代码大模型 / AI 编程

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

Ona de Gibert, Joseph Attieh, Teemu Vahtola, Mikko Aulamo, Zihao Li, Raúl Vázquez, Tiancheng Hu, Jörg Tiedemann

机构 * University of Helsinki（赫尔辛基大学） ； University of Cambridge（剑桥大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2025 Main Conference

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction

Yuan Xiao, Yuchen Chen, Shiqing Ma, Haocheng Huang, Chunrong Fang, Yanwei Chen, Weisong Sun, Yunfeng Zhu, Xiaofang Zhang, Zhenyu Chen

专题命中 代码评测 ：code model(abstract)；分类 cs.SE

Comments Accepted to ISSTA 2025. Code is available at https://github.com/xiaoyuanpigo/DeCoMa

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

机构 * Santa Clara University（圣克拉拉大学） ； DOCOMO Innovations, Inc.（DOCOMO创新公司） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Comments EMNLP Findings

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs

Kiho Lee, Jungkon Kim, Doowon Kim, Hyoungshick Kim

机构 * Samsung Research（三星研究院） ； University of Tennessee, Knoxville（田纳西大学 Knoxville分校） ； Sungkyunkwan University（成均馆大学） 纠错

专题命中 代码评测 ：code generation(abstract)；分类 cs.AI

Comments 25 pages

Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors

Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

机构 * Singapore Management University（新加坡管理大学） ； Tsinghua University（清华大学） 纠错

专题命中 代码评测 ：code generation(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2025 Main, Oral

SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

Iman Barati, Mostafa Amiri, Heshaam Faili

机构 * Iran University of Science and Technology（伊朗科学技术大学） ； University of Tehran（塔里哈大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks

Chien-Ming Chi

机构 * Academia Sinica（中华学术院） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.LG

Comments 34 pages, 3 figures, 7 tables

Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers

Morteza Kiani Haftlang, Mohammadhossein Malmir, Foroutan Parand, Umberto Michelucci, Safouane El Ghazouali

机构 * HSLU, Lucerne University of Applied Sciences and Arts（卢塞恩应用科学与艺术大学） ； Technical University of Munich（慕尼黑技术大学） ； University College London (UCL)（伦敦大学学院） ； TOELT LLC AI lab（TOELT LLC人工智能实验室） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL

Haoyang He, Zihua Rong, Kun Ji, Chenyang Li, Qing Huang, Chong Xia, Lan Yang, Honggang Zhang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai

机构 * University of Waterloo（滑铁卢大学） ； Toronto Metropolitan University（多伦多 Metropolitan 大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Deep Research Agents: A Systematic Examination And Roadmap

Yuxuan Huang, Yihang Chen, Haozheng Zhang, Kang Li, Huichi Zhou, Meng Fang, Linyi Yang, Xiaoguang Li, Lifeng Shang, Songcen Xu, Jianye Hao, Kun Shao, Jun Wang

机构 * Deep Research Agents（深度研究代理） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Scalable Thread-Safety Analysis of Java Classes with CodeQL

Bjørnar Haugstad Jåtten, Simon Boye Jørgensen, Rasmus Petersen, Raúl Pardo

专题命中 代码评测 ：repository(abstract)；分类 cs.SE

Dream-Coder 7B: An Open Diffusion Language Model for Code

Zhihui Xie, Jiacheng Ye, Lin Zheng, Jiahui Gao, Jingwei Dong, Zirui Wu, Xueliang Zhao, Shansan Gong, Xin Jiang, Zhenguo Li, Lingpeng Kong

机构 * The University of Hong Kong（香港大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 代码评测 ：code generation(abstract)；分类 cs.CL

InsBank: Evolving Instruction Subset for Ongoing Alignment

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

机构 * School of Computer Science, Beijing Institute of Technology（计算机科学学院，北京理工大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

UltraEar: a multicentric, large-scale database combining ultra-high-resolution computed tomography and clinical data for ear diseases

Ruowei Tang, Pengfei Zhao, Xiaoguang Li, Ning Xu, Yue Cheng, Mengshi Zhang, Zhixiang Wang, Zhengyu Zhang, Hongxia Yin, Heyu Ding, Shusheng Gong, Yuhe Liu, Zhenchang Wang

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models

Abu Sufian, Anirudha Ghosh, Debaditya Barman, Marco Leo, Cosimo Distante

机构 * CNR-ISASI（意大利那不勒斯） ； Visva-Bharati（维斯瓦-巴哈蒂） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Comments 6 pages, 4 figures, 13th International Workshop on Biometrics and Forensics (IWBF)

Controllable Conversational Theme Detection Track at DSTC 12

Igor Shalyminov, Hang Su, Jake Vincent, Siffi Singh, Jason Cai, James Gung, Raphael Shu, Saab Mansour

机构 * Amazon（亚马逊） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Comments DSTC12@SigDial2025; data and code available at https://github.com/amazon-science/dstc12-controllable-conversational-theme-detection

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation

Dan Ristea, Vasilios Mavroudis

机构 * Alan Turing Institute（艾伦·图灵研究所） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

CBMAP: Clustering-based manifold approximation and projection for dimensionality reduction

Berat Dogan

专题命中 代码评测 ：repository(abstract)；分类 cs.LG

Comments 22 pages, 10 figures, 2 tables

Journal ref IEEE Access, Volume 13, 2025

Optimization-based Prompt Injection Attack to LLM-as-a-Judge

Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, Neil Zhenqiang Gong

机构 * Huazhong University of Science and Technology（华中科技大学） ； University of Notre Dame（圣母大学） ； Lehigh University（莱文森大学） ； Duke University（杜克大学） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Comments To appear in the Proceedings of The ACM Conference on Computer and Communications Security (CCS), 2024

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers

Zhiqiang Wang, Yichao Gao, Yanting Wang, Suyuan Liu, Haifeng Sun, Haoran Cheng, Guanquan Shi, Haohua Du, Xiangyang Li

专题命中 代码评测 ：repository(abstract)；分类 cs.LG

Systematic FAIRness Assessment of Open Voice Biomarker Datasets for Mental Health and Neurodegenerative Diseases

Ishaan Mahapatra, Nihar R. Mahapatra

机构 * Haslett High School, Haslett, MI, USA Electrical \& Computer Eng., Michigan State University, East Lansing, MI, USA 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.LG

Comments To appear in the Proceedings of the 28th International Conference on Text, Speech and Dialogue (TSD 2025), Erlangen, Germany, August 25-28, 2025

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models

Wei Song, Haonan Zhong, Ziqi Ding, Jingling Xue, Yuekang Li

专题命中 代码评测 ：code generation(abstract)；分类 cs.AI

Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play

Lucia Cipolina-Kun, Marianna Nezhurina, Jenia Jitsev

机构 * LAION Juelich Supercomputing Center (JSC)（LAION尤利奇超级计算机中心（JSC）） ； Research Center Juelich (FZJ)（尤利奇研究中心（FZJ）） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Medico 2025: Visual Question Answering for Gastrointestinal Imaging

Sushant Gautam, Vajira Thambawita, Michael Riegler, Pål Halvorsen, Steven Hicks

机构 * SimulaMet - Simula Metropolitan Center for Digital Engineering, Oslo, Norway（SimulaMet - Simula Metropolitan Center for Digital Engineering，挪威奥斯陆） ； Simula Research Laboratory, Oslo, Norway（Simula研究实验室，挪威奥斯陆） ； OsloMet - Oslo Metropolitan University, Oslo, Norway（OsloMet - 奥斯陆 Metropolitan 大学，挪威奥斯陆） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions

Ziyang Xiao, Jingrong Xie, Lilin Xu, Shisi Guan, Jingyan Zhu, Xiongwei Han, Xiaojin Fu, WingYin Yu, Han Wu, Wei Shi, Qingcan Kang, Jiahui Duan, Tao Zhong, Mingxuan Yuan, Jia Zeng, Yuan Wang, Gang Chen, Dongxiang Zhang

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学） ； Huawei Noah’s Ark Lab（华为诺亚方舟实验室） ； School of Business, Singapore University of Social Sciences（新加坡国立大学商学院） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

eSASRec: Enhancing Transformer-based Recommendations in a Modular Fashion

Daria Tikhonovich, Nikita Zelinskiy, Aleksandr V. Petrov, Mayya Spirina, Andrei Semenov, Andrey V. Savchenko, Sergei Kuliev

机构 * Institute for Clarity in Documentation（文档清晰研究所） ； Inria Paris-Rocquencourt（巴黎-罗克琴库特研究所） ； Rajiv Gandhi University（拉贾·甘地大学） ； Tsinghua University（清华大学） ； Palmer Research Laboratories（帕勒尔研究实验室） ； Independent Researcher（独立研究者） ； Sber AI Lab（Sber人工智能实验室） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.LG

Comments Accepted at ACM RecSys 2025

STEPWISE-CODEX-Bench: Evaluating Complex Multi-Function Comprehension and Fine-Grained Execution Reasoning

Kaiwen Yan, Yuhang Chang, Zirui Guo, Yaling Mou, Jiang Ming, Jingwei Sun

专题命中 代码评测 ：program synthesis(abstract)；分类 cs.SE

Recent Advances in Speech Language Models: A Survey

Wenqian Cui, Dianzhi Yu, Xiaoqi Jiao, Ziqiao Meng, Guangyan Zhang, Qichao Wang, Yiwen Guo, Irwin King

机构 * Department of Computer Science and Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学） ； LIGHTSPEED STUDIOS ； National University of Singapore（新加坡国立大学） ； Tencent（腾讯） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.CL

Comments The reduced version of this paper has been accepted at ACL 2025

LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

Yi Gui, Zhen Li, Zhongyi Zhang, Guohao Wang, Tianpeng Lv, Gaoyang Jiang, Yi Liu, Dongping Chen, Yao Wan, Hongyu Zhang, Wenbin Jiang, Xuanhua Shi, Hai Jin

专题命中 代码评测 ：code generation(abstract)；分类 cs.SE

Comments KDD 2025 v2