ICML

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

Bowen Zheng, Tianming Yang

机构 * Institute of Neuroscience（神经科学研究所） ； Key Laboratory of Brain Cognition（脑认知重点实验室） ； Brain-inspired Intelligence Technology（脑启发智能技术） ； Center for Excellence in Brain Science（脑科学卓越中心） ； Intelligence Technology（智能技术） ； Chinese Academy of Sciences（中国科学院） ； Shanghai, China（上海中国） 纠错

Comments ICML 2025

G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration

Samuel Holt, Max Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） 纠错

Comments Accepted at the 42nd International Conference on Machine Learning (ICML 2025). 9 pages, 3 figures

Journal ref Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs

Greyson Brothers

机构 * Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室） 纠错

Comments [ICML 2025 Spotlight Poster] To be published in the Forty-Second International Conference on Machine Learning (ICML) Proceedings

Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism

Haoyuan Cai, Zhenghao Peng, Bolei Zhou

机构 * Computer Science Department, University of California, Los Angeles (UCLA)（加州大学洛杉矶分校计算机科学系） 纠错

Comments ICML 2025 Poster

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees

William de Vazelhes, Xiao-Tong Yuan, Bin Gu

机构 * School of Intelligence Science and Technology, Nanjing University, Suzhou, China（智能科学与技术学院，南京大学，苏州，中国） ； School of Artificial Intelligence, Jilin University, China（人工智能学院，吉林大学，中国） 纠错

Comments Accepted for publication at ICML 2025

Teaching Physical Awareness to LLMs through Sounds

Weiguo Wang, Andy Nie, Wenrui Zhou, Yi Kai, Chengchen Hu

机构 * Peking University（北京大学） 纠错

Comments ICML 2025

SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy

Yong Liang Goh, Zhiguang Cao, Yining Ma, Jianan Zhou, Mohammed Haroon Dupty, Wee Sun Lee

机构 * School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院） ； School of Computing and Information Systems, Singapore Management University, Singapore（新加坡管理学院计算机学院与信息系统学院） ； Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge MA, United States（麻省理工学院信息与决策系统实验室） ； College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院） ； Grabtaxi Holdings Pte Ltd, Singapore（Grabtaxi控股公司） ； Grab-NUS AI Lab, Singapore（Grab-NUS人工智能实验室） ； Institute of Data Science, National University of Singapore, Singapore（新加坡国立大学数据科学研究院） 纠错

Comments Accepted in the 42nd International Conference of Machine Learning (ICML)

Learnable Spatial-Temporal Positional Encoding for Link Prediction

Katherine Tieu, Dongqi Fu, Zihao Li, Ross Maciejewski, Jingrui He

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Meta AI ； Arizona State University（亚利桑那州立大学） 纠错

Comments Accepted by ICML 2025. 28 pages, 1 figures, 22 tables

Modified K-means Algorithm with Local Optimality Guarantees

Mingyi Li, Michael R. Metel, Akiko Takeda

机构 * Department of Mathematical Informatics, The University of Tokyo, Tokyo, Japan（东京大学数学信息学系） ； Huawei Noah's Ark Lab, Montréal, Canada（华为诺亚实验室） ； Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan（日本理化学研究所高级智能项目中心） 纠错

Comments ICML 2025

LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification

Hang Gao, Wenxuan Huang, Fengge Wu, Junsuo Zhao, Changwen Zheng, Huaping Liu

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； National Key Laboratory of Space Integrated Information System（空间信息集成系统国家重点实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； Tsinghua University（清华大学） 纠错

Comments Accepted by ICML 2025

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel

机构 * Weizmann Institute of Science（魏茨曼科学研究所） ； Intel Labs（英特尔实验室） 纠错

Comments ICML'25 Oral (top %1)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Kaijie Zhu, Xianjun Yang, Jindong Wang, Wenbo Guo, William Yang Wang

机构 * University of California, Santa Barbara（加州大学圣巴巴拉分校） 纠错

Comments ICML 2025

TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation

Daoyu Wang, Mingyue Cheng, Zhiding Liu, Qi Liu

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学） 纠错

Comments 25 pages, 7 figures, Accepted by the 42nd International Conference on Machine Learning (ICML 2025)

Archon: An Architecture Search Framework for Inference-Time Techniques

Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E. Kelly Buchanan, Mayee Chen, Neel Guha, Christopher Ré, Azalia Mirhoseini

机构 * Stanford University, Stanford, CA, USA（斯坦福大学） ； University of Washington, Seattle, WA, USA（华盛顿大学） 纠错

Comments International Conference on Machine Learning (ICML) 2025

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

Han Jiang, Xiaoyuan Yi, Zhihua Wei, Ziang Xiao, Shu Wang, Xing Xie

机构 * Tongji University（同济大学） ； Johns Hopkins University（约翰霍普金斯大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Microsoft Research Asia（微软亚洲研究院） 纠错

Comments ICML 2025

Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction

Ruben Weitzman, Peter Mørch Groth, Lood Van Niekerk, Aoi Otani, Yarin Gal, Debora Marks, Pascal Notin

机构 * Department of Systems Biology, Harvard Medical School（系统生物学系，哈佛医学院） ； Department of Computer Science, University of Oxford（计算机科学系，牛津大学） ； Department of Computer Science, University of Copenhagen（计算机科学系，哥本哈根大学） ； Enzyme research, Novonesis（酶研究，Novonesis） 纠错

Comments Accepted at ICML 2025

BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models

Amina Mollaysa, Artem Moskale, Pushpak Pati, Tommaso Mansi, Mangal Prakash, Rui Liao

Comments Proceedings of ICML 2025 Workshop on Multi-modal Foundation Proceedings of ICML 2025 Workshop on Multi-modal Foundation Proceedings of ICML 2025 Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities

Wendong Bu, Yang Wu, Qifan Yu, Minghe Gao, Bingchen Miao, Zhenkui Zhang, Kaihang Pan, Yunfei Li, Mengze Li, Wei Ji, Juncheng Li, Siliang Tang, Yueting Zhuang

Comments Accepted by ICML 2025 (Oral)

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search

Dongge Han, Menglin Xia, Daniel Madrigal Diaz, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Del Carmen Hipolito Garcia, Jin Xu, Victor Rühle, Saravan Rajmohan

机构 * Microsoft（微软） 纠错

Comments TTODLer-FM Workshop@ICML'25 (Tiny Titans: The next wave of On-Device Learning for Foundational Models)

Sample Efficient Demonstration Selection for In-Context Learning

Kiran Purohit, V Venktesh, Sourangshu Bhattacharya, Avishek Anand

机构 * Indian Institute of Technology, Kharagpur, India（印度理工学院Kharagpur分校） ； Delft University of Technology (TU Delft)（代尔夫特理工大学） 纠错

Comments Accepted at ICML 2025 , 24 pages

FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching

Sunny Gupta, Nikita Jangid, Shounak Das, Amit Sethi

机构 * Koita Centre for Digital Health IIT Bombay, Mumbai（Koita数字健康中心IIT博伊斯瓦尔，孟买） ； Department of Electrical Engineering, IIT Bombay, Mumbai（电气工程系IIT博伊斯瓦尔，孟买） 纠错

Comments Accepted at ICML 2025 Workshop on Collaborative and Federated Agentic Workflows CFAgentic @ ICML'25

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

Shahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner, Matthias Althoff, Guy Katz

机构 * Hebrew University of Jerusalem（希伯来大学） ； Technical University of Munich（慕尼黑技术大学） 纠错

Comments To appear in ICML 2025

Time-Aware World Model for Adaptive Prediction and Control

Anh N. Nhu, Sanghyun Son, Ming Lin

机构 * University of Maryland（马里兰大学） ； Department of Computer Science（计算机科学系） 纠错

Comments Paper accepted to ICML 2025

Olica: Efficient Structured Pruning of Large Language Models without Retraining

Jiujun He, Huazhen Lin

机构 * Center of Statistical Research, School of Statistics（统计研究中心、统计学与数据科学学院） ； New Cornerstone Science Laboratory, Southwestern University of Finance（新基石科学实验室、西南财经大学） 纠错

Comments Accepted to ICML 2025

Reinforce LLM Reasoning through Multi-Agent Reflection

Yurun Yuan, Tengyang Xie

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校） 纠错

Comments International Conference on Machine Learning (ICML), 2025

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving

Yuxuan Zhou, Xien Liu, Chenwei Yan, Chen Ning, Xiao Zhang, Boxun Li, Xiangling Fu, Shijin Wang, Guoping Hu, Yu Wang, Ji Wu

机构 * Department of Electronic Engineering, Tsinghua University, Beijing, China（清华大学电子工程系） ； College of AI, Tsinghua University, Beijing, China（清华大学人工智能学院） ； School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China（北京邮电大学计算机科学学院） ； iFLYTEK Research, Hefei, China（iFLYTEK研究院） 纠错

Comments 20 pages, 11 figures. Accepted by ICML 2025

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Zhanke Zhou, Xiao Feng, Zhaocheng Zhu, Jiangchao Yao, Sanmi Koyejo, Bo Han

机构 * TMLR Group, Department of Computer Science, Hong Kong Baptist University ； Stanford University ； Mila - Qu\'ebec AI Institute ； Cooperative Medianet Innovation Center, Shanghai Jiao Tong University 纠错

Comments Accepted by ICML 2025

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization

Xinyu Luo, Cedar Site Bai, Bolian Li, Petros Drineas, Ruqi Zhang, Brian Bullins

机构 * Purdue University（普渡大学） 纠错

Journal ref Published in ICML 2025: https://openreview.net/forum?id=TaqwI9qF5Q

BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly

Yan Shen, Ruihai Wu, Yubin Ke, Xinyuan Song, Zeyi Li, Xiaoqi Li, Hongwei Fan, Haoran Lu, Hao dong

机构 * CFCS, School of Computer Science, Peking University（计算机科学系，北京大学） ； PKU-Agibot Lab（北大Agibot实验室） 纠错

Comments ICML 2025

Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks

Thomas Massena, Léo andéol, Thibaut Boissin, Franck Mamalet, Corentin Friedrich, Mathieu Serrurier, Sébastien Gerchinovitz

Journal ref Forty-Second International Conference on Machine Learning (ICML 2025), Jul 2025, Vancouver, Canada