TMLR

Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods

Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong

机构 * Department of Computing Science University of Aberdeen, UK（计算科学系大学爱丁堡大学，英国） ； Department of Computing Science & Interdisciplinary Centre for Data and AI University of Aberdeen, UK（计算科学系与数据和人工智能交叉研究中心大学爱丁堡大学，英国） 纠错

Comments 17 pages, 6 figures, 12 tables, V2: fixed typos in the references

Journal ref TMLR 2024 (https://openreview.net/pdf?id=z5AXLMBWdU)

DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators

Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche, Mario Fritz

机构 * CISPA Helmholtz Center for Information Security（CISPA 欧洲信息安全研究中心） 纠错

Journal ref Transactions on Machine Learning Research (03/2025)

Semantic Consistency for Assuring Reliability of Large Language Models

Harsh Raj, Vipul Gupta, Domenic Rosati, Subhabrata Majumdar

Comments An updated version of this preprint is available at arXiv:2502.15924, and has been accepted at the Transactions on Machine Learning Research

Gaussian Pre-Activations in Neural Networks: Myth or Reality?

Pierre Wolinski, Julyan Arbel

Comments Published version. OpenReview URL: https://openreview.net/forum?id=goe6fv6iSh

Journal ref Transactions on Machine Learning Research, 04/2025

A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks

Xinzhe Li

机构 * Xinzhe Li 纠错

Comments TMLR (camera-ready). Details on https://openreview.net/forum?id=x9VQFjtOPS

When Are Bias-Free ReLU Networks Effectively Linear Networks?

Yedi Zhang, Andrew Saxe, Peter E. Latham

机构 * Gatsby Computational Neuroscience Unit（加布特计算神经科学单位） ； University College London（伦敦大学学院） ； Sainsbury Wellcome Centre（萨金斯韦尔康中心） 纠错

Comments TMLR

Semantic-Syntactic Discrepancy in Images (SSDI): Learning Meaning and Order of Features from Natural Images

Chun Tao, Timur Ibrayev, Kaushik Roy

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Purdue University（普渡大学） 纠错

Comments 32 pages, 22 figures, 10 tables Published in Transactions on Machine Learning Research (04/2025)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration

Hiroki Naganuma, Ryuichiro Hataya, Kotaro Yoshida, Ioannis Mitliagkas

机构 * Mila - Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； RIKEN AIP（日本理化学研究所AIP） ； Institute of Science Tokyo（东京科学研究所） 纠错

Comments Accepted to TMLR

Can Kernel Methods Explain How the Data Affects Neural Collapse?

Vignesh Kothapalli, Tom Tirer

机构 * Courant Institute of Mathematical Sciences（Courant数学科学研究所） ； New York University（纽约大学） ； Faculty of Engineering（工程学院） ； Bar-Ilan University（巴伊兰大学） 纠错

Comments Transactions on Machine Learning Research (TMLR)

RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning

Mingqi Yuan, Roger Creus Castanyer, Bo Li, Xin Jin, Wenjun Zeng, Glen Berseth

机构 * Department of Computing（计算系） ； The Hong Kong Polytechnic University（香港理工大学） ； Mila Québec AI Institute & Université de Montréal（魁北克AI研究所及蒙特利尔大学） ； Ningbo Institute of Digital Twin（宁波数字孪生研究所） ； Eastern Institute of Technology, Ningbo（宁波东部技术研究所） 纠错

Comments 42 pages, 31 figures. Transactions on Machine Learning Research, 2025

Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models

Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl

机构 * Volkswagen Group（大众集团） ； Technical University of Munich（慕尼黑技术大学） ； Eötvös Loránd University Budapest（布达佩斯欧多立大学） 纠错

Comments Accepted at TMLR

Covariate-dependent Graphical Model Estimation via Neural Networks with Statistical Guarantees

Jiahe Lin, Yikai Zhang, George Michailidis

机构 * Machine Learning Research, Morgan Stanley（摩根大通机器学习研究部） ； Department of Statistics and Data Science, UCLA（UCLA统计与数据科学系） 纠错

Comments Accepted by Transactions on Machine Learning Research (TMLR)

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching

Junn Yong Loo, Michelle Adeline, Julia Kaiwen Lau, Fang Yu Leong, Hwa Hui Tew, Arghya Pal, Vishnu Monn Baskaran, Chee-Ming Ting, Raphaël C. -W. Phan

机构 * Monash University Malaysia（墨尔本大学马来西亚分校） 纠错

Comments Accepted by Transactions on Machine Learning Research (TMLR)

When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study

Tomoyuki Obuchi, Toshiyuki Tanaka

机构 * Department of Systems Science（系统科学系） ； Kyoto University（京都大学） 纠错

Comments 33 pages, 14 figures

Journal ref Transactions on Machine Learning Research, 2025. Available at: https://openreview.net/forum?id=spqbyeGyLR

Active Diffusion Subsampling

Oisin Nolan, Tristan S. W. Stevens, Wessel L. van Nierop, Ruud J. G. van Sloun

机构 * Eindhoven University of Technology（埃因霍温理工大学） 纠错

Comments 27 pages, 16 figures

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

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods

Andres Fernandez, Frank Schneider, Maren Mahsereci, Philipp Hennig

机构 * Tübingen AI Center University of Tübingen（图宾根人工智能中心大学） 纠错

Comments Accepted at TMLR 2025

LLM-Select: Feature Selection with Large Language Models

Daniel P. Jeong, Zachary C. Lipton, Pradeep Ravikumar

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

LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations

Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong

Comments 15 pages, 5 figures, 9 tables - accepted at TMLR 10/2024; V4 corrected some typos in the references

Journal ref TMLR; 2024

Masked Capsule Autoencoders

Miles Everett, Mingjun Zhong, Georgios Leontidis

Comments 15 pages, 7 figures, 5 tables - accepted at TMLR

Journal ref TMLR 01/2025 - https://openreview.net/forum?id=JHxrh00W1j

Design Editing for Offline Model-based Optimization

Ye Yuan, Youyuan Zhang, Can Chen, Haolun Wu, Zixuan Li, Jianmo Li, James J. Clark, Xue Liu

Comments Accepted by Transactions on Machine Learning Research (TMLR)

MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory

Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze

Comments Published in Transactions on Machine Learning Research (TMLR)

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective

Satyapriya Krishna, Tessa Han, Alex Gu, Steven Wu, Shahin Jabbari, Himabindu Lakkaraju

Comments Published in Transactions on Machine Learning Research (TMLR). Updated Related Work and Acknowledgment Section

Open Problems in Technical AI Governance

Anka Reuel, Ben Bucknall, Stephen Casper, Tim Fist, Lisa Soder, Onni Aarne, Lewis Hammond, Lujain Ibrahim, Alan Chan, Peter Wills, Markus Anderljung, Ben Garfinkel, Lennart Heim, Andrew Trask, Gabriel Mukobi, Rylan Schaeffer, Mauricio Baker, Sara Hooker, Irene Solaiman, Alexandra Sasha Luccioni, Nitarshan Rajkumar, Nicolas Moës, Jeffrey Ladish, David Bau, Paul Bricman, Neel Guha, Jessica Newman, Yoshua Bengio, Tobin South, Alex Pentland, Sanmi Koyejo, Mykel J. Kochenderfer, Robert Trager

Comments Ben Bucknall and Anka Reuel contributed equally and share the first author position

Journal ref Transactions on Machine Learning Research, 2025

Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure

Tobias Ladner, Michael Eichelbeck, Matthias Althoff

Comments published at Transactions on Machine Learning Research (TMLR) 2025

Investigating Generalization Behaviours of Generative Flow Networks

Lazar Atanackovic, Emmanuel Bengio

Comments Accepted to TMLR

Reward Distance Comparisons Under Transition Sparsity

Clement Nyanhongo, Bruno Miranda Henrique, Eugene Santos

Comments Published in the TMLR, https://openreview.net/forum?id=haP586YomL

Journal ref Transactions on Machine Learning Research, 2025

Identifiable Deep Generative Models via Sparse Decoding

Gemma E. Moran, Dhanya Sridhar, Yixin Wang, David M. Blei

Comments Transactions on Machine Learning Research (2022)

Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review

Sofiane Ennadir, Gabriela Zarzar Gandler, Filip Cornell, Lele Cao, Oleg Smirnov, Tianze Wang, Levente Zólyomi, Björn Brinne, Sahar Asadi

Comments Accepted by TMLR. Source code: https://github.com/king/ctdg-info-flow

ResiDual Transformer Alignment with Spectral Decomposition

Lorenzo Basile, Valentino Maiorca, Luca Bortolussi, Emanuele Rodolà, Francesco Locatello

Comments Published in Transactions on Machine Learning Research (TMLR)

An Embedding is Worth a Thousand Noisy Labels

Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig

Comments Accepted to Transactions on Machine Learning Research (TMLR)