代码大模型 / AI 编程 - arXivDaily 专题

2502.14275 2025-08-20 cs.CL cs.LG 62%

Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments

Jiaxi Li, Yiwei Wang, Kai Zhang, Yujun Cai, Bryan Hooi, Nanyun Peng, Kai-Wei Chang, Jin Lu

机构 * University of Georgia（佐治亚大学）； University of California, Merced（加州大学默塞德分校）； Lehigh University（莱特大学）； The University of Queensland（昆士兰大学）； National University of Singapore（新加坡国立大学）； University of California, Los Angeles（加州大学洛杉矶分校）

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

Comments 15 pages, 11 figures

2507.02409 2025-08-19 cs.LG cs.AI 62%

S2FGL: Spatial Spectral Federated Graph Learning

Zihan Tan, Suyuan Huang, Guancheng Wan, Wenke Huang, He Li, Mang Ye

机构 * National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China（多媒体软件国家工程研究中心，计算机科学学院，武汉大学，武汉，中国）

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

2508.10461 2025-08-15 cs.LG cs.AI 62%

X-Node: Self-Explanation is All We Need

Prajit Sengupta, Islem Rekik

机构 * BASIRA Lab, Imperial-X (I-X)（BASIRA实验室，Imperial-X（I-X））； Department of Computing, Imperial College London, London, United Kingdom（计算系，伦敦帝国学院，伦敦，英国）

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

2504.17461 2025-08-13 cs.LG cs.AI 62%

Evaluating Time Series Models for Urban Wastewater Management: Predictive Performance, Model Complexity and Resilience

Vipin Singh, Tianheng Ling, Teodor Chiaburu, Felix Biessmann

机构 * Berlin University of Applied Sciences and Technology（柏林应用科学与技术大学）； Intelligent Embedded Systems Department, University of Duisburg-Essen（智能嵌入式系统系，杜伊斯堡- Essen大学）； Einstein Center Digital Future（爱因斯坦数字未来研究中心）

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

Comments 6 pages, 6 figures, accepted at 10th International Conference on Smart and Sustainable Technologies (SpliTech) 2025, GitHub: https://github.com/calgo-lab/resilient-timeseries-evaluation

2508.07966 2025-08-12 cs.SE cs.AI 62%

Exploring the Challenges and Opportunities of AI-assisted Codebase Generation

Philipp Eibl, Sadra Sabouri, Souti Chattopadhyay

机构 * Department of Computer Science University of Southern California Los Angeles, California（计算机科学系美国南加州大学洛杉矶加州）

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

2508.05547 2025-08-08 cs.LG cs.AI cs.CV 62%

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

Hao Dong, Lijun Sheng, Jian Liang, Ran He, Eleni Chatzi, Olga Fink

机构 * ETH Zürich（苏黎世联邦理工学院）； University of Science and Technology of China（中国科学技术大学）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； EPFL（苏黎世联邦理工学院）

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

Comments Discussions, comments, and questions are welcome in \url{https://github.com/tim-learn/Awesome-LabelFree-VLMs}

2508.02271 2025-08-06 cs.CL cs.AI 62%

Dynaword: From One-shot to Continuously Developed Datasets

Kenneth Enevoldsen, Kristian Nørgaard Jensen, Jan Kostkan, Balázs Szabó, Márton Kardos, Kirten Vad, Johan Heinsen, Andrea Blasi Núñez, Gianluca Barmina, Jacob Nielsen, Rasmus Larsen, Peter Vahlstrup, Per Møldrup Dalum, Desmond Elliott, Lukas Galke, Peter Schneider-Kamp, Kristoffer Nielbo

机构 * Aarhus University（奥胡斯大学）； The Alexandra Institute（亚历山大研究所）； Aalborg University（奥尔堡大学）； University of Southern Denmark（南丹麦大学）； University of Copenhagen（哥本哈根大学）

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

2508.01096 2025-08-05 cs.CL cs.AI cs.IR 62%

Cross-Domain Web Information Extraction at Pinterest

Michael Farag, Patrick Halina, Andrey Zaytsev, Alekhya Munagala, Imtihan Ahmed, Junhao Wang

机构 * Pinterest

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

2504.14026 2025-08-05 cs.SE cs.LG 62%

Assumptions to Evidence: Evaluating Security Practices Adoption and Their Impact on Outcomes in the npm Ecosystem

Nusrat Zahan, Imranur Rahman, Laurie Williams

机构 * North Carolina State University（北卡罗来纳州立大学）

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

Comments 12 pages, 2 figures, 4 tables

2507.17297 2025-07-24 cs.SD cs.AI cs.LG eess.AS 62%

On Temporal Guidance and Iterative Refinement in Audio Source Separation

Tobias Morocutti, Jonathan Greif, Paul Primus, Florian Schmid, Gerhard Widmer

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

2507.10562 2025-07-16 cs.AI cs.CR cs.DB cs.LG 62%

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents

Hari Masoor

机构 * Independent Researcher（独立研究者）

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

Comments 7 pages, 4 figures, 3 implementation examples. Original work submitted as a preprint

2504.06897 2025-07-14 cs.CV cs.AI cs.LG 62%

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

Jiawei Mao, Yuhan Wang, Yucheng Tang, Daguang Xu, Kang Wang, Yang Yang, Zongwei Zhou, Yuyin Zhou

机构 * UC Santa Cruz（加州大学圣克ruz分校）； NVIDIA（英伟达）； UC San Francisco（加州大学旧金山分校）； Johns Hopkins University（约翰霍普金斯大学）

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

Comments 12 pages, 8 figures, The project page can be accessed via https://jwmao1.github.io/MedSegFactory_web

2408.06687 2025-07-11 cs.CV cs.AI cs.LG 62%

Masked Image Modeling: A Survey

Vlad Hondru, Florinel Alin Croitoru, Shervin Minaee, Radu Tudor Ionescu, Nicu Sebe

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

Comments Accepted at the International Journal of Computer Vision

2507.05319 2025-07-09 cs.CL cs.AI 62%

LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review

Cheng Yuan, Xinkai Rui, Yongqi Fan, Yawei Fan, Boyang Zhong, Jiacheng Wang, Weiyan Zhang, Tong Ruan

机构 * East China University of Science and Technology（东华大学）； Ruijin Hospital（瑞金医院）； Shanghai Jiaotong University School of Medicine（上海交通大学医学院）

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

Comments ACL Demo 2025

2507.01031 2025-07-03 cs.LG cs.SE 62%

PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs

Fanchen Bu, Kijung Shin

机构 * KAIST（韩国国立釜山科学技术院）

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

Comments Conference paper: Accepted in Korea Computer Congress (KCC) 2025. The library is available at https://github.com/bokveizen/gaudi-geometric-learning

2507.00048 2025-07-02 cs.AI cond-mat.mtrl-sci cs.CE cs.LG 62%

A collaborative digital twin built on FAIR data and compute infrastructure

Thomas M. Deucher, Juan C. Verduzco, Michael Titus, Alejandro Strachan

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

Comments 10 pages, 5 figures

2506.01056 2025-06-25 cs.AI cs.SE 62%

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Xiang Fei, Xiawu Zheng, Hao Feng

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

2409.09957 2025-06-19 cs.LG cs.AI 62%

Deep Graph Anomaly Detection: A Survey and New Perspectives

Hezhe Qiao, Hanghang Tong, Bo An, Irwin King, Charu Aggarwal, Guansong Pang

机构 * School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学）； Department of Computer Science, University of Illinois at Urbana-Champaign（计算机科学系，伊利诺伊大学厄巴纳-香槟分校）； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）； Department of Computer Science & Engineering, Chinese University of Hong Kong（计算机科学与工程系，香港中文大学）； IBM T. J. Watson Research Center（IBM 托马斯·贾维斯·沃森研究中心）

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

Comments Accepted by TKDE

2405.06823 2025-06-16 cs.CR cs.AI cs.LG 62%

PLeak: Prompt Leaking Attacks against Large Language Model Applications

Bo Hui, Haolin Yuan, Neil Gong, Philippe Burlina, Yinzhi Cao

机构 * Johns Hopkins University（约翰霍普金斯大学）； Duke University（杜克大学）； Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室）

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

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

2506.07449 2025-06-10 cs.IR cs.AI cs.CL 62%

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

Vahid Azizi, Fatemeh Koochaki

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

2506.02160 2025-06-04 cs.IR cs.CL cs.LG 62%

A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering

Madan Krishnamurthy, Daniel Korn, Melissa A Haendel, Christopher J Mungall, Anne E Thessen

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

2505.23034 2025-05-30 cs.AI cs.LG 62%

Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction

Guangyi Liu, Yongqi Zhang, Xunyuan Liu, Quanming Yao

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））

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

2501.03228 2025-05-29 cs.IR cs.AI cs.LG 62%

LightGNN: Simple Graph Neural Network for Recommendation

Guoxuan Chen, Lianghao Xia, Chao Huang

机构 * University of Hong Kong（香港大学）

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

Comments Accepted to WSDM 2025

2505.17060 2025-05-26 cs.CL cs.AI 62%

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

Wenyi Yu, Siyin Wang, Xiaoyu Yang, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Guangzhi Sun, Lu Lu, Yuxuan Wang, Chao Zhang

机构 * Tsinghua University（清华大学）； ByteDance（字节跳动）； University of Cambridge（剑桥大学）

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

2505.15810 2025-05-23 cs.CL cs.AI cs.CV 62%

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Yuqi Zhou, Sunhao Dai, Shuai Wang, Kaiwen Zhou, Qinglin Jia, Jun Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学 Gallagher人工智能学院）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2505.07882 2025-05-14 cs.AI cs.LG 62%

Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey

Qian Xu, Lei Zhang, Yixiao Liu

机构 * Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University（道路交通工程重点实验室，教育部，同济大学）； College of Transportation, Tongji University（交通学院，同济大学）； Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究院，同济大学）

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

Comments 31 pages, 9 figures

2505.03443 2025-05-07 cs.DC cs.AI cs.CL 62%

Elevating Semantic Exploration: A Novel Approach Utilizing Distributed Repositories

Valerio Bellandi

机构 * Università Degli Studi di Milano, Department of Computer Science（米兰大学计算机科学系）

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

Comments This paper has been accepted at the 6th International Conference on Recent Trends and Applications in Computer Science. It will appear in the proceedings

2503.24235 2025-05-06 cs.CL cs.AI 62%

A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

Qiyuan Zhang, Fuyuan Lyu, Zexu Sun, Lei Wang, Weixu Zhang, Wenyue Hua, Haolun Wu, Zhihan Guo, Yufei Wang, Niklas Muennighoff, Irwin King, Xue Liu, Chen Ma

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

Comments v3: Expand Agentic and SFT Chapters. Build Website for better visualization

2505.01286 2025-05-05 cs.LG cs.AI 62%

2DXformer: Dual Transformers for Wind Power Forecasting with Dual Exogenous Variables

Yajuan Zhang, Jiahai Jiang, Yule Yan, Liang Yang, Ping Zhang

机构 * School of Artificial Intelligence, Hebei University of Technology, Tianjin, China（人工智能学院，河北工业大学，天津，中国）； State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China（电力设备可靠性与智能化国家重点实验室，河北工业大学，天津，中国）； Hebei Province Key Laboratory of Big Data Calculation, Hebei University of Technology, Tianjin, China（河北省大数据计算重点实验室，河北工业大学，天津，中国）

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

Comments Accepted by ICDM 2024

2504.13828 2025-04-29 cs.CL cs.AI 62%

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Shijie Xia, Yiwei Qin, Xuefeng Li, Yan Ma, Run-Ze Fan, Steffi Chern, Haoyang Zou, Fan Zhou, Xiangkun Hu, Jiahe Jin, Yanheng He, Yixin Ye, Yixiu Liu, Pengfei Liu

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

Comments v3: add the comparison to existing work part; fix some errors

1. 仓库级理解 3924 篇

Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments

S2FGL: Spatial Spectral Federated Graph Learning

X-Node: Self-Explanation is All We Need

Evaluating Time Series Models for Urban Wastewater Management: Predictive Performance, Model Complexity and Resilience

Exploring the Challenges and Opportunities of AI-assisted Codebase Generation

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

Dynaword: From One-shot to Continuously Developed Datasets

Cross-Domain Web Information Extraction at Pinterest

Assumptions to Evidence: Evaluating Security Practices Adoption and Their Impact on Outcomes in the npm Ecosystem

On Temporal Guidance and Iterative Refinement in Audio Source Separation

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

Masked Image Modeling: A Survey

LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review

PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs

A collaborative digital twin built on FAIR data and compute infrastructure

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Deep Graph Anomaly Detection: A Survey and New Perspectives

PLeak: Prompt Leaking Attacks against Large Language Model Applications

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering

Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction

LightGNN: Simple Graph Neural Network for Recommendation

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Enhancing Trust Management System for Connected Autonomous Vehicles Using Machine Learning Methods: A Survey

Elevating Semantic Exploration: A Novel Approach Utilizing Distributed Repositories

A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

2DXformer: Dual Transformers for Wind Power Forecasting with Dual Exogenous Variables

Generative AI Act II: Test Time Scaling Drives Cognition Engineering