ICML

Riemannian generative decoder

Andreas Bjerregaard, Søren Hauberg, Anders Krogh

机构 * University of Copenhagen（哥本哈根大学） ； Technical University of Denmark（丹麦技术大学） 纠错

Comments GenBio ICML 2025 (Proceedings of the Workshop on Generative AI for Biology at the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025)

Leveraging Predictive Equivalence in Decision Trees

Hayden McTavish, Zachery Boner, Jon Donnelly, Margo Seltzer, Cynthia Rudin

机构 * Duke University（杜克大学） ； University of British Columbia（不列颠哥伦比亚大学） 纠错

Comments Accepted to ICML 2025

Wyckoff Transformer: Generation of Symmetric Crystals

Nikita Kazeev, Wei Nong, Ignat Romanov, Ruiming Zhu, Andrey Ustyuzhanin, Shuya Yamazaki, Kedar Hippalgaonkar

机构 * Institute for Functional Intelligent Materials University of Singapore（功能智能材料研究所新加坡大学） ； School of Materials Science and Engineering（材料科学与工程学院） ； Nanyang Technological University（南洋理工大学） ； Constructor University（Constructor大学） ； Constructor Knowledge Labs（Constructor知识实验室） ； HSE University（莫斯科高等经济大学） ； Institute of Materials Research and Engineering（材料研究与工程研究所） 纠错

Comments https://github.com/SymmetryAdvantage/WyckoffTransformer

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29495-29526, 2025

Uncertainty Estimation by Density Aware Evidential Deep Learning

Taeseong Yoon, Heeyoung Kim

机构 * Department of Industrial and Systems Engineering, KAIST, Daejeon, Republic of Korea（工业与系统工程系，韩国科学技术院） 纠错

Comments ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML 2024), PMLR 235:57217-57243, 2024

Replicable Learning of Large-Margin Halfspaces

Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas, Felix Zhou

机构 * Yale University（耶鲁大学） ； Google Research（谷歌研究） ； Aarhus University（阿鲁斯大学） 纠错

Comments to be published in ICML 2024

Optimistic Multi-Agent Policy Gradient

Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen

机构 * Department of Electrical Engineering and Automation, Aalto University, Finland（艾尔沃斯大学电气工程与自动化系） ； Department of Computer Science, Aalto University, Finland（艾尔沃斯大学计算机科学系） ； School of Computer Science and Engineering, University of Electronic Science and Technology of China, China（电子科学与技术大学计算机科学与工程学院） ； University of Oulu, Finland（奥卢大学） 纠错

Comments Updated MMDP notation. Published at ICML 2024, 17 pages, 10 figures

Reproducibility: The New Frontier in AI Governance

Israel Mason-Williams, Gabryel Mason-Williams

机构 * Imperial College London（帝国理工学院） ； King's College London（国王学院） ； Independent Researcher（独立研究者） 纠错

Comments 12 pages,6 figures,Workshop on Technical AI Governance at ICML

Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate

Andrea Wynn, Harsh Satija, Gillian Hadfield

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Vector Institute（向量研究所） 纠错

Comments ICML MAS Workshop 2025

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Shiqi Chen, Tongyao Zhu, Ruochen Zhou, Jinghan Zhang, Siyang Gao, Juan Carlos Niebles, Mor Geva, Junxian He, Jiajun Wu, Manling Li

机构 * City University of Hong Kong（香港城市大学） ； National University of Singapore（新加坡国立大学） ； Hong Kong University of Science（香港科学大学） ； Stanford University（斯坦福大学） ； Salesforce Research（Salesforce研究） ； Tel Aviv University（特拉维夫大学） ； Northwestern University（西北大学） 纠错

Comments ICML 2025

ELMO: Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces

Jinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar

机构 * Department of Computer Science, Aalto University, Espoo, Finland（艾尔沃斯大学计算机科学系） ； Department of Computer Science, University of Bath, Bath, UK（巴斯大学计算机科学系） 纠错

Comments Accepted to ICML 2025

Isotropy and Geometry of Pretrained Protein LMs

Sheikh Azizul Hakim, Kowshic Roy, M Saifur Rahman

Comments Published in the Proceedings of the ICML 2025 Workshop on Multi-modal Foun- dation Models and Large Language Models for Life Sciences, Vancouver, Canada. 2025

Learning Diffusion Models with Flexible Representation Guidance

Chenyu Wang, Cai Zhou, Sharut Gupta, Zongyu Lin, Stefanie Jegelka, Stephen Bates, Tommi Jaakkola

Comments NeurIPS 2025; Also Oral at ICML 2025 FM4LS workshop

Learning Mixtures of Experts with EM: A Mirror Descent Perspective

Quentin Fruytier, Aryan Mokhtari, Sujay Sanghavi

Comments Accepted to ICML 2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17690-17726, 2025

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

Yongqiang Yao, Jingru Tan, Feizhao Zhang, Jiahao Hu, Yazhe Niu, Xin Jin, Bo Li, Pengfei Liu, Ruihao Gong, Dahua Lin, Ningyi Xu

机构 * Shanghai Jiao Tong University（上海交通大学） ； SenseTime Research（商汤科技研究院） ； Central South University（中南大学） ； Tongji University（同济大学） ； Beihang University（北航） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Accepted in ICML 2025

SAM2LoRA: Composite Loss-Guided, Parameter-Efficient Finetuning of SAM2 for Retinal Fundus Segmentation

Sayan Mandal, Divyadarshini Karthikeyan, Manas Paldhe

机构 * Amazon, Toronto ON M5J0A8, Canada（亚马逊公司，多伦多） 纠错

Comments Accepted for publication at the 2025 International Conference on Machine Learning and Applications (ICMLA)

Journal ref 2025 ICMLA, Florida, USA

Learning Representations of Event Time Series with Sparse Autoencoders for Anomaly Detection, Similarity Search, and Unsupervised Classification

Steven Dillmann, Juan Rafael Martínez-Galarza

机构 * Stanford University ； Center for Astrophysics | Harvard \& Smithsonian 纠错

Comments Accepted at the 2025 ICML Workshop on Machine Learning for Astrophysics, Code available at: https://github.com/StevenDillmann/ml-xraytransients-mnras

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu

机构 * Michigan State University（密歇根州立大学） ； IBM Research（IBM研究院） 纠错

Comments Accepted by ICML 2025

WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry

Filip Ekström Kelvinius, Oskar B. Andersson, Abhijith S. Parackal, Dong Qian, Rickard Armiento, Fredrik Lindsten

机构 * Department of Computer and Information Science (IDA), Linköping University, Sweden（计算机与信息科学系（IDA），_linköping大学，瑞典） ； Department of Physics, Chemistry and Biology (IFM), Linköping University, Sweden（物理、化学与生物学系（IFM），_linköping大学，瑞典） 纠错

Comments Accepted to ICML 2025, official PMLR proceedings can be found at https://proceedings.mlr.press/v267/ekstrom-kelvinius25a.html. Code is available online at https://github.com/httk/wyckoffdiff

Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo

Filip Ekström Kelvinius, Zheng Zhao, Fredrik Lindsten

机构 * Department of Computer and Information Science (IDA), Linköping University, Sweden（计算机与信息科学系（IDA），_linköping大学，瑞典） 纠错

Comments Accepted to ICML 2025, official PMLR proceedings can be found at https://proceedings.mlr.press/v267/ekstrom-kelvinius25b.html. Code available at https://github.com/filipekstrm/ddsmc

Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors

David Madras, Joshua Safyan, Qiuyi, Zhang

机构 * Google Deepmind（谷歌DeepMind） 纠错

Comments EXAIT Workshop paper at ICML 2025

Disparate Conditional Prediction in Multiclass Classifiers

Sivan Sabato, Eran Treister, Elad Yom-Tov

机构 * Department of Computing and Software, McMaster University（计算与软件系，麦斯特大学；加拿大 CIFAR 人工智能主席，向量研究所） ； Canada CIFAR AI Chair, Vector Institute（计算机科学系，巴伊兰大学） ； Department of Computer Science, Bar-Ilan University（计算机科学系，贝纳-加隆大学） ； Department of Computer Science, Ben-Gurion University of the Negev 纠错

Comments Published at ICML 2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML), PMLR 267:52508-52525, 2025

EpiCoder: Encompassing Diversity and Complexity in Code Generation

Yaoxiang Wang, Haoling Li, Xin Zhang, Jie Wu, Xiao Liu, Wenxiang Hu, Zhongxin Guo, Yangyu Huang, Ying Xin, Yujiu Yang, Jinsong Su, Qi Chen, Scarlett Li

机构 * Microsoft（微软公司） ； School of Informatics, Xiamen University（厦门大学信息学院） ； Key Laboratory of Digital Protection（数字保护关键实验室） ； Taiwan (Xiamen University), Ministry of Culture（文化部（厦门大学）） ； Tsinghua University（清华大学） 纠错

Comments ICML 2025

Resolving Lexical Bias in Model Editing

Hammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad

机构 * Department of Computer Science, Dalhousie University, Halifax, Canada（计算机科学系，达尔豪斯大学，哈利法克斯，加拿大） 纠错

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51747-51769, 2025

Sequential Disentanglement by Extracting Static Information From A Single Sequence Element

Nimrod Berman, Ilan Naiman, Idan Arbiv, Gal Fadlon, Omri Azencot

机构 * Department of Computer Science, Ben-Gurion University of the Negev, Beer-Sheva, Israel（计算机科学系，内盖夫本·古里安大学，贝尔谢巴，以色列） 纠错

Comments Accepted to ICML 2024; The first four authors contributed equally

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3539-3564, 2024

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

Seok-Ju Hahn, Gi-Soo Kim, Junghye Lee

机构 * Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST)（乌山国立科学与技术研究所人工智能研究生院） ； Policy Program, Seoul National University (SNU)（首尔国立大学政策项目） ； Graduate School of Engineering Practice, Seoul National University (SNU)（首尔国立大学工程实践研究生院） ； Institute of Engineering Research, Seoul National University (SNU)（首尔国立大学工程研究所） 纠错

Comments Accepted at ICML 2024; added missing but important references, fixed typos

The Logical Implication Steering Method for Conditional Interventions on Transformer Generation

Damjan Kalajdzievski

机构 * Damjan Kalajdzievski（独立研究者） 纠错

Journal ref Forty-second International Conference on Machine Learning, 2025

TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration

Cheng Xin, Fan Xu, Xin Ding, Jie Gao, Jiaxin Ding

机构 * School of Computer Science, Shanghai Jiao Tong University, Shanghai, China（上海交通大学计算机科学学院） ； Department of Computer Science, Rutgers University, Piscataway, NJ, USA（罗格斯大学计算机科学系） 纠错

Comments submitted to ICML 2025

Breaking Barriers: Combinatorial Algorithms for Non-monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation

Yixin Chen, Wenjing Chen, Alan Kuhnle

Comments Accepted by ICML 2025

Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions

Negin Golrezaei, Sourav Sahoo

机构 * Sloan School of Management, Massachusetts Institute of Technology（麻省理工学院斯隆管理学院） ； Operations Research Center, Massachusetts Institute of Technology（麻省理工学院运筹学研究中心） 纠错

Comments 84 pages, 5 figures. Appeared at ICML 2025. Fixed typos

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups

Weiqiu You, Helen Qu, Marco Gatti, Bhuvnesh Jain, Eric Wong

机构 * Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA（计算机与信息科学系，宾夕法尼亚大学，费城，PA，美国） ； Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA, USA（物理与天文学系，宾夕法尼亚大学，费城，PA，美国） 纠错

Comments ICML 2025