代码大模型 / AI 编程

P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code

Wali Mohammad Abdullah, Azmain Kabir

机构 * Mathematics \& Information Technology Concordia University of Edmonton Edmonton, Alberta, Canada ； Computer Science University of Manitoba Winnipeg, Manitoba, Canada 纠错

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

Language Modeling by Language Models

Junyan Cheng, Peter Clark, Kyle Richardson

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

MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing

Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos

机构 * Department of Computer Science, Virginia Tech（计算机科学系，弗吉尼亚理工大学） 纠错

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

Comments 9 pages, 4 figures, 2 tables

Steering Conceptual Bias via Transformer Latent-Subspace Activation

Vansh Sharma, Venkat Raman

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

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Yuanhe Zhang, Fanghui Liu, Yudong Chen

机构 * Department of Statistics, University of Warwick, UK.（威斯敏斯特大学统计学系） ； Department of Computer Science, University of Warwick, UK.（威斯敏斯特大学计算机科学系） ； Centre for Discrete Mathematics and its Applications (DIMAP), University of Warwick, UK.（威斯敏斯特大学离散数学及其应用中心（DIMAP）） 纠错

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

Comments Accepted by ICML 2025 (Oral)

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models

Yanlin Wang, Tianyue Jiang, Mingwei Liu, Jiachi Chen, Mingzhi Mao, Xilin Liu, Yuchi Ma, Zibin Zheng

机构 * Sun Yat-sen University（中山大学） ； Huawei Cloud Computing Technologies（华为云计算技术） 纠错

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

Comments 13pages, 14 figures

Semantic uncertainty in advanced decoding methods for LLM generation

Darius Foodeei, Simin Fan, Martin Jaggi

机构 * EPFL, Lausanne Switzerland（日内瓦联邦理工学院） 纠错

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

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs

Ricardo Rei, Nuno M. Guerreiro, José Pombal, João Alves, Pedro Teixeirinha, Amin Farajian, André F. T. Martins

机构 * Unbabel ； Instituto de Telecomunicações（电信研究所） ； Instituto Superior Técnico & Universidade de Lisboa (Lisbon ELLIS Unit)（里斯本大学技术学院及里斯本大学（里斯本ELLIS单位）） ； MICS, CentraleSupélec, Université Paris-Saclay（MICS，CentraleSupélec，巴黎萨克雷大学） 纠错

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

DeepRTL2: A Versatile Model for RTL-Related Tasks

Yi Liu, Hongji Zhang, Yunhao Zhou, Zhengyuan Shi, Changran Xu, Qiang Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； National Technology Innovation Center for EDA（EDA国家技术创新中心） 纠错

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

Comments ACL 2025 Findings

Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets

Mahmoud Jahanshahi, Audris Mockus

机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； University of Tennessee, Knoxville, USA（田纳西大学，基洛纳分校） 纠错

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

Comments Accepted in the Second International Workshop on Large Language Models for Code (LLM4Code 2025)

Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression

Hooman Shahrokhi, Devjeet Raj Roy, Yan Yan, Venera Arnaoudova, Janaradhan Rao Doppa

机构 * School of EECS, Washington State University（电子工程与科学学院，华盛顿州立大学） 纠错

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

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm

Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Chen Zhao, Yunji Chen

机构 * SKL of Processors, Institute of Computing Technology, CAS（处理器国家重点实验室，计算技术研究所，中国科学院） ； Intelligent Software Research Center, Institute of Software, CAS（智能软件研究中心，软件研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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

AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models

Haoyi Zhang, Shizhao Sun, Yibo Lin, Runsheng Wang, Jiang Bian

机构 * School of Integrated Circuits, Peking University（集成电路学院，北京大学） ； Institute of EDA, Peking University（EDA研究院，北京大学） ； Beijing Advanced Innovation Center for Integrated Circuits（北京集成电路先进创新中心） ； Microsoft Research Asia（微软亚洲研究院） 纠错

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

LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation

Ngoc Phuoc An Vo, Brent Paulovicks, Vadim Sheinin

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

Comments 10 pages

Application Modernization with LLMs: Addressing Core Challenges in Reliability, Security, and Quality

Ahilan Ayyachamy Nadar Ponnusamy

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

PyGen: A Collaborative Human-AI Approach to Python Package Creation

Saikat Barua, Mostafizur Rahman, Md Jafor Sadek, Rafiul Islam, Shehenaz Khaled, Md. Shohrab Hossain

机构 * North South University（北南大学） ； SpontAlign ； Bangladesh University of Engineering and Technology（孟加拉工程与技术大学） 纠错

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

Comments 33 pages, 13 figures

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Wentao Chen, Jiace Zhu, Qi Fan, Yehan Ma, An Zou

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

Pel, A Programming Language for Orchestrating AI Agents

Behnam Mohammadi

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

Comments 1. Updated author email address (I graduated so I added my alumni email). 2. Changed mono-font color to blue for better readability

Test-driven Software Experimentation with LASSO: an LLM Prompt Benchmarking Example

Marcus Kessel

机构 * University of Mannheim（曼海姆大学） 纠错

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

Comments under review

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models

Rihui Jin, Zheyu Xin, Xing Xie, Zuoyi Li, Guilin Qi, Yongrui Chen, Xinbang Dai, Tongtong Wu, Gholamreza Haffari

机构 * Southeast University（东南大学） ； Monash University（墨尔本大学） 纠错

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

ProSec: Fortifying Code LLMs with Proactive Security Alignment

Xiangzhe Xu, Zian Su, Jinyao Guo, Kaiyuan Zhang, Zhenting Wang, Xiangyu Zhang

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

Comments The first two authors contributed equally to this work

Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems

Sven Kirchner, Alois C. Knoll

机构 * Technical University of Munich（慕尼黑技术大学） 纠错

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

Comments 8 pages; Accepted for publication at the 36th IEEE Intelligent Vehicles Symposium (IV), Cluj-Napoca, Romania, June 22-25, 2025

Mind the Gap: A Practical Attack on GGUF Quantization

Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev

机构 * ETH Zurich, Switzerland（苏黎世联邦理工学院） ； The University of Tokyo, Japan（东京大学） ； University of California, Berkeley, USA（加州大学伯克利分校） 纠错

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

Comments ICML 2025

DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models

Jiancheng Ye, Sophie Bronstein, Jiarui Hai, Malak Abu Hashish

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

HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation

Weizhi Tang, Yixuan Li, Chris Sypherd, Elizabeth Polgreen, Vaishak Belle

机构 * University of Edinburgh（爱丁堡大学） 纠错

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

Comments Accepted to ACL 2025 Findings. Code available at https://github.com/RutaTang/HyGenar

CleanAgent: Automating Data Standardization with LLM-based Agents

Danrui Qi, Zhengjie Miao, Jiannan Wang

机构 * Simon Fraser University（西蒙弗雷泽大学） 纠错

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

Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems

Christopher D. Rosin

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

Comments arXiv admin note: text overlap with arXiv:2501.17725

LLM for SoC Security: A Paradigm Shift

Dipayan Saha, Shams Tarek, Katayoon Yahyaei, Sujan Kumar Saha, Jingbo Zhou, Mark Tehranipoor, Farimah Farahmandi

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

Comments 42 pages

MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps

Maximiliano Hormazábal Lagos, Álvaro Bueno Saez, Héctor Cerezo-Costas, Pedro Alonso Doval, Jorge Alcalde Vesteiro

机构 * Fundación Centro Tecnolóxico de Telecomunicacións de Galicia (GRADIANT)（加利西亚电信技术基金会（GRADIANT）） 纠错

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

Comments 7 pages, 6 tables

Large Language Models for IT Automation Tasks: Are We There Yet?

Md Mahadi Hassan, John Salvador, Akond Rahman, Santu Karmaker

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

Comments 8 pages