TMLR

Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness

深度学习中的利普希茨连续性：理论基础、估计方法、正则化方法及可验证鲁棒性的系统综述

Róisín Luo, James McDermott, Colm O'Riordan

机构 * Research Ireland – Centre for Research Training in AI (CRT-AI)（爱尔兰研究机构——人工智能研究培训中心（CRT-AI）） ； J.E. Cairnes School of Business & Economics（J.E. Cairnes 商学院） ； School of Computer Science（计算机科学学院） ； University of Galway, Ireland（爱尔兰Galway大学） 纠错

AI总结 本文系统综述深度学习中利普希茨连续性，涵盖理论基础、估计方法、正则化方法及可验证鲁棒性，为研究者和从业者深入理解其在深度学习中的意义提供全面参考。

Comments Published in Transactions on Machine Learning Research (TMLR)

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation

基于肿瘤锚定的深度特征随机森林用于肺癌分割中的分布外检测

Aneesh Rangnekar, Harini Veeraraghavan

机构 * Memorial Sloan Kettering Cancer Center（纪念斯隆凯特林癌症中心） 纠错

AI总结 本文提出RF-Deep框架，利用深度特征提升CT扫描的分布外检测性能，通过少量标注数据改进分割管道的安全性。

Comments Accepted for publication in Transactions on Machine Learning Research (TMLR), 2026. Code available at: https://github.com/aneesh3108/RF-Deep

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

学习编码-解码方向对以揭示深度视觉网络中的影响概念

Alexandros Doumanoglou, Kurt Driessens, Dimitrios Zarpalas

机构 * Department of Advanced Computing Sciences (DACS), University of Maastricht (UM)（先进计算科学系（DACS）、马斯特里赫特大学（UM）） ； Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH)（信息科技研究所（ITI）、希腊研究中心与技术中心（CERTH）） 纠错

AI总结 本文提出了一种无监督方法，通过学习编码-解码方向对揭示深度视觉网络中的影响概念，提升模型的可解释性和可控性。

Comments 80 Pages. The paper's abstract was shortened to fit the character limit. Accepted at TMLR. This differs from the accepted version in clarity: revised text in introduction & background and moved related work to the end of the main paper

MACAW: A Causal Generative Model for Medical Imaging

MACAW：一种用于医学影像的因果生成模型

Vibujithan Vigneshwaran, Erik Ohara, Matthias Wilms, Nils Forkert

机构 * organization= Department of Radiology, University of Calgary , addressline= 2500 University Dr NW , city= Calgary , postcode= T2N 1N4 , state= Alberta , country= Canada ； organization= Hotchkiss Brain Institute, University of Calgary , addressline= 2500 University Dr NW , city= Calgary , postcode= T2N 1N4 , state= Alberta , country= Canada ； organization= Department of Pediatrics, University of Calgary , addressline= 28 Oki Dr , city= Calgary , postcode= T2N 6A8 , state= Alberta , country= Canada ； organization= Department of Community Health Sciences, University of Calgary , addressline= 3330 Hospital Dr NW , city= Calgary , postcode= T2N 4Z5 , state= Alberta , country= Canada ； organization= Alberta Children’s Hospital Research Institute, University of Calgary , addressline= 28 Oki Dr , city= Calgary , postcode= T2N 6A8 , state= Alberta , country= Canada 纠错

AI总结 MACAW通过整合因果知识提升医学影像生成和预测的准确性与不确定性估计。

Comments 27 pages

Journal ref Transactions on Machine Learning Research, 2026