ICML - arXivDaily 期刊&会议

2505.07004 2025-09-23 cs.LG

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance

Jinuk Kim, Marwa El Halabi, Wonpyo Park, Clemens JS Schaefer, Deokjae Lee, Yeonhong Park, Jae W. Lee, Hyun Oh Song

机构 * Department of XXX, University of YYY, Location, Country ； School of ZZZ, Institute of WWW, Location, Country ； Department of Computer Science ； Engineering, Seoul National University ； Neural Processing Research Center ； Samsung AI Lab, Montreal ； Google

Comments ICML 2025

2503.09767 2025-09-23 cs.LG cs.CG math.AT stat.ML

Cover Learning for Large-Scale Topology Representation

Luis Scoccola, Uzu Lim, Heather A. Harrington

机构 * Centre de Recherches Mathématiques et Institut des sciences mathématiques, Laboratoire de combinatoire et d'informatique mathématique de l'Université du Québec à Montréal, Université de Sherbrooke, Canada（数学研究中心和数学科学研究所，魁北克大学蒙特利尔分校组合与数学信息学实验室， Sherbrooke 大学，加拿大）； Queen Mary University of London, United Kingdom（伦敦女王学院，英国）； Max Planck Institute of Molecular Cell Biology and Genetics（分子细胞生物学与遗传学马克斯·普朗克研究所）； Centre for Systems Biology, Dresden, Germany（系统生物学中心，德累斯顿，德国）； Faculty of Mathematics, Technische Universität Dresden, Germany（数学系，德累斯顿技术大学，德国）； Mathematical Institute, University of Oxford, United Kingdom（数学研究所，牛津大学，英国）

Comments 29 pages, 19 figures, 5 tables; final version at ICML 2025

2509.16860 2025-09-23 cs.LG

LVADNet3D: A Deep Autoencoder for Reconstructing 3D Intraventricular Flow from Sparse Hemodynamic Data

Mohammad Abdul Hafeez Khan, Marcello Mattei Di Eugeni, Benjamin Diaz, Ruth E. White, Siddhartha Bhattacharyya, Venkat Keshav Chivukula

机构 * Florida Institute of Technology, USA（佛罗里达理工学院）

Comments Accepted to International Conference on Machine Learning and Applications (ICMLA), 6 pages, 4 figure, 3 tables

2504.07343 2025-09-23 cs.SE

Code Generation with Small Language Models: A Codeforces-Based Study

Débora Souza, Rohit Gheyi, Lucas Albuquerque, Gustavo Soares, Márcio Ribeiro

Comments Accepted at International Conference on Machine Learning and Applications (ICMLA 2025)

2503.05683 2025-09-23 cs.CL cs.LG

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akata, Tom Hartvigsen

机构 * Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； Technical University, Munich（慕尼黑技术大学）； University of Virginia（弗吉尼亚大学）

Comments published at ICML 2025

2502.10691 2025-09-23 cs.LG

Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning

Md Yousuf Harun, Jhair Gallardo, Christopher Kanan

机构 * Rochester Institute of Technology（罗切斯特技术学院）； University of Rochester（罗切斯特大学）

Comments Published in ICML 2025

2509.16542 2025-09-23 cs.CL cs.IR cs.LG

Mental Multi-class Classification on Social Media: Benchmarking Transformer Architectures against LSTM Models

Khalid Hasan, Jamil Saquer, Yifan Zhang

机构 * Dept. of Computer Science Missouri State University Springfield, MO, USA（计算机科学系莫斯科州立大学斯普林菲尔德 MO 美国）

Comments 24th IEEE International Conference on Machine Learning and Applications, ICMLA 2025 (camera-ready)

Journal ref 2025 International Conference on Machine Learning and Applications (ICMLA)

2509.16463 2025-09-23 cs.LG cs.AI

Entropic Causal Inference: Graph Identifiability

Spencer Compton, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu

机构 * Massachusetts Institute of Technology（麻省理工学院）； MIT-IBM Watson AI Lab（MIT-IBM Watson AI实验室）； IBM Research（IBM研究院）； Purdue University（普渡大学）

Comments Presented at ICML 2022. This version corrects a bug in semi-synthetic experiments