TMLR

RouteFinder: Towards Foundation Models for Vehicle Routing Problems

Federico Berto, Chuanbo Hua, Nayeli Gast Zepeda, André Hottung, Niels Wouda, Leon Lan, Junyoung Park, Kevin Tierney, Jinkyoo Park

机构 * KAIST（韩国科学技术院） ； Bielefeld University（比勒菲尔德大学） ； Rotterdam School of Management（鹿特丹管理学院） ； VU Amsterdam（阿姆斯特丹自由大学） ； Omelet AI4CO 纠错

Comments TMLR 2025. A previous version of this work was presented as Oral at the ICML 2024 FM-Wild Workshop

Understanding Emergent In-Context Learning from a Kernel Regression Perspective

Chi Han, Ziqi Wang, Han Zhao, Heng Ji

机构 * Siebel School of Computing and Data Science（计算与数据科学学院） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments Transactions on Machine Learning Research (TMLR 2025)

The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design

Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling

机构 * Collaborative Artificial Intelligence University of Stuttgart, Germany（协同人工智能大学斯图加特, 德国） 纠错

Comments TMLR, 31 pages

Uncertainty Quantification in Retrieval Augmented Question Answering

Laura Perez-Beltrachini, Mirella Lapata

机构 * University of Edinburgh（爱丁堡大学） 纠错

Comments TMLR (09/2025)

AdaWaveNet: Adaptive Wavelet Network for Time Series Analysis

Han Yu, Peikun Guo, Akane Sano

Comments Transactions on Machine Learning Research; code: https://github.com/comp-well-org/AdaWaveNet ; TMLR review: https://openreview.net/forum?id=m4bE9Y9FlX

FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models

Kai Yi, Georg Meinhardt, Laurent Condat, Peter Richtárik

机构 * King Abdullah University of Science and Technology (KAUST)（国王阿卜杜勒-阿齐兹大学科学与技术学院） ； SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence (SDAIA-KAUST AI)（SDAIA-KAUST数据科学与人工智能卓越中心） 纠错

Comments Accepted version at Transactions on Machine Learning Research (TMLR)

Approximations to worst-case data dropping: unmasking failure modes

Jenny Y. Huang, David R. Burt, Yunyi Shen, Tin D. Nguyen, Tamara Broderick

Comments 71 pages

Journal ref Transactions on Machine Learning Research, July 2025

CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives

Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah

机构 * Sharif University of Technology（谢里夫理工大学） 纠错

Comments Accepted to TMLR 2025

An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration

Vasilis Siomos, Jonathan Passerat-Palmbach, Giacomo Tarroni

机构 * Department of Computer Science, City St. George’s, University of London（伦敦大学城市圣乔治学院计算机科学系） ； BioMedIA, Department of Computing, Imperial College London（伦敦帝国理工学院计算系BioMedIA） 纠错

Comments Accepted into TMLR, version of record https://openreview.net/forum?id=GtdYFLsblb

The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms

Fin Amin, Jung-Eun Kim

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

Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution

Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi

机构 * The University of Tokyo（东京大学） ； RIKEN Center for Advanced Intelligence Project（RIKEN高级智能项目中心） 纠错

Comments 28 pages

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

HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection

Min-Hsuan Yeh, Max Kamachee, Seongheon Park, Yixuan Li

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） 纠错

Comments TMLR 2025

Identifying Macro Causal Effects in a C-DMG over ADMGs

Simon Ferreira, Charles K. Assaad

机构 * Sorbonne Université（索邦大学） ； INSERM（国家医学研究院） ； Institut Pierre Louis d’Epidémiologie et de Santé Publique（皮埃尔-吕克流行病学与公共卫生研究所） 纠错

Comments Accepted to TMLR

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models

Yang Zhang, Chenjia Bai, Bin Zhao, Junchi Yan, Xiu Li, Xuelong Li

机构 * Tsinghua University（清华大学） ； Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究所（TeleAI），中国电信） ； Shanghai AI Laboratory（上海人工智能实验室） ； Shanghai Jiaotong University（上海交通大学） 纠错

Comments Accepted by Transactions on Machine Learning Research

Learning in complex action spaces without policy gradients

Arash Tavakoli, Sina Ghiassian, Nemanja Rakićević

机构 * Riot Games ； Spotify ； Google ； DeepMind 纠错

Comments Published in TMLR (2025). Code: https://github.com/atavakol/qmle

Journal ref Transactions on Machine Learning Research (2025)

Mamba State-Space Models Are Lyapunov-Stable Learners

John T. Halloran, Manbir Gulati, Paul F. Roysdon

机构 * Leidos（莱迪奥斯公司） 纠错

Comments TMLR, 27 pages, 12 figures, 4 tables

MobileCLIP2: Improving Multi-Modal Reinforced Training

Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander Toshev, Oncel Tuzel, Hadi Pouransari

机构 * Apple（苹果公司） 纠错

Comments TMLR August 2025

Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation

Michael Hagmann, Michael Staniek, Stefan Riezler

机构 * Department of Computational Linguistics（计算语言学系） ； Heidelberg University（海德堡大学） ； Department of Computational Linguistics and Interdisciplinary Center for Scientific Computing (IWR)（计算语言学系和科学计算跨学科中心） 纠错

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

LASE: Learned Adjacency Spectral Embeddings

Sofía Pérez Casulo, Marcelo Fiori, Federico Larroca, Gonzalo Mateos

机构 * Facultad de Ingeniería Universidad de la República（工程学院拉美大学） ； Department of Electrical and Computer Engineering University of Rochester（电气与计算机工程系罗切斯特大学） 纠错

Journal ref Transactions on Machine Learning Research, 2025

A Proximal Operator for Inducing 2:4-Sparsity

Jonas M Kübler, Yu-Xiang Wang, Shoham Sabach, Navid Ansari, Matthäus Kleindessner, Kailash Budhathoki, Volkan Cevher, George Karypis

机构 * Amazon（亚马逊公司） ； University of California, San Diego, USA（美国加州大学圣迭戈分校） ； Max Planck Institute for Informatics, Saarbrücken, Germany（德国马克斯·普朗克信息研究所） ； Technion–Israel Institute of Technology, Haifa, Israel（以色列技术学院） 纠错

Journal ref Transactions on Machine Learning Research, 2835-8856, 2025 (https://openreview.net/forum?id=AsFbXRIe4q)

FraGNNet: A Deep Probabilistic Model for Tandem Mass Spectrum Prediction

Adamo Young, Fei Wang, David S Wishart, Bo Wang, Russell Greiner, Hannes Röst

机构 * Department of Computer Science, University of Toronto（计算机科学系，多伦多大学） ； Vector Institute for Artificial Intelligence（人工智能向量研究所） ； Terrence Donnelly Centre for Cellular and Biomolecular Research, University of Toronto（细胞和生物分子研究中心，多伦多大学） ； Department of Computing Science, University of Alberta（计算科学系，阿尔伯塔大学） ； Alberta Machine Intelligence Institute（阿尔伯塔人工智能研究所） ； Department of Biological Sciences, University of Alberta（生物科学系，阿尔伯塔大学） ； Department of Laboratory Medicine and Pathology, University of Alberta（实验室医学与病理学系，阿尔伯塔大学） ； Faculty of Pharmacy and Pharmaceutical Sciences, University of Alberta（药学与制药科学学院，阿尔伯塔大学） ； Department of Laboratory Medicine and Pathobiology, University of Toronto（实验室医学与病理学系，多伦多大学） ； Peter Munk Cardiac Centre, University Health Network（彼得·默克心脏中心，大学健康网络） ； Department of Molecular Genetics, University of Toronto（分子遗传学系，多伦多大学） 纠错

Journal ref Transactions on Machine Learning Research (TMLR), 08/2025

Keep your distance: learning dispersed embeddings on $\mathbb{S}_m$

Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae

Journal ref TMLR (2025)

Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis

Kushal Raj Bhandari, Sixue Xing, Soham Dan, Jianxi Gao

机构 * Rensselaer Polytechnic Institute（拉特盖尔理工学院） ； Microsoft（微软） 纠错

Comments Accepted TMLR 2025

ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment

Tomer Borreda, Daniel Freedman, Or Litany

机构 * NVIDIA（NVIDIA公司） 纠错

Comments TMLR 2025. Project page: https://tomerborreda.github.io/rehub/

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, Andrew Wen, Shaochen Zhong, Na Zou, Hanjie Chen, Xia Hu

机构 * Rice University（里士大学） ； University of Houston（休斯顿大学） 纠错

Comments Accepted by TMLR 2025. Project website: https://github.com/Eclipsess/Awesome-Efficient-Reasoning-LLMs

A Curious Case of Remarkable Resilience to Gradient Attacks via Fully Convolutional and Differentiable Front End with a Skip Connection

Leonid Boytsov, Ameya Joshi, Filipe Condessa

机构 * Bosch Center for Artificial Intelligence（博世人工智能中心） 纠错

Comments Accepted at TMLR (2025/08)

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Benjamin Schneider, Florian Kerschbaum, Wenhu Chen

机构 * University of Waterloo（滑铁卢大学） 纠错

Comments TMLR 2025

Generalizable Spectral Embedding with an Application to UMAP

Nir Ben-Ari, Amitai Yacobi, Uri Shaham

机构 * Department of Computer Science Bar-Ilan University（计算机科学系巴伊兰大学） 纠错

Journal ref Transactions on Machine Learning Research, 2025

Label Smoothing is a Pragmatic Information Bottleneck

Sota Kudo

机构 * Nara Institute of Science and Technology（那拉科学与技术研究所） 纠错

Comments 18 pages, 8 figures, published in Transactions on Machine Learning Research (TMLR), 2025

Can Masked Autoencoders Also Listen to Birds?

Lukas Rauch, René Heinrich, Ilyass Moummad, Alexis Joly, Bernhard Sick, Christoph Scholz

机构 * University of Kassel（卡塞尔大学） ； Fraunhofer IEE（弗劳恩霍夫研究所） ； INRIA Montpellier（蒙彼利埃INRIA） 纠错

Comments accepted @TMLR: https://openreview.net/forum?id=GIBWR0Xo2J