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

2510.01581 2025-10-03 cs.LG cs.AI cs.CL

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad, Elias Stengel-Eskin, Akshay Nambi, 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）； Microsoft Research（微软研究院）

Comments Code: https://github.com/joykirat18/TRAAC

2506.21285 2025-10-03 cs.CL

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

Xin Xu, Tianhao Chen, Fan Zhang, Wanlong Liu, Pengxiang Li, Ajay Kumar Jaiswal, Yuchen Yan, Jishan Hu, Yang Wang, Hao Chen, Shiwei Liu, Shizhe Diao, Can Yang, Lu Yin

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； University of Electronic Science and Technology of China（电子科技大学）； Dalian University of Technology（大连理工大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； Zhejiang University（浙江大学）； University of Oxford（牛津大学）； NVIDIA（NVIDIA公司）； University of Surrey（萨里大学）

Comments 10 pages

2504.15254 2025-10-03 cs.SE cs.CL cs.LG

CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation

Anirudh Khatry, Robert Zhang, Jia Pan, Ziteng Wang, Qiaochu Chen, Greg Durrett, Isil Dillig

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； New York University（纽约大学）

Comments To be published at COLM, 2025