturesAnnie S. Chen, Yoonho Lee 0001, Amrith Setlur, Sergey Levine, Chelsea Finn. [doi]
• SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMsJaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park, Sang-Woo Lee 0001, Minjoon Seo, Jung-Woo Ha 0001, Jinwoo Shin. [doi]
• NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear InterpolationPengfei Zheng, Yonggang Zhang, Zhen Fang 0001, Tongliang Liu, Defu Lian, Bo Han 0003. [doi]
• Understanding Addition in TransformersPhilip Quirke, Fazl Barez. [doi]
• Understanding the Robustness of Multi-modal Contrastive Learning to Distribution ShiftYihao Xue, Siddharth Joshi, Dang Nguyen, Baharan Mirzasoleiman. [doi]
• Debiasing Attention Mechanism in Transformer without DemographicsShenyu Lu, Yipei Wang, Xiaoqian Wang 0001. [doi]
• Scaling Laws of RoPE-based ExtrapolationXiaoran Liu, Hang Yan 0001, Chenxin An, Xipeng Qiu, Dahua Lin. [doi]
• Demystifying Embedding Spaces using Large Language ModelsGuy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Jihwan Jeong, Lior Shani, Azamat Tulepbergenov, Deepak Ramachandran, Martin Mladenov, Craig Boutilier. [doi]
• Unified Human-Scene Interaction via Prompted Chain-of-ContactsZeqi Xiao, Tai Wang, Jingbo Wang 0003, Jinkun Cao, Wenwei Zhang, Bo Dai 0002, Dahua Lin, Jiangmiao Pang. [doi]
• ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language ModelsIlker Kesen, Andrea Pedrotti, Mustafa Dogan, Michele Cafagna, Emre Can Acikgoz, Letitia Parcalabescu, Iacer Calixto, Anette Frank, Albert Gatt, Aykut Erdem, Erkut Erdem. [doi]
• DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction ModelYinghao Xu, Hao Tan 0002, Fujun Luan, Sai Bi, Peng Wang 0099, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, Kai Zhang 0045. [doi]
• Searching for High-Value Molecules Using Reinforcement Learning and TransformersRaj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, Glen Berseth. [doi]
• On the Hardness of Constrained Cooperative Multi-Agent Reinforcement LearningZiyi Chen 0002, Yi Zhou 0017, Heng Huang. [doi]
• Understanding Catastrophic Forgetting in Language Models via Implicit InferenceSuhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan. [doi]
• Denoising Task Routing for Diffusion ModelsByeongjun Park, Sangmin Woo, Hyojun Go, Jin Young Kim, Changick Kim. [doi]
• Improving Offline RL by Blending HeuristicsSinong Geng, Aldo Pacchiano, Andrey Kolobov, Ching-An Cheng. [doi]
• Bridging Neural and Symbolic Representations with Transitional Dictionary LearningJunyan Cheng, Peter Chin 0001. [doi]
• Sample-Efficient Multi-Agent RL: An Optimization PerspectiveNuoya Xiong, Zhihan Liu, Zhaoran Wang 0001, Zhuoran Yang. [doi]
• Quadratic models for understanding catapult dynamics of neural networksLibin Zhu, Chaoyue Liu 0001, Adityanarayanan Radhakrishnan, Mikhail Belkin. [doi]
• A robust differential Neural ODE OptimizerPanagiotis Theodoropoulos, Guan-Horng Liu, Tianrong Chen, Augustinos D. Saravanos, Evangelos A. Theodorou. [doi]
• A 2-Dimensional State Space Layer for Spatial Inductive BiasEthan Baron 0002, Itamar Zimerman, Lior Wolf. [doi]
• H-GAP: Humanoid Control with a Generalist PlannerZhengyao Jiang, Yingchen Xu, Nolan Wagener, Yicheng Luo, Michael Janner, Edward Grefenstette, Tim Rocktäschel, Yuandong Tian. [doi]
• Partitioning Message Passing for Graph Fraud DetectionWei Zhuo, Zemin Liu, Bryan Hooi, Bingsheng He, Guang Tan, Rizal Fathony, Jia Chen. [doi]
• BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain AbstractionJiangmeng Li, Fei Song, Yifan Jin, Wenwen Qiang, Changwen Zheng, Fuchun Sun 0001, Hui Xiong 0001. [doi]
• AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic ImagesPrithvijit Chattopadhyay, Bharat Goyal, Boglarka Ecsedi, Viraj Prabhu, Judy Hoffman. [doi]
• BadEdit: Backdooring Large Language Models by Model EditingYanzhou Li, Tianlin Li, Kangjie Chen, Jian Zhang, Shangqing Liu, Wenhan Wang, Tianwei Zhang 0004, Yang Liu 0003. [doi]
• A Unified and General Framework for Continual LearningZhenyi Wang, Yan Li, Li Shen 0008, Heng Huang. [doi]
• Addressing Signal Delay in Deep Reinforcement LearningWilliam Wei Wang, Dongqi Han, Xufang Luo, Dongsheng Li 0002. [doi]
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing SynthesizersKai Shen, Zeqian Ju, Xu Tan 0003, Eric Liu, Yichong Leng, Lei He 0005, Tao Qin 0001, Sheng Zhao, Jiang Bian 0002. [doi]
• Robust agents learn causal world modelsJonathan Richens, Tom Everitt. [doi]
• Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class ClassificationGuodong Wang, Yunhong Wang, Xiuguo Bao, Di Huang 0001. [doi]
• Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at OddsMichael-Andrei Panaitescu-Liess, Yigitcan Kaya, Sicheng Zhu, Furong Huang, Tudor Dumitras. [doi]
• Grokking as a First Order Phase Transition in Two Layer NetworksNoa Rubin, Inbar Seroussi, Zohar Ringel. [doi]
• Privacy-Preserving In-Context Learning with Differentially Private Few-Shot GenerationXinyu Tang, Richard Shin, Huseyin A. Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin 0001, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim. [doi]
• Hypergraph Dynamic SystemJielong Yan, Yifan Feng, Shihui Ying, Yue Gao 0002. [doi]
• Repelling Random WalksIsaac Reid, Eli Berger, Krzysztof Marcin Choromanski, Adrian Weller. [doi]
• Distinguished In Uniform: Self-Attention Vs. Virtual NodesEran Rosenbluth, Jan Tönshoff, Martin Ritzert, Berke Kisin, Martin Grohe. [doi]
• Graph Parsing NetworksYunchong Song, Siyuan Huang 0003, Xinbing Wang, Chenghu Zhou, Zhouhan Lin. [doi]
• 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud PretrainingSiming Yan, Yuqi Yang, Yu-Xiao Guo 0001, Hao Pan 0001, Peng-Shuai Wang, Xin Tong 0001, Yang Liu 0014, Qixing Huang. [doi]
• MMICL: Empowering Vision-language Model with Multi-Modal In-Context LearningHaozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen 0024, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang. [doi]
• Self-supervised Pocket Pretraining via Protein Fragment-Surroundings AlignmentBowen Gao, Yinjun Jia, Yuanle Mo, Yuyan Ni, Wei-Ying Ma, Zhi-Ming Ma, Yanyan Lan. [doi]
• Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence RateMeirui Jiang, Anjie Le, Xiaoxiao Li, Qi Dou 0001. [doi]
• Xformer: Hybrid X-Shaped Transformer for Image DenoisingJiale Zhang, Yulun Zhang, Jinjin Gu, Jiahua Dong, Linghe Kong, Xiaokang Yang. [doi]
• Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent GeometriesHaitz Sáez de Ocáriz Borde, Anastasis Kratsios. [doi]
• PRIME: Prioritizing Interpretability in Failure Mode ExtractionKeivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi. [doi]
• Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement LearningSumeet Batra, Bryon Tjanaka, Matthew Christopher Fontaine, Aleksei Petrenko, Stefanos Nikolaidis, Gaurav S. Sukhatme. [doi]
• Protein Multimer Structure Prediction via Prompt LearningZiqi Gao, Xiangguo Sun, Zijing Liu, Yu Li, Hong Cheng 0001, Jia Li 0009. [doi]
• SAFLEX: Self-Adaptive Augmentation via Feature Label ExtrapolationMucong Ding, Bang An, Yuancheng Xu, Anirudh Satheesh, Furong Huang. [doi]
• Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real WorldRujie Wu, Xiaojian Ma, Zhenliang Zhang 0002, Wei Wang 0115, Qing Li 0003, Song Chun Zhu, Yizhou Wang 0001. [doi]
• Transferring Learning Trajectories of Neural NetworksDaiki Chijiwa. [doi]
• Learning with a Mole: Transferable latent spatial representations for navigation without reconstructionGuillaume Bono, Leonid Antsfeld, Assem Sadek, Gianluca Monaci, Christian Wolf 0001. [doi]
• NOLA: Compressing LoRA using Linear Combination of Random BasisSoroush Abbasi Koohpayegani, Navaneet K. L., Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash. [doi]
• Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech SynthesisZiyue Jiang 0001, Jinglin Liu, Yi Ren 0006, Jinzheng He, Zhenhui Ye, Shengpeng Ji, Qian Yang, Chen Zhang 0020, Pengfei Wei, Chunfeng Wang, Xiang Yin 0006, Zejun Ma, Zhou Zhao. [doi]
• Elucidating the Exposure Bias in Diffusion ModelsMang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Önal Ertugrul. [doi]
• Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL PoliciesHaanvid Lee, Tri Wahyu Guntara, Jongmin Lee 0004, Yung-Kyun Noh, Kee-Eung Kim. [doi]
• Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy EvaluationHaruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito. [doi]
• Successor Heads: Recurring, Interpretable Attention Heads In The WildRhys Gould, Euan Ong, George Ogden, Arthur Conmy. [doi]
• Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement LearningGe Li, Hongyi Zhou, Dominik Roth, Serge Thilges, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann. [doi]
• Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining ApproachXiang Lan 0004, Hanshu Yan, Shenda Hong, Mengling Feng. [doi]
• Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated LearningYavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin, Salman Avestimehr. [doi]
• To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic DatasetsDarshil Doshi, Aritra Das, Tianyu He, Andrey Gromov. [doi]
• Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videoShashanka Venkataramanan, Mamshad Nayeem Rizve, João Carreira 0001, Yuki M. Asano, Yannis Avrithis. [doi]
• IRAD: Implicit Representation-driven Image Resampling against Adversarial AttacksYue Cao, Tianlin Li, Xiaofeng Cao 0002, Ivor W. Tsang, Yang Liu 0003, Qing Guo 0005. [doi]
• CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-SpeechJaehyeon Kim, Keon Lee, Seungjun Chung, Jaewoong Cho. [doi]
• LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained DescriptorsSheng Jin 0002, Xueying Jiang, Jiaxing Huang 0001, Lewei Lu, Shijian Lu. [doi]
• Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rankZihan Wang, Arthur Jacot. [doi]
• Learning interpretable control inputs and dynamics underlying animal locomotionThomas Soares Mullen, Marine Schimel, Guillaume Hennequin, Christian K. Machens, Michael B. Orger, Adrien Jouary. [doi]
• Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity TrackingNikhil Prakash, Tamar Rott Shaham, Tal Haklay, Yonatan Belinkov, David Bau. [doi]
• Information Bottleneck Analysis of Deep Neural Networks via Lossy CompressionIvan Butakov, Aleksander Tolmachev, Sofia Malanchuk, Anna Neopryatnaya, Alexey A. Frolov, Kirill V. Andreev. [doi]
• Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human DemonstrationsXiaogang Jia, Denis Blessing, Xinkai Jiang, Moritz Reuss, Atalay Donat, Rudolf Lioutikov, Gerhard Neumann. [doi]
• SAS: Structured Activation SparsificationYusuke Sekikawa, Shingo Yashima. [doi]
• An interpretable error correction method for enhancing code-to-code translationMin Xue, Artur Andrzejak 0001, Marla Leuther. [doi]
• R-MAE: Regions Meet Masked AutoencodersDuy-Kien Nguyen, Yanghao Li, Vaibhav Aggarwal, Martin R. Oswald, Alexander Kirillov, Cees G. M. Snoek, Xinlei Chen. [doi]
• In-Context Learning Dynamics with Random Binary SequencesEric J. Bigelow, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tomer D. Ullman. [doi]
• Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised LearningSheng Li 0019, Chao Wu, Ao Li, Yanzhi Wang, Xulong Tang, Geng Yuan. [doi]
• On the Effect of Batch Size in Byzantine-Robust Distributed LearningYi-Rui Yang, Chang-Wei Shi, Wu-Jun Li. [doi]
• Lagrangian Flow Networks for Conservation LawsFabricio Arend Torres, Marcello Massimo Negri, Marco Inversi, Jonathan Aellen, Volker Roth 0001. [doi]
• On Trajectory Augmentations for Off-Policy EvaluationGe Gao, Qitong Gao, Xi Yang 0019, Song Ju, Miroslav Pajic, Min Chi. [doi]
• Efficient Heterogeneous Meta-Learning via Channel Shuffling ModulationMinh Hoang, Carl Kingsford. [doi]
• SF(DA)2: Source-free Domain Adaptation Through the Lens of Data AugmentationUiwon Hwang, Jonghyun Lee 0004, Juhyeon Shin, Sungroh Yoon. [doi]
• Tree-Planner: Efficient Close-loop Task Planning with Large Language ModelsMengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu 0004, Wenqi Shao, Qiguang Chen, Bin Wang 0034, Yu Qiao 0001, Ping Luo 0002. [doi]
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsWenqi Shao, Mengzhao Chen, Zhaoyang Zhang 0004, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao 0007, Yu Qiao 0001, Ping Luo 0002. [doi]
• DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric VoxelizationYanpeng Zhao, Siyu Gao, Yunbo Wang, Xiaokang Yang. [doi]
• Linear Log-Normal Attention with Unbiased ConcentrationYury Nahshan, Joseph Kampeas, Emir Haleva. [doi]
• MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to UseYue Huang, Jiawen Shi, Yuan Li, Chenrui Fan, Siyuan Wu, Qihui Zhang, Yixin Liu 0002, Pan Zhou 0001, Yao Wan 0001, Neil Zhenqiang Gong, Lichao Sun 0001. [doi]
• Learning Energy-Based Models by Cooperative Diffusion Recovery LikelihoodYaxuan Zhu, Jianwen Xie, Ying Nian Wu, RuiQi Gao. [doi]
• Modeling Boundedly Rational Agents with Latent Inference BudgetsAthul Paul Jacob, Abhishek Gupta 0004, Jacob Andreas. [doi]
• Meta-Evolve: Continuous Robot Evolution for One-to-many Policy TransferXingyu Liu, Deepak Pathak, Ding Zhao. [doi]
• Momentum Benefits Non-iid Federated Learning Simply and ProvablyZiheng Cheng, Xinmeng Huang, Pengfei Wu, Kun Yuan. [doi]
• BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input DetectionTinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal. [doi]
• Self-Alignment with Instruction BacktranslationXian Li, Ping Yu, Chunting Zhou, Timo Schick, Omer Levy, Luke Zettlemoyer, Jason Weston, Mike Lewis. [doi]