ICML

To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers

Roman Plaud, Alexandre Perez-Lebel, Matthieu Labeau, Antoine Saillenfest, Thomas Bonald

机构 * Soda, Inria Saclay, France（Soda，法国萨克利研究所） ； Fundamental Technologies, USA（Fundamental Technologies，美国） 纠错

Comments Accepted at ICML 2025

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

Minghao Xu, Jiaze Song, Keming Wu, Xiangxin Zhou, Bin Cui, Wentao Zhang

Comments Published at ICML 2025. All code and data are released

No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks

Attila Szász, Balázs Bánhelyi, Márk Jelasity

Comments accepted at ICML 2025. For the implementation, see https://github.com/szasza1/no_soundness

Enhancing Parallelism in Decentralized Stochastic Convex Optimization

Ofri Eisen, Ron Dorfman, Kfir Y. Levy

Comments ICML 2025

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning

Kyowoon Lee, Jaesik Choi

Comments ICML 2025

"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift

Harvineet Singh, Fan Xia, Alexej Gossmann, Andrew Chuang, Julian C. Hong, Jean Feng

Comments 13 pages, 9 figures, 8 tables, 18 pages appendix. To be published in Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Kuan-Po Huang, Shu-wen Yang, Huy Phan, Bo-Ru Lu, Byeonggeun Kim, Sashank Macha, Qingming Tang, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, Chao Wang

Comments Accepted by ICML 2025. Project website: https://audio-impact.github.io/

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro, Aaron Courville, Glen Berseth

Comments Accepted to ICML 2025

Score Matching With Missing Data

Josh Givens, Song Liu, Henry W J Reeve

机构 * School of Mathematics, University of Bristol, Bristol, UK（布里斯托大学数学学院） ； School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院） 纠错

Comments Accepted for ICML 2025 Conference Proceedings (Spotlight)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time

Mohamad Chehade, Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Dinesh Manocha, Hao Zhu, Amrit Singh Bedi

Comments Accepted at ICML 2025

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

Yaoyang Liu, Junlin Li, Yinjun Wu, Zhen Chen

Comments Published in ICML 2025

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection

Xinyue Zeng, Haohui Wang, Junhong Lin, Jun Wu, Tyler Cody, Dawei Zhou

Comments Accepted by ICML'2025

AdaWorld: Learning Adaptable World Models with Latent Actions

Shenyuan Gao, Siyuan Zhou, Yilun Du, Jun Zhang, Chuang Gan

Comments ICML 2025. Project page: https://adaptable-world-model.github.io/, code: https://github.com/Little-Podi/AdaWorld, model: https://huggingface.co/Little-Podi/AdaWorld

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

Han-Byul Kim, Duc Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho

Comments International Conference on Machine Learning (ICML) 2025

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

Maksim Zhdanov, Max Welling, Jan-Willem van de Meent

Comments Accepted to ICML 2025. Code: https://github.com/maxxxzdn/erwin

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Yuliang Liu, Junjie Lu, Zhaoling Chen, Chaofeng Qu, Jason Klein Liu, Chonghan Liu, Zefan Cai, Yunhui Xia, Li Zhao, Jiang Bian, Chuheng Zhang, Wei Shen, Zhouhan Lin

Comments ICML 2025

Falsification of Unconfoundedness by Testing Independence of Causal Mechanisms

Rickard K. A. Karlsson, Jesse H. Krijthe

Comments ICML 2025 camera-ready version; 20 pages, including 5 figures, 2 tables, and appendices

Reflection-Window Decoding: Text Generation with Selective Refinement

Zeyu Tang, Zhenhao Chen, Xiangchen Song, Loka Li, Yunlong Deng, Yifan Shen, Guangyi Chen, Peter Spirtes, Kun Zhang

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

Causal Abstraction Learning based on the Semantic Embedding Principle

Gabriele D'Acunto, Fabio Massimo Zennaro, Yorgos Felekis, Paolo Di Lorenzo

Journal ref Proceedings of the Forty-second International Conference on Machine Learning (ICML 2025)

PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion

Sophia Tang, Yinuo Zhang, Pranam Chatterjee

机构 * Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学） ； Center of Computational Biology, Duke-NUS Medical School（计算生物学中心，杜克-新加坡医学学校） ； Department of Bioengineering, University of Pennsylvania（生物工程系，宾夕法尼亚大学） 纠错

Comments Published at ICML 2025. (Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada)

Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents

Junyan Liu, Lillian J. Ratliff

Comments 48 pages, ICML 2025

Distributionally Robust Policy Learning under Concept Drifts

Jingyuan Wang, Zhimei Ren, Ruohan Zhan, Zhengyuan Zhou

Comments Poster at ICML2025

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

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

Guoxuan Chen, Han Shi, Jiawei Li, Yihang Gao, Xiaozhe Ren, Yimeng Chen, Xin Jiang, Zhenguo Li, Weiyang Liu, Chao Huang

Comments Accepted to ICML 2025

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho

Comments ICML 2025

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Chejian Xu, Mintong Kang, Jiawei Zhang, Zeyi Liao, Lingbo Mo, Mengqi Yuan, Huan Sun, Bo Li

Comments ICML 2025

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich, Achin Kulshrestha, Nathalie Rauschmayr, Yejin Choi, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister

Comments ICML 2025

Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees

Xin Yu, Zelin He, Ying Sun, Lingzhou Xue, Runze Li

Comments Published in Proceedings of the 42st International Conference on Machine Learning (ICML 2025)

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration

Yushi Huang, Zining Wang, Ruihao Gong, Jing Liu, Xinjie Zhang, Jinyang Guo, Xianglong Liu, Jun Zhang

机构 * iComAI Lab, Hong Kong University of Science and Technology（香港科技大学iComAI实验室） ； SenseTime Research（商汤科技研究院） ； SCSE, Beihang University（北京航空航天大学SCSE） ； IAI, Beihang University（北京航空航天大学IAI） ； SKLCCSE, Beihang University（北京航空航天大学SKLCCSE） ； ZIP Lab, Monash University（墨尔本大学ZIP实验室） 纠错

Comments Accepted by ICML 2025

Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation

Junlin Han, Jianyuan Wang, Andrea Vedaldi, Philip Torr, Filippos Kokkinos

Comments ICML 25. Project page: https://junlinhan.github.io/projects/flex3d/

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training

Zizheng Huang, Haoxing Chen, Jiaqi Li, Jun Lan, Huijia Zhu, Weiqiang Wang, Limin Wang

Comments accpeted to ICML25

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