ICML

Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation

Yoann Boget

机构 * Data Mining and Machine Learning group, School for Business Administration (HEG-Geneva), University of Applied Sciences and Arts of Western Switzerland（应用科学与艺术大学西瑞士分校数据挖掘与机器学习小组） ； Computer Science Department, University of Geneva, Switzerland（日内瓦大学计算机科学系） 纠错

Comments ICML 2025 Accepted paper

Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems

Mikołaj Małkiński, Szymon Pawlonka, Jacek Mańdziuk

机构 * Warsaw University of Technology, Warsaw, Poland（华沙技术大学） ； AGH University of Krakow, Krakow, Poland（克拉科夫AGH大学） 纠错

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

Resampling Augmentation for Time Series Contrastive Learning: Application to Remote Sensing

Antoine Saget, Baptiste Lafabregue, Antoine Cornuéjols, Pierre Gançarski

机构 * ICube, University of Strasbourg, Strasbourg, France（ICube，斯特拉斯堡大学，法国斯特拉斯堡） 纠错

Comments 10 pages, 2 figures, accepted at 42nd International Conference on Machine Learning (ICML 2025) Terrabytes workshop

Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective

Jianyu Wang, Zhiqiang Hu, Lidong Bing

机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团） ； Hupan Lab（虎扑实验室） 纠错

Comments ICML 2025, and Code will be released at: https://github.com/jianyu-cs/PromptQuine/

Journal ref Forty-second International Conference on Machine Learning, 2025

Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics

Haoming Jing, Yorie Nakahira

Comments Accepted to ICML 2025

Geometric Contact Flows: Contactomorphisms for Dynamics and Control

Andrea Testa, Søren Hauberg, Tamim Asfour, Leonel Rozo

机构 * Bosch Center for Artificial Intelligence（博世人工智能中心） ； Institute for Anthropomatics and Robotics（人机学与机器人研究所） ； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院） ； Section of Cognitive Systems（认知系统部门） 纠错

Comments Accepted at ICML 2025

Reimagining Parameter Space Exploration with Diffusion Models

Lijun Zhang, Xiao Liu, Hui Guan

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

Comments Accepted at ICML 2025 EXAIT Workshop

SynDaCaTE: A Synthetic Dataset For Evaluating Part-Whole Hierarchical Inference

Jake Levi, Mark van der Wilk

机构 * Department of Computer Science, University of Oxford（牛津大学计算机科学系） 纠错

Comments Accepted at Methods and Opportunities at Small Scale (MOSS), ICML 2025, Vancouver, Canada

From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents

Mohammad Amaan Sayeed, Mohammed Talha Alam, Raza Imam, Shahab Saquib Sohail, Amir Hussain

机构 * Mohamed bin Zayed University of Artificial Intelligence, UAE（阿布扎克穆罕默德·本·扎耶德人工智能大学） ； Edinburgh Napier University, UK（爱丁堡纳皮尔大学） ； VIT Bhopal University, India（比哈尔大学） 纠错

Comments Published at the 4th Muslims in Machine Learning (MusIML) Workshop (ICML-25)

Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

Yunhak Oh, Junseok Lee, Yeongmin Kim, Sangwoo Seo, Namkyeong Lee, Chanyoung Park

机构 * Graduate School of Data Science, KAIST, Daejeon, Republic of Korea ； Department of Industrial \& Systems Engineering, KAIST, Daejeon, Republic of Korea ； Department of Mathematical Sciences, KAIST, Daejeon, Republic of Korea 纠错

Comments ICML 2025

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

机构 * Technical University of Munich, Munich, Germany（慕尼黑技术大学） 纠错

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

Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents

Soyeon Choi, Kangwook Lee, Oliver Sng, Joshua M. Ackerman

机构 * Department of Psychology, University of Wisconsin-Madison（威斯康星大学麦迪逊分校心理学系） ； Department of Electrical and Computer Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校电气与计算机工程系） ； Department of Psychological Science, University of California, Irvine（加州大学伊文斯分校心理学科学系） ； Department of Psychology, University of Michigan, Ann Arbor（密歇根大学安娜堡分校心理学系） 纠错

Comments ICML 2025 Workshop on Multi-Agent Systems in the Era of Foundation Models: Opportunities, Challenges and Futures

Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis

Pranav Agarwal, Ioana Ciucă

机构 * Stanford University（斯坦福大学） ； Mila, Quebec AI Institute（魁北克AI研究院） 纠错

Comments Accepted at Actionable Interpretability Workshop at ICML 2025

DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy

Kaixuan Xu, Jiajun Chai, Sicheng Li, Yuqian Fu, Yuanheng Zhu, Dongbin Zhao

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京，中国） ； State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京，中国） 纠错

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

PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views

Mohamed Rayan Barhdadi, Hasan Kurban, Hussein Alnuweiri

机构 * Department of Electrical and Computer Engineering, Texas A\&M University, Doha, Qatar（电气与计算机工程系，德克萨斯A&M大学，多哈，卡塔尔） ； College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar（科学与工程学院，哈马德·本·卡伊夫大学，多哈，卡塔尔） 纠错

Comments 4 pages, 2 figures, 2 tables. Appearing in Building Physically Plausible World Models at the 42nd International Conference on Machine Learning (ICML 2025), Vancouver, Canada

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang

机构 * Tsinghua University（清华大学） ； The University of Texas at Austin（得克萨斯大学） ； NVIDIA（英伟达） 纠错

Comments ICML 2025 Spotlight Project Page: https://research.nvidia.com/labs/dir/ddo/ Code: https://github.com/NVlabs/DDO

RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

Guanzheng Chen, Qilong Feng, Jinjie Ni, Xin Li, Michael Qizhe Shieh

机构 * National University of Singapore（新加坡国立大学） ； DAMO Academy, Alibaba Group（阿里巴巴集团达摩院） ； Hupan Lab, 310023, Hangzhou, China（杭州研究院） 纠错

Comments ICML 2025 Spotlight

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

Sangyeon Park, Isaac Han, Seungwon Oh, Kyung-Joong Kim

机构 * Department of AI Convergence, Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea（人工智能融合学院，全州科学技术研究院（GIST），全州，韩国） 纠错

Comments Accepted to ICML 2025 (poster)

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

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Yuanhe Zhang, Fanghui Liu, Yudong Chen

机构 * Department of Statistics, University of Warwick, UK.（威斯敏斯特大学统计学系） ； Department of Computer Science, University of Warwick, UK.（威斯敏斯特大学计算机科学系） ； Centre for Discrete Mathematics and its Applications (DIMAP), University of Warwick, UK.（威斯敏斯特大学离散数学及其应用中心（DIMAP）） 纠错

Comments Accepted by ICML 2025 (Oral)

How Far is Video Generation from World Model: A Physical Law Perspective

Bingyi Kang, Yang Yue, Rui Lu, Zhijie Lin, Yang Zhao, Kaixin Wang, Gao Huang, Jiashi Feng

机构 * ByteDance Research（字节跳动研究团队） ； Tsinghua University（清华大学） 纠错

Comments ICML 2025

Validating Mechanistic Interpretations: An Axiomatic Approach

Nils Palumbo, Ravi Mangal, Zifan Wang, Saranya Vijayakumar, Corina S. Pasareanu, Somesh Jha

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Colorado State University（科罗拉多州立大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted to ICML 2025

G-Adaptivity: optimised graph-based mesh relocation for finite element methods

James Rowbottom, Georg Maierhofer, Teo Deveney, Eike Mueller, Alberto Paganini, Katharina Schratz, Pietro Liò, Carola-Bibiane Schönlieb, Chris Budd

机构 * Department of Applied Mathematics ； Theoretical Physics, University of Cambridge, UK ； Department of Mathematical Sciences, University of Bath, UK ； Department of Computer Science, University of Bath, UK ； School of Computing ； Mathematical Sciences, University of Leicester, UK ； Laboratoire Jacques-Louis Lions, Sorbonne Universit\'e, France ； Department of Computer Science ； Technology, University of Cambridge, UK 纠错

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

Learning interpretable positional encodings in transformers depends on initialization

Takuya Ito, Luca Cocchi, Tim Klinger, Parikshit Ram, Murray Campbell, Luke Hearne

机构 * Mathematics \& Theoretical Computer Science Department, IBM Research, NY, USA ； QIMR Berghofer Medical Research Institute Brisbane, QLD, Australia 纠错

Comments ICML 2025, Workshop on Actionable Interpretability

Navigating Conflicting Views: Harnessing Trust for Learning

Jueqing Lu, Wray Buntine, Yuanyuan Qi, Joanna Dipnall, Belinda Gabbe, Lan Du

机构 * Department of Data Science \& AI, Monash University ； School of Public Health ； Preventive Medicine, Monash University ； College of Engineering ； Computer Science, VinUniversity 纠错

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

An Unsupervised Approach for Periodic Source Detection in Time Series

Berken Utku Demirel, Christian Holz

机构 * Department of Computer Science, ETH Zurich, Switzerland（计算机科学系，苏黎世联邦理工学院，瑞士） 纠错

Comments To appear at the International Conference on Machine Learning (ICML) 2024

Journal ref Proc. 41st Int. Conf. Mach. Learn. (ICML), PMLR 235 (2024)

Supercharging Graph Transformers with Advective Diffusion

Qitian Wu, Chenxiao Yang, Kaipeng Zeng, Michael Bronstein

机构 * Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard（埃里克和wendy Schmidt中心，MIT和哈佛大学Broad研究所） ； Toyota Technological Institute at Chicago（芝加哥丰田技术研究所） ； Shanghai Jiao Tong University（上海交通大学） ； University of Oxford（牛津大学） 纠错

Comments Accepted to ICML 2025

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection

Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha

机构 * Depart of Computer Sciences, University of Wisconsin-Madison, Madison, WI, USA（威斯康星大学麦迪逊分校计算机科学系） ； Google（谷歌） 纠错

Comments Accepted to ICML 2024

DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation

Shuyuan Wang, Philip D. Loewen, Michael Forbes, Bhushan Gopaluni, Wei Pan

机构 * The University of British Columbia, Vancouver, Canada（不列颠哥伦比亚大学） ； The University of Manchester, Manchester, England（曼彻斯特大学） 纠错

Comments Accepted at ICML 2025. Official conference page: https://icml.cc/virtual/2025/poster/44176. OpenReview page: https://openreview.net/forum?id=m2EfTrbv4o

When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network

Dong Xiao, Guangyao Chen, Peixi Peng, Yangru Huang, Yifan Zhao, Yongxing Dai, Yonghong Tian

机构 * National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学） ； Department of Software and Microelectronics, Peking University（软件与微电子系，北京大学） ； School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学） ； State Key Laboratory of Virtual Reality Technology and Systems, SCSE, Beihang University（虚拟现实技术与系统国家重点实验室，北航软件学院） ； Peng Cheng Laboratory（鹏城实验室） ； Baidu Inc（百度公司） 纠错

Comments ICML 2025 Spotlight

Efficient Quantification of Multimodal Interaction at Sample Level

Zequn Yang, Hongfa Wang, Di Hu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学语言学院） ； Tencent Data Platform（腾讯数据平台） ； Tsinghua University, Beijing, China（清华大学） ； 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 to ICML 2025