TMLR

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing

Arash Behboodi, Gabriele Cesa

Comments 48 pages, TMLR accepted

Explicitly Disentangled Representations in Object-Centric Learning

Riccardo Majellaro, Jonathan Collu, Aske Plaat, Thomas M. Moerland

Comments Published in TMLR

Journal ref Transactions on Machine Learning Research (2025)

Compositional Instruction Following with Language Models and Reinforcement Learning

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Ray Mooney, Benjamin Rosman

Comments TMLR 2024

Analysis of Classifier-Free Guidance Weight Schedulers

Xi Wang, Nicolas Dufour, Nefeli Andreou, Marie-Paule Cani, Victoria Fernandez Abrevaya, David Picard, Vicky Kalogeiton

Journal ref Transactions on Machine Learning Research, 2835-8856, 2024

Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens

Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor

Comments Published in TMLR

BM$^2$: Coupled Schrödinger Bridge Matching

Stefano Peluchetti

Comments Archival of: TMLR, 12/2024, https://openreview.net/forum?id=fqkq1MgONB

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images

Zhuoran Yu, Chenchen Zhu, Sean Culatana, Raghuraman Krishnamoorthi, Fanyi Xiao, Yong Jae Lee

Comments Accepted by Transactions on Machine Learning Research (TMLR)

Global Safe Sequential Learning via Efficient Knowledge Transfer

Cen-You Li, Olaf Duennbier, Marc Toussaint, Barbara Rakitsch, Christoph Zimmer

Comments Accepted for publication in TMLR 2025

Graph-level Representation Learning with Joint-Embedding Predictive Architectures

Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani

Comments Accepted in Transactions of Machine Learning Research (TMLR)

Decoupled Sequence and Structure Generation for Realistic Antibody Design

Nayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park

Comments 22 pages, 6 figures

Journal ref Transactions on Machine Learning Research, 2025

Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations

Dominik Baumann, Erfaun Noorani, James Price, Ole Peters, Colm Connaughton, Thomas B. Schön

Comments Accepted final version to appear in the Transactions on Machine Learning Research

Can AI-Generated Text be Reliably Detected?

Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi

Comments Published in Transactions on Machine Learning Research (TMLR)

Identifying Spurious Correlations using Counterfactual Alignment

Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari

Comments Accepted to Transactions on Machine Learning Research (TMLR), Code: https://github.com/ieee8023/latentshift

PRIMO: Private Regression in Multiple Outcomes

Seth Neel

Journal ref Transactions on Machine Learning Research (January 2025)

Pre-trained Vision-Language Models Learn Discoverable Visual Concepts

Yuan Zang, Tian Yun, Hao Tan, Trung Bui, Chen Sun

Comments Transactions on Machine Learning Research, 2025

Generating Less Certain Adversarial Examples Improves Robust Generalization

Minxing Zhang, Michael Backes, Xiao Zhang

Comments Published in Transactions on Machine Learning Research (TMLR)

Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective

Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P Dickerson, Pin-Yu Chen, Jeff Bilmes

Comments Accepted at TMLR (https://openreview.net/forum?id=Conma3qnaT)

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures

Yihang Gao, Chuanyang Zheng, Enze Xie, Han Shi, Tianyang Hu, Yu Li, Michael K. Ng, Zhenguo Li, Zhaoqiang Liu

Comments Published at Transactions on Machine Learning Research (TMLR). The paper provides insight that the Transformer architectures can mimic the algorithm structures in (in-context) algorithm learning and representation. The incorporated algorithmic structure in Algoformer shows its potential in (deep learning for) scientific computing, besides the real language tasks

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers

Tobias Leemann, Alina Fastowski, Felix Pfeiffer, Gjergji Kasneci

Comments TMLR Camera-Ready version

An Analysis of Model Robustness across Concurrent Distribution Shifts

Myeongho Jeon, Suhwan Choi, Hyoje Lee, Teresa Yeo

Comments Accepted to TMLR

S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks

Marco Paul E. Apolinario, Kaushik Roy

Comments 23 pages, 5 figures

Journal ref Transactions on Machine Learning Research 2025

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

Yifei He, Yuzheng Hu, Yong Lin, Tong Zhang, Han Zhao

Comments TMLR camera-ready version

Highway Graph to Accelerate Reinforcement Learning

Zidu Yin, Zhen Zhang, Dong Gong, Stefano V. Albrecht, Javen Q. Shi

Comments Published in TMLR

Simple Imputation Rules for Prediction with Missing Data: Contrasting Theoretical Guarantees with Empirical Performance

Dimitris Bertsimas, Arthur Delarue, Jean Pauphilet

Journal ref Transactions on Machine Learning Research, 2024

Fairness Through Matching

Kunwoong Kim, Insung Kong, Jongjin Lee, Minwoo Chae, Sangchul Park, Yongdai Kim

Comments Published in TMLR

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models

Shuai Zhao, Meihuizi Jia, Zhongliang Guo, Leilei Gan, Xiaoyu Xu, Xiaobao Wu, Jie Fu, Yichao Feng, Fengjun Pan, Luu Anh Tuan

Comments Accepted in TMLR

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning

Peihong Yu, Manav Mishra, Alec Koppel, Carl Busart, Priya Narayan, Dinesh Manocha, Amrit Bedi, Pratap Tokekar

Comments accepted in Transactions on Machine Learning Research

Transformers in Uniform TC$^0$

David Chiang

Journal ref Transactions on Machine Learning Research, January 2025

SC2 Benchmark: Supervised Compression for Split Computing

Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, Stephan Mandt

Comments Accepted at TMLR. Code and models are available at https://github.com/yoshitomo-matsubara/sc2-benchmark

Journal ref Transactions on Machine Learning Research (2023)

Perception Stitching: Zero-Shot Perception Encoder Transfer for Visuomotor Robot Policies

Pingcheng Jian, Easop Lee, Zachary Bell, Michael M. Zavlanos, Boyuan Chen

Comments TMLR, 2024

Journal ref Published in Transactions on Machine Learning Research (11/2024)