ICML

Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation

Xiaoyu Jin, Zunnan Xu, Mingwen Ou, Wenming Yang

Comments Accepted to CVG@ICML 2024

How to set AdamW's weight decay as you scale model and dataset size

Xi Wang, Laurence Aitchison

Comments Published in ICML 2025

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation

Benjamin Dupuis, Umut Şimşekli

机构 * Benjamin Dupuis（本杰明·杜皮斯） ； Umut Şimşekli（乌木特·西姆谢利） 纠错

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12087-12137, 2024

On Temperature Scaling and Conformal Prediction of Deep Classifiers

Lahav Dabah, Tom Tirer

Comments ICML 2025 (camera-ready). Code can be found at: https://github.com/lahavdabah/TS4CP

MixFlows: principled variational inference via mixed flows

Zuheng Xu, Naitong Chen, Trevor Campbell

Journal ref International Conference on Machine Learning, 2023

Channel Normalization for Time Series Channel Identification

Seunghan Lee, Taeyoung Park, Kibok Lee

机构 * Yonsei University（延世大学） ； Department of Statistics and Data Science, Yonsei University（延世大学统计与数据科学系） 纠错

Comments ICML 2025

iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection

Huahui Yi, Wei Xu, Ziyuan Qin, Xi Chen, Xiaohu Wu, Kang Li, Qicheng Lao

Comments accepted to ICML 2025

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective

Junze Deng, Qinhang Wu, Peizhong Ju, Sen Lin, Yingbin Liang, Ness Shroff

Comments accepted to ICML 2025

Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures

Jie Gao, Rajesh Jayaram, Benedikt Kolbe, Shay Sapir, Chris Schwiegelshohn, Sandeep Silwal, Erik Waingarten

Comments ICML 2025

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

Jiahui Zhu, Kihyun Yu, Dabeen Lee, Xin Liu, Honghao Wei

Comments Proceedings of the 41 st International Conference on Machine Learning

How Do Transformers Learn Variable Binding in Symbolic Programs?

Yiwei Wu, Atticus Geiger, Raphaël Millière

Comments 16 pages, 10 figures, 1 table. To appear in the Proceedings of the 42nd International Conference on Machine Learning (ICML 2025). v2: Added link to Variable Scope in abstract

What makes a good feedforward computational graph?

Alex Vitvitskyi, João G. M. Araújo, Marc Lackenby, Petar Veličković

Comments To appear at ICML 2025. 17 pages, 7 figures

Algebra Unveils Deep Learning -- An Invitation to Neuroalgebraic Geometry

Giovanni Luca Marchetti, Vahid Shahverdi, Stefano Mereta, Matthew Trager, Kathlén Kohn

Comments Published at ICML 2025

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?

Liangze Jiang, Damien Teney

Comments ICML 2025

Softmax is not Enough (for Sharp Size Generalisation)

Petar Veličković, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu

Comments To appear at ICML 2025. 22 pages, 9 figures

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Wanyun Xie, Francesco Tonin, Volkan Cevher

Comments ICML 2025

Tackling View-Dependent Semantics in 3D Language Gaussian Splatting

Jiazhong Cen, Xudong Zhou, Jiemin Fang, Changsong Wen, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian

Comments ICML 2025 camera ready. Project Page: https://jumpat.github.io/laga-page/

PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations

Benjamin Holzschuh, Qiang Liu, Georg Kohl, Nils Thuerey

Comments ICML 2025. Code available at https://github.com/tum-pbs/pde-transformer

K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes

Hideaki Kim, Tomoharu Iwata, Akinori Fujino

Comments Accepted to ICML 2025

WILTing Trees: Interpreting the Distance Between MPNN Embeddings

Masahiro Negishi, Thomas Gärtner, Pascal Welke

Comments 25 pages, 10 figures. Accepted to ICML 2025. See https://github.com/masahiro-negishi/wilt for code

Learning Safety Constraints for Large Language Models

Xin Chen, Yarden As, Andreas Krause

Comments ICML 2025 (Spotlight)

SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation

Yuqi Fan, Zhiyong Cui, Zhenning Li, Yilong Ren, Haiyang Yu

Comments 17 pages, 8 figures, International Conference on Machine Learning

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Yilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang, Li Shen, Xueqian Wang, Dacheng Tao

Comments ICML 2025

Aligning Protein Conformation Ensemble Generation with Physical Feedback

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Aurélie Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang

Comments Published as a conference paper at ICML 2025

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Chen Huang, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Josh Susskind

Comments ICML 2025

A Mathematical Framework for AI-Human Integration in Work

L. Elisa Celis, Lingxiao Huang, Nisheeth K. Vishnoi

机构 * Yale University（耶鲁大学） ； Nanjing University（南京大学） 纠错

Comments This paper will appear in ICML 2025

Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel

Carlota Parés-Morlans, Michelle Yi, Claire Chen, Sarah A. Wu, Rika Antonova, Tobias Gerstenberg, Jeannette Bohg

Comments Accepted to ICML 2025

IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction

Zhangyi Hu, Jiemin Wu, Hua Xu, Mingqian Liao, Ninghui Feng, Bo Gao, Songning Lai, Yutao Yue

Comments ICML 2025

Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures

Dongzhe Zheng, Wenjie Mei

机构 * Dongzhe Zheng ； Wenjie Mei 纠错

Comments Accepted by ICML 2025

Safety Alignment Can Be Not Superficial With Explicit Safety Signals

Jianwei Li, Jung-Eun Kim

Comments ICML 2025