AI 大模型

代码大模型 / AI 编程

代码生成、软件工程智能体、程序修复、测试生成和开发者工具。

2025-09-10 至 2025-09-10 共收录 5 篇信号源：cs.SE, cs.CL, cs.AI, cs.LG, cs.PL

1. 仓库级理解 5 篇

2509.07851 2025-09-10 cs.SE 79%

"We provide our resources in a dedicated repository": Surveying the Transparency of HICSS publications

Irdin Pekaric, Giovanni Apruzzese

专题命中仓库级理解：repository(title,abstract)；分类 cs.SE

2509.07006 2025-09-10 cs.CY cs.AI cs.CL cs.LG 67%

ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code

Kapil Madan

机构 * Principled Evolution（原则进化）

专题命中仓库级理解：repository(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 53 pages, 7 figures, 8 tables. Open-source implementation available at: https://github.com/Principled-Evolution/argen-demo. Work explores the integration of policy-as-code for AI alignment, with a case study in culturally-nuanced, ethical AI using Dharmic principles

2508.16665 2025-09-10 cs.CL cs.AI 62%

Trust but Verify! A Survey on Verification Design for Test-time Scaling

V Venktesh, Mandeep Rathee, Avishek Anand

机构 * Stockholm University（斯德哥尔摩大学）； L3S Research Center（L3S研究中心）； TU Delft（代尔夫特理工大学）

专题命中仓库级理解：repository(abstract)；分类 cs.CL、cs.AI

Comments 18 pages

2509.06977 2025-09-10 cs.LG cs.AI 62%

Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification

Zehua Li

机构 * Department of Computer Science Dalhousie University（计算机科学系达勒豪西大学）

专题命中仓库级理解：repository(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 7 figures, 3 tables, appendix, code available at https://github.com/william-zehua-li/cross-backend-model-checker

2509.07507 2025-09-10 cs.CV 50%

MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection

Saad Lahlali, Alexandre Fournier Montgieux, Nicolas Granger, Hervé Le Borgne, Quoc Cuong Pham

机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学、欧洲原子能机构、List）

专题命中仓库级理解：repository(abstract)

Comments Accepted at WACV 2026