ICML

Learning to Stop: Deep Learning for Mean Field Optimal Stopping

Lorenzo Magnino, Yuchen Zhu, Mathieu Laurière

机构 * Shanghai Frontiers Science Center of Artificial Intelligence（上海人工智能前沿科学中心） ； NYU-ECNU Institute of Mathematical Sciences（纽约大学-复旦大学数学科学研究院） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments Accepted to ICML 2025

Improving Generalization with Flat Hilbert Bayesian Inference

Tuan Truong, Quyen Tran, Quan Pham-Ngoc, Nhat Ho, Dinh Phung, Trung Le

Comments Accepted (ICML 2025)

Tree-Sliced Wasserstein Distance: A Geometric Perspective

Viet-Hoang Tran, Trang Pham, Tho Tran, Minh Khoi Nguyen Nhat, Thanh Chu, Tam Le, Tan M. Nguyen

Comments Accepted to ICML 2025

Nonparametric Modern Hopfield Models

Jerry Yao-Chieh Hu, Bo-Yu Chen, Dennis Wu, Feng Ruan, Han Liu

机构 * Department of Computer Science, Northwestern University, Evanston, IL, USA（计算机科学系，西北大学，伊利诺伊州埃文斯顿） ； Department of Physics and Computer Science, National Taiwan University, Taipei, Taiwan（物理与计算机科学系，国立台湾大学，台湾台北） ； Department of Statistics and Data Science, Northwestern University, Evanston, IL, USA（统计与数据科学系，西北大学，伊利诺伊州埃文斯顿） 纠错

Comments Accepted at ICML 2025. Code available at https://github.com/MAGICS-LAB/NonparametricHopfield. v2 matches with camera-ready version

On Hypothesis Transfer Learning of Functional Linear Models

Haotian Lin, Matthew Reimherr

机构 * Department of Statistics, The Pennsylvania State University（统计学系，宾夕法尼亚州立大学） ； Amazon Science（亚马逊科学） 纠错

Comments Accepted by ICML 2024

Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More

Geonhui Yoo, Minhak Song, Chulhee Yun

Comments ICML 2025

Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning

Armin Behnamnia, Gholamali Aminian, Alireza Aghaei, Chengchun Shi, Vincent Y. F. Tan, Hamid R. Rabiee

Comments Accepted as spotlight poster in ICML 2025

Curvature Enhanced Data Augmentation for Regression

Ilya Kaufman Sirot, Omri Azencot

机构 * Ilya Kaufman Omri Azencot 纠错

Comments Accepted to ICML 2025

Continuous Semi-Implicit Models

Longlin Yu, Jiajun Zha, Tong Yang, Tianyu Xie, Xiangyu Zhang, S. -H. Gary Chan, Cheng Zhang

Comments 26 pages, 8 figures, ICML 2025

Learning Distribution-Wise Control in Representation Space for Language Models

Chunyuan Deng, Ruidi Chang, Hanjie Chen

Comments ICML 2025

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

Hong-Ming Chiu, Hao Chen, Huan Zhang, Richard Y. Zhang

Comments ICML 2025

SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes

Yishan Shen, Yuyang Ye, Hui Xiong, Yong Chen

Comments Accepted by ICML 2025

Direct Prediction Set Minimization via Bilevel Conformal Classifier Training

Yuanjie Shi, Hooman Shahrokhi, Xuesong Jia, Xiongzhi Chen, Janardhan Rao Doppa, Yan Yan

Comments Accepted for Publication at International Conference on Machine Learning (ICML), 2025

Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks

Zijiang Yan, Hao Zhou, Jianhua Pei, Hina Tabassum

Comments Accepted in ICML 2025 Workshop on Machine Learning for Wireless Communication and Networks (ML4Wireless)

Enhancing Decision-Making of Large Language Models via Actor-Critic

Heng Dong, Kefei Duan, Chongjie Zhang

Comments Forty-second International Conference on Machine Learning (ICML 2025)

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding

Peihua Mai, Youlong Ding, Ziyan Lyu, Minxin Du, Yan Pang

Comments 26 pages, accepted by ICML 2025

Directly Forecasting Belief for Reinforcement Learning with Delays

Qingyuan Wu, Yuhui Wang, Simon Sinong Zhan, Yixuan Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Jürgen Schmidhuber, Chao Huang

Journal ref 42nd International Conference on Machine Learning, ICML 2025

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani, Amir Barati Farimani, Khoa D Doan, Chandan K Reddy

Comments ICML 2025 Oral. Project page: https://github.com/deep-symbolic-mathematics/llm-srbench , Benchmark page: https://huggingface.co/datasets/nnheui/llm-srbench

KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies

Shih-Min Yang, Martin Magnusson, Johannes A. Stork, Todor Stoyanov

Comments Accepted to ICML 2025

Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection

Peipeng Yu, Jianwei Fei, Hui Gao, Xuan Feng, Zhihua Xia, Chip Hong Chang

Comments Accepted by ICML 2025

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs

Ravi Ghadia, Avinash Kumar, Gaurav Jain, Prashant Nair, Poulami Das

Comments Published in the Proceedings of the 42nd International Conference on Machine Learning (ICML), Vancouver, Canada

MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding

Weikang Qiu, Zheng Huang, Haoyu Hu, Aosong Feng, Yujun Yan, Rex Ying

Comments Forty-Second International Conference on Machine Learning (ICML 2025)

Improving the Diffusability of Autoencoders

Ivan Skorokhodov, Sharath Girish, Benran Hu, Willi Menapace, Yanyu Li, Rameen Abdal, Sergey Tulyakov, Aliaksandr Siarohin

Comments ICML 2025

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior

Ching-Hua Lee, Chouchang Yang, Jaejin Cho, Yashas Malur Saidutta, Rakshith Sharma Srinivasa, Yilin Shen, Hongxia Jin

Comments Accepted by ICML 2025 - Camera Ready Version

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation

Minghao Fu, Guo-Hua Wang, Liangfu Cao, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang

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

Comments ICML 2025. The code is publicly available at https://github.com/AIDC-AI/CHATS

When Incentives Backfire, Data Stops Being Human

Sebastin Santy, Prasanta Bhattacharya, Manoel Horta Ribeiro, Kelsey Allen, Sewoong Oh

机构 * Sebastin Santy（独立研究者） ； Prasanta Bhattacharya（独立研究者） ； Manoel Horta Ribeiro（独立研究者） ； Kelsey Allen（独立研究者） ； Sewoong Oh（独立研究者） 纠错

Comments Position Paper at ICML 2025

RelGNN: Composite Message Passing for Relational Deep Learning

Tianlang Chen, Charilaos Kanatsoulis, Jure Leskovec

Comments 17 pages, 4 figures, 7 tables. ICML 2025

Sparse Autoencoders for Hypothesis Generation

Rajiv Movva, Kenny Peng, Nikhil Garg, Jon Kleinberg, Emma Pierson

Comments ICML 2025. First two authors contributed equally. v3 adds SAE ablation experiments and qualitative annotation study to v2. Code: https://github.com/rmovva/HypotheSAEs

Refining Adaptive Zeroth-Order Optimization at Ease

Yao Shu, Qixin Zhang, Kun He, Zhongxiang Dai

机构 * Yao Shu ； Qixin Zhang ； Kun He ； Zhongxiang Dai 纠错

Comments Published as a conference paper at ICML 2025

Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge

Hanna Wallach, Meera Desai, A. Feder Cooper, Angelina Wang, Chad Atalla, Solon Barocas, Su Lin Blodgett, Alexandra Chouldechova, Emily Corvi, P. Alex Dow, Jean Garcia-Gathright, Alexandra Olteanu, Nicholas Pangakis, Stefanie Reed, Emily Sheng, Dan Vann, Jennifer Wortman Vaughan, Matthew Vogel, Hannah Washington, Abigail Z. Jacobs

Comments In Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025