ICML

REG: Rectified Gradient Guidance for Conditional Diffusion Models

Zhengqi Gao, Kaiwen Zha, Tianyuan Zhang, Zihui Xue, Duane S. Boning

Comments 20 pages, 10 figures; accepted by ICML'25

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

Benjamin Feuer, Chinmay Hegde

Comments ICML 2025

Doubly Robust Conformalized Survival Analysis with Right-Censored Data

Matteo Sesia, Vladimir Svetnik

Comments Revision after ICML review

Compact Matrix Quantum Group Equivariant Neural Networks

Edward Pearce-Crump

Comments ICML 2025 Poster; 32 pages

Learning Formal Specifications from Membership and Preference Queries

Ameesh Shah, Marcell Vazquez-Chanlatte, Sebastian Junges, Sanjit A. Seshia

Comments 10 pages, appeared at International Conference on Neuro-symbolic Systems 2025; also presented at ICML 2023 Workshop on The Many Facets of Preference-Based Learning

Fully Dynamic Submodular Maximization over Matroids

Paul Dütting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zadimoghaddam

Comments Accepted at ICML 2023

Journal ref ACM Transactions on Algorithms, Volume 21, Issue 1 (2025), Article No.: 11

Deletion Robust Non-Monotone Submodular Maximization over Matroids

Paul Dütting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zadimoghaddam

Comments Preliminary versions of this work appeared as arXiv:2201.13128 and in ICML'22. The main difference with respect to these versions consists in extending our results to non-monotone submodular functions

Journal ref Journal of Machine Learning Research 26 (2025) 1-28

GCAL: Adapting Graph Models to Evolving Domain Shifts

Ziyue Qiao, Qianyi Cai, Hao Dong, Jiawei Gu, Pengyang Wang, Meng Xiao, Xiao Luo, Hui Xiong

Comments Accepted to ICML 2025

Maximum Total Correlation Reinforcement Learning

Bang You, Puze Liu, Huaping Liu, Jan Peters, Oleg Arenz

Comments ICML 2025

Ranked Entropy Minimization for Continual Test-Time Adaptation

Jisu Han, Jaemin Na, Wonjun Hwang

Comments ICML 2025

SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval

Nikolaos Chaidos, Angeliki Dimitriou, Maria Lymperaiou, Giorgos Stamou

Journal ref ICML 2025

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

Wenhao Shen, Wanqi Yin, Xiaofeng Yang, Cheng Chen, Chaoyue Song, Zhongang Cai, Lei Yang, Hao Wang, Guosheng Lin

Comments Accepted to ICML 2025. Code: https://github.com/shenwenhao01/ADHMR

In-Context Adaptation to Concept Drift for Learned Database Operations

Jiaqi Zhu, Shaofeng Cai, Yanyan Shen, Gang Chen, Fang Deng, Beng Chin Ooi

Comments Accepted by ICML 2025

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators

Yilun Zhou, Austin Xu, Peifeng Wang, Caiming Xiong, Shafiq Joty

Comments ICML 2025. The first two authors contributed equally. The codebase is at https://github.com/SalesforceAIResearch/jetts-benchmark

PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

Fanmeng Wang, Wentao Guo, Qi Ou, Hongshuai Wang, Haitao Lin, Hongteng Xu, Zhifeng Gao

Comments Accepted by the 42nd International Conference on Machine Learning (ICML 2025)

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

Chaitanya K. Joshi, Xiang Fu, Yi-Lun Liao, Vahe Gharakhanyan, Benjamin Kurt Miller, Anuroop Sriram, Zachary W. Ulissi

机构 * Fundamental AI Research (FAIR) at Meta（Meta 基础人工智能研究） ； University of Cambridge（剑桥大学） ； MIT（麻省理工学院） 纠错

Comments ICML 2025

Steer LLM Latents for Hallucination Detection

Seongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang, Yixuan Li

Comments ICML 2025

Function-Space Learning Rates

Edward Milsom, Ben Anson, Laurence Aitchison

Comments ICML 2025 Camera Ready Version, 27 pages, 26 figures

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

Guoxin Chen, Minpeng Liao, Peiying Yu, Dingmin Wang, Zile Qiao, Chao Yang, Xin Zhao, Kai Fan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； Tongyi Lab（通义实验室） ； Soochow University（苏州大学） ； University of Oxford（牛津大学） ； Tsinghua University（清华大学） 纠错

Comments Camera ready version for ICML 2025

WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction

Fanmeng Wang, Minjie Cheng, Hongteng Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院） ； Beijing Key Laboratory of Research on Large Models（北京大型模型研究关键实验室） ； Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心） 纠错

Comments Accepted by the 42nd International Conference on Machine Learning (ICML 2025)

On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics

Binghui Li, Yuanzhi Li

Comments Published as a conference paper at ICML 2025; 28 pages

Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM

Penghao Wu, Lewei Lu, Ziwei Liu

Comments ICML 2025

Adaptive Estimation and Learning under Temporal Distribution Shift

Dheeraj Baby, Yifei Tang, Hieu Duy Nguyen, Yu-Xiang Wang, Rohit Pyati

Comments Accepted at ICML 2025

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

Zichao Li, Xueru Wen, Jie Lou, Yuqiu Ji, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun

Comments ICML 2025

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Junlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu, Junxian He

Comments ICML 2025

DPO Meets PPO: Reinforced Token Optimization for RLHF

Han Zhong, Zikang Shan, Guhao Feng, Wei Xiong, Xinle Cheng, Li Zhao, Di He, Jiang Bian, Liwei Wang

机构 * Peking University（北京大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学香槟分校） ； Microsoft Research Asia（微软亚洲研究院） 纠错

Comments ICML 2025

An Efficient Private GPT Never Autoregressively Decodes

Zhengyi Li, Yue Guan, Kang Yang, Yu Feng, Ning Liu, Yu Yu, Jingwen Leng, Minyi Guo

Comments Accepted by ICML 2025

Nonparametric Teaching for Graph Property Learners

Chen Zhang, Weixin Bu, Zeyi Ren, Zhengwu Liu, Yik-Chung Wu, Ngai Wong

Comments ICML 2025 Spotlight (25 pages, 17 figures)

Unlocking the Power of SAM 2 for Few-Shot Segmentation

Qianxiong Xu, Lanyun Zhu, Xuanyi Liu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao

Comments This paper is accepted by ICML'25

FG-CLIP: Fine-Grained Visual and Textual Alignment

Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Gengshen Zhang, Dawei Leng, Yuhui Yin

Comments Accepted at ICML 2025