TMLR

Part-aware Prompted Segment Anything Model for Adaptive Segmentation

Chenhui Zhao, Liyue Shen

机构 * Department of Computer Science and Engineering, University of Michigan（计算机科学与工程系，密歇根大学） ； Department of Electrical and Computer Engineering, University of Michigan（电气与计算机工程系，密歇根大学） 纠错

Comments TMLR 2025

Efficient Training of Multi-task Neural Solver for Combinatorial Optimization

Chenguang Wang, Zhang-Hua Fu, Pinyan Lu, Tianshu Yu

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（大数据研究所以） ； School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（科学与工程学院，香港中文大学（深圳）） ； Shenzhen Institute of Artificial Intelligence and Robotics for Society（人工智能与社会机器人研究所） ； Shanghai University of Finance and Economics（上海金融学院） 纠错

Comments Accepted by TMLR

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

Accelerating Learned Image Compression Through Modeling Neural Training Dynamics

Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu

Comments Accepted to TMLR

Diffusion Model Predictive Control

Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju, J. Swaroop Guntupalli, Wolfgang Lehrach, Joseph Ortiz, Antoine Dedieu, Miguel Lázaro-Gredilla, Kevin Murphy

Comments Published at TMLR

Distributed and Secure Kernel-Based Quantum Machine Learning

Arjhun Swaminathan, Mete Akgün

Comments This paper contains 23 pages, 5 figures, 1 table and 3 appendices. For associated supplementary code, see https://github.com/mdppml/distributed-secure-kernel-based-QML

Journal ref Transactions on Machine Learning Research, 2025

Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry

Supriya Manna, Niladri Sett

机构 * SRM University AP, India（SRM大学） 纠错

Comments Accepted at TMLR

Robust Offline Imitation Learning from Diverse Auxiliary Data

Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li, Konstantinos Karydis, Amit K. Roy-Chowdhury

机构 * University of California, Riverside（加州大学河滨分校） ； AWS AI Labs（AWS人工智能实验室） 纠错

Comments Accepted at TMLR

Algorithm Configuration for Structured Pfaffian Settings

Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Toyota Technological Institute at Chicago（丰田技术研究所（芝加哥）） 纠错

Comments Accepted to TMLR

Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts

Debarshi Brahma, Anuska Roy, Soma Biswas

机构 * Indian Institute of Science（印度科学研究院） 纠错

Comments Published in TMLR (2025)

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis

Zehao Wang, Han Zhou, Matthew B. Blaschko, Tinne Tuytelaars, Minye Wu

机构 * ESAT - Processing Speech and Images KU Leuven（ESAT-语音与图像处理研究所 韩国鲁汶大学） 纠错

Comments 12 pages, TMLR 2025

Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive review

Davide Carbone

机构 * Laboratoire de Physique de l’Ecole Normale Supérieure, ENS Université PSL, CNRS, Sorbonne Université, Université de Paris（巴黎高等师范学院物理实验室，巴黎大学PSL，法国国家科学研究中心，索邦大学，巴黎大学） 纠错

Journal ref Transactions on Machine Learning Research, 2025

Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs

Pranav Maneriker, Aditya T. Vadlamani, Anutam Srinivasan, Yuntian He, Ali Payani, Srinivasan Parthasarathy

机构 * Dolby Laboratories（多利贝实验室） ； The Ohio State University（俄亥俄州立大学） ； Cisco Systems（思科系统） 纠错

Comments TMLR 2025 Camera Ready Version

Towards identifiability of micro total effects in summary causal graphs with latent confounding: extension of the front-door criterion

Charles K. Assaad

Comments Accepted at TMLR

Policy Optimization via Adv2: Adversarial Learning on Advantage Functions

Matthieu Jonckheere, Chiara Mignacco, Gilles Stoltz

Journal ref Transactions on Machine Learning Research Journal, 2025, https://openreview.net/forum?id=Oyueig10Ed

A replica analysis of under-bagging

Takashi Takahashi

Comments 31 pages, 14 figures

Journal ref Transactions on Machine Learning Research. 2024

Linear Attention Sequence Parallelism

Weigao Sun, Zhen Qin, Dong Li, Xuyang Shen, Yu Qiao, Yiran Zhong

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； TapTap 纠错

Comments Accepted by TMLR, 23 pages

Machine Learning with Physics Knowledge for Prediction: A Survey

Joe Watson, Chen Song, Oliver Weeger, Theo Gruner, An T. Le, Kay Pompetzki, Ahmed Hendawy, Oleg Arenz, Will Trojak, Miles Cranmer, Carlo D'Eramo, Fabian Bülow, Tanmay Goyal, Jan Peters, Martin W. Hoffman

机构 * Technical University of Darmstadt（德累斯顿技术大学） ； German Research Center for AI (DFKI)（德国人工智能研究中心） ； Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心） ； University of Würzburg（乌尔姆大学） ； ABB Corporate Research Center（ABB企业研究中心） ； IBM Research UKI（IBM英国实验室） ； University of Cambridge（剑桥大学） 纠错

Comments 61 pages, 8 figures, 2 tables. Accepted at the Transactions of Machine Learning Research (TMLR)

Time-Uniform Confidence Spheres for Means of Random Vectors

Ben Chugg, Hongjian Wang, Aaditya Ramdas

Comments 52 pages; 3 figures. Published in Transactions on Machine Learning Research

Conformal Bounds on Full-Reference Image Quality for Imaging Inverse Problems

Jeffrey Wen, Rizwan Ahmad, Philip Schniter

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； The Ohio State University（俄亥俄州立大学） ； Department of Biomedical Engineering（生物医学工程系） 纠错

Journal ref Transactions on Machine Learning Research, May 2025

Local Differential Privacy-Preserving Spectral Clustering for General Graphs

Sayan Mukherjee, Vorapong Suppakitpaisarn

Comments Version accepted at TMLR: https://openreview.net/forum?id=zo5b60AuAH

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

机构 * The University of Tokyo（东京大学） 纠错

Comments Published at Transactions on Machine Learning Research (TMLR)

Piecewise Constant Spectral Graph Neural Network

Vahan Martirosyan, Jhony H. Giraldo, Fragkiskos D. Malliaros

机构 * Université Paris-Saclay CentraleSupélec, Inria, France（巴黎-萨克雷大学中央超算研究所、法国国家信息与自动化技术研究院） 纠错

Comments Accepted to TMLR 2025

Generating Symbolic World Models via Test-time Scaling of Large Language Models

Zhouliang Yu, Yuhuan Yuan, Tim Z. Xiao, Fuxiang Frank Xia, Jie Fu, Ge Zhang, Ge Lin, Weiyang Liu

机构 * Westlake University（西湖大学） ； The Chinese University of Hong Kong（香港中文大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Max Planck Institute for Intelligent Systems, Tübingen（智能系统马克斯·普朗克研究所（图宾根）） ； Environmental Systems Research Institute, Inc.（环境系统研究所） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； SEED, Bytedance（字节跳动SEED团队） ； The Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments Accepted by TMLR2025 (32 pages, 6 figures)

Journal ref Transactions on Machine Learning Research, 2025

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Weixin Liang, Lili Yu, Liang Luo, Srinivasan Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, Xi Victoria Lin

Comments Accepted to TMLR 2025; 48 pages

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

Optimizing Cycle Life Prediction of Lithium-ion Batteries via a Physics-Informed Model

Constantin-Daniel Nicolae, Sara Sameer, Nathan Sun, Karena Yan

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

PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off

Sachit Kuhar, Yash Jain, Alexey Tumanov

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments OpenReview: https://openreview.net/forum?id=IEKtMMSblm

Journal ref Transactions on Machine Learning Research, 2024

Closed-Form Diffusion Models

Christopher Scarvelis, Haitz Sáez de Ocáriz Borde, Justin Solomon

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） ； University of Oxford（牛津大学） 纠错

Comments Published in TMLR, May 2025

CoDe: Blockwise Control for Denoising Diffusion Models

Anuj Singh, Sayak Mukherjee, Ahmad Beirami, Hadi Jamali-Rad

机构 * Delft University of Technology（代尔夫特理工大学） ； Shell Global Solutions International B.V.（壳牌全球解决方案国际有限公司） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Non-Myopic Multi-Objective Bayesian Optimization

Syrine Belakaria, Alaleh Ahmadianshalchi, Barbara Engelhardt, Stefano Ermon, Janardhan Rao Doppa

机构 * Stanford University（斯坦福大学） ； Washington State University（华盛顿州立大学） 纠错

Comments Published in Transactions on Machine Learning Research (TMLR)

Latte: Latent Diffusion Transformer for Video Generation

Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, Yu Qiao

机构 * Department of Data Science & AI, Faculty of Information Technology, Monash University（数据科学与人工智能系，信息科技学院，莫纳什大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Nanjing University of Posts and Telecommunications（南京邮电大学） ； S-Lab, Nanyang Technological University（南洋理工大学S实验室） 纠错

Comments Accepted by Transactions on Machine Learning Research 2025; Project Page: https://maxin-cn.github.io/latte_project