ICML

Optimal Auction Design in the Joint Advertising

Yang Li, Yuchao Ma, Qi Qi

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学人工智能学院） ； Beijing Key Laboratory of Research on Large Models（北京大型模型研究重点实验室） ； Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心） 纠错

Comments Accepted by ICML 2025 (International Conference on Machine Learning). 17 pages, 4 figures

MAEBE: Multi-Agent Emergent Behavior Framework

Sinem Erisken, Timothy Gothard, Martin Leitgab, Ram Potham

机构 * Independent Researcher（独立研究者） 纠错

Comments Preprint. This work has been submitted to the Multi-Agent Systems Workshop at ICML 2025 for review

Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components

Ram Potham

机构 * Independent Researcher（独立研究者） 纠错

Comments Preprint. This work has been submitted to the Technical AI Governance Workshop at ICML 2025 for review

Revisiting the Predictability of Performative, Social Events

Juan C. Perdomo

机构 * Harvard University（哈佛大学） ； Harvard Center for Research on Computation and Society（哈佛大学计算与社会研究中心） 纠错

Comments 21 pages, accepted to ICML 2025

Deep Learning is Not So Mysterious or Different

Andrew Gordon Wilson

机构 * New York University（纽约大学） 纠错

Comments ICML 2025

Parametric Scaling Law of Tuning Bias in Conformal Prediction

Hao Zeng, Kangdao Liu, Bingyi Jing, Hongxin Wei

机构 * Department of Statistics and Data Science, Southern University of Science and Technology（统计与数据科学系，南方科技大学） ； Department of Computer and Information Science, University of Macau（计算机与信息科学系，澳门大学） 纠错

Comments ICML 2025: https://icml.cc/virtual/2025/poster/44287 and code at: https://github.com/ml-stat-Sustech/Parametric-Scaling-Law-CP-Tuning

Long-Form Speech Generation with Spoken Language Models

Se Jin Park, Julian Salazar, Aren Jansen, Keisuke Kinoshita, Yong Man Ro, RJ Skerry-Ryan

机构 * Google DeepMind（谷歌DeepMind） ； Language Lab, KAIST（语言实验室，韩国科学技术院） 纠错

Comments Accepted to ICML 2025 (oral)

Constrain Alignment with Sparse Autoencoders

Qingyu Yin, Chak Tou Leong, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang

机构 * Zhejiang University（浙江大学） ； Hongkong Polytechnic University（香港理工大学） ； University College London（伦敦大学学院） ； Westlake University（西湖大学） ； King's College London（国王学院） ； Southern University of Science and Technology（南方科技大学） 纠错

Journal ref ICML 2025

Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound

David Boetius, Stefan Leue, Tobias Sutter

机构 * Department of Computer and Information Science, University of Konstanz, Konstanz, Baden-Würtemberg, Germany（计算机与信息科学系，康斯坦茨大学，康斯坦茨，巴登-符腾堡，德国） 纠错

Comments Accepted at ICML 2025. Code available at https://github.com/sen-uni-kn/probspecs. 9 pages, 3 figures, 31 pages references and appendix, including 8 more figures

Structure Guided Large Language Model for SQL Generation

Qinggang Zhang, Hao Chen, Junnan Dong, Shengyuan Chen, Feiran Huang, Xiao Huang

机构 * Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR, China（香港理工大学计算机系） ； City University of Macau, Macau SAR, China（澳门城市大学） ； College of Information Science and Technology, Jinan University, GZ, China（广州jinan大学信息科学与技术学院） 纠错

Comments The 42nd International Conference on Machine Learning

Audio-Visual Speech Separation via Bottleneck Iterative Network

Sidong Zhang, Shiv Shankar, Trang Nguyen, Andrea Fanelli, Madalina Fiterau

机构 * Manning College of Information \& Computer Sciences, University of Massachusetts Amherst, Amherst, U.S. ； Dolby Laboratories, San Francisco, U.S. 纠错

Comments Accepted to the 42nd International Conference on Machine Learning Workshop on Machine Learning for Audio

Interpretable EEG-to-Image Generation with Semantic Prompts

Arshak Rezvani, Ali Akbari, Kosar Sanjar Arani, Maryam Mirian, Emad Arasteh, Martin J. McKeown

机构 * Pacific Parkinson’s Research Centre, Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, Canada（太平洋帕金森研究中心、Djavad Mowafaghian脑健康中心、不列颠哥伦比亚大学，温哥华，加拿大） ； Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran（电气与计算机工程系、伊朗德黑兰大学，德黑兰，伊朗） ； Department of Medicine British Columbia, Vancouver, Canada（医学系、不列颠哥伦比亚大学，温哥华，加拿大） 纠错

Comments Actionable Interpretability Workshop (non-archival) at the 42 International Conference on Machine Learning

Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in Astrophysics

Xueqing Xu, Boris Bolliet, Adrian Dimitrov, Andrew Laverick, Francisco Villaescusa-Navarro, Licong Xu, Íñigo Zubeldia

机构 * Institute of Astronomy, University of Cambridge, Cambridge, United Kingdom（英国剑桥大学天文研究所） ； Kavli Institute for Cosmology, University of Cambridge, Cambridge, United Kingdom（英国剑桥大学卡弗里宇宙研究所） ； Department of Physics, University of Cambridge, Cambridge, United Kingdom（英国剑桥大学物理系） ； Center for Computational Astrophysics, Flatiron Institute, New York, NY, USA（Flatiron研究所计算天体物理学中心） ； Department of Astrophysical Sciences, Princeton University, Princeton, NJ, USA（普林斯顿大学天体物理学系） 纠错

Comments Accepted contribution (spotlight) to the ICML 2025 Workshop on Machine Learning for Astrophysics; codes: https://huggingface.co/datasets/ASTROANTS/CosmoPaperQA, https://github.com/CMBAgents/cmbagent, https://github.com/CMBAgents/scirag

Robust Multimodal Large Language Models Against Modality Conflict

Zongmeng Zhang, Wengang Zhou, Jie Zhao, Houqiang Li

机构 * School of Artificial Intelligence（人工智能学院） ； Data Science, University of Science（数据科学，科学大学） ； Department of Electronic Engineering（电子工程系） ； Information Science, University of Science（信息科学，科学大学） ； Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

Comments ICML 2025

Large Language Model for Extracting Complex Contract Information in Industrial Scenes

Yunyang Cao, Yanjun Li, Silong Dai

机构 * Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China（上海智能自主系统研究院，同济大学） ； School of Computer Science and Technology, East China Normal University, Shanghai, China（计算机科学与技术学院，华东师范大学） 纠错

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

Unifews: You Need Fewer Operations for Efficient Graph Neural Networks

Ningyi Liao, Zihao Yu, Ruixiao Zeng, Siqiang Luo

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡） ； College of Computing（计算学院） ； Data Science, Nanyang Technological University, Singapore（数据科学，南洋理工大学，新加坡） 纠错

Comments Accepted by ICML 2025

Does Data Scaling Lead to Visual Compositional Generalization?

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

机构 * Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学） ； Technical University of Munich（慕尼黑技术大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Max Planck Institute for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所，图宾根） 纠错

Comments ICML 2025

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

Lan Li, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

机构 * School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学） ； National Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家实验室，南京大学） 纠错

Comments Accepted by ICML 2025

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Jinmin He, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng

机构 * C2DL, Institute of Automation, Chinese Academy of Sciences（C2DL，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； Tencent AI Lab（腾讯AI实验室） ； Tsinghua University（清华大学） 纠错

Comments ICML2025

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

Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models

Arjun Banerjee, David Martinez, Camille Dang, Ethan Tam

机构 * Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, California（电气工程与计算机科学系，加州大学伯克利分校） 纠错

Comments 15 pages, 13 figures. Accepted to Proceedings of the Workshop on Generative AI for Biology at the 42nd International Conference on Machine Learning (Spotlight)

Deprecating Benchmarks: Criteria and Framework

Ayrton San Joaquin, Rokas Gipiškis, Leon Staufer, Ariel Gil

机构 * AI Standards Lab（AI标准实验室） ； Technical University of Munich（慕尼黑技术大学） ； Institute of Data Science（数据科学研究所） ； Digital Technologies（数字技术） ； Trajectory Labs（轨迹实验室） 纠错

Comments 10 pages, 1 table. Accepted to the ICML 2025 Technical AI Governance Workshop

Representing Prompting Patterns with PDL: Compliance Agent Case Study

Mandana Vaziri, Louis Mandel, Yuji Watanabe, Hirokuni Kitahara, Martin Hirzel, Anca Sailer

机构 * IBM Research, Yorktown Heights, USA（IBM研究院，Yorktown Heights，美国） ； IBM Research, Tokyo, Japan（IBM研究院，Tokyo，日本） 纠错

Comments ICML 2025 Workshop on Programmatic Representations for Agent Learning

Evaluating Morphological Alignment of Tokenizers in 70 Languages

Catherine Arnett, Marisa Hudspeth, Brendan O'Connor

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

Comments 6 pages, 3 figures. Accepted to the Tokenization Workshop at ICML 2025

Differentiable Stellar Atmospheres with Physics-Informed Neural Networks

Jiadong Li, Mingjie Jian, Yuan-Sen Ting, Gregory M. Green

Comments Accepted at the Workshop on Machine Learning for Astrophysics (ICML 2025)

Probing and Steering Evaluation Awareness of Language Models

Jord Nguyen, Khiem Hoang, Carlo Leonardo Attubato, Felix Hofstätter

机构 * Pivotal Research ； Waseda University（早稻田大学） ； Apollo Research 纠错

Comments Actionable Interpretability Workshop (Poster) and Workshop on Technical AI Governance (Poster) at ICML 2025, Vancouver, Canada

Adaptive Elicitation of Latent Information Using Natural Language

Jimmy Wang, Thomas Zollo, Richard Zemel, Hongseok Namkoong

机构 * Columbia University（哥伦比亚大学） 纠错

Comments ICML 2025

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

Chris Pedersen, Laure Zanna, Joan Bruna

机构 * Courant Institute of Mathematical Sciences, New York University, USA（Courant数学科学研究所，纽约大学，美国） ； Center for Data Science, New York University, USA（数据科学中心，纽约大学，美国） 纠错

Comments To appear at ICML'25

Oscillation-Reduced MXFP4 Training for Vision Transformers

Yuxiang Chen, Haocheng Xi, Jun Zhu, Jianfei Chen

机构 * Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系，人工智能研究所，BNRist中心，THBI实验室，清华-博世联合机器学习中心，清华大学） ； Zhili College, Tsinghua University（智理学院，清华大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)

Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST

Rithwik Gupta, Daniel Muthukrishna, Nabeel Rehemtulla, Ved Shah

机构 * Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology（凯斯勒天体物理与空间研究研究所，麻省理工学院） ； Irvington High School（伊里弗顿高中） ； Department of Physics and Astronomy, Northwestern University（物理与天文学系，西北大学） ； Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA)（天体物理学跨学科探索与研究中心（CIERA）） ； NSF-Simons AI Institute for the Sky (SkAI)（NSF-模拟ons人工智能研究所（SkAI）） 纠错

Comments 7 pages, 5 figures, 1 table. Accepted for publication in MNRAS Letters. A version of this paper was also accepted to the Machine Learning for Astrophysics Workshop 2025 at ICML

(How) Can Transformers Predict Pseudo-Random Numbers?

Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

机构 * Department of Physics, University of Maryland, College Park, USA（物理系，马里兰大学，College Park, USA） ； Department of Computer Science, University of Maryland, College Park, USA（计算机科学系，马里兰大学，College Park, USA） ； Joint Quantum Institute, University of Maryland, College Park, USA（联合量子研究所，马里兰大学，College Park, USA） 纠错

Comments ICML 2025 (camera-ready version). 10+17 pages, 13+23 figures

Journal ref TIn Forty-second International Conference on Machine Learning (2025)