ICML

Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation

Zecheng Hao, Qichao Ma, Kang Chen, Yi Zhang, Zhaofei Yu, Tiejun Huang

Comments Accepted to ICML 2025

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Zhao Jin, Dacheng Tao

Comments 18 pages, 14 figures. Accepted by ICML 2025. The code is available at https://github.com/wenhao728/AsymRnR

The Double-Ellipsoid Geometry of CLIP

Meir Yossef Levi, Guy Gilboa

机构 * The Double-Ellipsoid Geometry of CLIP（CLIP双椭球几何） 纠错

Comments Accepted to ICML 2025. This version matches the camera-ready version

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

AAAR-1.0: Assessing AI's Potential to Assist Research

Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun, Yusen Zhang, Jihyun Janice Ahn, Hongchao Fang, Zhuoyang Zou, Wenchao Ma, Xi Li, Kai Zhang, Congying Xia, Lifu Huang, Wenpeng Yin

Comments ICML 2025. Project Webpage: https://renzelou.github.io/AAAR-1.0/

Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations

Kexuan Shi, Hai Chen, Leheng Zhang, Shuhang Gu

Comments Accepted to ICML 2025. Code available at https://github.com/LabShuHangGU/IGA-INR

Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery

Pratinav Seth, Michelle Lin, Brefo Dwamena Yaw, Jade Boutot, Mary Kang, David Rolnick

机构 * Pratinav Seth（未知） ； Michelle Lin（未知） ； Brefo Dwamena Yaw（未知） ； Jade Boutot（未知） ； Mary Kang（未知） ； David Rolnick（未知） 纠错

Comments Accepted to ICML 2025

IT$^3$: Idempotent Test-Time Training

Nikita Durasov, Assaf Shocher, Doruk Oner, Gal Chechik, Alexei A. Efros, Pascal Fua

Comments Accepted at ICML 2025

Do Vision-Language Models Really Understand Visual Language?

Yifan Hou, Buse Giledereli, Yilei Tu, Mrinmaya Sachan

Comments ICML 2025

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

Tao Li, Zhengbao He, Yujun Li, Yasheng Wang, Lifeng Shang, Xiaolin Huang

Comments ICML 2025

Parrot: Multilingual Visual Instruction Tuning

Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye

Comments Accepted to ICML 2025. Code and dataset are available at: https://github.com/AIDC-AI/Parrot

Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints

Dániel Rácz, Mihály Petreczky, Bálint Daróczy

Comments preliminary version accepted at ICML 2024 Next Generation of Sequence Modeling Architectures Workshop

Variational Schrödinger Diffusion Models

Wei Deng, Weijian Luo, Yixin Tan, Marin Biloš, Yu Chen, Yuriy Nevmyvaka, Ricky T. Q. Chen

Comments ICML 2024

Enabling Uncertainty Estimation in Iterative Neural Networks

Nikita Durasov, Doruk Oner, Jonathan Donier, Hieu Le, Pascal Fua

Comments Accepted at ICML 2024

Discrepancy Minimization in Input-Sparsity Time

Yichuan Deng, Xiaoyu Li, Zhao Song, Omri Weinstein

Comments ICML 2025

Test-Time Adaptation with Binary Feedback

Taeckyung Lee, Sorn Chottananurak, Junsu Kim, Jinwoo Shin, Taesik Gong, Sung-Ju Lee

Comments Accepted to ICML 2025

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

Zhining Liu, Ze Yang, Xiao Lin, Ruizhong Qiu, Tianxin Wei, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong

Comments Accepted by ICML 2025. 22 pages, 6 Figures, 12 tables

Taming Diffusion for Dataset Distillation with High Representativeness

Lin Zhao, Yushu Wu, Xinru Jiang, Jianyang Gu, Yanzhi Wang, Xiaolin Xu, Pu Zhao, Xue Lin

Comments The paper is accepted by ICML 2025

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Rahul Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal

机构 * Ritual ； Stanford University（斯坦福大学） ； Columbia University（哥伦比亚大学） 纠错

Comments To be published in ICML 2025 Main Proceedings as "Hidden No More: Attacking and Defending Private Third-Party LLM Inference"

Doubly Robust Fusion of Many Treatments for Policy Learning

Ke Zhu, Jianing Chu, Ilya Lipkovich, Wenyu Ye, Shu Yang

Comments Accepted by ICML 2025

LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification

Yiding Lu, Mouxing Yang, Dezhong Peng, Peng Hu, Yijie Lin, Xi Peng

Comments Accepted by ICML 2025

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba Ba, Talia Konkle

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

Variational Control for Guidance in Diffusion Models

Kushagra Pandey, Farrin Marouf Sofian, Felix Draxler, Theofanis Karaletsos, Stephan Mandt

Comments Camera-Ready. Accepted at ICML 2025. 9 pages in main text. Total of 26 pages

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks

Laines Schmalwasser, Niklas Penzel, Joachim Denzler, Julia Niebling

Comments Accepted at ICML 2025, 27 pages, 20 figures, 9 tables

Joker: Joint Optimization Framework for Lightweight Kernel Machines

Junhong Zhang, Zhihui Lai

Comments 24 pages, 5 figures, accepted by ICML 2025

Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing

Ye Du, Chen Yang, Nanxi Yu, Wanyu Lin, Qian Zhao, Shujun Wang

Comments Accepted by ICML 2025

HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting

Boyuan Li, Yicheng Luo, Zhen Liu, Junhao Zheng, Jianming Lv, Qianli Ma

Comments Accepted in ICML 2025

Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition

Zichen Wang, Chuanhao Li, Huazheng Wang

Comments ICML 2025

Robust ML Auditing using Prior Knowledge

Jade Garcia Bourrée, Augustin Godinot, Martijn De Vos, Milos Vujasinovic, Sayan Biswas, Gilles Tredan, Erwan Le Merrer, Anne-Marie Kermarrec

机构 * LAAS, CNRS, Toulouse, France（法国图卢兹Laas-CNRS研究所） ； Inria, Rennes, France（法国里昂Inria研究所） ； IRISA/CNRS, Rennes, France（法国里昂IRISA-CNRS研究所） ； EPFL, Lausanne, Switzerland（瑞士洛桑联邦理工学院） 纠错

Comments Accepted to the 42nd International Conference on Machine Learning ICML25

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention

Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu

Comments Accepted at ICML 2025

Permutation Equivariant Neural Networks for Symmetric Tensors

Edward Pearce-Crump

Comments ICML 2025 Poster; 40 pages