ICML

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

Ruiyu Wang, Yu Yuan, Shizhao Sun, Jiang Bian

Comments ICML 2025 camera ready

Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?

Konrad Mundinger, Max Zimmer, Aldo Kiem, Christoph Spiegel, Sebastian Pokutta

机构 * Department for AI in Science, Society, and Technology, Zuse Institute Berlin, Germany（人工智能科学、社会与技术部门，柏林Zuse研究所） ； Institute of Mathematics, Technische Universität Berlin, Germany（数学研究所，柏林技术大学） 纠错

Comments 9 pages main paper, 11 pages references and appendix, 17 figures, 1 table

Journal ref Proc. 42nd ICML, PMLR 267, 2025

Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks

Keyue Qiu, Yuxuan Song, Jie Yu, Hongbo Ma, Ziyao Cao, Zhilong Zhang, Yushuai Wu, Mingyue Zheng, Hao Zhou, Wei-Ying Ma

Comments Accepted to ICML 2025

Autoformulation of Mathematical Optimization Models Using LLMs

Nicolás Astorga, Tennison Liu, Yuanzhang Xiao, Mihaela van der Schaar

机构 * DAMTP, University of Cambridge, Cambridge, UK（剑桥大学 DAMTP 部门） ； ECE, University of Hawaii at Manoa, Honolulu, USA（夏威夷大学马诺а分校电子与计算机工程学院） 纠错

Comments *Astorga and Liu contributed equally. Published as a conference paper at ICML 2025

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams, Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin

Comments ICML 2025. First two authors contributed equally

Isolated Causal Effects of Natural Language

Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael

Comments ICML 2025

The Disparate Benefits of Deep Ensembles

Kajetan Schweighofer, Adrian Arnaiz-Rodriguez, Sepp Hochreiter, Nuria Oliver

Comments ICML 2025

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain

Comments Accepted at ICML 2025 (also at the NeurIPS 2024 Workshop on Compression in Machine Learning)

Average Certified Radius is a Poor Metric for Randomized Smoothing

Chenhao Sun, Yuhao Mao, Mark Niklas Müller, Martin Vechev

Comments ICML'25

SPHINX: Structural Prediction using Hypergraph Inference Network

Iulia Duta, Pietro Liò

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

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution

Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh

Comments Accepted to ICML 2025

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding

Kevin Xu, Issei Sato

Comments Camera-ready version for ICML 2025

EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities

Talor Abramovich, Meet Udeshi, Minghao Shao, Kilian Lieret, Haoran Xi, Kimberly Milner, Sofija Jancheska, John Yang, Carlos E. Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik Narasimhan, Ramesh Karri, Ofir Press

机构 * Tel Aviv University（特拉维夫大学） ； NYU Tandon School of Engineering（纽约大学工程学院） ； New York University Abu Dhabi（纽约大学阿布扎克分校） ； Princeton Language and Intelligence（普林斯顿语言与智能） ； Stanford University（斯坦福大学） 纠错

Comments ICML 2025; Project website https://enigma-agent.com

LEMoN: Label Error Detection using Multimodal Neighbors

Haoran Zhang, Aparna Balagopalan, Nassim Oufattole, Hyewon Jeong, Yan Wu, Jiacheng Zhu, Marzyeh Ghassemi

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments Published in ICML 2025

Scaling Trends in Language Model Robustness

Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth, Michał Zajac, Tom Tseng, Aaron Tucker, Pierre-Luc Bacon, Adam Gleave

Comments 59 pages; updated to ICML version

Causal Discovery from Conditionally Stationary Time Series

Carles Balsells-Rodas, Xavier Sumba, Tanmayee Narendra, Ruibo Tu, Gabriele Schweikert, Hedvig Kjellstrom, Yingzhen Li

Comments ICML 2025

Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models

Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli

Comments ICML 2025

Improving Out-of-Distribution Detection with Markov Logic Networks

Konstantin Kirchheim, Frank Ortmeier

Journal ref International Conference on Machine Learning (ICML) 2025

Sounding that Object: Interactive Object-Aware Image to Audio Generation

Tingle Li, Baihe Huang, Xiaobin Zhuang, Dongya Jia, Jiawei Chen, Yuping Wang, Zhuo Chen, Gopala Anumanchipalli, Yuxuan Wang

Comments ICML 2025

Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems

Yujun Kim, Jaeyoung Cha, Chulhee Yun

Comments Accepted to ICML 2025, 56 pages, 6 figures

Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

HyunGi Kim, Jisoo Mok, Dongjun Lee, Jaihyun Lew, Sungjae Kim, Sungroh Yoon

Comments Accepted to ICML 2025

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win

Lorenz Kummer, Samir Moustafa, Anatol Ehrlich, Franka Bause, Nikolaus Suess, Wilfried N. Gansterer, Nils M. Kriege

Comments Accepted at ICML 2025

Revisiting Unbiased Implicit Variational Inference

Tobias Pielok, Bernd Bischl, David Rügamer

Comments Accepted to ICML 2025

ConText: Driving In-context Learning for Text Removal and Segmentation

Fei Zhang, Pei Zhang, Baosong Yang, Fei Huang, Yanfeng Wang, Ya Zhang

Comments 19 pages, 9 figures, Accepted at ICML 2025

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Zhepei Wei, Wei-Lin Chen, Xinyu Zhu, Yu Meng

Comments ICML 2025. Code: https://github.com/weizhepei/AdaDecode

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

Walter Mayor, Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro

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

The Limits of Predicting Agents from Behaviour

Alexis Bellot, Jonathan Richens, Tom Everitt

Journal ref ICML 2025

Mind the Gap: A Practical Attack on GGUF Quantization

Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev

机构 * ETH Zurich, Switzerland（苏黎世联邦理工学院） ； The University of Tokyo, Japan（东京大学） ； University of California, Berkeley, USA（加州大学伯克利分校） 纠错

Comments ICML 2025

Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation

Zixuan Hu, Yichun Hu, Xiaotong Li, Shixiang Tang, Ling-Yu Duan

Comments Accepted by ICML 2025

Towards Trustworthy Federated Learning with Untrusted Participants

Youssef Allouah, Rachid Guerraoui, John Stephan

Comments ICML 2025 conference paper