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

Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns

Hanqi Xiao, Vaidehi Patil, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments Code: https://github.com/The-Inscrutable-X/CalibratedModelAgnosticCorrectness

Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models

Seungjun Yi, Joakim Nguyen, Terence Lim, Andrew Well, Joseph Skrovan, Mehak Beri, YongGeon Lee, Kavita Radhakrishnan, Liu Leqi, Mia Markey, Ying Ding

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Vanderbilt University School of Medicine（范德比大学医学院） 纠错

Comments Presented at GenAI4Health @ NeurIPS 2025

Muon Optimizes Under Spectral Norm Constraints

Lizhang Chen, Jonathan Li, Qiang Liu

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective

Hoang Phan, Lam Tran, Quyen Tran, Ngoc N. Tran, Tuan Truong, Qi Lei, Nhat Ho, Dinh Phung, Trung Le

机构 * New York University（纽约大学） ； Qualcomm AI Research（高通人工智能研究） ； Vanderbilt University（范德比大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Monash University（墨尔本大学） 纠错

Comments ICCV 2025 highlight paper

Communication-aware Wide-Area Damping Control using Risk-Constrained Reinforcement Learning

Kyung-bin Kwon, Lintao Ye, Vijay Gupta, Hao Zhu

机构 * Optimization and Control Group, Pacific Northwest National Laboratory（优化与控制组，太平洋西北国家实验室） ； School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（人工智能与自动化学院，华中科技大学） ； Elmore School of Electrical and Computer Engineering, Purdue University（Elmore电气与计算机工程学院，普渡大学） ； Chandra Family Department of Electrical & Computer Engineering, The University of Texas at Austin（Chandra家族电气与计算机工程系，德克萨斯大学奥斯汀分校） 纠错

Comments 12 pages, 14 figures, Accepted for publication in IEEE Transactions on Smart Grid, 2025

GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models

Zhangyu Wang, Nemin Wu, Qian Cao, Jiangnan Xia, Zeping Liu, Yiqun Xie, Akshay Nambi, Tanuja Ganu, Ni Lao, Ninghao Liu, Gengchen Mai

机构 * SIT Lab, University of Maine（缅因大学SIT实验室） ； University of Georgia（佐治亚大学） ； SEAI Lab, University of Texas at Austin（德克萨斯大学奥斯汀分校SEAI实验室） ； University of Maryland（马里兰大学） ； Microsoft Research（微软研究院） 纠错

Probabilistic Soundness Guarantees in LLM Reasoning Chains

Weiqiu You, Anton Xue, Shreya Havaldar, Delip Rao, Helen Jin, Chris Callison-Burch, Eric Wong

机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments EMNLP 2025 camera ready

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking

Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen, Xi Ye

机构 * Princeton Language and Intelligence, Princeton University（普林斯顿语言与智能研究所，普林斯顿大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments EMNLP 2025; Code at https://github.com/princeton-pli/QRHead

ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction

Qimin Chen, Yuezhi Yang, Wang Yifan, Vladimir G. Kim, Siddhartha Chaudhuri, Hao Zhang, Zhiqin Chen

机构 * Simon Fraser University（西蒙 Fraser大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Adobe Research（Adobe研究） 纠错

Comments Accepted to SIGGRAPH Asia 2025 conference track. Code: https://qiminchen.github.io/artdeco/

Gaussian Universality for Diffusion Models

Reza Ghane, Anthony Bao, Danil Akhtiamov, Babak Hassibi

机构 * Department of Electrical Engineering, California Institute of Technology（电气工程系，加利福尼亚理工学院） ； Department of Electrical and Computer Engineering, University of Texas at Austin（电气与计算机工程系，德克萨斯大学奥斯汀分校） ； Department of Computing and Mathematical Sciences, California Institute of Technology（计算与数学科学系，加利福尼亚理工学院） 纠错

Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification

Anisha Gunjal, Greg Durrett

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2024 (2024) 3751-3768

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

机构 * UT Austin（得克萨斯大学） ； SUTD（新加坡科技设计大学） 纠错

Comments Fixing typos and adding invertibility assumption