代码大模型 / AI 编程

WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation

Mingde Xu, Zhen Yang, Wenyi Hong, Lihang Pan, Xinyue Fan, Yan Wang, Xiaotao Gu, Bin Xu, Jie Tang

机构 * Faculty of Mathematics, University of Waterloo（滑铁卢大学数学系） ； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程集团） ； Zhipu AI（智谱AI） 纠错

专题命中 代码生成 ：code generation(title,abstract)；code model(abstract)；分类 cs.SE、cs.AI

Comments 36 pages, 30 figures

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis

Jan Ondras, Marek Šuppa

机构 * MIT（麻省理工学院） ； Comenius University in Bratislava（布拉迪斯拉发孔院大学） 纠错

专题命中 代码生成 ：program synthesis(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted to The 5th Workshop on Mathematical Reasoning and AI at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025); 25 pages, 14 figures, 8 tables; Code available at https://github.com/NaiveNeuron/FractalBench

Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation

K M Nafi Asib, Sourav Saha, Mohammed Moshiul Hoque

机构 * Department of Computer Science and Engineering（计算机科学与工程系） 纠错

专题命中 代码生成 ：code generation(title,abstract)；分类 cs.CL

Comments 8 pages, 1 figure, experimental scripts publicly available at https://github.com/NafiAsib/Retriv-BLP25-Task-2

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

Speed Zhu, Jianwei Cai, Guang Chen, Lulu Wu, Saiyong Yang, Wiggin Zhou

机构 * Hunyuan Team, Tencent（腾讯 Hunyuan 团队） 纠错

专题命中 代码生成 ：code generation(title,abstract)；分类 cs.LG

Comments 15 pages, 8 figures

NoteEx: Interactive Visual Context Manipulation for LLM-Assisted Exploratory Data Analysis in Computational Notebooks

Mohammad Hasan Payandeh, Lin-Ping Yuan, Jian Zhao

机构 * School of Computer Science\ of Waterloo Waterloo Ontario Canada ； The Hong Kong University of Science ； School of Computer Science\ of Waterloo 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.AI

SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim

专题命中 代码生成 ：code generation(abstract)；分类 cs.AI

Comments superseded by newest version of arXiv:2505.12006

An Empirical Study of Reasoning Steps in Thinking Code LLMs

Haoran Xue, Gias Uddin, Song Wang

机构 * York University（约克大学） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.AI

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

Yigitcan Kaya, Anton Landerer, Stijn Pletinckx, Michelle Zimmermann, Christopher Kruegel, Giovanni Vigna

机构 * University of California, Santa Barbara（加州大学圣巴bara分校） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.AI

Comments At IEEE S&P 2026

OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning

Yifeng Xiong, Xiaohui Xie

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL

LLMs as Packagers of HPC Software

Caetano Melone, Daniel Nichols, Konstantinos Parasyris, Todd Gamblin, Harshitha Menon

机构 * Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） 纠错

专题命中 仓库级理解 ：code generation(abstract)；repository(abstract)；分类 cs.SE、cs.AI

How do Machine Learning Models Change?

Joel Castaño, Rafael Cabañas, Antonio Salmerón, David Lo, Silverio Martínez-Fernández

机构 * Department of Mathematics（数学系） ； CDTIME, University of Almería（CDTIME，阿尔梅里亚大学） ； Singapore Management University（新加坡管理大学） 纠错

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

Comments This paper has been accepted for publication in ACM Transactions on Software Engineering and Methodology (TOSEM)

One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks

Vinicius Yuiti Fukase, Heitor Gama, Barbara Bueno, Lucas Libanio, Anna Helena Reali Costa, Artur Jordao

机构 * Escola Politécnica, Universidade de São Paulo（圣保罗大学politécnica学院） 纠错

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

PyGress: Tool for Analyzing the Progression of Code Proficiency in Python OSS Projects

Rujiphart Charatvaraphan, Bunradar Chatchaiyadech, Thitirat Sukijprasert, Chaiyong Ragkhitwetsagul, Morakot Choetkiertikul, Raula Gaikovina Kula, Thanwadee Sunetnanta, Kenichi Matsumoto

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

tcrLM: a lightweight protein language model for predicting T cell receptor and epitope binding specificity

Xing Fang, Chenpeng Yu, Shiye Tian, Hui Liu

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

Retuve: Automated Multi-Modality Analysis of Hip Dysplasia with Open Source AI

Adam McArthur, Stephanie Wichuk, Stephen Burnside, Andrew Kirby, Alexander Scammon, Damian Sol, Abhilash Hareendranathan, Jacob L. Jaremko

机构 * Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB T6G 2R3, Canada（放射学与诊断影像学系，阿尔伯塔大学，爱德蒙顿，AB T6G 2R3，加拿大） ； Department of Radiology, NHS Lothian, Edinburgh, EH16 4SA, United Kingdom（放射学系，NHS洛锡安，爱丁堡，EH16 4SA，英国） ； Insight Softmax Consulting, 4 Embarcadero Center, Suite 1400 San Francisco, CA 94111（Insight Softmax咨询公司，4 Embarcadero中心，Suite 1400，旧金山，CA 94111） 纠错

专题命中 仓库级理解 ：repository(abstract)

Comments 12 pages, 7 figures, submitted to Software Impacts

Resolving Indirect Calls in Binary Code via Cross-Reference Augmented Graph Neural Networks

Haotian Zhang, Kun Liu, Cristian Garces, Chenke Luo, Yu Lei, Jiang Ming

专题命中 程序分析与验证 ：repository(abstract)