ICML

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Han Zhong, Yutong Yin, Shenao Zhang, Xiaojun Xu, Yuanxin Liu, Yifei Zuo, Zhihan Liu, Boyi Liu, Sirui Zheng, Hongyi Guo, Liwei Wang, Mingyi Hong, Zhaoran Wang

机构 * Peking University（北京大学） ； Northwestern University（西北大学） ； Bytedance Inc（字节跳动公司） ； University of Minnesota（明尼苏达大学） 纠错

Comments ICML 2025

Scaling Inference-Efficient Language Models

Song Bian, Minghao Yan, Shivaram Venkataraman

Comments 21 pages, 18 figures, ICML 2025

Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts

Amir Najafi, Samin Mahdizadeh Sani, Farzan Farnia

Comments Published at the International Conference on Machine Learning (ICML) 2025. 36 pages, 10 figures

Mixed-curvature decision trees and random forests

Philippe Chlenski, Quentin Chu, Raiyan R. Khan, Kaizhu Du, Antonio Khalil Moretti, Itsik Pe'er

机构 * Columbia University（哥伦比亚大学） ； Barnard College（巴纳德学院） ； Spelman College（斯佩尔曼学院） 纠错

Comments 30 pages, 12 figures, 13 tables. Camera-ready version for ICML 2025

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization

Guy Kornowski, Daogao Liu, Kunal Talwar

机构 * Weizmann Institute of Science（魏茨曼科学研究所） ； Google（谷歌） ； University of Washington（华盛顿大学） ； Apple（苹果公司） 纠错

Comments Accepted to ICML 2025; some fixes following reviews

Generalization and Robustness of the Tilted Empirical Risk

Gholamali Aminian, Amir R. Asadi, Tian Li, Ahmad Beirami, Gesine Reinert, Samuel N. Cohen

Comments Accepted in ICML 2025

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

Yao Shu, Wenyang Hu, See-Kiong Ng, Bryan Kian Hsiang Low, Fei Richard Yu

Comments Published as a conference paper at ICML 2025

From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications

Ajay Jaiswal, Yifan Wang, Lu Yin, Shiwei Liu, Runjin Chen, Jiawei Zhao, Ananth Grama, Yuandong Tian, Zhangyang Wang

Comments Accepted in ICML 2025

Differentiable Quadratic Optimization For The Maximum Independent Set Problem

Ismail Alkhouri, Cedric Le Denmat, Yingjie Li, Cunxi Yu, Jia Liu, Rongrong Wang, Alvaro Velasquez

Journal ref International Conference on Machine Learning 2025

Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion

David Geissbühler, Hatef Otroshi Shahreza, Sébastien Marcel

机构 * Idiap Research Institute, Martigny, Switzerland ； \' E cole Polytechnique F\' e d\' e rale de Lausanne (EPFL), Lausanne, Switzerland 纠错

Comments Accepted in ICML 2025

VideoPrism: A Foundational Visual Encoder for Video Understanding

Long Zhao, Nitesh B. Gundavarapu, Liangzhe Yuan, Hao Zhou, Shen Yan, Jennifer J. Sun, Luke Friedman, Rui Qian, Tobias Weyand, Yue Zhao, Rachel Hornung, Florian Schroff, Ming-Hsuan Yang, David A. Ross, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Ting Liu, Boqing Gong

Comments Accepted to ICML 2024. v2: added retrieval results on MSRVTT (1K-A), more data analyses, and ablation studies; v3: released models at https://github.com/google-deepmind/videoprism

CoMemo: LVLMs Need Image Context with Image Memory

Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, Jifeng Dai

机构 * Shi Liu ； Weijie Su ； Xizhou Zhu ； Wenhai Wang ； Jifeng Dai 纠错

Comments ICML 2025

Transformative or Conservative? Conservation laws for ResNets and Transformers

Sibylle Marcotte, Rémi Gribonval, Gabriel Peyré

Comments Accepted to ICML 2025

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization

Muhammed Ustaomeroglu, Guannan Qu

Comments Accepted to ICML 2025

The Lock-in Hypothesis: Stagnation by Algorithm

Tianyi Alex Qiu, Zhonghao He, Tejasveer Chugh, Max Kleiman-Weiner

Comments ICML 2025, 46 pages

System-Aware Unlearning Algorithms: Use Lesser, Forget Faster

Linda Lu, Ayush Sekhari, Karthik Sridharan

Comments ICML 2025

Large Language Models are Demonstration Pre-Selectors for Themselves

Jiarui Jin, Yuwei Wu, Haoxuan Li, Xiaoting He, Weinan Zhang, Yiming Yang, Yong Yu, Jun Wang, Mengyue Yang

Comments ICML 2025

Runtime Analysis of Evolutionary NAS for Multiclass Classification

Zeqiong Lv, Chao Qian, Yun Liu, Jiahao Fan, Yanan Sun

Comments Accepted by ICML 2025

LightGTS: A Lightweight General Time Series Forecasting Model

Yihang Wang, Yuying Qiu, Peng Chen, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo

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

On Measuring Long-Range Interactions in Graph Neural Networks

Jacob Bamberger, Benjamin Gutteridge, Scott le Roux, Michael M. Bronstein, Xiaowen Dong

Comments ICML 2025

On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization

Undral Byambadalai, Tomu Hirata, Tatsushi Oka, Shota Yasui

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

Stealix: Model Stealing via Prompt Evolution

Zhixiong Zhuang, Hui-Po Wang, Maria-Irina Nicolae, Mario Fritz

Comments Accepted at ICML 2025. The project page is at https://zhixiongzh.github.io/stealix/

Positional Encoding meets Persistent Homology on Graphs

Yogesh Verma, Amauri H. Souza, Vikas Garg

Comments Accepted at ICML 2025

Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization

Yuki Takezawa, Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich

Comments ICML 2025

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks

Tuomas Oikarinen, Ge Yan, Tsui-Wei Weng

Comments Published at ICML 2025

Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants

Daniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Mathias Drton, Negar Kiyavash

Comments Accepted at ICML 2025

Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction

Yanbin Wei, Xuehao Wang, Zhan Zhuang, Yang Chen, Shuhao Chen, Yulong Zhang, Yu Zhang, James Kwok

Comments ICML 2025

Taming Knowledge Conflicts in Language Models

Gaotang Li, Yuzhong Chen, Hanghang Tong

Comments ICML 2025 (Spotlight)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Yukang Yang, Declan Campbell, Kaixuan Huang, Mengdi Wang, Jonathan Cohen, Taylor Webb

Comments This is an extended version of a paper that has been accepted to ICML 2025

Feedforward Few-shot Species Range Estimation

Christian Lange, Max Hamilton, Elijah Cole, Alexander Shepard, Samuel Heinrich, Angela Zhu, Subhransu Maji, Grant Van Horn, Oisin Mac Aodha

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