TMLR

Contextualized Messages Boost Graph Representations

Brian Godwin Lim, Galvin Brice Sy Lim, Renzo Roel Tan, Kazushi Ikeda

机构 * Nara Institute of Science and Technology（奈良科学技术大学） ； De La Salle University - Manila（德拉萨大学-马尼拉） ； Ateneo de Manila University（马尼拉大学） 纠错

Comments Published in Transactions on Machine Learning Research

Journal ref Transactions on Machine Learning Research. (2025)

On Convolutions, Intrinsic Dimension, and Diffusion Models

Kin Kwan Leung, Rasa Hosseinzadeh, Gabriel Loaiza-Ganem

机构 * Layer 6 AI 纠错

Comments TMLR 2025 (expert certification)

Understanding Self-supervised Contrastive Learning through Supervised Objectives

Byeongchan Lee

机构 * KAIST（韩国科学技术院） 纠错

Comments Accepted at TMLR 2025

On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection

Tai Le-Gia, Ahn Jaehyun

Comments Published in TMLR (10/2025)

AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers

Benedikt Alkin, Maurits Bleeker, Richard Kurle, Tobias Kronlachner, Reinhard Sonnleitner, Matthias Dorfer, Johannes Brandstetter

机构 * Emmi AI ； ELLIS Unit, LIT AI Lab, JKU Linz（ELLIS单位、LIT AI实验室、JKU林茨） 纠错

Comments Published in Transactions on Machine Learning Research

Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights

Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou

机构 * Alibaba Group（阿里巴巴集团） 纠错

Comments TMLR camera-ready version

Equivalent Linear Mappings of Large Language Models

James R. Golden

Comments title changed; major revisions; code available at https://github.com/jamesgolden1/equivalent-linear-LLMs/; published at https://openreview.net/forum?id=oDWbJsIuEp

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

Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles

Zifu Wang, Junyi Zhu, Bo Tang, Zhiyu Li, Feiyu Xiong, Jiaqian Yu, Matthew B. Blaschko

Comments TMLR 2025

A Comprehensive Survey on Knowledge Distillation

Amir M. Mansourian, Rozhan Ahmadi, Masoud Ghafouri, Amir Mohammad Babaei, Elaheh Badali Golezani, Zeynab Yasamani Ghamchi, Vida Ramezanian, Alireza Taherian, Kimia Dinashi, Amirali Miri, Shohreh Kasaei

机构 * Sharif University of Technology（谢里夫科技大学） 纠错

Comments Published at TMLR (102 pages, 10 figures, 17 tables)

Learning to Be Cautious

Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, Michael Bowling

机构 * University of Alberta（阿尔伯塔大学） ； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔人工智能研究所） 纠错

Comments Published at the Transactions on Machine Learning Research Journal (TMLR)

Preference Discerning with LLM-Enhanced Generative Retrieval

Fabian Paischer, Liu Yang, Linfeng Liu, Shuai Shao, Kaveh Hassani, Jiacheng Li, Ricky Chen, Zhang Gabriel Li, Xiaoli Gao, Wei Shao, Xue Feng, Nima Noorshams, Sem Park, Bo Long, Hamid Eghbalzadeh

机构 * ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单位、LIT人工智能实验室、机器学习研究所、JKU林茨） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； AI at Meta（Meta人工智能） 纠错

Comments Accepted at TMLR, Code available at https://github.com/facebookresearch/preference_discerning

Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors

Soumava Paul, Prakhar Kaushik, Alan Yuille

机构 * CCVL, Johns Hopkins University（CCVL，约翰霍普金斯大学） 纠错

Comments Accepted to TMLR 2025. Code and models released at https://gaussianscenes.github.io/

Agreement-Based Cascading for Efficient Inference

Steven Kolawole, Don Dennis, Ameet Talwalkar, Virginia Smith

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Published at TMLR (July 2025)

Journal ref TMLR 2025

Generalized Orders of Magnitude for Scalable, Parallel, High-Dynamic-Range Computation

Franz A. Heinsen, Leo Kozachkov

机构 * GlassRoom Software LLC（GlassRoom软件公司） ； Thomas J. Watson Research Center, IBM Research（IBM研究院Watson研究中心） ； Brown University（布朗大学） 纠错

Comments 18 pages, 4 figures (main text). 14 pages, 21 figures (appendix). Code is at https://github.com/glassroom/generalized_orders_of_magnitude

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

Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD

Lea Demelius, Dominik Kowald, Simone Kopeinik, Roman Kern, Andreas Trügler

机构 * Know Center Research GmbH ； Graz University of Technology（格拉茨技术大学） ； University of Graz（格拉茨大学） 纠错

Journal ref Transactions on Machine Learning Research 2835-8856 (2025)

Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning

Yuxuan Bai, Gauri Pradhan, Marlon Tobaben, Antti Honkela

Comments 30 pages, 13 figures, published in TMLR https://openreview.net/forum?id=UligTUCgdt

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

SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis

Jipeng Lyu, Jiahua Dong, Yu-Xiong Wang

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

Comments Published in Transactions on Machine Learning Research (06/2025)

Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning

Jingcheng Niu, Subhabrata Dutta, Ahmed Elshabrawy, Harish Tayyar Madabushi, Iryna Gurevych

机构 * Technical University of Darmstadt（德累斯顿技术大学） ； UKP Lab（UKP实验室） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； The University of Bath（巴斯大学） 纠错

Comments TMLR

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities

Yanis Lalou, Théo Gnassounou, Antoine Collas, Antoine de Mathelin, Oleksii Kachaiev, Ambroise Odonnat, Alexandre Gramfort, Thomas Moreau, Rémi Flamary

机构 * École Polytechnique, IP Paris, CMAP, UMR 7641（巴黎理工学院） ； Université Paris-Saclay, Inria, CEA（巴黎萨克雷大学） ； Inria（法国国家信息与自动化技术研究院） ； CEA（法国原子能机构） ； Centre Borelli, ENS Paris-Saclay（巴黎-萨克雷大学博雷利中心） ； Università degli Studi di Genova（热那亚大学） ； Inria, Univ. Rennes 2, CNRS, IRISA（法国国家信息与自动化技术研究院、里昂二大学、法国国家科学研究中心、IRISA） 纠错

Comments Published in Transactions on Machine Learning Research

Neural Deconstruction Search for Vehicle Routing Problems

André Hottung, Paula Wong-Chung, Kevin Tierney

机构 * Bielefeld University, Germany（弗赖堡大学） ； University of British Columbia, Canada（不列颠哥伦比亚大学） 纠错

Comments Published in TMLR

Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models

Jingming Liu, Yumeng Li, Boyuan Xiao, Yichang Jian, Ziang Qin, Tianjia Shao, Yao-Xiang Ding, Kun Zhou

机构 * State Key Laboratory of CAD&CG（计算机辅助设计与图形学国家重点实验室） 纠错

Comments Published in TMLR

Spurious Privacy Leakage in Neural Networks

Chenxiang Zhang, Jun Pang, Sjouke Mauw

机构 * University of Luxembourg（卢森堡大学） 纠错

Comments published in TMLR

A Case for Library-Level k-Means Binning in Histogram Gradient-Boosted Trees

Asher Labovich

机构 * Brown University（布朗大学） 纠错

Comments Published in Transactions on Machine Learning Research (TMLR), 2025. [Link to OpenReview forum: https://openreview.net/forum?id=UaTrLLspJa]

Capsule Network Projectors are Equivariant and Invariant Learners

Miles Everett, Aiden Durrant, Mingjun Zhong, Georgios Leontidis

机构 * Department of Computing Science University of Aberdeen, UK（计算机科学系阿伯丁大学） 纠错

Comments V4: accepted at TMLR; V3: Ignore V1 and V2 as we have fixed a bug; 18 pages, 5 figures, 10 Tables

Journal ref Transactions on Machine Learning Research (TMLR), October 2025 - https://openreview.net/pdf?id=7owCO3qskH

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness

Emanuele Ballarin, Alessio Ansuini, Luca Bortolussi

机构 * AIlab University of Trieste（AI实验室特伦蒂诺大学） ； Data Engineering Laboratory（数据工程实验室） ； AREA Science Park（AREA科学公园） 纠错

Comments Published in Transactions on Machine Learning Research (09/2025). 25 pages, 1 figure, 19 tables

Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing

Amin Jalali, Milad Soltany, Michael Greenspan, Ali Etemad

Comments Accepted in Transactions on Machine Learning Research

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

On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifs

James Matthew Young, O. Deniz Akyildiz

Comments Published in Transactions on Machine Learning Research (09/2025). Reviewed on OpenReview: https://openreview.net/forum?id=KXRYY7iwqh

Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization

Yufeng Yang, Erin Tripp, Yifan Sun, Shaofeng Zou, Yi Zhou

Comments 40 pages, 1 tables

Journal ref Transactions on Machine Learning Research (TMLR), 07/2025

Goal Recognition Design for General Behavioral Agents using Machine Learning

Robert Kasumba, Guanghui Yu, Chien-Ju Ho, Sarah Keren, William Yeoh

机构 * Washington University in Saint Louis（华盛顿大学圣路易斯分校） ； Technion – Israel Institute of Technology（技术学院-以色列理工学院） 纠错

Journal ref Transactions on Machine Learning Research, 2025

CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning

Nurbek Tastan, Samuel Horvath, Karthik Nandakumar

机构 * Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（莫德尔·本·扎耶德人工智能大学） ； Michigan State University (MSU)（密歇根州立大学） 纠错

Comments Published in TMLR 08/2025