ICML

Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion

Anle Ke, Xu Zhang, Tong Chen, Ming Lu, Chao Zhou, Jiawen Gu, Zhan Ma

Journal ref ICML 2025

COMRECGC: Global Graph Counterfactual Explainer through Common Recourse

Gregoire Fournier, Sourav Medya

Comments Accepted at ICML 2025

Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

Shuanghao Bai, Wanqi Zhou, Pengxiang Ding, Wei Zhao, Donglin Wang, Badong Chen

机构 * Shuanghao Bai（双浩白） ； Wanqi Zhou（王婉琪） ； Pengxiang Ding（丁鹏祥） ； Wei Zhao（赵伟） ； Donglin Wang（王东林） ； Badong Chen（陈Badong） 纠错

Comments Accepted by ICML 2025

Position: AI Scaling: From Up to Down and Out

Yunke Wang, Yanxi Li, Chang Xu

Comments ICML 2025

Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models

Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang

Comments Accepted by ICML 2025

Continuous Visual Autoregressive Generation via Score Maximization

Chenze Shao, Fandong Meng, Jie Zhou

Comments ICML 2025

Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources

Renzhe Xu, Kang Wang, Bo Li

机构 * Key Laboratory of Interdisciplinary Research of Computation and Economics, Institute for Theoretical Computer Science, Shanghai University of Finance and Economics（计算与经济学交叉研究重点实验室，理论计算机科学研究所，上海金融学院） ； College of Management and Economics, Tianjin University（管理学院，天津大学） ； School of Economics and Management, Tsinghua University（经济管理学院，清华大学） 纠错

Comments ICML 2025

On the Robustness of Reward Models for Language Model Alignment

Jiwoo Hong, Noah Lee, Eunki Kim, Guijin Son, Woojin Chung, Aman Gupta, Shao Tang, James Thorne

Comments ICML 2025

When Dynamic Data Selection Meets Data Augmentation

Suorong Yang, Peng Ye, Furao Shen, Dongzhan Zhou

Journal ref ICML 2025

Unbiased Evaluation of Large Language Models from a Causal Perspective

Meilin Chen, Jian Tian, Liang Ma, Di Xie, Weijie Chen, Jiang Zhu

Comments Accepted by ICML 2025

Unsupervised Learning for Class Distribution Mismatch

Pan Du, Wangbo Zhao, Xinai Lu, Nian Liu, Zhikai Li, Chaoyu Gong, Suyun Zhao, Hong Chen, Cuiping Li, Kai Wang, Yang You

Comments Accepted by ICML 2025

Whitened CLIP as a Likelihood Surrogate of Images and Captions

Roy Betser, Meir Yossef Levi, Guy Gilboa

Comments Accepted to ICML 2025. This version matches the camera-ready version

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

LineFlow: A Framework to Learn Active Control of Production Lines

Kai Müller, Martin Wenzel, Tobias Windisch

Comments Accepted at ICML 2025

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model

Baijiong Lin, Weisen Jiang, Yuancheng Xu, Hao Chen, Ying-Cong Chen

Comments Accepted by ICML 2025

FloE: On-the-Fly MoE Inference on Memory-constrained GPU

Yuxin Zhou, Zheng Li, Jun Zhang, Jue Wang, Yiping Wang, Zhongle Xie, Ke Chen, Lidan Shou

Comments Accepted by ICML 2025

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Yixin Cheng, Hongcheng Guo, Yangming Li, Leonid Sigal

Comments ICML 2025 Accpeted

Robust Learning of Diverse Code Edits

Tushar Aggarwal, Swayam Singh, Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan

机构 * Microsoft Research India（微软印度研究院） 纠错

Comments To appear in ICML 2025 as 'NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits'

Clustering Properties of Self-Supervised Learning

Xi Weng, Jianing An, Xudong Ma, Binhang Qi, Jie Luo, Xi Yang, Jin Song Dong, Lei Huang

Comments Accepted at ICML 2025

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

Letian Chen, Nina Moorman, Matthew Gombolay

机构 * School of Interactive Computing, Georgia Institute of Technology, Atlanta, United States（交互计算学院，佐治亚理工学院，美国亚特兰大） ； Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，Location Country） ； School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，Location Country） 纠错

Comments ICML 2025

Reward-free World Models for Online Imitation Learning

Shangzhe Li, Zhiao Huang, Hao Su

Comments ICML 2025; Code available at: https://github.com/TobyLeelsz/iqmpc

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

Shenao Zhang, Zhihan Liu, Boyi Liu, Yufeng Zhang, Yingxiang Yang, Yongfei Liu, Liyu Chen, Tao Sun, Zhaoran Wang

Comments Published at ICML 2025

Branches: Efficiently Seeking Optimal Sparse Decision Trees with AO*

Ayman Chaouki, Jesse Read, Albert Bifet

机构 * AI Institute, University of Waikato（瓦卡托大学人工智能研究所） 纠错

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

Demystifying SGD with Doubly Stochastic Gradients

Kyurae Kim, Joohwan Ko, Yi-An Ma, Jacob R. Gardner

机构 * Department of Computer and Information Sciences, University of Pennsylvania, Philadelphia, PA, U.S.A.（宾夕法尼亚大学计算机与信息科学系） ； Hal c o g lu Data Science Institute, University of California San Diego, San Diego, CA, U.S.A.（加州大学圣地亚哥分校Hal c o g lu数据科学研究所） 纠错

Comments Accepted to ICML'24; v2: fixed typo in complexity statements

Fleet of Agents: Coordinated Problem Solving with Large Language Models

Lars Klein, Nearchos Potamitis, Roland Aydin, Robert West, Caglar Gulcehre, Akhil Arora

Comments ICML 2025; 28 pages, 68 figures, 8 tables

DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers

Xuanlei Zhao, Shenggan Cheng, Chang Chen, Zangwei Zheng, Ziming Liu, Zheming Yang, Yang You

Comments ICML 2025

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

Federico Errica, Henrik Christiansen, Viktor Zaverkin, Takashi Maruyama, Mathias Niepert, Francesco Alesiani

Journal ref International Conference on Machine Learning (ICML 2025)

MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs

Tommaso Mencattini, Adrian Robert Minut, Donato Crisostomi, Andrea Santilli, Emanuele Rodolà

Comments In Proceedings of The Forty-Second International Conference on Machine Learning (ICML 2025)

Distillation of Discrete Diffusion through Dimensional Correlations

Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji

Comments 39 pages, ICML 2025 accepted

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Yi Yu, Song Xia, Siyuan Yang, Chenqi Kong, Wenhan Yang, Shijian Lu, Yap-Peng Tan, Alex C. Kot

Comments Accepted by ICML 2025

Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective

Hechuan Wen, Tong Chen, Mingming Gong, Li Kheng Chai, Shazia Sadiq, Hongzhi Yin

Comments Accepted by ICML'25