ICML

InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory

Feifei Li, Mi Zhang, Zhaoxiang Wang, Min Yang

Comments Accepted by ICML 2025 (Poster)

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

Zican Hu, Wei Liu, Xiaoye Qu, Xiangyu Yue, Chunlin Chen, Zhi Wang, Yu Cheng

机构 * Nanjing University（南京大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； The Hong Kong University of Science and Technology（香港科学与技术大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Accepted by ICML 2025, 21 pages

Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning

Xinrui Wang, Shao-yuan Li, Jiaqiang Zhang, Songcan Chen

Comments accepted by ICML 2025

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation

Piyush Tiwary, Kinjawl Bhattacharyya, Prathosh A. P

机构 * Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore, India（电子通信工程系，印度科学研究院，班加罗尔） 纠错

Comments Accepted at ICML 2025

Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams

Yuan Feng, Yukun Cao, Hairu Wang, Xike Xie, S Kevin Zhou

Comments ICML 2025

Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games

Yi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang, Volkan Cevher

Comments Accepted for ICML 2025

Sampling from Binary Quadratic Distributions via Stochastic Localization

Chenguang Wang, Kaiyuan Cui, Weichen Zhao, Tianshu Yu

Comments Accepted by ICML 2025

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Qinsi Wang, Hancheng Ye, Ming-Yu Chung, Yudong Liu, Yueqian Lin, Martin Kuo, Mingyuan Ma, Jianyi Zhang, Yiran Chen

Comments ICML 2025

I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts

Jiayi Xin, Sukwon Yun, Jie Peng, Inyoung Choi, Jenna L. Ballard, Tianlong Chen, Qi Long

Comments ICML 2025 Poster

CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations

Haotian Si, Changhua Pei, Jianhui Li, Dan Pei, Gaogang Xie

Comments Accepted by Forty-second International Conference on Machine Learning (ICML'25)

On the Role of Label Noise in the Feature Learning Process

Andi Han, Wei Huang, Zhanpeng Zhou, Gang Niu, Wuyang Chen, Junchi Yan, Akiko Takeda, Taiji Suzuki

Comments Accepted to ICML 2025

Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning

Wenbo He, Zhijian Ou

机构 * Wenbo He（温波 海） ； Zhijian Ou（欧志健） 纠错

Comments ICML 2018 submission. arXiv admin note: text overlap with arXiv:1808.01630

B-score: Detecting biases in large language models using response history

An Vo, Mohammad Reza Taesiri, Daeyoung Kim, Anh Totti Nguyen

Comments Accepted to ICML 2025 (Main track)

Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization

Robbert Reijnen, Yaoxin Wu, Zaharah Bukhsh, Yingqian Zhang

Comments Accepted at ICML 2025

Improving Compositional Generation with Diffusion Models Using Lift Scores

Chenning Yu, Sicun Gao

Journal ref ICML 2025

One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework

Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Xiaochun Cao, Qingming Huang

Comments This paper has been accepeted to ICML 2025

Vision Graph Prompting via Semantic Low-Rank Decomposition

Zixiang Ai, Zichen Liu, Jiahuan Zhou

Comments Accepted by ICML 2025

Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction

Yi He, Yiming Yang, Xiaoyuan Cheng, Hai Wang, Xiao Xue, Boli Chen, Yukun Hu

Comments To be published in the proceedings of the 42nd International Conference on Machine Learning (ICML), Vancouver, Canada. PMLR 267, 2025

Beyond One-Hot Labels: Semantic Mixing for Model Calibration

Haoyang Luo, Linwei Tao, Minjing Dong, Chang Xu

Comments Accepted by ICML 2025

Societal Impacts Research Requires Benchmarks for Creative Composition Tasks

Judy Hanwen Shen, Carlos Guestrin

Comments v1: ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign) v2: ICML 2025 Position Paper

Mixture of Lookup Experts

Shibo Jie, Yehui Tang, Kai Han, Yitong Li, Duyu Tang, Zhi-Hong Deng, Yunhe Wang

Comments ICML 2025

Empirical Privacy Variance

Yuzheng Hu, Fan Wu, Ruicheng Xian, Yuhang Liu, Lydia Zakynthinou, Pritish Kamath, Chiyuan Zhang, David Forsyth

Comments Accepted at ICML 2025

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Jingang Qu, David Holzmüller, Gaël Varoquaux, Marine Le Morvan

Comments Published at ICML 2025

Flow Q-Learning

Seohong Park, Qiyang Li, Sergey Levine

机构 * ucb（加州大学伯克利分校） 纠错

Comments ICML 2025

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

Changdae Oh, Zhen Fang, Shawn Im, Xuefeng Du, Yixuan Li

机构 * Changdae Oh ； Zhen Fang ； Shawn Im ； Xuefeng Du ； Yixuan Li 纠错

Comments ICML 2025 camera-ready

Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images

Zhengrui Guo, Qichen Sun, Jiabo Ma, Lishuang Feng, Jinzhuo Wang, Hao Chen

Comments Accepted by ICML 2025

Beyond Message Passing: Neural Graph Pattern Machine

Zehong Wang, Zheyuan Zhang, Tianyi Ma, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Comments Accepted by ICML 2025

NExtLong: Toward Effective Long-Context Training without Long Documents

Chaochen Gao, Xing Wu, Zijia Lin, Debing Zhang, Songlin Hu

Comments Accepted by ICML 2025. Corresponding authors: xing wu, and songlin hu

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

Yang Shen, Xiu-Shen Wei, Yifan Sun, Yuxin Song, Tao Yuan, Jian Jin, Heyang Xu, Yazhou Yao, Errui Ding

Comments ICML'25, 44 pages

Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees

Zehong Wang, Zheyuan Zhang, Tianyi Ma, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Comments Accepted by ICML 2025