TMLR

Sparsity regularization via tree-structured environments for disentangled representations

Elliot Layne, Jason Hartford, Sébastien Lachapelle, Mathieu Blanchette, Dhanya Sridhar

机构 * McGill University（麦吉尔大学） ； Mila ； Valence Labs（Valence实验室） ； Université de Montréal（蒙特利尔大学） ； Samsung - SAIT AI Lab（三星-SAIT人工智能实验室） 纠错

Journal ref Transactions on Machine Learning Research, 2835-8856, 2025

Tracking the Median of Gradients with a Stochastic Proximal Point Method

Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert Gower

机构 * Technical University of Munich and Inria Paris, ENS, PSL Research University（慕尼黑技术大学和巴黎Inria、ENS、PSL研究大学） ； Université Paris Cité and Sorbonne Université, CNRS（巴黎国立大学和索邦大学、CNRS） ； Inria, CNRS, ENS, PSL Research University Paris（Inria、CNRS、ENS、PSL研究大学巴黎） ； CCM, Flatiron Institute, Simons Foundation（CCM、Flatiron研究所、Simons基金会） 纠错

Journal ref Transactions on Machine Learning Research (2025)

Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective

Tobias Kortus, Ralf Keidel, Nicolas R. Gauger

机构 * Chair for Scientific Computing University of Kaiserslautern-Landau (RPTU)（科学计算研究所 卡塞尔拉特大学（RPTU）） 纠错

Comments Published in Transactions on Machine Learning Research (TMLR), 2025

Hyperparameters in Continual Learning: A Reality Check

Sungmin Cha, Kyunghyun Cho

机构 * New York University（纽约大学） ； Genentech（基因泰克） 纠错

Comments TMLR 2025 camera ready version

Offline Learning and Forgetting for Reasoning with Large Language Models

Tianwei Ni, Allen Nie, Sapana Chaudhary, Yao Liu, Huzefa Rangwala, Rasool Fakoor

机构 * Mila - Quebec AI Institute & Université de Montréal（魁北克AI研究所与蒙特利尔大学） ； Amazon Web Services（亚马逊网络服务） 纠错

Comments Published in Transactions on Machine Learning Research (TMLR), 2025. Code: https://github.com/twni2016/llm-reasoning-uft

Simplifying Knowledge Transfer in Pretrained Models

Siddharth Jain, Shyamgopal Karthik, Vineet Gandhi

机构 * Center for Visual Information Technology（视觉信息技术中心） ； International Institute of Information Technology, Hyderabad（海得拉巴国际信息科技研究所） ； University of Tübingen（图宾根大学） 纠错

Comments 12 pages, 3 figures, 6 tables, Accepted at TMLR 2025

Journal ref Transactions on Machine Learning Research (TMLR), 2025

PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training

Anirudh Satheesh, Anant Khandelwal, Mucong Ding, Radu Balan

机构 * Department of Computer Science（计算机科学系） ； University of Maryland, College Park（马里兰大学学院公园分校） ； Georgia Institute of Technology（佐治亚理工学院） ； Department of Mathematics（数学系） ； Center for Scientific Computation and Mathematical Modeling（科学计算与数学建模中心） 纠错

Comments Submitted to TMLR 2025

Robust Multimodal Learning via Cross-Modal Proxy Tokens

Md Kaykobad Reza, Ameya Patil, Mashhour Solh, M. Salman Asif

机构 * University of California Riverside（加州大学河滨分校） ； Amazon（亚马逊） 纠错

Comments 28 Pages, 13 Figures, 11 Tables. Accepted by Transactions on Machine Learning Research (TMLR)

Dataset Condensation with Color Compensation

Huyu Wu, Duo Su, Junjie Hou, Guang Li

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Tsinghua University（清华大学） ； Hong Kong University of Science and Technology（香港科技大学） ； Hokkaido University（北海道大学） 纠错

Comments Accepted in TMLR

Mixture of Experts in Image Classification: What's the Sweet Spot?

Mathurin Videau, Alessandro Leite, Marc Schoenauer, Olivier Teytaud

机构 * Meta AI, TAU, INRIA, and LISN (CNRS & Univ. Paris-Saclay)（Meta AI、TAU、INRIA 和 LISN（CNRS 与 巴黎-萨克雷大学）） ； INSA Rouen Normandy, University of Rouen Normandy, LITIS UR 4108（INSA 罗阿恩诺曼底、罗阿恩诺曼底大学、LITIS UR 4108） ； TAU, INRIA and LISN (CNRS & Univ. Paris-Saclay)（TAU、INRIA 和 LISN（CNRS 与 巴黎-萨克雷大学）） ； Thales, CortAIx-Labs（Thales、CortAIx-Labs） 纠错

Comments Published in Transactions on Machine Learning Research

ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence

Luoxiao Yang, Yun Wang, Xinqi Fan, Israel Cohen, Jingdong Chen, Zijun Zhang

Journal ref Transactions on Machine Learning Research,2025

Partial-Label Learning with a Reject Option

Tobias Fuchs, Florian Kalinke, Klemens Böhm

机构 * Karlsruhe Institute of Technology, Germany（卡尔斯鲁厄理工学院） 纠错

Comments Accepted for publication at TMLR

Journal ref Transactions on Machine Learning Research, January 2025

Exploring the Limitations of Layer Synchronization in Spiking Neural Networks

Roel Koopman, Amirreza Yousefzadeh, Mahyar Shahsavari, Guangzhi Tang, Manolis Sifalakis

机构 * Machine Learning Group, Centrum Wiskunde & Informatica (CWI)（机器学习组，数学与信息学中心（CWI）） ； Faculty of Electrical Engineering, Mathematics & Computer Science, University of Twente（电气工程、数学与计算机科学学院，乌得勒支大学） ； Donders Centre for Cognition, Radboud University（多纳尔斯认知中心，拉德堡德大学） ； Department of Advanced Computing Sciences, Maastricht University（高级计算科学系，马斯特里赫特大学） ； Innatera Nanosystems BV（Innatera纳米系统公司） 纠错

Journal ref Transactions on Machine Learning Research (09/2025)

Bi-Mamba: Towards Accurate 1-Bit State Space Models

Shengkun Tang, Liqun Ma, Haonan Li, Mingjie Sun, Zhiqiang Shen

Comments Accepted in TMLR 2025

Where are we with calibration under dataset shift in image classification?

Mélanie Roschewitz, Raghav Mehta, Fabio de Sousa Ribeiro, Ben Glocker

机构 * Imperial College London（帝国理工学院伦敦分校） 纠错

Comments Code available at https://github.com/biomedia-mira/calibration_under_shifts. Published in TMLR, October 2025 (https://openreview.net/forum?id=1NYKXlRU2H)

Journal ref Transactions on Machine Learning Research (10/2025)

Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents

Irene Testini, José Hernández-Orallo, Lorenzo Pacchiardi

机构 * Leverhulme Centre for the Future of Intelligence, University of Cambridge, UK（未来智能研究中心、剑桥大学） ； Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, Spain（瓦伦西亚人工智能研究 institutes (VRAIN)、瓦伦西亚理工大学） 纠错

Comments Published in Transactions of Machine Learning Research (TMLR), 10/2025 https://openreview.net/forum?id=MB0TCLfLn1

Customizing Spider Silk: Generative Models with Mechanical Property Conditioning for Protein Engineering

Neeru Dubey, Elin Karlsson, Miguel Angel Redondo, Johan Reimegård, Anna Rising, Hedvig Kjellström

机构 * Division of Robotics, Perception and Learning（机器人、感知与学习 division） ； KTH Royal Institute of Technology（皇家理工学院） ； Department of Animal Biosciences（动物生物学系） ； Swedish University of Agricultural Sciences (SLU)（瑞典农业科学大学） ； Science for Life Laboratory (SciLifeLab)（生命科学实验室） ； Uppsala University（乌普萨拉大学） 纠错

Comments 23 pages, 11 figures

Journal ref Transactions on Machine Learning Research volume 7 2025

Phase-driven Domain Generalizable Learning for Nonstationary Time Series

Payal Mohapatra, Lixu Wang, Qi Zhu

机构 * Northwestern University（西北大学） 纠错

Comments TMLR 2025

Modeling Human Beliefs about AI Behavior for Scalable Oversight

Leon Lang, Patrick Forré

Comments 56 pages

Journal ref Transactions on Machine Learning Research, Aug. 2025. https://openreview.net/forum?id=gSJfsdQnex

AcademicEval: Live Long-Context LLM Benchmark

Haozhen Zhang, Tao Feng, Pengrui Han, Jiaxuan You

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments Accepted by TMLR. Code is available at https://github.com/ulab-uiuc/AcademicEval

ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment

Amir Aghdam, Vincent Tao Hu, Björn Ommer

机构 * Department of Computer Science, Temple University（Temple大学计算机科学系） ； Munich Center for Machine Learning（慕尼黑机器学习中心） 纠错

Comments Accepted to TMLR 2025 - Project page: https://amir-aghdam.github.io/act-align/

PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization

Nicolas Talabot, Olivier Clerc, Arda Cinar Demirtas, Alexis Goujon, Hieu Le, Doruk Oner, Pascal Fua

机构 * EPFL（苏黎世联邦理工学院） ； Bilkent University（比尔肯特大学） ； University of North Carolina at Charlotte（北卡罗来纳州夏洛特大学） ； Neural Concept（神经概念） 纠错

Comments Accepted to TMLR (33 pages, 22 figures)

Adapting Chat Language Models Using Only Target Unlabeled Language Data

Atsuki Yamaguchi, Terufumi Morishita, Aline Villavicencio, Nikolaos Aletras

机构 * University of Sheffield（谢菲尔德大学） ； Hitachi, Ltd.（日立株式会社） ； University of Exeter（埃克塞特大学） 纠错

Comments Accepted to TMLR

Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervision

Delaram Pirhayati, Arlei Silva

机构 * Rice University（里士大学） 纠错

Comments Accepted at Transactions on Machine Learning Research (TMLR), 2025

Journal ref Pirhayatifard, D. and Silva, A. (2025). Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervision. Transactions on Machine Learning Research (TMLR). https://openreview.net/forum?id=sB3LqdOlNb

Rethinking Robustness in Machine Learning: A Posterior Agreement Approach

João Borges S. Carvalho, Victor Jimenez Rodriguez, Alessandro Torcinovich, Antonio E. Cinà, Carlos Cotrini, Lea Schönherr, Joachim M. Buhmann

机构 * Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系） ； Faculty of Engineering, Free University of Bozen-Bolzano（博兹纳-博尔扎诺自由大学工程学院） ； Department of Computer Science, University of Genoa（热那亚大学计算机科学系） ； CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍茨研究中心） 纠错

Comments Preprint submitted to TMLR. 37 pages, 18 figures

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation

Sayantan Adak, Somnath Banerjee, Rajarshi Mandal, Avik Halder, Sayan Layek, Rima Hazra, Animesh Mukherjee

Comments Accepted at Transactions on Machine Learning Research (TMLR)

Disentangled and Self-Explainable Node Representation Learning

Simone Piaggesi, André Panisson, Megha Khosla

机构 * University of Pisa（比萨大学） ； CENTAI Institute（CENTAI研究院） ； Delft University of Technology（代尔夫特理工大学） 纠错

Comments TMLR 2025

HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model

Peter Van Katwyk, Karianne J. Bergen

机构 * Department of Earth, Environment, and Planetary Sciences, Brown University（布朗大学地球、环境与行星科学系） ； Data Science Institute, Brown University（布朗大学数据科学研究院） ； Department of Computer Science, Brown University（布朗大学计算机科学系） 纠错

Comments Reviewed and published in TMLR at https://openreview.net/forum?id=xRiEdSyVjY

Journal ref Transactions on Machine Learning Research, 2025

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations

A. Bochkov

机构 * Moscow Institute of Physics and Technology (MIPT)（莫斯科物理技术学院） 纠错

Comments Published in Transactions on Machine Learning Research (10/2025). OpenReview: https://openreview.net/forum?id=Odh8IynO1o

Journal ref Transactions on Machine Learning Research (TMLR), 2025

Chimera: State Space Models Beyond Sequences

Aakash Lahoti, Tanya Marwah, Ratish Puduppully, Albert Gu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； IT University of Copenhagen（哥本哈根IT大学） ； Cartesia AI 纠错

Comments Published in TMLR (October 2025); 22 Pages, 6 Figures, 11 Tables