代码大模型 / AI 编程

Adapting Neural Text Classification for Improved Software Categorization

Alexander LeClair, Zachary Eberhart, Collin McMillan

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

Modified SMOTE Using Mutual Information and Different Sorts of Entropies

Sima Sharifirad, Azra Nazari, Mehdi Ghatee

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

Comments 10 Pages, 4 Tables, 8 Figures, Extracted from an MSc project with Department of Computer Science, Amirkabir University of Technology, Tehran, Iran

Supervising Unsupervised Learning

Vikas K. Garg, Adam Kalai

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

Comments 11 two column pages. arXiv admin note: substantial text overlap with arXiv:1612.09030

MIT at SemEval-2017 Task 10: Relation Extraction with Convolutional Neural Networks

Ji Young Lee, Franck Dernoncourt, Peter Szolovits

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

Comments Accepted at SemEval 2017. The first two authors contributed equally to this work

Relationship Maintenance in Software Language Repositories

Ralf Lämmel

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

Comments The Art, Science, and Engineering of Programming, Vol. 1, Issue 1, Article 4

Journal ref The Art, Science, and Engineering of Programming, 2017, Vol. 1, Issue 1, Article 4

Knowledge-based system for collaborative process specification

Frederick Benaben, Vatcharaphun Rajsiri, Jean-Pierre Lorré, Hervé Pingaud

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

Comments \<10.1016/j.compind.2009.10.012\&gt

Journal ref Computers and Industrial Engineering, Elsevier, 2010, 61 (2), pp.161-175

Discovering Valuable Items from Massive Data

Hastagiri P. Vanchinathan, Andreas Marfurt, Charles-Antoine Robelin, Donald Kossmann, Andreas Krause

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

Autonomous Agents Coordination: Action Languages meet CLP(FD) and Linda

Agostino Dovier, Andrea Formisano, Enrico Pontelli

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

A General Framework for Development of the Cortex-like Visual Object Recognition System: Waves of Spikes, Predictive Coding and Universal Dictionary of Features

Sergey S. Tarasenko

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

Towards Design and Implementation of a Language Technology based Information Processor for PDM Systems

Zeeshan Ahmed, Saman Majeed, Thomas Dandekar

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

Journal ref IST Transactions of Information Technology- Theory and Applications, Vol. 1, No. 1 (2),ISSN 1913-8822, pp. 1-7, 2010

Codified Context: Infrastructure for AI Agents in a Complex Codebase

编译上下文：复杂代码库中AI代理的基础设施

Aristidis Vasilopoulos

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

AI总结 本文提出了一种编译上下文基础设施，通过编码约定、领域专家代理和知识库，提升大规模多代理项目中的代码一致性与可靠性。

Comments 9 pages, 4 figures, companion repository: https://github.com/arisvas4/codified-context-infrastructure, code DOI: 10.5281/zenodo.18746623

Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey

基于图像-语言基础模型的图像到视频迁移学习：全面综述

Jinxuan Li, Chaolei Tan, Haoxuan Chen, Jianxin Ma, Jian-Fang Hu, Jianhuang Lai, Wei-Shi Zheng

机构 * School of Computer Science and Engineering, Sun Yat-sen University（计算机科学与工程学院，中山大学） 纠错

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

AI总结 本文综述了基于图像-语言基础模型的图像到视频迁移学习，系统分类了现有技术并分析了其在视频-文本任务中的应用与挑战。

Comments Updated version, github repository is available at https://github.com/YuriPreisdent/awesome-image-to-video-transfer

The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA

Quanzhu Niu, Dengxian Gong, Shihao Chen, Tao Zhang, Yikang Zhou, Haobo Yuan, Lu Qi, Xiangtai Li, Shunping Ji

机构 * Wuhan University（武汉大学） ； University of California, Merced（加州大学默塞德分校） ； Nanyang Technological University（南洋理工大学） 纠错

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

Comments The 1st place report of 7th LSVOS challenge RVOS track in ICCV 2025. The code is released in Sa2VA repository: https://github.com/bytedance/Sa2VA

Improving Machine Hearing on Limited Data Sets

Pavol Harar, Roswitha Bammer, Anna Breger, Monika Dörfler, Zdenek Smekal

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

Comments 13 pages, 3 figures, 2 tables. Repository for reproducibility: https://gitlab.com/hararticles/gs-ms-mt/. Keywords: audio, CNN, limited data, Mel scattering, mel-spectrogram, augmented target loss function. Rewritten and restructured after peer revision. Recomputed and added new experiments and visualizations. Changed the presentation of the results

Journal ref 2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pp. 1-6. IEEE, 2019

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

Kaizhong Zheng, Shujian Yu, Baojuan Li, Robert Jenssen, Badong Chen

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

Comments This paper is accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS), code is available at GitHub repository (https://github.com/SJYuCNEL/brain-and-Information-Bottleneck/)

A Survey of Graph Neural Networks for Social Recommender Systems

Kartik Sharma, Yeon-Chang Lee, Sivagami Nambi, Aditya Salian, Shlok Shah, Sang-Wook Kim, Srijan Kumar

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

Comments Published in ACM CSUR April 2024. GitHub repository with the curated list of papers: https://github.com/claws-lab/awesome-GNN-social-recsys

Journal ref ACM Comput. Surv. (April 2024)

CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis

Kaizhong Zheng, Shujian Yu, Badong Chen

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

Comments Manuscript ia accepted by Neural Networks, The source code and implementation details are freely available at GitHub repository (https://github.com/ZKZ-Brain/CI-GNN/). 45 pages, 14 figures

Multi-output Ensembles for Multi-step Forecasting

Vitor Cerqueira, Luis Torgo

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

Comments 19 pages, github repository available

Synergy of Machine and Deep Learning Models for Multi-Painter Recognition

Vassilis Lyberatos, Paraskevi-Antonia Theofilou, Jason Liartis, Georgios Siolas

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

Comments Github Repository: https://github.com/jliartis/art-recognition

Equal Improvability: A New Fairness Notion Considering the Long-term Impact

Ozgur Guldogan, Yuchen Zeng, Jy-yong Sohn, Ramtin Pedarsani, Kangwook Lee

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

Comments Codes are available in a GitHub repository, see https://github.com/guldoganozgur/ei_fairness. ICLR 2023 Poster. 31 pages, 10 figures, 6 tables

RcTorch: a PyTorch Reservoir Computing Package with Automated Hyper-Parameter Optimization

Hayden Joy, Marios Mattheakis, Pavlos Protopapas

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

Comments 18 pages, 12 figures, and 43 citations. GitHub repository and documentation information included and linked

Determining the best classifier for predicting the value of a boolean field on a blood donor database using genetic algorithms

Ritabrata Maiti

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

Comments GitHub Repository here: https://github.com/ritabratamaiti/Blooddonorprediction

Collective Mind: cleaning up the research and experimentation mess in computer engineering using crowdsourcing, big data and machine learning

Grigori Fursin

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

Comments I started drafting this document at the beginning of the development of the 3rd version of plugin-based cTuning infrastructure and repository (aka Collective Mind) to systematize and crowdsource program and architecture auto-tuning; (2013)

Optimizing Binary Code Produced by Valgrind (Project Report on Virtual Execution Environments Course - AVExe)

Filipe Cabecinhas, Nuno Lopes, Renato Crisostomo, Luis Veiga

专题命中 仓库级理解 ：code generation(abstract,comments)；分类 cs.PL

Comments Technical report from INESC-ID Lisboa describing optimizations to code generation of the Valgring execution environment. Work developed in the context of a Virtual Execution Environments course (AVExe) at IST/Technical university of Lisbon

Implicit, Yet Impactful: Understanding Hidden Dependencies in Java Projects

隐式却影响重大：理解Java项目中的隐藏依赖关系

Lyuye Zhang, Chengwei Liu, Fangyuan Zhang, Yiran Zhang, Yuan Zhou, Yang Liu

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

AI总结 本研究针对Java项目的隐式依赖问题，构建含1157个库、19812个版本及972个模块的数据集，量化其影响并分析应对措施，为开源生态系统提供解决方案。

Comments 13 pages, ASE 2026

Strategic Technical Debt: A Real Options Approach to Early-Stage Software Experimentation

策略性技术债务：早期软件实验的实物期权方法

Rashid Azarang, Mohammad Reza Azarang Esfandiari

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

AI总结 本文将早期软件实验中刻意产生的技术债务视为看涨期权，明确策略性与有毒债务的边界，构建序贯模型得出关键结论，并开展两项预注册实证检验。

Comments 25 pages, 4 figures. Pre-registered empirical program: OSF bs3cr (EP3'), rvx5t (EP-Pi)

Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant

在多物理场AI助手MOOSEnger中部署前沿智能体技术

Zaid Abulawi, Mengnan Li, Guillaume Giudicelli, Yang Liu, Cody Permann

机构 * Texas A&M University (TAMU)（德克萨斯农工大学） ； Idaho National Laboratory (INL)（爱达荷国家实验室） 纠错

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

AI总结 本研究为面向MOOSE框架的AI智能体MOOSEnger扩展本地托管模型管控层，经多类工程任务测试，MOOSEnger-GPT-5.2成功率达90%，凸显智能体管控层对多物理场仿真的支撑价值。

A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

双语混合专家语言模型中专家路由的声明式-过程式视角

Amrit Gopinath (1), Raghul (1), Durairaj Thenmozhi (2) ((1) Sri Sivasubramaniya Nadar College of Engineering, Chennai, India, (2) Shiv Nadar University Chennai, India)

机构 * Sri Sivasubramaniya Nadar College of Engineering（斯里·西瓦苏布拉马尼亚·纳达尔工程学院） ； Shiv Nadar University Chennai（钦奈希夫·纳达尔大学） 纠错

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

AI总结 该研究探究双语MoE语言模型的专家路由是否形成语言结构，对比课程学习与无课程训练的模型，发现无课程模型专业化更强但依赖随机种子，课程模型路由更均衡，揭示MoE路由可出现可解释语言组织。

Comments 15 pages, 6 figures, 12 tables (including appendix)

Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

表示签名与LLM交易智能体中的风险反馈对齐

Weicheng Xue

机构 * Virginia Tech（弗吉尼亚理工大学） 纠错

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

AI总结 通过TradeArena测试平台研究LLM交易智能体在金融决策中的行为对齐与表示动态，发现故障前表示签名（规划嵌入漂移、流形有效秩收缩）并验证风险反馈作为外部对齐信号的有效性。

Model Inversion Attacks: A Survey of Approaches and Countermeasures

模型反演攻击：方法与对策综述

Zhanke Zhou, Jianing Zhu, Fengfei Yu, Xuan Li, Xiong Peng, Tongliang Liu, Bo Han

机构 * Hong Kong Baptist University（香港 Baptist 大学） ； The University of Sydney（悉尼大学） 纠错

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

AI总结 本综述针对模型反演攻击，综合分析其在多领域的有效性及神经网络的脆弱性，对比攻击与防御的多维度要素，明确建模与优化挑战并维护相关研究知识库。