University of Texas at Austin（得克萨斯大学奥斯汀分校）

2509.20177 2025-09-25 cs.LG

Generative Model Inversion Through the Lens of the Manifold Hypothesis

Xiong Peng, Bo Han, Fengfei Yu, Tongliang Liu, Feng Liu, Mingyuan Zhou

机构 * TMLR Group, Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）； Sydney AI Centre, The University of Sydney（悉尼大学人工智能中心）； School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系）； McCombs School of Business, The University of Texas at Austin（德克萨斯大学奥斯汀分校麦科姆斯商学院）

Comments NeurIPS 2025

2509.19589 2025-09-25 cs.CV

Synthesizing Artifact Dataset for Pixel-level Detection

Dennis Menn, Feng Liang, Diana Marculescu

机构 * Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电子与计算机工程系）； Meta

Comments Under submission to WACV

2503.11381 2025-09-25 cs.CL

Modeling Subjectivity in Cognitive Appraisal with Language Models

Yuxiang Zhou, Hainiu Xu, Desmond C. Ong, Maria Liakata, Petr Slovak, Yulan He

机构 * Queen Mary University of London（伦敦大学玛丽女王学院）； King’s College London（伦敦大学国王学院）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； The Alan Turing Institute（艾伦·图灵研究所）

Comments EMNLP 2025 Findings

2503.07513 2025-09-25 cs.CL cs.AI

Language Models Fail to Introspect About Their Knowledge of Language

Siyuan Song, Jennifer Hu, Kyle Mahowald

机构 * Department of Linguistics The University of Texas at Austin（语言学系德克萨斯大学奥斯汀分校）； Department of Cognitive Science Johns Hopkins University（认知科学系约翰霍普金斯大学）

Comments 23 pages, 10 figures, COLM 2025 camera ready

2308.00177 2025-09-25 cs.LG cs.AI

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, Sujay Sanghavi

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）； Carnegie Mellon University（卡内基梅隆大学）； Amazon（亚马逊）； Department of Computer Science（计算机科学系）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

Comments Published in TMLR, ICML-MFPL 2023 Workshop Oral, SPIGM@ICML2024