TMLR

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