ICML

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, Taiji Suzuki

机构 * Department of Computer Science, City University of Hong Kong, Hong Kong SAR ； Center for Advanced Intelligence Project, RIKEN, Japan ； Institute of High Performance Computing (IHPC), Agency for Science, Technology ； Research (A STAR), Singapore ； Centre for Frontier AI Research (CFAR), Agency for Science, Technology ； College of Computing ； Data Science, Nanyang Technological University, Singapore ； Department of Mathematical Informatics, The University of Tokyo, Japan ； School of Mathematics ； Statistics, The University of Sydney, Australia 纠错

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

Improving Diversity in Language Models: When Temperature Fails, Change the Loss

Alexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Negrevergne

Comments Forty-Second International Conference on Machine Learning, ICML2025

The Importance of Being Lazy: Scaling Limits of Continual Learning

Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta, Thomas Hofmann, Lorenzo Noci

机构 * Electrical Engineering, ETH Zurich, Switzerland（电子工程系，苏黎世联邦理工学院） ； Dept. of Computer Science, ETH Zurich（计算机科学系，苏黎世联邦理工学院） ； ETH AI Center（苏黎世联邦理工学院人工智能中心） ； Astronomy, University of Padua, Italy（天文学系，帕多瓦大学） 纠错

Comments Proceedings of the 42nd International Conference on Machine Learning (2025). JG and AB contributed equally to this work

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning

Motoki Omura, Kazuki Ota, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada

机构 * The University of Tokyo（东京大学） 纠错

Comments Accepted at ICML 2025. Source code: https://github.com/motokiomura/annealed-q-learning

RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov

机构 * NVIDIA, Santa Clara, USA（NVIDIA公司） ； Georgia Institute of Technology, Atlanta, USA（佐治亚理工学院） 纠错

Comments ICML 2025

Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity

Alessandro Pierro, Steven Abreu, Jonathan Timcheck, Philipp Stratmann, Andreas Wild, Sumit Bam Shrestha

机构 * Neuromorphic Computing Lab, Intel Corporation, USA ； Institute of Informatics, LMU Munich, Germany ； Bernoulli Institute \& CogniGron, University of Groningen, Netherlands 纠错

Comments ICML 2025

Towards flexible perception with visual memory

Robert Geirhos, Priyank Jaini, Austin Stone, Sourabh Medapati, Xi Yi, George Toderici, Abhijit Ogale, Jonathon Shlens

机构 * Google DeepMind（谷歌DeepMind） 纠错

Comments ICML 2025 camera ready version

Importance Corrected Neural JKO Sampling

Johannes Hertrich, Robert Gruhlke

机构 * University College London（伦敦大学学院） 纠错

Comments Accepted at ICML 2025

Discrete Neural Algorithmic Reasoning

Gleb Rodionov, Liudmila Prokhorenkova

机构 * Yandex Research（Yandex研究院） 纠错

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

Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models

Jialin Zhao, Yingtao Zhang, Carlo Vittorio Cannistraci

机构 * Center for Complex Network Intelligence (CCNI), Tsinghua Laboratory of Brain and Intelligence (THBI), Department of Psychological and Cognitive Sciences（复杂网络智能中心（CCNI）、清华脑智能实验室（THBI）、心理与认知科学系） ； Department of Computer Science（计算机科学系） ； Department of Biomedical Engineering, Tsinghua University, China（生物医学工程系，清华大学，中国） 纠错

Comments ICML 2025

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

Jialin Zhao, Yingtao Zhang, Xinghang Li, Huaping Liu, Carlo Vittorio Cannistraci

机构 * Center for Complex Network Intelligence (CCNI), Tsinghua Laboratory of Brain and Intelligence (THBI), Department of Psychological and Cognitive Sciences（复杂网络智能中心（CCNI）、清华脑智能实验室（THBI）、心理与认知科学系） ； Department of Computer Science（计算机科学系） ； Department of Biomedical Engineering, Tsinghua University, China（生物医学工程系，清华大学，中国） 纠错

Comments ICML 2025