ICML

Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking

Weijian Deng, Weijie Tu, Ibrahim Radwan, Mohammad Abu Alsheikh, Stephen Gould, Liang Zheng

机构 * School of Computing, The Australian National University（澳大利亚国立大学计算机学院） ； University of Canberra（堪培拉大学） 纠错

Comments 15 pages, 11 figures, extension of ICML'23 work: Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation

Modern Methods in Associative Memory

Dmitry Krotov, Benjamin Hoover, Parikshit Ram, Bao Pham

机构 * IBM Research（IBM研究院） ； MIT（麻省理工学院） ； Georgia Tech（佐治亚理工学院） ； RPI（罗切斯特理工学院） 纠错

Comments Tutorial at ICML 2025

Exponential Family Variational Flow Matching for Tabular Data Generation

Andrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem van de Meent

机构 * Vector Institute（向量研究所） ； Bosch-Delta Lab（博世-德尔塔实验室） 纠错

Comments 14 pages, 1 figure, and 9 tables; To be published in the Proceedings of the Forty-Second International Conference on Machine Learning

CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering

Zhe Zhang, Mingxiu Cai, Hanxiao Wang, Gaochang Wu, Tianyou Chai, Xiatian Zhu

机构 * State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China（合成过程工业综合自动化国家重点实验室，东北大学，沈阳，中国） ； Meta, London, U.K.（Meta，伦敦，英国） ； Surrey Institute for People-Centred Artificial Intelligence（以人为本的人工智能研究院） 纠错

Comments 25 pages, 12 figures, 20 tables, accepted by Forty-Second International Conference on Machine Learning ( ICML 2025 ), link: https://icml.cc/virtual/2025/poster/46359

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning

Adrià López Escoriza, Nicklas Hansen, Stone Tao, Tongzhou Mu, Hao Su

机构 * University of California San Diego（加州大学圣迭戈分校） ； ETH Zürich, Switzerland（苏黎世联邦理工学院） 纠错

Comments Project page can be found at https://adrialopezescoriza.github.io/demo3/

Journal ref ICML 2025

Ranked from Within: Ranking Large Multimodal Models Without Labels

Weijie Tu, Weijian Deng, Dylan Campbell, Yu Yao, Jiyang Zheng, Tom Gedeon, Tongliang Liu

机构 * Australian National University ； Sydney AI Centre, The University of Sydney ； Curtin University ； University of \'OBuda 纠错

Comments ICML 2025 Camera Ready

BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators

Kma Solaiman

机构 * Department of CSEE, University of Maryland, Baltimore County, MD, USA（电子工程系，马里兰大学巴尔的摩县分校） 纠错

Comments Presented at ICML 2025 2nd Workshop on Models of Human Feedback for AI Alignment, Vancouver, Canada

Diffusion Adversarial Post-Training for One-Step Video Generation

Shanchuan Lin, Xin Xia, Yuxi Ren, Ceyuan Yang, Xuefeng Xiao, Lu Jiang

Comments ICML 2025

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

Jintao Zhang, Haofeng Huang, Pengle Zhang, Jia Wei, Jun Zhu, Jianfei Chen

机构 * Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系，人工智能研究院，BNRist中心，THBI实验室，清华-博世联合机器学习中心，清华大学） ； Institute for Interdisciplinary Information Sciences, Tsinghua University（交叉信息学院，清华大学） 纠错

Comments @inproceedings{zhang2024sageattention2, title={Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization}, author={Zhang, Jintao and Huang, Haofeng and Zhang, Pengle and Wei, Jia and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Machine Learning (ICML)}, year={2025} }

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)

Fully Heteroscedastic Count Regression with Deep Double Poisson Networks

Spencer Young, Porter Jenkins, Longchao Da, Jeff Dotson, Hua Wei

机构 * Brigham Young University, Department of Computer Science（Brigham Young 大学计算机科学系） ； Arizona State University, School of Computing and Augmented Intelligence（亚利桑那州立大学计算与增强智能学院） ； Ohio State University, Department of Marketing（俄亥俄州立大学市场营销系） 纠错

Comments Forty-Second International Conference on Machine Learning (ICML 2025)

Nonparametric Identification of Latent Concepts

Yujia Zheng, Shaoan Xie, Kun Zhang

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

Comments ICML 2025

What if Othello-Playing Language Models Could See?

Xinyi Chen, Yifei Yuan, Jiaang Li, Serge Belongie, Maarten de Rijke, Anders Søgaard

机构 * University of Amsterdam（阿姆斯特丹大学） ； ETH Zürich（苏黎世联邦理工学院） ； University of Copenhagen（哥本哈根大学） 纠错

Comments ICML 2025 Assessing World Models Workshop; EMNLP 2025 Findings

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

Haoyu He, Haozheng Luo, Yan Chen, Qi R. Wang

机构 * Northeastern University, Boston, MA（东北大学） ； Northwestern University, Evanston, IL（西北大学） 纠错

Journal ref Proceedings of the 3rd Workshop on Efficient Systems for Foundation Models (ES-FoMo III) at ICML 2025

Mimicking Better by Matching the Approximate Action Distribution

João A. Cândido Ramos, Lionel Blondé, Naoya Takeishi, Alexandros Kalousis

机构 * University of Geneva (UNIGE), Switzerland（日内瓦大学） ； University of Applied Sciences（应用科学大学） ； The University of Tokyo, Japan（东京大学） ； RIKEN Center for Advanced Intelligence Project, Japan（日本RIKEN高级智能项目中心） 纠错

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5513-5532, 2024

TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation

Gwen Yidou Weng, Benjie Wang, Guy Van den Broeck

机构 * ucla（美国加州大学洛杉矶分校） 纠错

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

Vintix: Action Model via In-Context Reinforcement Learning

Andrey Polubarov, Nikita Lyubaykin, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin, Vladislav Kurenkov

机构 * Innopolis University（因诺波利斯大学） ； Research Center for Trusted Artificial Intelligence, ISP RAS（可信人工智能研究所以及ISP俄罗斯科学院） 纠错

Comments ICML 2025, Poster

Societal Capacity Assessment Framework: Measuring Resilience to Inform Advanced AI Risk Management

Milan Gandhi, Peter Cihon, Owen Larter, Rebecca Anselmetti

机构 * Microsoft（微软） ； UK AI Security Institute（英国人工智能安全研究所） 纠错

Comments Workshop on Technical AI Governance (TAIG) at ICML 2025

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs

Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani, Junyoung Park, Yifan Zao, He Zhang, Tian Liu, Yiping Yang, Xin Yuan, Jiuyan Lu, Chris Lott, Mingu Lee

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

Comments 8 pages, 4 figures, 5 tables, accepted at ICML 2025 workshop on Efficient Systems for Foundational Models

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs

Emilio Barkett, Olivia Long, Madhavendra Thakur

机构 * Columbia University（哥伦比亚大学） 纠错

Comments Published at the ICML 2025 Workshop on Models of Human Feedback for AI Alignment

Causal Abstraction Inference under Lossy Representations

Kevin Xia, Elias Bareinboim

机构 * CausalAI Lab, Columbia University（因果推理实验室，哥伦比亚大学） 纠错

Comments 35 pages, 8 figures, published at ICML 2025

Object Identification Under Known Dynamics: A PIRNN Approach for UAV Classification

Nyi Nyi Aung, Neil Muralles, Adrian Stein

机构 * Department of Mechanical and Industrial Engineering（机械与工业工程系） ； Louisiana State University（路易斯安那州立大学） 纠错

Comments 2025 International Conference on Machine Learning and Applications (ICMLA)

Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models

Xiaoyu Wu, Jiaru Zhang, Zhiwei Steven Wu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Purdue University（普渡大学） 纠错

Comments Accepted at the International Conference on Machine Learning (ICML) 2025

Levels of AGI for Operationalizing Progress on the Path to AGI

Meredith Ringel Morris, Jascha Sohl-Dickstein, Noah Fiedel, Tris Warkentin, Allan Dafoe, Aleksandra Faust, Clement Farabet, Shane Legg

机构 * Google DeepMind, Seattle, WA, USA（谷歌DeepMind，美国华盛顿州西雅图） ； Google DeepMind, Mountain View, CA, USA（谷歌DeepMind，美国加利福尼亚州山景城） ； Google DeepMind, London, UK（谷歌DeepMind，英国伦敦） 纠错

Comments version 5 - We updated the nomenclature of Level 4 to be "Exceptional" instead of "Virtuoso"; due to ICML 2024 position paper titling requirements, the title is now "Levels of AGI for Operationalizing Progress on the Path to AGI" rather than "Levels of AGI: Operationalizing Progress on the Path to AGI"

Journal ref Proceedings of ICML 2024

FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

Ganyu Wang, Jinjie Fang, Maxwell J. Yin, Bin Gu, Xi Chen, Boyu Wang, Yi Chang, Charles Ling

机构 * Western University（温莎大学） ； Jilin University（吉林大学） ； McGill University（麦吉尔大学） ； Vector Institute（向量研究所） 纠错

Comments Published in Proceedings of the 42nd International Conference on Machine Learning

Journal ref Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, PMLR267, 2025

Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs

Sagnik Mukherjee, Abhinav Chinta, Takyoung Kim, Tarun Anoop Sharma, Dilek Hakkani-Tür

机构 * University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments Accepted at ICML 2025

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, Sujay Sanghavi

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Carnegie Mellon University（卡内基梅隆大学） ； Amazon（亚马逊） ； Department of Computer Science（计算机科学系） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments Published in TMLR, ICML-MFPL 2023 Workshop Oral, SPIGM@ICML2024

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

Dongchi Huang, Jiaqi Wang, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang

机构 * School of Computer Science, University of Beihang, Beijing, China（北京航空航天大学计算机学院） ； School of Computer Science, Chinese University of Hong Kong, Hongkong, China（香港中文大学计算机学院） ； JD Explore Academy, Beijing, China（京东探索研究院） ； North Automatic Control Institute, Taiyuan, China（太原北自动控制研究所） 纠错

Comments ICML 2025

Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data

Mohammad Hosseini, Maryam M. Shanechi

机构 * Viterbi School of Engineering, University of Southern California (USC)（维特比工程学院，南加州大学） 纠错

Comments Published at the 42nd International Conference on Machine Learning (ICML) 2025. Code available at: https://github.com/ShanechiLab/SBIND/

Journal ref ICML 2025

Is Pre-training Truly Better Than Meta-Learning?

Brando Miranda, Patrick Yu, Saumya Goyal, Yu-Xiong Wang, Sanmi Koyejo

机构 * Department of Computer Science, Stanford University（斯坦福大学计算机科学系） ； Machine Learning Department, Carnegie Mellon University（卡内基梅隆大学机器学习系） ； Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系） 纠错

Journal ref Proceedings of the 40th International Conference on Machine Learning 2023 DMLR Workshop

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance

Jinuk Kim, Marwa El Halabi, Wonpyo Park, Clemens JS Schaefer, Deokjae Lee, Yeonhong Park, Jae W. Lee, Hyun Oh Song

机构 * Department of XXX, University of YYY, Location, Country ； School of ZZZ, Institute of WWW, Location, Country ； Department of Computer Science ； Engineering, Seoul National University ； Neural Processing Research Center ； Samsung AI Lab, Montreal ； Google 纠错

Comments ICML 2025