default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID42nd ICML 2025: Vancouver, BC, Canada
- Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net 2025
Accept (oral)
- Santhosh Karnik, Anna Veselovska, Mark A. Iwen, Felix Krahmer:
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent. - Loek van Rossem, Andrew M. Saxe:
Algorithm Development in Neural Networks: Insights from the Streaming Parity Task. - Zhiyuan Yan, Jiangming Wang, Peng Jin, Ke-Yue Zhang, Chengchun Liu, Shen Chen, Taiping Yao, Shouhong Ding, Baoyuan Wu, Li Yuan:
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection. - Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel:
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies. - Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani, Amir Barati Farimani, Khoa D. Doan, Chandan K. Reddy:
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models. - Alec Helbling, Tuna Han Salih Meral, Benjamin Hoover, Pinar Yanardag, Duen Horng Chau:
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features. - Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin:
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. - Peter Halmos, Julian Gold, Xinhao Liu, Benjamin J. Raphael:
Hierarchical Refinement: Optimal Transport to Infinity and Beyond. - Jaeyeon Kim, Kulin Shah, Vasilis Kontonis, Sham M. Kakade, Sitan Chen:
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions. - Tomohiro Shiraishi, Tatsuya Matsukawa, Shuichi Nishino, Ichiro Takeuchi:
Statistical Test for Feature Selection Pipelines by Selective Inference. - Jasper C. H. Lee, Walter McKelvie, Maoyuan Song, Paul Valiant:
All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance. - Samuel Miserendino, Michele Wang, Tejal Patwardhan, Johannes Heidecke:
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering? - Fahim Tajwar, Yiding Jiang, Abitha Thankaraj, Sumaita Sadia Rahman, J. Zico Kolter, Jeff Schneider, Russ Salakhutdinov:
Training a Generally Curious Agent. - Georgy Noarov, Ramya Ramalingam, Aaron Roth, Stephan Xie:
High-Dimensional Prediction for Sequential Decision Making. - Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang:
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents. - Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri:
Auditing $f$-differential privacy in one run. - Lorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart:
Learning with Expected Signatures: Theory and Applications. - Ilias Diakonikolas, Mingchen Ma, Lisheng Ren, Christos Tzamos:
Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise. - Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm:
Expected Variational Inequalities. - Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano:
Improving the Scaling Laws of Synthetic Data with Deliberate Practice. - Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala:
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks. - Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon Shaolei Du, Max Kleiman-Weiner, Natasha Jaques:
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination. - Oscar Skean, Md Rifat Arefin, Dan Zhao, Niket Patel, Jalal Naghiyev, Yann LeCun, Ravid Shwartz-Ziv:
Layer by Layer: Uncovering Hidden Representations in Language Models. - Filippo Bigi, Marcel F. Langer, Michele Ceriotti:
The dark side of the forces: assessing non-conservative force models for atomistic machine learning. - Nuno Gonçalves, Marcos V. Treviso, André F. T. Martins:
AdaSplash: Adaptive Sparse Flash Attention. - Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Rémi Munos, Alessandro Lazaric, Ahmed Touati:
Temporal Difference Flows. - Josh Givens, Song Liu, Henry W. J. Reeve:
Score Matching with Missing Data. - Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan:
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction. - Rylan Schaeffer, Joshua Kazdan, John Hughes, Jordan Juravsky, Sara Price, Aengus Lynch, Erik Jones, Robert Kirk, Azalia Mirhoseini, Sanmi Koyejo:
How Do Large Language Monkeys Get Their Power (Laws)? - Antoine Wehenkel, Juan L. Gamella, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Jörn-Henrik Jacobsen, Marco Cuturi:
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration. - Nuojin Cheng, Leonard Papenmeier, Stephen Becker, Luigi Nardi:
A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization. - Jake C. Snell, Thomas L. Griffiths:
Conformal Prediction as Bayesian Quadrature. - Weihan Li, Yule Wang, Chengrui Li, Anqi Wu:
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes. - Gramoz Goranci, Peter Kiss, Neel Patel, Martin P. Seybold, Eva Szilagyi, Da Wei Zheng:
Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time. - Unai Fischer Abaigar, Christoph Kern, Juan Carlos Perdomo:
The Value of Prediction in Identifying the Worst-Off. - Alexandra Maria Proca, Clémentine Carla Juliette Dominé, Murray Shanahan, Pedro A. M. Mediano:
Learning dynamics in linear recurrent neural networks. - Zheng Lian, Haoyu Chen, Lan Chen, Haiyang Sun, Licai Sun, Yong Ren, Zebang Cheng, Bin Liu, Rui Liu, Xiaojiang Peng, Jiangyan Yi, Jianhua Tao:
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models. - Yiming Qin, Manuel Madeira, Dorina Thanou, Pascal Frossard:
DeFoG: Discrete Flow Matching for Graph Generation. - Sumin Cho, Dongwon Kim, Kwangsu Kim:
One-Step Generalization Ratio Guided Optimization for Domain Generalization. - Junlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu, Junxian He:
CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction. - Matthew Smart, Alberto Bietti, Anirvan M. Sengupta:
In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval. - Zhijing Wan, Zhixiang Wang, Zheng Wang, Xin Xu, Shin'ichi Satoh:
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection. - Tiansheng Wen, Yifei Wang, Zequn Zeng, Zhong Peng, Yudi Su, Xinyang Liu, Bo Chen, Hongwei Liu, Stefanie Jegelka, Chenyu You:
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation. - Ermis Soumalias, Jakob Heiss
, Jakob Weissteiner, Sven Seuken:
Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All. - Niclas Boehmer, Sara Fish, Ariel D. Procaccia:
Generative Social Choice: The Next Generation. - Saurabh Jha, Rohan R. Arora, Yuji Watanabe, Takumi Yanagawa, Yinfang Chen, Jackson Clark, Bhavya, Mudit Verma, Harshit Kumar, Hirokuni Kitahara, Noah Zheutlin, Saki Takano, Divya Pathak, Felix George, Xinbo Wu, Bekir O. Turkkan, Gerard Vanloo, Michael Nidd, Ting Dai, Oishik Chatterjee, Pranjal Gupta, Suranjana Samanta, Pooja Aggarwal, Rong Lee, Jae-wook Ahn, Debanjana Kar, Amit M. Paradkar, Yu Deng, Pratibha Moogi, Prateeti Mohapatra, Naoki Abe, Chandrasekhar Narayanaswami, Tianyin Xu, Lav R. Varshney, Ruchi Mahindru, Anca Sailer, Laura Shwartz, Daby Sow, Nicholas C. Fuller, Ruchir Puri:
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks. - Niclas Dern, John Patrick Cunningham, Geoff Pleiss:
Theoretical Limitations of Ensembles in the Age of Overparameterization. - Mason Kamb, Surya Ganguli:
An analytic theory of creativity in convolutional diffusion models. - Jeffrey A. Chan-Santiago, Praveen Tirupattur, Gaurav Kumar Nayak, Gaowen Liu, Mubarak Shah:
MGD3 : Mode-Guided Dataset Distillation using Diffusion Models. - Varun Babbar, Hayden McTavish, Cynthia Rudin, Margo I. Seltzer:
Near-Optimal Decision Trees in a SPLIT Second. - Shiqing Gao, Jiaxin Ding, Luoyi Fu, Xinbing Wang:
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration. - Konstantinos A. Oikonomidis, Jan Quan, Emanuel Laude, Panagiotis Patrinos:
Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness. - Anshuman Chhabra, Bo Li, Jian Chen, Prasant Mohapatra, Hongfu Liu:
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models. - Xiang Fu, Brandon M. Wood, Luis Barroso-Luque, Daniel S. Levine, Meng Gao, Misko Dzamba, C. Lawrence Zitnick:
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction. - Nicholas Carlini, Edoardo Debenedetti, Javier Rando, Milad Nasr, Florian Tramèr:
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses. - Juan L. Gamella, Simon Bing, Jakob Runge:
Sanity Checking Causal Representation Learning on a Simple Real-World System. - Sibylle Marcotte, Rémi Gribonval, Gabriel Peyré:
Transformative or Conservative? Conservation laws for ResNets and Transformers. - Michael Sucker, Peter Ochs:
A Generalization Result for Convergence in Learning-to-Optimize. - Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, Mao Yang:
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking. - Lifu Liu, Shiyuan He, Jianhua Guo:
An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfer. - Etienne Gauthier, Francis Bach, Michael I. Jordan:
Statistical Collusion by Collectives on Learning Platforms. - Konrad Mundinger, Max Zimmer, Aldo Kiem, Christoph Spiegel, Sebastian Pokutta:
Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? - Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe:
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning. - Guanghui Wang, Zhiyong Yang, Zitai Wang, Shi Wang, Qianqian Xu, Qingming Huang:
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-Divergence. - Jongwoo Ko, Tianyi Chen, Sungnyun Kim, Tianyu Ding, Luming Liang, Ilya Zharkov, Se-Young Yun:
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs. - Xin Su, Man Luo, Kris W. Pan, Tien Pei Chou, Vasudev Lal, Phillip Howard:
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs. - Xingjin Wang, Howe Tissue, Lu Wang, Linjing Li, Daniel Dajun Zeng:
Learning Dynamics in Continual Pre-Training for Large Language Models. - Junsu Kim, Jaeyeon Kim, Ernest K. Ryu:
LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail). - Yuhan Ye, Ying Cui, Jingyi Wang:
An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions. - Kwangjun Ahn, Gagik Magakyan, Ashok Cutkosky:
General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization. - Jan Betley, Daniel Chee Hian Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, Owain Evans:
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs. - Jie Hu, Yi-Ting Ma, Do Young Eun:
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs. - Se Jin Park, Julian Salazar, Aren Jansen, Keisuke Kinoshita, Yong Man Ro, R. J. Skerry-Ryan:
Long-Form Speech Generation with Spoken Language Models. - Ronak Mehta, Zaïd Harchaoui:
A Generalization Theory for Zero-Shot Prediction. - Herman Chau, Helen Jenne, Davis Brown, Jesse He, Mark Raugas, Sara C. Billey, Henry Kvinge:
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics. - Longzhu He, Chaozhuo Li, Peng Tang, Sen Su:
Going Deeper into Locally Differentially Private Graph Neural Networks. - Tian-Zuo Wang, Wen-Bo Du, Zhi-Hua Zhou:
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules. - Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Jian Tong, Haodong Duan, Qipeng Guo, Jiaqi Wang, Xipeng Qiu, Dahua Lin:
VideoRoPE: What Makes for Good Video Rotary Position Embedding? - Linqi Zhou, Stefano Ermon, Jiaming Song:
Inductive Moment Matching. - Guozheng Ma, Lu Li, Zilin Wang, Li Shen, Pierre-Luc Bacon, Dacheng Tao:
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning. - Yuanhe Zhang, Fanghui Liu, Yudong Chen:
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently. - Yejiang Wang, Yuhai Zhao, Zhengkui Wang, Ling Li, Jiapu Wang, Fangting Li, Miaomiao Huang, Shirui Pan, Xingwei Wang:
Equivalence is All: A Unified View for Self-supervised Graph Learning. - Hao Fei, Yuan Zhou, Juncheng Li, Xiangtai Li, Qingshan Xu, Bobo Li, Shengqiong Wu, Yaoting Wang, Junbao Zhou, Jiahao Meng, Qingyu Shi, Zhiyuan Zhou, Liangtao Shi, Minghe Gao, Daoan Zhang, Zhiqi Ge, Siliang Tang, Kaihang Pan, Yaobo Ye, Haobo Yuan, Tao Zhang, Weiming Wu, Tianjie Ju, Zixiang Meng, Shilin Xu, Liyu Jia, Wentao Hu, Meng Luo, Jiebo Luo, Tat-Seng Chua, Shuicheng Yan, Hanwang Zhang:
On Path to Multimodal Generalist: General-Level and General-Bench. - Yong Liu, Guo Qin, Zhiyuan Shi, Zhi Chen, Caiyin Yang, Xiangdong Huang, Jianmin Wang, Mingsheng Long:
Sundial: A Family of Highly Capable Time Series Foundation Models. - Xuesong Wang, He Zhao, Edwin V. Bonilla:
Rényi Neural Processes. - Amber Yijia Zheng, Site Bai, Brian Bullins, Raymond A. Yeh:
Model Immunization from a Condition Number Perspective. - Clément Bonet, Christophe Vauthier, Anna Korba:
Flowing Datasets with Wasserstein over Wasserstein Gradient Flows. - Wenbin Wang, Yongcheng Jing, Liang Ding, Yingjie Wang, Li Shen, Yong Luo, Bo Du, Dacheng Tao:
Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG. - Fangwen Wu, Lechao Cheng, Shengeng Tang, Xiaofeng Zhu, Chaowei Fang, Dingwen Zhang, Meng Wang:
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning. - Yunzhuo Hao, Jiawei Gu, Huichen Will Wang, Linjie Li, Zhengyuan Yang, Lijuan Wang, Yu Cheng:
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark. - Shogo Iwazaki, Shion Takeno:
Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance. - Shirley Wu, Michel Galley, Baolin Peng, Hao Cheng, Gavin Li, Yao Dou, Weixin Cai, James Zou, Jure Leskovec, Jianfeng Gao:
CollabLLM: From Passive Responders to Active Collaborators. - Angéline Pouget, Mohammad Yaghini, Stephan Rabanser, Nicolas Papernot:
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings. - Erez Peterfreund, Ofir Lindenbaum, Yuval Kluger, Boris Landa:
Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data. - Marvin Li, Aayush Karan, Sitan Chen:
Blink of an eye: a simple theory for feature localization in generative models. - Shiyuan Feng, Ying Feng, George Zhaoqi Li, Zhao Song, David P. Woodruff, Lichen Zhang:
On Differential Privacy for Adaptively Solving Search Problems via Sketching. - Yangsibo Huang, Milad Nasr, Anastasios Nikolas Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Ken Liu, Ion Stoica, Florian Tramèr, Chiyuan Zhang:
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards. - Wendong Bu, Yang Wu, Qifan Yu, Minghe Gao, Bingchen Miao, Zhenkui Zhang, Kaihang Pan, Liyunfei, Mengze Li, Wei Ji, Juncheng Li, Siliang Tang, Yueting Zhuang:
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities. - Chengmei Niu, Zhenyu Liao, Zenan Ling, Michael W. Mahoney:
Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton. - Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao Gu, Huangjie Zheng, Tianrong Chen, Miguel Ángel Bautista, Navdeep Jaitly, Joshua M. Susskind:
Normalizing Flows are Capable Generative Models. - Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, Xiang Wang:
Multi-agent Architecture Search via Agentic Supernet. - Hila Chefer, Uriel Singer, Amit Zohar, Yuval Kirstain, Adam Polyak, Yaniv Taigman, Lior Wolf, Shelly Sheynin:
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models. - Shuting He, Guangquan Jie, Changshuo Wang, Yun Zhou, Shuming Hu, Guanbin Li, Henghui Ding:
ReferSplat: Referring Segmentation in 3D Gaussian Splatting. - Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, Jun Zhu:
STAIR: Improving Safety Alignment with Introspective Reasoning. - Chi Zhang, Lianhai Ren, Jingpu Cheng, Qianxiao Li:
From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control. - Shibo Jie, Yehui Tang, Kai Han, Yitong Li, Duyu Tang, Zhi-Hong Deng, Yunhe Wang:
Mixture of Lookup Experts. - Haibo Chen, Xin Wang, Zeyang Zhang, Haoyang Li, Ling Feng, Wenwu Zhu:
AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization. - Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, Ying Fan, Jungtaek Kim, Hyung Il Koo, Kannan Ramchandran, Dimitris Papailiopoulos, Kangwook Lee:
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data.
Accept (spotlight poster)
- Junyi Lu, Lili Jiang, Xiaojia Li, Jianbing Fang, Fengjun Zhang, Li Yang, Chun Zuo:
Towards Practical Defect-Focused Automated Code Review. - Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanovic, Jingxuan He, Martin T. Vechev:
BaxBench: Can LLMs Generate Correct and Secure Backends? - Marvin F. da Silva, Felix Dangel, Sageev Oore:
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It. - Abdülkadir Gökce, Martin Schrimpf:
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream. - Dongjae Jeon, Dueun Kim, Albert No:
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes. - Tuan Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard:
Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport. - Hyeongwon Jang, Changhun Kim, Eunho Yang:
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation. - Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen, Alexander M. Rush, Wenting Zhao, Sanjiban Choudhury:
Multi-Turn Code Generation Through Single-Step Rewards. - Ulzee An, Moonseong Jeong, Simon A. Lee, Aditya Gorla, Yuzhe Yang, Sriram Sankararaman:
Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models. - Max Hopkins, Shay Moran:
The Role of Randomness in Stability. - Ruichuan Huang, Jiawei Zhang, Ahmet Alacaoglu:
Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints. - Hao Chen, Yujin Han, Fangyi Chen, Xiang Li, Yidong Wang, Jindong Wang, Ze Wang, Zicheng Liu, Difan Zou, Bhiksha Raj:
Masked Autoencoders Are Effective Tokenizers for Diffusion Models. - Linxi Zhao, Yihe Deng, Weitong Zhang, Quanquan Gu:
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance. - Taehyun Cho, Seokhun Ju, Seungyub Han, Dohyeong Kim, Kyungjae Lee, Jungwoo Lee:
Policy-labeled Preference Learning: Is Preference Enough for RLHF? - David Fleischer, David A. Stephens, Archer Y. Yang:
Generalized Random Forests Using Fixed-Point Trees. - Ilias Diakonikolas, Daniel Kane, Sushrut Karmalkar, Jasper C. H. Lee, Thanasis Pittas:
On Learning Parallel Pancakes with Mostly Uniform Weights. - Jaesik Yoon, Hyeonseo Cho, Doojin Baek, Yoshua Bengio, Sungjin Ahn:
Monte Carlo Tree Diffusion for System 2 Planning. - Shayan Kiyani, George J. Pappas, Aaron Roth, Hamed Hassani:
Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents. - Judy Hanwen Shen, Ellen Vitercik, Anders Wikum:
Algorithms with Calibrated Machine Learning Predictions. - Avery Ma, Yangchen Pan, Amir-massoud Farahmand:
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling. - Jonas Gehring, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, Gabriel Synnaeve:
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning. - Terje Mildner, Oliver Hamelijnck, Paris Giampouras, Theodoros Damoulas:
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework. - Georgy Noarov, Riccardo Fogliato, Martín Bertrán, Aaron Roth:
Stronger Neyman Regret Guarantees for Adaptive Experimental Design. - Divya Shyamal, Jiaqi Zhang, Caroline Uhler:
Probabilistic Factorial Experimental Design for Combinatorial Interventions. - Etowah Adams, Liam Bai, Minji Lee, Yiyang Yu, Mohammed AlQuraishi:
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models. - Aditya Gorla, Ryan Wang, Zhengtong Liu, Ulzee An, Sriram Sankararaman:
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation. - Yizhuo Chen, Chun-Fu Chen, Hsiang Hsu, Shaohan Hu, Tarek F. Abdelzaher:
PASS: Private Attributes Protection with Stochastic Data Substitution. - Sunny Sanyal, Hayden Prairie, Rudrajit Das, Ali Kavis, Sujay Sanghavi:
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting. - Ali Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran:
Not All Wrong is Bad: Using Adversarial Examples for Unlearning. - Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher:
Training Deep Learning Models with Norm-Constrained LMOs. - Tim Vieira, Benjamin LeBrun, Mario Giulianelli, Juan Luis Gastaldi, Brian DuSell, John Terilla, Timothy J. O'Donnell, Ryan Cotterell:
From Language Models over Tokens to Language Models over Characters. - Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti:
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety. - Alessandro Palma, Sergei Rybakov, Leon Hetzel, Stephan Günnemann, Fabian J. Theis:
Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation. - Hjalmar Wijk, Tao Roa Lin, Joel Becker, Sami Jawhar, Neev Parikh, Thomas Broadley, Lawrence Chan, Michael Chen, Joshua Clymer, Jai Dhyani, Elena Ericheva, Katharyn Garcia, Brian Goodrich, Nikola Jurkovic, Megan Kinniment, Aron Lajko, Seraphina Nix, Lucas Jun Koba Sato, William Saunders, Maksym Taran, Ben West, Elizabeth Barnes:
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts. - Seth Karten, Andy Luu Nguyen, Chi Jin:
PokéChamp: an Expert-level Minimax Language Agent. - James Rowbottom, Georg Maierhofer, Teo Deveney, Eike Hermann Müller, Alberto Paganini, Katharina Schratz, Pietro Lio, Carola-Bibiane Schönlieb, Chris J. Budd:
G-Adaptivity: optimised graph-based mesh relocation for finite element methods. - John Schultz, Jakub Adámek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada A. Lewis, Anian Ruoss, Tom Zahavy, Petar Velickovic, Laurel Prince, Satinder Singh, Eric Malmi, Nenad Tomasev:
Mastering Board Games by External and Internal Planning with Language Models. - Dong Xiao, Guangyao Chen, Peixi Peng, Yangru Huang, Yifan Zhao, Yongxing Dai, Yonghong Tian:
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network. - Andreas Kalavas, Evangelos Kipouridis, Nithin Varma:
Towards Better-than-2 Approximation for Constrained Correlation Clustering. - Zhengxuan Wu, Aryaman Arora, Atticus Geiger, Zheng Wang, Jing Huang, Dan Jurafsky, Christopher D. Manning, Christopher Potts:
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders. - Amrith Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar:
Scaling Test-Time Compute Without Verification or RL is Suboptimal. - Haotian Wu, Gongpu Chen, Pier Luigi Dragotti, Deniz Gündüz:
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression. - Hugh Dance, Pierre Glaser, Peter Orbanz, Ryan P. Adams:
Efficiently Vectorized MCMC on Modern Accelerators. - Chenlu Ye, Yujia Jin, Alekh Agarwal, Tong Zhang:
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards. - Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora:
On the Power of Context-Enhanced Learning in LLMs. - Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka, Stephan Günnemann:
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting. - Damian Smith, Harvey Mannering, Antonia Marcu:
Functional Alignment Can Mislead: Examining Model Stitching. - Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang:
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals. - Shentong Mo, Sukmin Yun:
GMAIL: Generative Modality Alignment for generated Image Learning. - Georg Bökman, David Nordström, Fredrik Kahl:
Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency. - Yuanhong Zhang, Muyao Yuan, Weizhan Zhang, Tieliang Gong, Wen Wen, Jiangyong Ying, Weijie Shi:
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective. - Charita Dellaporta, Patrick O'Hara, Theodoros Damoulas:
Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets. - Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo:
Hyperspherical Normalization for Scalable Deep Reinforcement Learning. - Tejas Jayashankar, Jongha Jon Ryu, Gregory W. Wornell:
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions. - Thomas Pouplin, Kasia Kobalczyk, Hao Sun, Mihaela van der Schaar:
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data. - Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian, Roberto Bondesan, Alán Aspuru-Guzik, Arnaud Doucet, Rob Brekelmans, Alexander Tong, Kirill Neklyudov:
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts. - Tin Dizdarevic, Ravi Hammond, Tobias Gessler, Anisoara Calinescu, Jonathan Cook, Matteo Gallici, Andrei Lupu, Jakob Nicolaus Foerster:
Ad-Hoc Human-AI Coordination Challenge. - Shanshan Luo, Yixuan Yu, Chunchen Liu, Feng Xie, Zhi Geng:
Causal Attribution Analysis for Continuous Outcomes. - John Stewart Fabila-Carrasco, He Sun:
Signed Laplacians for Constrained Graph Clustering. - Hong-Ming Chiu, Hao Chen, Huan Zhang, Richard Y. Zhang:
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming. - Guanzheng Chen, Qilong Feng, Jinjie Ni, Xin Li, Michael Qizhe Shieh:
RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding. - Yi Xu, Laura Ruis, Tim Rocktäschel, Robert Kirk:
Investigating Non-Transitivity in LLM-as-a-Judge. - Linjian Meng, Wubing Chen, Wenbin Li, Tianpei Yang, Youzhi Zhang, Yang Gao:
Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games. - Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig:
Linearization Turns Neural Operators into Function-Valued Gaussian Processes. - Shira Vansover-Hager, Tomer Koren, Roi Livni:
Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization. - Jianqing Zhang, Yang Liu, Jie Fu, Yang Hua, Tianyuan Zou, Jian Cao, Qiang Yang:
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs. - Cosimo Gregucci, Bo Xiong, Daniel Hernández, Lorenzo Loconte, Pasquale Minervini, Steffen Staab, Antonio Vergari:
Is Complex Query Answering Really Complex? - Zhangyi Liu, Feng Liu, Rui Gao, Shuang Li:
Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization. - Anders Aamand, Fabrizio Boninsegna, Abigail Gentle, Jacob Imola, Rasmus Pagh:
Lightweight Protocols for Distributed Private Quantile Estimation. - Yikang Chen, Dehui Du:
Exogenous Isomorphism for Counterfactual Identifiability. - Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, Woohyung Lim:
Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data. - Qinglin Zhu, Runcong Zhao, Hanqi Yan, Yulan He, Yudong Chen, Lin Gui:
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration. - Olga Ovcharenko, Florian Barkmann, Philip Toma, Imant Daunhawer, Julia E. Vogt, Sebastian Schelter, Valentina Boeva:
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data. - Xingyu Zhou, Yulian Wu, Francesco Orabona:
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO. - Guiomar Pescador-Barrios, Sarah Filippi, Mark van der Wilk:
Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough? - Zhicheng Zhang, Wuyou Xia, Chenxi Zhao, Zhou Yan, Xiaoqiang Liu, Yongjie Zhu, Wenyu Qin, Pengfei Wan, Di Zhang, Jufeng Yang:
MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding. - Hao Li, Qi Lv, Rui Shao, Xiang Deng, Yinchuan Li, Jianye Hao, Liqiang Nie:
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization. - Yucheng Hu, Yanjiang Guo, Pengchao Wang, Xiaoyu Chen, Yen-Jen Wang, Jianke Zhang, Koushil Sreenath, Chaochao Lu, Jianyu Chen:
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations. - Xujie Song, Liangfa Chen, Tong Liu, Wenxuan Wang, Yinuo Wang, Shentao Qin, Yinsong Ma, Jingliang Duan, Shengbo Eben Li:
LipsNet++: Unifying Filter and Controller into a Policy Network. - Thibaut Issenhuth, Sangchul Lee, Ludovic Dos Santos, Jean-Yves Franceschi, Chansoo Kim, Alain Rakotomamonjy:
Improving Consistency Models with Generator-Augmented Flows. - Florian Peter Busch, Roshni Ramanna Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt:
Where is the Truth? The Risk of Getting Confounded in a Continual World. - Dongzhe Zheng, Wenjie Mei:
Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures. - Haoyang Li, Xin Wang, Zeyang Zhang, Zongyuan Wu, Linxin Xiao, Wenwu Zhu:
Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum. - Huanjian Zhou, Masashi Sugiyama:
Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models. - Yizi Zhang, Yanchen Wang, Mehdi Azabou, Alexandre Andre, Zixuan Wang, Hanrui Lyu, International Brain Laboratory, Eva L. Dyer, Liam Paninski, Cole Lincoln Hurwitz:
Neural Encoding and Decoding at Scale. - Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite:
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization. - Yu Sun, Xinhao Li, Karan Dalal, Jiarui Xu, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin:
Learning to (Learn at Test Time): RNNs with Expressive Hidden States. - Zichen Liu, Guoji Fu, Chao Du, Wee Sun Lee, Min Lin:
Continual Reinforcement Learning by Planning with Online World Models. - Sally Zhu, Ahmed M. Ahmed, Rohith Kuditipudi, Percy Liang:
Independence Tests for Language Models. - Tinglin Huang, Tianyu Liu, Mehrtash Babadi, Wengong Jin, Rex Ying:
Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching. - Guancheng Wan, Zijie Huang, Wanjia Zhao, Xiao Luo, Yizhou Sun, Wei Wang:
Rethink GraphODE Generalization within Coupled Dynamical System. - Yichen Li, Yuying Wang, Haozhao Wang, Yining Qi, Tianzhe Xiao, Ruixuan Li:
FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence. - Jintao Tong, Ran Ma, Yixiong Zou, Guangyao Chen, Yuhua Li, Ruixuan Li:
Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation. - Xinyue Zheng, Haowei Lin, Kaichen He, Zihao Wang, Qiang Fu, Haobo Fu, Zilong Zheng, Yitao Liang:
MCU: An Evaluation Framework for Open-Ended Game Agents. - Binchi Zhang, Zaiyi Zheng, Zhengzhang Chen, Jundong Li:
Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion. - Juan D. Correa, Elias Bareinboim:
Counterfactual Graphical Models: Constraints and Inference. - Daniel Shao, Richard J. Chen, Andrew H. Song, Joel Runevic, Ming Y. Lu, Tong Ding, Faisal Mahmood:
Do Multiple Instance Learning Models Transfer? - Xiyuan Wei, Ming C. Lin, Fanjiang Ye, Fengguang Song, Liangliang Cao, My T. Thai, Tianbao Yang:
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws. - Huigen Ye, Hua Xu, An Yan, Yaoyang Cheng:
Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems. - Zhenghai Xue, Lang Feng, Jiacheng Xu, Kang Kang, Xiang Wen, Bo An, Shuicheng Yan:
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning. - Daoyuan Chen, Haibin Wang, Yilun Huang, Ce Ge, Yaliang Li, Bolin Ding, Jingren Zhou:
Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development. - Nikolaus H. R. Howe, Ian R. McKenzie, Oskar John Hollinsworth, Michal Zajac, Tom Tseng, Aaron David Tucker, Pierre-Luc Bacon, Adam Gleave:
Scaling Trends in Language Model Robustness. - Lukas Braun, Erin Grant, Andrew M. Saxe:
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks. - Matthew Niedoba, Berend Zwartsenberg, Kevin Patrick Murphy, Frank Wood:
Towards a Mechanistic Explanation of Diffusion Model Generalization. - Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee, Nakul Agarwal, Sean Dae Houlihan, Soroush Vosoughi, Shao-Yuan Lo:
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner. - Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn:
Latent Diffusion Planning for Imitation Learning. - Mina Dalirrooyfard, Konstantin Makarychev, Slobodan Mitrovic:
Sparse-pivot: Dynamic correlation clustering for node insertions. - Kristina Nikolic, Luze Sun, Jie Zhang, Florian Tramèr:
The Jailbreak Tax: How Useful are Your Jailbreak Outputs? - Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt:
Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions. - Yu He, Ellen Vitercik:
Primal-Dual Neural Algorithmic Reasoning. - Yu Xin Li, Felix Dangel, Derek Tam, Colin Raffel:
Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator. - Chi-Ning Chou, Hang Le, Yichen Wang, SueYeon Chung:
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry. - Gwanhyeong Koo, Sunjae Yoon, Younghwan Lee, Ji Woo Hong, Chang D. Yoo:
FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields. - Cheng-Yen Hsieh, Xinyou Wang, Daiheng Zhang, Dongyu Xue, Fei Ye, Shujian Huang, Zaixiang Zheng, Quanquan Gu:
Elucidating the Design Space of Multimodal Protein Language Models. - Geigh Zollicoffer, Kenneth Eaton, Jonathan C. Balloch, Julia M. Kim, Wei Zhou, Robert Wright, Mark O. Riedl:
Novelty Detection in Reinforcement Learning with World Models. - Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka, Patrick Jaillet:
Learning with Exact Invariances in Polynomial Time. - Greyson Brothers:
Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs. - Attila Szász, Balázs Bánhelyi, Márk Jelasity:
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks. - Seungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal:
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective. - Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K. Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping:
Great Models Think Alike and this Undermines AI Oversight. - Zheyang Xiong, Ziyang Cai, John Cooper, Albert Ge, Vasilis Papageorgiou, Zack Sifakis, Angeliki Giannou, Ziqian Lin, Liu Yang, Saurabh Agarwal, Grigorios Chrysos, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos:
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition. - Mahir Labib Dihan, Md Tanvir Hassan, Md Tanvir Parvez, Md Hasebul Hasan, Md Almash Alam, Muhammad Aamir Cheema, Mohammed Eunus Ali, Md. Rizwan Parvez:
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models. - Abdulrahman Diaa, Toluwani Aremu, Nils Lukas:
Optimizing Adaptive Attacks against Watermarks for Language Models. - Jade Garcia Bourrée, Augustin Godinot, Sayan Biswas, Anne-Marie Kermarrec, Erwan Le Merrer, Gilles Trédan, Martijn de Vos, Milos Vujasinovic:
Robust ML Auditing using Prior Knowledge. - Armin Behnamnia, Gholamali Aminian, Alireza Aghaei, Chengchun Shi, Vincent Y. F. Tan, Hamid R. Rabiee:
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning. - Matteo Zecchin, Sangwoo Park, Osvaldo Simeone:
Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection. - Hanshi Sun, Li-Wen Chang, Wenlei Bao, Size Zheng, Ningxin Zheng, Xin Liu, Harry Dong, Yuejie Chi, Beidi Chen:
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference. - Marc Jourdan, Gizem Yüce, Nicolas Flammarion:
Learning Parametric Distributions from Samples and Preferences. - Lena Stempfle, Anton Matsson, Newton Mwai Kinyanjui, Fredrik D. Johansson:
Prediction models that learn to avoid missing values. - Siyuan Duan, Wenyuan Wu, Peng Hu, Zhenwen Ren, Dezhong Peng, Yuan Sun:
CoPINN: Cognitive Physics-Informed Neural Networks. - Mark Schöne, Babak Rahmani, Heiner Kremer, Fabian Falck, Hitesh Ballani, Jannes Gladrow:
Implicit Language Models are RNNs: Balancing Parallelization and Expressivity. - Liyuan Liang, Xinyi Chen, Gan Luo, Kun Yuan:
Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks. - Xingyu Wu, Jibin Wu, Yu Zhou, Liang Feng, Kc Tan:
Towards Robustness and Explainability of Automatic Algorithm Selection. - Zhen Liu, Yicheng Luo, Boyuan Li, Emadeldeen Eldele, Min Wu, Qianli Ma:
Learning Soft Sparse Shapes for Efficient Time-Series Classification. - Yuchen Zeng, Tuan Dinh, Wonjun Kang, Andreas C. Mueller:
TabFlex: Scaling Tabular Learning to Millions with Linear Attention. - Han Zhong, Zikang Shan, Guhao Feng, Wei Xiong, Xinle Cheng, Li Zhao, Di He, Jiang Bian, Liwei Wang:
DPO Meets PPO: Reinforced Token Optimization for RLHF. - Yuan Deng, Amin Karbasi, Vahab Mirrokni, Renato Paes Leme, Grigoris Velegkas, Song Zuo:
Procurement Auctions via Approximately Optimal Submodular Optimization. - Quang-Duy Tran, Bao Duong, Phuoc Nguyen, Thin Nguyen:
Identifying Causal Direction via Variational Bayesian Compression. - Weiwei Ye, Zhuopeng Xu, Ning Gui:
Non-stationary Diffusion For Probabilistic Time Series Forecasting. - Junchao Zhou, Yao Lu, Jie Wen, Guangming Lu:
Efficient and Separate Authentication Image Steganography Network. - Zheng Li, Zeyu Liu, Feng Xie, Hao Zhang, Chunchen Liu, Zhi Geng:
Local Identifying Causal Relations in the Presence of Latent Variables. - Mingjun Wang, Yihan Wen, Bin Sun, Jianan Mu, Juan Li, Xiaoyi Wang, Jing Justin Ye, Bei Yu, Huawei Li:
Bridging Layout and RTL: Knowledge Distillation based Timing Prediction. - Xiuyuan Wang, Chaochao Chen, Weiming Liu, Xinting Liao, Fan Wang, Xiaolin Zheng:
Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization. - Pablo Samuel Castro, Nenad Tomasev, Ankit Anand, Navodita Sharma, Rishika Mohanta, Aparna Dev, Kuba Perlin, Siddhant Jain, Kyle Levin, Noémi Élteto, Will Dabney, Alexander Novikov, Glenn C. Turner, Maria K. Eckstein, Nathaniel D. Daw, Kevin J. Miller, Kim Stachenfeld:
Discovering Symbolic Cognitive Models from Human and Animal Behavior. - Rina Bao, Shilong Dong, Zhenfang Chen, Sheng He, Ellen Grant, Yangming Ou:
Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning. - Jiayue Liu, Zhongchao Yi, Zhengyang Zhou, Qihe Huang, Kuo Yang, Xu Wang, Yang Wang:
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation. - Liang Yang, Yuwei Liu, Jiaming Zhuo, Di Jin, Chuan Wang, Zhen Wang, Xiaochun Cao:
Do We Really Need Message Passing in Brain Network Modeling? - Connor Schenck, Isaac Reid, Mithun George Jacob, Alex Bewley, Joshua Ainslie, David Rendleman, Deepali Jain, Mohit Sharma, Kumar Avinava Dubey, Ayzaan Wahid, Sumeet Singh, René Wagner, Tianli Ding, Chuyuan Fu, Arunkumar Byravan, Jake Varley, Alexey A. Gritsenko, Matthias Minderer, Dmitry Kalashnikov, Jonathan Tompson, Vikas Sindhwani, Krzysztof Marcin Choromanski:
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING. - Taj Jones-McCormick, Aukosh Jagannath, Subhabrata Sen:
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models. - Yupeng Hou, Jianmo Ni, Zhankui He, Noveen Sachdeva, Wang-Cheng Kang, Ed H. Chi, Julian J. McAuley, Derek Zhiyuan Cheng:
ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation. - Matthew Ashman, Cristiana Diaconu, Eric Langezaal, Adrian Weller, Richard E. Turner:
Gridded Transformer Neural Processes for Spatio-Temporal Data. - Yujin Oh, Pengfei Jin, Sangjoon Park, Sekeun Kim, Siyeop Yoon, Jin Sung Kim, Kyungsang Kim, Xiang Li, Quanzheng Li:
Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective. - Xin Chen, Yarden As, Andreas Krause:
Learning Safety Constraints for Large Language Models. - Yuxuan Zhu, Antony Kellermann, Dylan Bowman, Philip Li, Akul Gupta, Adarsh Danda, Richard Fang, Conner Jensen, Eric Ihli, Jason Benn, Jet Geronimo, Avi Dhir, Sudhit Rao, Kaicheng Yu, Twm Stone, Daniel Kang:
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities. - Paul McVay, Sergio Arnaud, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula, Phillip Thomas, Ruslan Partsey, Daniel Dugas, Abha Gejji, Alexander Sax, Vincent-Pierre Berges, Mikael Henaff, Ayush Jain, Ang Cao, Ishita Prasad, Mrinal Kalakrishnan, Michael Rabbat, Nicolas Ballas, Mido Assran, Oleksandr Maksymets, Aravind Rajeswaran:
LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D. - Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang:
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator. - Zian Li, Cai Zhou, Xiyuan Wang, Xingang Peng, Muhan Zhang:
Geometric Representation Condition Improves Equivariant Molecule Generation. - Moshe Eliasof, Alessio Gravina, Andrea Ceni, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schönlieb:
Graph Adaptive Autoregressive Moving Average Models. - Zirui Liu, Jiatong Li, Yan Zhuang, Qi Liu, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang:
am-ELO: A Stable Framework for Arena-based LLM Evaluation. - Chen Zhang, Weixin Bu, Zeyi Ren, Zhengwu Liu, Yik-Chung Wu, Ngai Wong:
Nonparametric Teaching for Graph Property Learners. - Harikrishna Metta, Venkatesh Babu Radhakrishnan:
Discovering a Zero (Zero-Vector Class of Machine Learning). - Yinhong Liu, Zhijiang Guo, Tianya Liang, Ehsan Shareghi, Ivan Vulic, Nigel Collier:
Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models. - Fan Li, Xuan Wang, Min Qi, Zhaoxiang Zhang, Yuelei Xu:
Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance. - Wei Qu, Jiawei Guan, Rui Ma, Ke Zhai, Weikun Wu, Haobo Wang:
P(all-atom) Is Unlocking New Path For Protein Design. - Pedro P. Santos, Alberto Sardinha, Francisco S. Melo:
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes. - Unique Subedi, Ambuj Tewari:
On the Benefits of Active Data Collection in Operator Learning. - Qi Yang, Chenghao Zhang, Lubin Fan, Kun Ding, Jieping Ye, Shiming Xiang:
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger. - Diyuan Wu, Marco Mondelli:
Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime. - Zexu Sun, Qiyu Han, Hao Yang, Anpeng Wu, Minqin Zhu, Dugang Liu, Chen Ma, Yunpeng Weng, Xing Tang, Xiuqiang He:
Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency. - Guibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang, Tianlong Chen, Dawei Cheng:
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks. - Dongyeop Lee, Kwanhee Lee, Jinseok Chung, Namhoon Lee:
SAFE: Finding Sparse and Flat Minima to Improve Pruning. - Ruiqi Feng, Chenglei Yu, Wenhao Deng, Peiyan Hu, Tailin Wu:
On the Guidance of Flow Matching. - Wenjun Zhang, Liangxiao Jiang, Chaoqun Li:
TLLC: Transfer Learning-based Label Completion for Crowdsourcing. - Henry B. Moss, Sebastian W. Ober, Tom Diethe:
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces. - Michalis K. Titsias:
New Bounds for Sparse Variational Gaussian Processes. - Zhengyu Zhou, Weiwei Liu:
An Error Analysis of Flow Matching for Deep Generative Modeling. - Lisha Chen, Quan Xiao, Ellen Hidemi Fukuda, Xinyi Chen, Kun Yuan, Tianyi Chen:
Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance. - Xihong Yang, Siwei Wang, Fangdi Wang, Jiaqi Jin, Suyuan Liu, Yue Liu, En Zhu, Xinwang Liu, Yueming Jin:
Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios. - Junhao Dong, Piotr Koniusz, Yifei Zhang, Hao Zhu, Weiming Liu, Xinghua Qu, Yew-Soon Ong:
Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices. - Xianghua Zeng, Hang Su, Zhengyi Wang, Zhiyuan Lin:
Graph Diffusion for Robust Multi-Agent Coordination. - Zi-Hao Zhou, Jun-Jie Wang, Tong Wei, Min-Ling Zhang:
Weakly-Supervised Contrastive Learning for Imprecise Class Labels. - Xinyan Liang, Ruijie Sang, Yuhua Qian, Qian Guo, Feijiang Li, Liang Du:
Robust Automatic Modulation Classification with Fuzzy Regularization. - Ken Liu, Christopher A. Choquette-Choo, Matthew Jagielski, Peter Kairouz, Sanmi Koyejo, Percy Liang, Nicolas Papernot:
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On. - Gaotang Li, Yuzhong Chen, Hanghang Tong:
Taming Knowledge Conflicts in Language Models. - Kaizhen Zhu, Mokai Pan, Yuexin Ma, Yanwei Fu, Jingyi Yu, Jingya Wang, Ye Shi:
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control. - Xingjian Wu, Xiangfei Qiu, Hongfan Gao, Jilin Hu, Bin Yang, Chenjuan Guo:
K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting. - Matteo Sesia, Vladimir Svetnik:
Doubly Robust Conformalized Survival Analysis with Right-Censored Data. - Tianwei Lin, Wenqiao Zhang, Sijing Li, Yuqian Yuan, Binhe Yu, Haoyuan Li, Wanggui He, Hao Jiang, Mengze Li, Xiaohui Song, Siliang Tang, Jun Xiao, Hui Lin, Yueting Zhuang, Beng Chin Ooi:
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation. - Qihe Huang, Zhengyang Zhou, Kuo Yang, Zhongchao Yi, Xu Wang, Yang Wang:
TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting. - Yiyang Fang, Jian Liang, Wenke Huang, He Li, Kehua Su, Mang Ye:
Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models. - Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit Roy-Chowdhury:
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models. - Yedi Zhang, Aaditya K. Singh, Peter E. Latham, Andrew M. Saxe:
Training Dynamics of In-Context Learning in Linear Attention. - Elias Kempf, Simon Schrodi, Max Argus, Thomas Brox:
When and How Does CLIP Enable Domain and Compositional Generalization? - Gaozheng Pei, Ke Ma, Yingfei Sun, Qianqian Xu, Qingming Huang:
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain. - Jinyu Cai, Yunhe Zhang, Fusheng Liu, See-Kiong Ng:
Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection. - Junjie Yao, Zhongwang Zhang, Zhi-Qin John Xu:
An Analysis for Reasoning Bias of Language Models with Small Initialization. - Chengyuan Li, Liangxiao Jiang, Wenjun Zhang, Liangjun Yu, Huan Zhang:
Instance Correlation Graph-based Naive Bayes. - Xinyan Liang, Shijie Wang, Yuhua Qian, Qian Guo, Liang Du, Bingbing Jiang, Tingjin Luo, Feijiang Li:
Trusted Multi-View Classification with Expert Knowledge Constraints. - Yichuan Deng, Xiaoyu Li, Zhao Song, Omri Weinstein:
Discrepancy Minimization in Input-Sparsity Time. - Yingzhen Yang:
Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate. - Bo-Han Lai, Pin-Han Huang, Bo-Han Kung, Shang-Tse Chen:
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss. - Yeyun Chen:
Relational Invariant Learning for Robust Solvation Free Energy Prediction. - Xiang Fang, Arvind Easwaran, Blaise Genest:
Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection. - Seung Yul Lee, Hojoon Kim, Yutack Park, Dawoon Jeong, Seungwu Han, Yeonhong Park, Jae W. Lee:
FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials. - Shaokun Zhang, Ming Yin, Jieyu Zhang, Jiale Liu, Zhiguang Han, Jingyang Zhang, Beibin Li, Chi Wang, Huazheng Wang, Yiran Chen, Qingyun Wu:
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems. - Abhra Chaudhuri, Anjan Dutta, Tu Bui, Serban Georgescu:
A Closer Look at Multimodal Representation Collapse. - Artem Moskalev, Mangal Prakash, Junjie Xu, Tianyu Cui, Rui Liao, Tommaso Mansi:
Geometric Hyena Networks for Large-scale Equivariant Learning. - Antonis Vasileiou, Ben Finkelshtein, Floris Geerts, Ron Levie, Christopher Morris:
Covered Forest: Fine-grained generalization analysis of graph neural networks. - Shuai Yi, Yixiong Zou, Yuhua Li, Ruixuan Li:
Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning. - Yi-Rui Yang, Chang-Wei Shi, Wu-Jun Li:
On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning. - Weizhong Huang, Yuxin Zhang, Xiawu Zheng, Fei Chao, Rongrong Ji:
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective.
Accept (poster)
- Marten Lienen, Abdullah Saydemir, Stephan Günnemann:
UnHiPPO: Uncertainty-aware Initialization for State Space Models. - Min-Yeong Park, Won-Jeong Lee, Seong Tae Kim, Gyeong-Moon Park:
When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series. - Hongrui Peng, Haolang Lu, Yuanlong Yu, Weiye Fu, Kun Wang, Guoshun Nan:
KGMark: A Diffusion Watermark for Knowledge Graphs. - Elizabeth Fons, Alejandro Sztrajman, Yousef El-Laham, Luciana Ferrer, Svitlana Vyetrenko, Manuela Veloso:
LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation. - Zhipeng Wei, Yuqi Liu, N. Benjamin Erichson:
Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection. - Julia Gusak, Xunyi Zhao, Théotime Le Hellard, Zhe Li, Lionel Eyraud-Dubois, Olivier Beaumont:
HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks. - Yilin Wang, Peixuan Lei, Jie Song, Yuzhe Hao, Tao Chen, Yuxuan Zhang, Lei Jia, Yuanxiang Li, Zhongyu Wei:
ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset. - Nannan Wu, Yuming Huang, Yiming Zhao, Jie Chen, Wenjun Wang:
GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning. - Ansgar Lößer, Max Schlecht, Florian Schintke, Joel Witzke, Matthias Weidlich, Björn Scheuermann:
Fast Min-ϵ Segmented Regression using Constant-Time Segment Merging. - Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart:
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained. - Sophie Hanna Langbein, Niklas Koenen, Marvin N. Wright:
Gradient-based Explanations for Deep Learning Survival Models. - Xuetong Li, Danyang Huang, Hansheng Wang:
Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes. - Zhaorun Chen, Mintong Kang, Bo Li:
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning. - Ruichen Xu, Kexin Chen:
Rethinking Benign Overfitting in Two-Layer Neural Networks. - Hohyun Kim, Seunggeun Lee, Min-hwan Oh:
Symmetry-Aware GFlowNets. - François R. J. Cornet, Federico Bergamin, Arghya Bhowmik, Juan Maria Garcia Lastra, Jes Frellsen, Mikkel N. Schmidt:
Kinetic Langevin Diffusion for Crystalline Materials Generation. - Thibaud Southiratn, Bonil Koo, Yijingxiu Lu, Sun Kim:
CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation. - Iurii Kemaev, Dan A. Calian, Luisa M. Zintgraf, Gregory Farquhar, Hado van Hasselt:
Scalable Meta-Learning via Mixed-Mode Differentiation. - Qingpo Wuwu, Chonghan Gao, Tianyu Chen, Yihang Huang, Yuekai Zhang, Jianing Wang, Jianxin Li, Haoyi Zhou, Shanghang Zhang:
PINNsAgent: Automated PDE Surrogation with Large Language Models. - Qiyao Liang, Daoyuan Qian, Liu Ziyin, Ila R. Fiete:
Compositional Generalization via Forced Rendering of Disentangled Latents. - Duc Anh Nguyen, Ernesto Araya, Adalbert Fono, Gitta Kutyniok:
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time. - Yuhui Ding, Thomas Hofmann:
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment. - Peter Sorrenson, Daniel Behrend-Uriarte, Christoph Schnörr, Ullrich Köthe:
Learning Distances from Data with Normalizing Flows and Score Matching. - Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta, Thomas Hofmann, Lorenzo Noci:
The Importance of Being Lazy: Scaling Limits of Continual Learning. - Muhammed Goktepe, Amir Hossein Shamseddin, Erencan Uysal, Javier Muinelo Monteagudo, Lukas Drees, Aysim Toker, Senthold Asseng, Malte von Bloh:
EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery. - Tobias Braun, Mark Rothermel, Marcus Rohrbach, Anna Rohrbach:
DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts. - Leello Tadesse Dadi, Volkan Cevher:
Generalization of noisy SGD in unbounded non-convex settings. - Paulius Rauba, Qiyao Wei, Mihaela van der Schaar:
Statistical Hypothesis Testing for Auditing Robustness in Language Models. - Grigory Bartosh, Dmitry P. Vetrov, Christian A. Naesseth:
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations. - Daiqing Wu, Dongbao Yang, Sicheng Zhao, Can Ma, Yu Zhou:
An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability. - Gengluo Li, Huawen Shen, Yu Zhou:
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts. - Chengxing Jia, Ziniu Li, Pengyuan Wang, Yi-Chen Li, Zhenyu Hou, Yuxiao Dong, Yang Yu:
Controlling Large Language Model with Latent Action. - Franck Signe Talla, Edouard Grave, Hervé Jégou:
Neutral residues: revisiting adapters for model extension. - Matthew Wicker, Philip Sosnin, Igor Shilov, Adrianna Janik, Mark Niklas Müller, Yves-Alexandre de Montjoye, Adrian Weller, Calvin Tsay:
Certification for Differentially Private Prediction in Gradient-Based Training. - Vincent Herrmann, Róbert Csordás, Jürgen Schmidhuber:
Measuring In-Context Computation Complexity via Hidden State Prediction. - Mingzhe Yang, Sihao Lin, Changlin Li, Xiaojun Chang:
Let LLM Tell What to Prune and How Much to Prune. - Junbin Liu, Farzan Farnia, Wing-Kin Ma:
Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference. - Laurens Devos, Timo Martens, Deniz Can Oruc, Wannes Meert, Hendrik Blockeel, Jesse Davis:
Compressing tree ensembles through Level-wise Optimization and Pruning. - Thibaut Germain, Chrysoula Kosma, Laurent Oudre:
Time Series Representations with Hard-Coded Invariances. - Mengmeng Chen, Xiaohu Wu, Qiqi Liu, Tiantian He, Yew-Soon Ong, Yaochu Jin, Qicheng Lao, Han Yu:
Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning. - Mohamad Al Ahdab, John Leth, Zheng-Hua Tan:
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics. - Haoxuan Li, Zeyu Tang, Zhichao Jiang, Zhuangyan Fang, Yue Liu, Zhi Geng, Kun Zhang:
Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness. - Andrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem van de Meent:
Exponential Family Variational Flow Matching for Tabular Data Generation. - Bilgehan Sel, Lifu Huang, Naren Ramakrishnan, Ruoxi Jia, Ming Jin:
LLMs Can Reason Faster Only If We Let Them. - Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama, Erik J. Bekkers, Max Welling, Christian A. Naesseth, Jan-Willem van de Meent:
Controlled Generation with Equivariant Variational Flow Matching. - Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer:
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces. - Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Michal Valko, Vianney Perchet:
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback. - Lang Feng, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu, Ming Yan, Fei Huang, Bo An:
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning. - Xinhao Zheng, Huiqi Deng, Quanshi Zhang:
Towards Attributions of Input Variables in a Coalition. - Gefan Yang, Frank van der Meulen, Stefan Sommer:
Neural Guided Diffusion Bridges. - Jinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar:
ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces. - Ignacio Peis, Batuhan Koyuncu, Isabel Valera, Jes Frellsen:
Hyper-Transforming Latent Diffusion Models. - Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu:
Emergent Response Planning in LLMs. - Xiangkun Hu, Lemin Kong, Tong He, David Wipf:
Explicit Preference Optimization: No Need for an Implicit Reward Model. - Han Li, Fei Liu, Zhi Zheng, Yu Zhang, Zhenkun Wang:
CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention. - Dominik Fuchsgruber, Tom Wollschläger, Johannes Bordne, Stephan Günnemann:
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory. - Yash, Avishek Ghosh, Nikhil Karamchandani:
Near Optimal Best Arm Identification for Clustered Bandits. - Ruiyuan Huang, Zengfeng Huang:
High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions. - Yucen Wang, Rui Yu, Shenghua Wan, Le Gan, De-Chuan Zhan:
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making. - Geonhui Yoo, Minhak Song, Chulhee Yun:
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More. - Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari, Shoham Sabach, Branislav Kveton:
Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method. - Marco Cipriano, Moritz Feuerpfeil, Gerard de Melo:
Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision. - Mingyang Sun, Pengxiang Ding, Weinan Zhang, Donglin Wang:
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport. - Alessandro Pierro, Steven Abreu, Jonathan Timcheck, Philipp Stratmann, Andreas Wild, Sumit Bam Shrestha:
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity. - Renhao Lu:
Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation. - Zhe Zhao, Haibin Wen, Pengkun Wang, Shuang Wang, Zhenkun Wang, Qingfu Zhang, Yang Wang:
Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data. - Ben Lonnqvist, Elsa Scialom, Abdulkadir Gokce, Zehra Merchant, Michael H. Herzog, Martin Schrimpf:
Contour Integration Underlies Human-Like Vision. - Rong-Xi Tan, Ming Chen, Ke Xue, Yao Wang, Yaoyuan Wang, Sheng Fu, Chao Qian:
Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings. - Naoki Nishikawa, Yujin Song, Kazusato Oko, Denny Wu, Taiji Suzuki:
Nonlinear transformers can perform inference-time feature learning. - Antonia Wüst, Tim Nelson Tobiasch, Lukas Helff, Inga Ibs, Wolfgang Stammer, Devendra Singh Dhami, Constantin A. Rothkopf, Kristian Kersting:
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad? - Muskan Dosi, Chiranjeev Chiranjeev, Kartik Thakral, Mayank Vatsa, Richa Singh:
Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres. - Anissa Alloula, Charles Jones, Ben Glocker, Bartlomiej W. Papiez:
Subgroups Matter for Robust Bias Mitigation. - Juwei Yue, Haikuo Li, Jiawei Sheng, Xiaodong Li, Taoyu Su, Tingwen Liu, Li Guo:
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations. - Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin T. Vechev:
Mind the Gap: A Practical Attack on GGUF Quantization. - Xuantong Liu, Shaozhe Hao, Xianbiao Qi, Tianyang Hu, Jun Wang, Rong Xiao, Yuan Yao:
Elucidating the design space of language models for image generation. - Kuheli Pratihar, Debdeep Mukhopadhyay:
Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders. - Yujun Kim, Jaeyoung Cha, Chulhee Yun:
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems. - Yeseul Cho, Baekrok Shin, Changmin Kang, Chulhee Yun:
Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty. - Yao Zhu, Zhenyuan Li, Yangyang Wei, Shouling Ji:
The Case for Learned Provenance-based System Behavior Baseline. - Zihan Zhou, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Da Yan, Ruoming Jin, Dejing Dou:
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning. - Xinyi Wan, Penghui Qi, Guangxing Huang, Min Lin, Jialin Li:
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization. - Yigit Narter, Alihan Hüyük, Mihaela van der Schaar, Cem Tekin:
Unified Screening for Multiple Diseases. - Daniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Negar Kiyavash, Mathias Drton:
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants. - Saksham Rastogi, Pratyush Maini, Danish Pruthi:
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings. - Stelios Triantafyllou, Aleksa Sukovic, Yasaman Zolfimoselo, Goran Radanovic:
Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making. - Suyu Liu, Zhiguang Cao, Shanshan Feng, Yew-Soon Ong:
A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver. - Chenglong Wang, Yang Gan, Yifu Huo, Yongyu Mu, Qiaozhi He, Murun Yang, Bei Li, Tong Xiao, Chunliang Zhang, Tongran Liu, JingBo Zhu:
GRAM: A Generative Foundation Reward Model for Reward Generalization. - Sanghyeok Chu, Seonguk Seo, Bohyung Han:
Fine-Grained Captioning of Long Videos through Scene Graph Consolidation. - Hongyang Lei, Xiaolong Cheng, Qi Qin, Dan Wang, Huazhen Huang, Qingqing Gu, Yetao Wu, Luo Ji:
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture. - Sai Advaith Maddipatla, Nadav Bojan Sellam, Meital Bojan, Sanketh Vedula, Paul Schanda, Ailie Marx, Alexander M. Bronstein:
Inverse problems with experiment-guided AlphaFold. - Lei Zhang, Jiaxi Yang, Min Yang, Jian Yang, Mouxiang Chen, Jiajun Zhang, Zeyu Cui, Binyuan Hui, Junyang Lin:
Synthesizing Software Engineering Data in a Test-Driven Manner. - Xiangyu Qu, Guojing Liu, Liang Li:
AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation. - Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Susumu Takeuchi:
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models. - Peer Nagy, Sascha Yves Frey, Kang Li, Bidipta Sarkar, Svitlana Vyetrenko, Stefan Zohren, Ani Calinescu, Jakob Nicolaus Foerster:
LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data. - Xuening Feng, Zhaohui Jiang, Timo Kaufmann, Eyke Hüllermeier, Paul Weng, Yifei Zhu:
Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries. - Dongmin Bang, Inyoung Sung, Yinhua Piao, Sangseon Lee, Sun Kim:
BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization. - Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti:
Private Federated Learning using Preference-Optimized Synthetic Data. - Donghwa Kim, Jaewook Lee, Chulhee Yun:
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent. - Sanghoon Yu, Min-hwan Oh:
Optimal and Practical Batched Linear Bandit Algorithm. - Hantao Lou, Changye Li, Jiaming Ji, Yaodong Yang:
SAE-V: Interpreting Multimodal Models for Enhanced Alignment. - Justin Cui, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh:
OR-Bench: An Over-Refusal Benchmark for Large Language Models. - Gwen Yidou Weng, Benjie Wang, Guy Van den Broeck:
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation. - Manu Bhat, Jonghyun Park, Jianke Yang, Nima Dehmamy, Robin Walters, Rose Yu:
AtlasD: Automatic Local Symmetry Discovery. - Nong Minh Hieu, Antoine Ledent:
Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings. - Gaspard Lambrechts, Damien Ernst, Aditya Mahajan:
A Theoretical Justification for Asymmetric Actor-Critic Algorithms. - Yuguang Yan, Zongyu Li, Haolin Yang, Zeqin Yang, Hao Zhou, Ruichu Cai, Zhifeng Hao:
Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal Transport. - Won-Jun Jang, Hyeon-Seo Park, Si-Hyeon Lee:
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead. - Jonggeon Park, Giung Nam, Hyunsu Kim, Jongmin Yoon, Juho Lee:
Ensemble Distribution Distillation via Flow Matching. - Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda:
Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines. - Jing Huang, Junyi Tao, Thomas Icard, Diyi Yang, Christopher Potts:
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors. - Yanxiang Ma, Zixuan Huang, Minjing Dong, Shan You, Chang Xu:
Adversarial Robustness via Deformable Convolution with Stochasticity. - Jiawei Zhang, Shuang Yang, Bo Li:
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning. - Anqi Lu, Junchi Yan:
Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision. - Jing Qiao, Yu Liu, Zengzhe Chen, Mingyi Li, Yuan Yuan, Xiao Zhang, Dongxiao Yu:
PDUDT: Provable Decentralized Unlearning under Dynamic Topologies. - Xingyu Miao, Haoran Duan, Yang Long, Jungong Han:
Rethinking Score Distilling Sampling for 3D Editing and Generation. - Alexander Nikulin, Ilya Zisman, Denis Tarasov, Nikita Lyubaykin, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov:
Latent Action Learning Requires Supervision in the Presence of Distractors. - Jiawei Zhang, Xuan Yang, Taiqi Wang, Yu Yao, Aleksandr Petiushko, Bo Li:
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models. - Minh Nguyen Nhat To, Paul F. R. Wilson, Viet Nguyen, Mohamed Harmanani, Michael Cooper, Fahimeh Fooladgar, Purang Abolmaesumi, Parvin Mousavi, Rahul G. Krishnan:
Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift. - Xuelin Shen, Jiayin Xu, Kangsheng Yin, Wenhan Yang:
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models. - Chiqiang Liu, Dazi Li:
HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning. - Jing Qiao, Yu Liu, Yuan Yuan, Xiao Zhang, Zhipeng Cai, Dongxiao Yu:
How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective. - Binghui Peng, Aviad Rubinstein:
A Near Linear Query Lower Bound for Submodular Maximization. - Vitaly Feldman, Audra McMillan, Guy N. Rothblum, Kunal Talwar:
Local Pan-privacy for Federated Analytics. - Ilya Kaufman, Omri Azencot:
Curvature Enhanced Data Augmentation for Regression. - Chejian Xu, Mintong Kang, Jiawei Zhang, Zeyi Liao, Lingbo Mo, Mengqi Yuan, Huan Sun, Bo Li:
AdvAgent: Controllable Blackbox Red-teaming on Web Agents. - Ekin Akyürek, Mehul Damani, Adam Zweiger, Linlu Qiu, Han Guo, Jyothish Pari, Yoon Kim, Jacob Andreas:
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning. - Niket Patel, Guido Montúfar:
On the Local Complexity of Linear Regions in Deep ReLU Networks. - Jack Min Ong, Matthew Di Ferrante, Aaron Pazdera, Ryan Garner, Sami Jaghouar, Manveer Basra, Max Ryabinin, Johannes Hagemann:
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference. - Yinpeng Chen, Dongdong Chen, Xiyang Dai, Mengchen Liu, Yinan Feng, Youzuo Lin, Lu Yuan, Zicheng Liu:
Exploring Invariance in Images through One-way Wave Equations. - Zhigaoyuan Wang, Ying Sun, Hengshu Zhu:
Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach. - Shuyuan Wang, Philip D. Loewen, Michael G. Forbes, R. Bhushan Gopaluni, Wei Pan:
DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation. - Kajetan Schweighofer, Adrián Arnaiz-Rodríguez, Sepp Hochreiter, Nuria Oliver:
The Disparate Benefits of Deep Ensembles. - Tuan Dam:
Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search. - Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, Taiji Suzuki:
Provable In-Context Vector Arithmetic via Retrieving Task Concepts. - Puning Zhao, Rongfei Fan, Shaowei Wang, Li Shen, Qixin Zhang, Zong Ke, Tianhang Zheng:
Contextual Bandits for Unbounded Context Distributions. - Xinghe Fu, Zhiyuan Yan, Zheng Yang, Taiping Yao, Yandan Zhao, Shouhong Ding, Xi Li:
PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals. - Sen Peng, Mingyue Wang, Jianfei He, Jijia Yang, Xiaohua Jia:
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models. - Tuan Dam, Kishan Panaganti, Brahim Driss, Adam Wierman:
Online Robust Reinforcement Learning Through Monte-Carlo Planning. - Ankit Ghosh, Gargee Kashyap, Sarthak Mittal, Nupur Jain, Raghavan B. Sunoj, Abir De:
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction. - Zuchao Li, Yonghua Hei, Qiwei Li, Lefei Zhang, Ping Wang, Hai Zhao, Baoyuan Qi, Liu Guoming:
What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning. - Alex Kokot, Octavian-Vlad Murad, Marina Meila:
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction. - Xiangheng Wang, Ziquan Fang, Chenglong Huang, Danlei Hu, Lu Chen, Yunjun Gao:
GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning. - Saaketh Narayan, Abhay Gupta, Mansheej Paul, Davis W. Blalock:
µnit Scaling: Simple and Scalable FP8 LLM Training. - Omar Bennouna, Jiawei Zhang, Saurabh Amin, Asuman E. Ozdaglar:
Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach. - Jiecheng Lu, Shihao Yang:
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting. - Tushar Aggarwal, Swayam Singh, Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan:
NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits. - The Viet Bui, Tien Anh Mai, Thanh Hong Nguyen:
O-MAPL: Offline Multi-agent Preference Learning. - Quan Wei, Chung-Yiu Yau, Hoi-To Wai, Yang Zhao, Dongyeop Kang, Youngsuk Park, Mingyi Hong:
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models. - Lingyu Li, Yixu Wang, Haiquan Zhao, Shuqi Kong, Yan Teng, Chunbo Li, Yingchun Wang:
Reflection-Bench: Evaluating Epistemic Agency in Large Language Models. - Chamika Sudusinghe, Gerasimos Gerogiannis, Damitha Lenadora, Charles Block, Josep Torrellas, Charith Mendis:
COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning. - Haoyuan Cai, Zhenghao Peng, Bolei Zhou:
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism. - Martin Andrews, Sam Witteveen:
A Reasoning-Based Approach to Cryptic Crossword Clue Solving. - Shanda Li, Shinjae Yoo, Yiming Yang:
Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators. - Qiuxia Lin, Rongyu Chen, Kerui Gu, Angela Yao:
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation. - Yueheng Li, Guangming Xie, Zongqing Lu:
Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning. - Xuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song:
Improving LLM Safety Alignment with Dual-Objective Optimization. - Zhen Xiang, Linzhi Zheng, Yanjie Li, Junyuan Hong, Qinbin Li, Han Xie, Jiawei Zhang, Zidi Xiong, Chulin Xie, Carl Yang, Dawn Song, Bo Li:
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning. - Yujin Han, Andi Han, Wei Huang, Chaochao Lu, Difan Zou:
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images? - Elliot Myunghoon Kim, Avi Garg, Kenny Peng, Nikhil Garg:
Correlated Errors in Large Language Models. - Jiecheng Lu, Xu Han, Yan Sun, Shihao Yang:
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting. - Lan Li, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan:
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts. - Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, Jihoon Tack:
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification. - Guixiang Wang, Jianjun Li:
Large Displacement Motion Transfer with Unsupervised Anytime Interpolation. - Yinghui Li, Jiayi Kuang, Haojing Huang, Zhikun Xu, Xinnian Liang, Yi Yu, Wenlian Lu, Yangning Li, Xiaoyu Tan, Chao Qu, Ying Shen, Hai-Tao Zheng, Philip S. Yu:
One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs. - Peter Holderrieth, Michael Samuel Albergo, Tommi S. Jaakkola:
LEAPS: A discrete neural sampler via locally equivariant networks. - Ning Liu, Yue Yu:
Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery. - Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, Yi-Hsuan Yang:
MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners. - Hengyuan Hu, Aniket Das, Dorsa Sadigh, Nima Anari:
Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation. - Arnas Uselis, Andrea Dittadi, Seong Joon Oh:
Does Data Scaling Lead to Visual Compositional Generalization? - Yinyan Bu, Jiajie Yu, Kai Zheng, Xinyu Zhang, Piya Pal:
NEAR: Neural Electromagnetic Array Response. - Bariscan Kurtkaya, Fatih Dinc, Mert Yüksekgönül, Marta Blanco-Pozo, Ege Çirakman, Mark J. Schnitzer, Yucel Yemez, Hidenori Tanaka, Peng Yuan, Nina Miolane:
Dynamical phases of short-term memory mechanisms in RNNs. - Anders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao Wu:
Improved Approximations for Hard Graph Problems using Predictions. - Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan, Adam Ibrahim, Herbie Bradley, Stella Biderman, Sanmi Koyejo:
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? - Qiwei Di, Jiafan He, Quanquan Gu:
Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback. - Haike Xu, Zongyu Lin, Kai-Wei Chang, Yizhou Sun, Piotr Indyk:
Contradiction Retrieval via Contrastive Learning with Sparsity. - Tingle Li, Baihe Huang, Xiaobin Zhuang, Dongya Jia, Jiawei Chen, Yuping Wang, Zhuo Chen, Gopala Anumanchipalli, Yuxuan Wang:
Sounding that Object: Interactive Object-Aware Image to Audio Generation. - Soheil Behnezhad, Moses Charikar, Vincent Cohen-Addad, Alma Ghafari, Weiyun Ma:
Correlation Clustering Beyond the Pivot Algorithm. - Linjing You, Jiabao Lu, Xiayuan Huang:
Test-time Correlation Alignment. - Dongliang Guo, Mengxuan Hu, Zihan Guan, Thomas Hartvigsen, Sheng Li:
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing. - Simin Chen, Pranav Pusarla, Baishakhi Ray:
DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination. - Yuanchao Xu, Kaidi Shao, Nikos K. Logothetis, Zhongwei Shen:
ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals. - Tony Shen, Seonghwan Seo, Ross Irwin, Kieran Didi, Simon Olsson, Woo Youn Kim, Martin Ester:
Compositional Flows for 3D Molecule and Synthesis Pathway Co-design. - Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Aurélie C. Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang:
Aligning Protein Conformation Ensemble Generation with Physical Feedback. - Lucy Xiaoyang Shi, Brian Ichter, Michael Robert Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Driess, Lachy Groom, Sergey Levine, Chelsea Finn:
Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models. - Sangyeon Park, Isaac Han, Seungwon Oh, Kyung-Joong Kim:
Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss. - Shelvia Wongso, Rohan Ghosh, Mehul Motani:
Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study. - Rohan Deb, Kiran Koshy Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton:
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain. - Tao Jin, Yue Wu, Quanquan Gu, Farzad Farnoud:
Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity. - Zipeng Ji, Guanghui Zhu, Chunfeng Yuan, Yihua Huang:
RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy. - Jianliang He, Xintian Pan, Siyu Chen, Zhuoran Yang:
In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention. - Hengquan Guo, Lingkai Zu, Xin Liu:
Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints. - Ruhan Wang, Zhiyong Wang, Chengkai Huang, Rui Wang, Tong Yu, Lina Yao, John C. S. Lui, Dongruo Zhou:
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality. - Shiyu Wang, Mariam Avagyan, Yihan Shen, Arnaud Lamy, Tingran Wang, Szabolcs Márka, Zsuzsa Márka, John Wright:
Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization. - Tao Feng, Yexin Wu, Guanyu Lin, Jiaxuan You:
Graph World Model. - Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Keunho Jang, Zheng Hui:
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale. - Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu:
Understanding Mode Connectivity via Parameter Space Symmetry. - Mahavir Dabas, Si Chen, Charles Fleming, Ming Jin, Ruoxi Jia:
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning. - Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Mahdi Soltanolkotabi, Marco Mondelli, Samet Oymak:
Test-Time Training Provably Improves Transformers as In-context Learners. - Sayed Mohammad Hosseini, Maryam Shanechi:
Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data. - Chen Wang, Siyu Hu, Guangming Tan, Weile Jia:
ELoRA: Low-Rank Adaptation for Equivariant GNNs. - Joe Suk, Jung-hun Kim:
Tracking Most Significant Shifts in Infinite-Armed Bandits. - Ryan Liu, Jiayi Geng, Addison J. Wu, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths:
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse. - Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park:
Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions. - Xiner Li, Limei Wang, Youzhi Luo, Carl Edwards, Shurui Gui, Yuchao Lin, Heng Ji, Shuiwang Ji:
Geometry Informed Tokenization of Molecules for Language Model Generation. - Chengpiao Huang, Yuhang Wu, Kaizheng Wang:
Uncertainty Quantification for LLM-Based Survey Simulations. - Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He, Maissam Barkeshli:
(How) Can Transformers Predict Pseudo-Random Numbers? - Kevin Muyuan Xia, Elias Bareinboim:
Causal Abstraction Inference under Lossy Representations. - Ke Fan, Jinpeng Zhang, Xuefeng Zhang, Yunze Wu, Jingyu Cao, Yuan Zhou, Jianzhu Ma:
Safety-Polarized and Prioritized Reinforcement Learning. - Honghua Dong, Jiacheng Yang, Xun Deng, Yuhe Jiang, Gennady Pekhimenko, Fan Long, Xujie Si:
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories. - Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn:
On Exact Bit-level Reversible Transformers Without Changing Architecture. - Junmin Zhong, Emiliano Quiñones Yumbla, Seyed Yousef Soltanian, Ruofan Wu, Wenlong Zhang, Jennie Si:
Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a Simulator. - Lei Yan, Xin Zhang, Qing Mai:
Heterogeneous Sufficient Dimension Reduction and Subspace Clustering. - Harit Vishwakarma, Alan Mishler, Thomas Cook, Niccolò Dalmasso, Natraj Raman, Sumitra Ganesh:
Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction. - Runquan Gui, Zhihai Wang, Jie Wang, Chi Ma, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Defu Lian, Enhong Chen, Feng Wu:
HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking. - Han Zhong, Yutong Yin, Shenao Zhang, Xiaojun Xu, Yuanxin Liu, Yifei Zuo, Zhihan Liu, Boyi Liu, Sirui Zheng, Hongyi Guo, Liwei Wang, Mingyi Hong, Zhaoran Wang:
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning. - Zhiqiang Wang, Jianghao Wen, Jianqing Liang:
Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph. - Kahim Wong, Jicheng Zhou, Jiantao Zhou, Yain-Whar Si:
An End-to-End Model for Logits-Based Large Language Models Watermarking. - Wei Liu, Zhongyu Niu, Lang Gao, Zhiying Deng, Jun Wang, Haozhao Wang, Ruixuan Li:
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets. - Heyang Zhao, Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang:
Logarithmic Regret for Online KL-Regularized Reinforcement Learning. - Weichen Li, Albert Jan, Baishakhi Ray, Junfeng Yang, Chengzhi Mao, Kexin Pei:
EditLord: Learning Code Transformation Rules for Code Editing. - Ning Wang, Zekun Li, Tongxin Bai, Man Yao, Zhen Qin, Guoqi Li:
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition. - Catherine Yu-Chi Chen, Jingyan Shen, Zhun Deng, Lihua Lei:
Conformal Tail Risk Control for Large Language Model Alignment. - Zhiyong Wang, Jiahang Sun, Mingze Kong, Jize Xie, Qinghua Hu, John C. S. Lui, Zhongxiang Dai:
Online Clustering of Dueling Bandits. - Yilong Song, Peijin Li, Bin Gao, Kun Yuan:
Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold. - Huang Liang, Benedict Lee, Daniel Hui Loong Ng, Kelin Xia:
Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification. - Haoyu Wei, Runzhe Wan, Lei Shi, Rui Song:
Zero-Inflated Bandits. - Samir Khaki, Xiuyu Li, Junxian Guo, Ligeng Zhu, Konstantinos N. Plataniotis, Amir Yazdanbakhsh, Kurt Keutzer, Song Han, Zhijian Liu:
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity. - Kevin Rojas, Yuchen Zhu, Sichen Zhu, Felix X.-F. Ye, Molei Tao:
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces. - Zhihai Wang, Jie Wang, Jilai Pan, Xilin Xia, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Feng Wu:
Accelerating Large Language Model Reasoning via Speculative Search. - Gül Sena Altintas, Devin Kwok, Colin Raffel, David Rolnick:
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions. - Yaoxuan Feng, Wenchao Chen, Yuxin Li, Bo Chen, Yubiao Wang, Zixuan Zhao, Hongwei Liu, Mingyuan Zhou:
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation. - Zihan Chen, Song Wang, Zhen Tan, Jundong Li, Cong Shen:
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning. - Oliver Broadrick, Sanyam Agarwal, Guy Van den Broeck, Markus Bläser:
The Limits of Tractable Marginalization. - Yifan Zhang, Zijian Wei, Haojie Ren, Changliang Zou:
e-GAI: e-value-based Generalized α-Investing for Online False Discovery Rate Control. - Michael Samuel Albergo, Eric Vanden-Eijnden:
NETS: A Non-equilibrium Transport Sampler. - Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine:
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models. - Philipp Höllmer, Thomas Egg, Maya M. Martirossyan, Eric Fuemmeler, Zeren Shui, Amit Gupta, Pawan Prakash, Adrian Roitberg, Mingjie Liu, George Karypis, Mark K. Transtrum, Richard G. Hennig, Ellad B. Tadmor, Stefano Martiniani:
Open Materials Generation with Stochastic Interpolants. - Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu, Sashank J. Reddi, Gang Fu, MohammadHossein Bateni, Sanjiv Kumar:
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation. - Anne Ouyang, Simon Guo, Simran Arora, Alex L. Zhang, William Hu, Christopher Ré, Azalia Mirhoseini:
KernelBench: Can LLMs Write Efficient GPU Kernels? - Haorui Wang, Jeff Guo, Lingkai Kong, Rampi Ramprasad, Philippe Schwaller, Yuanqi Du, Chao Zhang:
LLM-Augmented Chemical Synthesis and Design Decision Programs. - Enming Liang, Minghua Chen:
Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General Set. - Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, Yu Su:
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models. - Mohit Pandey, Gopeshh Subbaraj, Artem Cherkasov, Martin Ester, Emmanuel Bengio:
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation. - Jiaqi Yan, Changping Wang, De Ma, Huajin Tang, Qian Zheng, Gang Pan:
Training High Performance Spiking Neural Network by Temporal Model Calibration. - Hao Wang, Zhichao Chen, Haotian Wang, Yanchao Tan, Pan Li, Tianqiao Liu, Xu Chen, Haoxuan Li, Zhouchen Lin:
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning. - Jiachang Liu, Soroosh Shafiee, Andrea Lodi:
Scalable First-order Method for Certifying Optimal k-Sparse GLMs. - Ian Magnusson, Nguyen Tai, Ben Bogin, David Heineman, Jena D. Hwang, Luca Soldaini, Akshita Bhagia, Jiacheng Liu, Dirk Groeneveld, Oyvind Tafjord, Noah A. Smith, Pang Wei Koh, Jesse Dodge:
DataDecide: How to Predict Best Pretraining Data with Small Experiments. - Edoardo Botta, Yuchen Li, Aashay Mehta, Jordan T. Ash, Cyril Zhang, Andrej Risteski:
On the Query Complexity of Verifier-Assisted Language Generation. - Sifan Yang, Yuanyu Wan, Peijia Li, Yibo Wang, Xiao Zhang, Zhewei Wei, Lijun Zhang:
Dimension-Free Adaptive Subgradient Methods with Frequent Directions. - Yitian Zhang, Liheng Ma, Antonios Valkanas, Boris N. Oreshkin, Mark Coates:
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting. - Yuyang Hu, Albert Peng, Weijie Gan, Peyman Milanfar, Mauricio Delbracio, Ulugbek S. Kamilov:
Stochastic Deep Restoration Priors for Imaging Inverse Problems. - Su Jia, Peter I. Frazier, Nathan Kallus:
Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits. - Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite:
Leveraging Per-Instance Privacy for Machine Unlearning. - Liang Chen, Xueting Han, Li Shen, Jing Bai, Kam-Fai Wong:
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning. - Steve Hanneke, Qinglin Meng, Amirreza Shaeiri:
Representation Preserving Multiclass Agnostic to Realizable Reduction. - Sushant Agarwal, Amit Deshpande, Rajmohan Rajaraman, Ravi Sundaram:
Optimal Fair Learning Robust to Adversarial Distribution Shift. - Xinyu Zhao, Fangcong Yin, Greg Durrett:
Understanding Synthetic Context Extension via Retrieval Heads. - Zihao Wang, Yibo Jiang, Jiahao Yu, Heqing Huang:
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them). - Vikram Kher, Manolis Zampetakis:
Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design. - Shi Yin, Xinyang Pan, Fengyan Wang, Lixin He:
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction. - Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang:
SlimLLM: Accurate Structured Pruning for Large Language Models. - Qinggang Zhang, Hao Chen, Junnan Dong, Shengyuan Chen, Feiran Huang, Xiao Huang:
Structure-Guided Large Language Models for Text-to-SQL Generation. - Ji Deng, Zhao Li, Ji Zhang, Jun Gao:
EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation. - Steve Hanneke, Amirreza Shaeiri:
A Trichotomy for List Transductive Online Learning. - Zhangchi Zhao, Jun Shu, Deyu Meng, Zongben Xu:
Improving Memory Efficiency for Training KANs via Meta Learning. - Ruiqi Zhang, Jingfeng Wu, Peter L. Bartlett:
Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes. - Jun Chen, Hong Chen, Yonghua Yu, Yiming Ying:
How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction. - Dongwoo Lee, Dong Bok Lee, Steven Adriaensen, Juho Lee, Sung Ju Hwang, Frank Hutter, Seon Joo Kim, Hae Beom Lee:
Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks. - Qingchuan Ma, Yuhang Wu, Xiawu Zheng, Rongrong Ji:
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective. - Felipe Areces, Christopher Mohri, Tatsunori Hashimoto, John C. Duchi:
Online Conformal Prediction via Online Optimization. - Kenneth Li, Yida Chen, Fernanda B. Viégas, Martin Wattenberg:
When Bad Data Leads to Good Models. - Jiancong Xiao, Bojian Hou, Zhanliang Wang, Ruochen Jin, Qi Long, Weijie J. Su, Li Shen:
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach. - Jian Bi, Qianliang Wu, Xiang Li, Shuo Chen, Jianjun Qian, Lei Luo, Jian Yang:
Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation. - Yilun Zhou, Austin Xu, Peifeng Wang, Caiming Xiong, Shafiq Joty:
Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators. - Haoyu Peter Wang, Shikun Liu, Rongzhe Wei, Pan Li:
Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models. - Udaya Ghai, Karan Singh:
Sample-Optimal Agnostic Boosting with Unlabeled Data. - Xiaoyan Feng, He Zhang, Yanjun Zhang, Leo Yu Zhang, Shirui Pan:
BiMark: Unbiased Multilayer Watermarking for Large Language Models. - Adibvafa Fallahpour, Jun Ma, Alif Munim, Hongwei Lyu, Bo Wang:
MedRAX: Medical Reasoning Agent for Chest X-ray. - Nuoya Xiong, Aarti Singh:
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF. - Joseph Lazzaro, Ciara Pike-Burke:
Fixed-Confidence Multiple Change Point Identification under Bandit Feedback. - Yongjian Zhong, Liao Zhu, Hieu Vu, Bijaya Adhikari:
Implicit Subgraph Neural Network. - Taehyun Cho, Seungyub Han, Seokhun Ju, Dohyeong Kim, Kyungjae Lee, Jungwoo Lee:
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation. - Can Chen, Jun-Kun Wang:
Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting. - Zijian Liu, Zhengyuan Zhou:
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization. - Jiawei Cao, Chaochen Gu, Hao Cheng, Xiaofeng Zhang, Kaijie Wu, Changsheng Lu:
EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation. - Mingkang Zhu, Xi Chen, Zhongdao Wang, Bei Yu, Hengshuang Zhao, Jiaya Jia:
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization. - Eric Zhao, Pranjal Awasthi, Sreenivas Gollapudi:
Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification. - Xin Yu, Zelin He, Ying Sun, Lingzhou Xue, Runze Li:
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees. - Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang:
Scaling Laws for Differentially Private Language Models. - Kei Sen Fong, Mehul Motani:
Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms. - Helia Niaparast, Benjamin Moseley, Karan Singh:
Faster Global Minimum Cut with Predictions. - Kei Sen Fong, Mehul Motani:
FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation. - Sanjeev Raja, Martin Sípka, Michael Psenka, Tobias Kreiman, Michal Pavelka, Aditi S. Krishnapriyan:
Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional. - Fei Shen, Cong Wang, Junyao Gao, Qin Guo, Jisheng Dang, Jinhui Tang, Tat-Seng Chua:
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model. - Aaron J. Havens, Benjamin Kurt Miller, Bing Yan, Carles Domingo-Enrich, Anuroop Sriram, Daniel S. Levine, Brandon M. Wood, Bin Hu, Brandon Amos, Brian Karrer, Xiang Fu, Guan-Horng Liu, Ricky T. Q. Chen:
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching. - Yash Shah, Camila González, Mohammad Hasan Abbasi, Qingyu Zhao, Kilian M. Pohl, Ehsan Adeli:
Confounder-Free Continual Learning via Recursive Feature Normalization. - Sang T. Truong, Yuheng Tu, Percy Liang, Bo Li, Sanmi Koyejo:
Reliable and Efficient Amortized Model-based Evaluation. - Qi Xu, Jie Deng, Jiangrong Shen, Biwu Chen, Huajin Tang, Gang Pan:
Hybrid Spiking Vision Transformer for Object Detection with Event Cameras. - Mauricio Soroco, Jialin Song, Mengzhou Xia, Kye Emond, Weiran Sun, Wuyang Chen:
PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs. - Eshika Saxena, Alberto Alfarano, Emily Wenger, Kristin E. Lauter:
Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic. - Jack Cai, Ammar Vora, Randolph Zhang, Mark O'Connor, Mark C. Jeffrey:
Attention-Level Speculation. - Daniel Csillag, Cláudio José Struchiner, Guilherme Tegoni Goedert:
Prediction-Powered E-Values. - Jennifer Hsia, Afreen Shaikh, Zora Zhiruo Wang, Graham Neubig:
RAGGED: Towards Informed Design of Scalable and Stable RAG Systems. - Rushuang Zhou, Yuanting Zhang, Yining Dong:
H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models. - Yiwei Wu, Atticus Geiger, Raphaël Millière:
How Do Transformers Learn Variable Binding in Symbolic Programs? - Jiacheng Zhang, Benjamin I. P. Rubinstein, Jingfeng Zhang, Feng Liu:
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy. - Xiaorui Su, Shvat Messica, Yepeng Huang, Ruth Johnson, Lukas Fesser, Shanghua Gao, Faryad Sahneh, Marinka Zitnik:
Multimodal Medical Code Tokenizer. - Letian Chen, Nina Marie Moorman, Matthew Craig Gombolay:
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics. - Yi-Fan Zhang, Min-Ling Zhang:
Tight and Fast Bounds for Multi-Label Learning. - Dachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong, Jan Kautz, Pavlo Molchanov, Yingyan Celine Lin:
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models. - Zhiqiang Wang, Xiaoyi Wang, Jianqing Liang:
CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs. - Junze Deng, Qinhang Wu, Peizhong Ju, Sen Lin, Yingbin Liang, Ness B. Shroff:
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective. - Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro:
Weak-to-Strong Generalization Even in Random Feature Networks, Provably. - Zhengming Chen, Yewei Xia, Feng Xie, Jie Qiao, Zhifeng Hao, Ruichu Cai, Kun Zhang:
Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations. - Awni Altabaa, John Lafferty:
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures. - Yuhao Sun, Jiacheng Zhang, Zesheng Ye, Chaowei Xiao, Feng Liu:
Sample-specific Noise Injection for Diffusion-based Adversarial Purification. - Semyon Savkin, Eitan Porat, Or Ordentlich, Yury Polyanskiy:
NestQuant: nested lattice quantization for matrix products and LLMs. - Jiachen Guo, Xiaoyu Xie, Chanwook Park, Hantao Zhang, Matthew Politis, Gino Domel, Wing Kam Liu:
Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems. - Arsalan Sharifnassab, Saber Salehkaleybar, Richard S. Sutton:
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters. - Chao Cui, Shisong Tang, Fan Li, Jiechao Gao, Hechang Chen:
Calibrating Video Watch-time Predictions with Credible Prototype Alignment. - Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi, Percy Liang, Tatsunori Hashimoto:
Auditing Prompt Caching in Language Model APIs. - Seokhun Park, Insung Kong, Yongchan Choi, Chanmoo Park, Yongdai Kim:
Tensor Product Neural Networks for Functional ANOVA Model. - Bairu Hou, Qibin Chen, Jianyu Wang, Guoli Yin, Chong Wang, Nan Du, Ruoming Pang, Shiyu Chang, Tao Lei:
Instruction-Following Pruning for Large Language Models. - Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S. Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro:
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities. - Arun Ganesh, Ryan McKenna, Hugh Brendan McMahan, Adam Smith, Fan Wu:
It's My Data Too: Private ML for Datasets with Multi-User Training Examples. - Raphael A. Meyer, William J. Swartworth, David P. Woodruff:
Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra. - Kunwoong Kim, Jihu Lee, Sangchul Park, Yongdai Kim:
Fair Clustering via Alignment. - Evi Micha, Vasilis Varsamis:
Computing Voting Rules with Improvement Feedback. - Yuan Li, Zhengzhong Liu, Eric P. Xing:
Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models. - Ruben Weitzman, Peter Mørch Groth, Lood van Niekerk, Aoi Otani, Yarin Gal, Debora Susan Marks, Pascal Notin:
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction.