LLM4Code 2025 Contributors

Filter

Role Type

Contributing to

Number of Roles

Country

Results (125)

A Israel AdewuyiAdewuyi, Israel Innopolis University YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
Ibrahim Al AzherAl Azher, Ibrahim Northern Illinois University From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks (Virtual Talk)
Salwa AlamirAlamir, Salwa J.P. Morgan AI Research From Zero to Sixty at the Speed of RAG: Improving YAML Recipe Generation via Retrieval
Hamed AlhooriAlhoori, Hamed Dept. of Computer Science at the Northern Illinois University From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks (Virtual Talk)
Gabin AnAn, Gabin KAISTSouth Korea METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries COSMosFL: Ensemble of Small Language Models for Fault Localisation
Md. Fahim ArefinArefin, Md. Fahim University of Dhaka LLM-ProS: Analyzing Large Language Models’ Performance in Competitive Problem Solving
Mihir AthaleAthale, Mihir Northeastern University Knowledge Graph Based Repository-Level Code Generation (Virtual Talk)
B Petr BabkinBabkin, Petr J.P. Morgan AI Research From Zero to Sixty at the Speed of RAG: Improving YAML Recipe Generation via Retrieval
Michael BartholfBartholf, Michael MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Claas BegerBeger, Claas Cornell University CoCoNUT: Structural Code Understanding does not fall out of a tree (Virtual Talk)
Abhinav BhateleBhatele, Abhinav University of Maryland Understanding Code Properties: Is Code All You Need?
Justin F. BrunelleBrunelle, Justin F. MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
C Paulo CanelasCanelas, Paulo Carnegie Mellon UniversityUnited States Are Large Language Models Memorizing Bug Benchmarks?
Rongyu CaoCao, Rongyu Tongyi Lab, Alibaba, China Do Code LLMs Understand Design Patterns? (Virtual Talk)
Federico CassanoCassano, Federico Cursor AIUnited States Keynote 1: Building the Hybrid Human-AI Developer: From Code Completion to Agents (zoom talk)
Marco ChiesaChiesa, Marco KTH Royal Institute of Technology Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk) From Scientific Texts to Verifiable Code: Automating the Process with Transformers (Virtual Talk) Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Hyunjoon ChoCho, Hyunjoon KAIST COSMosFL: Ensemble of Small Language Models for Fault Localisation
Daniele CipolloneCipollone, Daniele Delft University of TechnologyNetherlands Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Leyi CuiCui, Leyi Columbia UniversityUnited States CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Álvaro CárdenasCárdenas, Álvaro University of California, Santa Cruz With a Little Help from My (LLM) Friends: Enhancing Static Analysis with LLMs to Detect Software Vulnerabilities
D Abdelhalim DahouDahou, Abdelhalim GESIS – Leibniz-Institute for the Social Sciences Evaluating Language Models for Computer Graphics Code Completion
Yuntian DengDeng, Yuntian University of Waterloo Mix-of-Language-Experts Architecture for Multilingual Programming
Prem DevanbuDevanbu, Prem University of California at DavisUnited States Session Chair of Keynote 2 / Paper Session 2 (part of LLM4Code) Opening
Nilesh DhulshetteDhulshette, Nilesh TCS Research Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs (Virtual Talk)
Colin DiggsDiggs, Colin MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Quinn DoughertyDougherty, Quinn Unaffiliated Proving the Coding Interview: A Benchmark for Formally Verified Code Generation
Michael DoyleDoyle, Michael MITRE CorporationUnited States Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Saikat DuttaDutta, Saikat Cornell UniversityUnited States CoCoNUT: Structural Code Understanding does not fall out of a tree (Virtual Talk)
E Emily EscamillaEscamilla, Emily MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
F Farima FarmahinifarahaniFarmahinifarahani, Farima J.P. Morgan AI ResearchUnited States From Zero to Sixty at the Speed of RAG: Improving YAML Recipe Generation via Retrieval
Alireza FarshinFarshin, Alireza NVIDIA Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk)
Simone FerlinFerlin, Simone Red Hat Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Bertram FuchsFuchs, Bertram Siemens AG Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
G Catarina GamboaGamboa, Catarina Carnegie Mellon UniversityPortugal Are Large Language Models Memorizing Bug Benchmarks?
Roman GaraevGaraev, Roman Innopolis University YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
Chris GlaszGlasz, Chris MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Adwait GodboleGodbole, Adwait University of California, Berkeley Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
Juanita GomezGomez, Juanita University of California, Santa Cruz With a Little Help from My (LLM) Friends: Enhancing Static Analysis with LLMs to Detect Software Vulnerabilities
Wang GuanlinGuanlin, Wang National University of Singapore Analysis of Student-LLM Interaction in a Software Engineering Project
H Aaron HaagHaag, Aaron Siemens AG Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
Mengting HeHe, Mengting The Pennsylvania State University SC-Bench: A Large-Scale Dataset for Smart Contract Auditing
Md Sifat HossainHossain, Md Sifat University of Dhaka LLM-ProS: Analyzing Large Language Models’ Performance in Competitive Problem Solving
Kele HuangHuang, Kele Columbia University CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
I Vladimir IvanovIvanov, Vladimir Innopolis University Code Summarization Beyond Function Level (Virtual Talk) YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
Ganesh Neelakanta IyerIyer, Ganesh Neelakanta National University of Singapore Analysis of Student-LLM Interaction in a Software Engineering Project
Maliheh IzadiIzadi, Maliheh Delft University of TechnologyNetherlands Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
J Mahmoud JahanshahiJahanshahi, Mahmoud University of TennesseeUnited States Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets
Kush JainJain, Kush Carnegie Mellon UniversityUnited States Are Large Language Models Memorizing Bug Benchmarks?
Naman JainJain, Naman University of California, Berkeley Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
K Altay KacanKacan, Altay Siemens AG Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
Sungmin KangKang, Sungmin KAISTSouth Korea COSMosFL: Ensemble of Small Language Models for Fault Localisation
Jan KelsKels, Jan Heinrich-Heine-Universität DüsseldorfGermany Evaluating Language Models for Computer Graphics Code Completion
Paul KirkKirk, Paul MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Dejan KosticKostic, Dejan KTH Royal Institute of Technology Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk) Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Vinay KulkarniKulkarni, Vinay Tata Consultancy Services ResearchIndia Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs (Virtual Talk)
L Claire Le GouesLe Goues, Claire Carnegie Mellon University Are Large Language Models Memorizing Bug Benchmarks?
Hyunseok LeeLee, Hyunseok KAIST METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries
Binhua LiLi, Binhua Tongyi Lab, Alibaba, China Do Code LLMs Understand Design Patterns? (Virtual Talk)
Yongbin LiLi, Yongbin Tongyi Lab, Alibaba, China Do Code LLMs Understand Design Patterns? (Virtual Talk)
Han LiuLiu, Han Northwestern University Do Code LLMs Understand Design Patterns? (Virtual Talk)
Xiaomo LiuLiu, Xiaomo J.P. Morgan AI Research From Zero to Sixty at the Speed of RAG: Improving YAML Recipe Generation via Retrieval
Oliver LohseLohse, Oliver Siemens AG Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
Vadim LomshakovLomshakov, Vadim JetBrains YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
M William MackeMacke, William MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Amit MadanMadan, Amit MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Vladimir MakharevMakharev, Vladimir Innopolis University, AIRIRussia Code Summarization Beyond Function Level (Virtual Talk)
Claudia MamedeMamede, Claudia Carnegie Mellon UniversityPortugal Are Large Language Models Memorizing Bug Benchmarks?
Brigitte MathiakMathiak, Brigitte GESIS – Leibniz-Institute for the Social Sciences Evaluating Language Models for Computer Graphics Code Completion
Ronak MehtaMehta, Ronak Unaffiliated Proving the Coding Interview: A Benchmark for Formally Verified Code Generation
Audris MockusMockus, Audris University of Tennessee Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets
Martin MonperrusMonperrus, Martin KTH Royal Institute of TechnologySweden RepairBench: Leaderboard of Frontier Models for Program Repair
Amy MunsonMunson, Amy University of California, San Diego With a Little Help from My (LLM) Friends: Enhancing Static Analysis with LLMs to Detect Software Vulnerabilities
N Nitin NaikNaik, Nitin MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Agrawal NamanNaman, Agrawal National University of Singapore Analysis of Student-LLM Interaction in a Software Engineering Project
Naveed NekooNekoo, Naveed MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Daniel NicholsNichols, Daniel University of Maryland Understanding Code Properties: Is Code All You Need?
Pengyu NieNie, Pengyu University of WaterlooCanada Mix-of-Language-Experts Architecture for Multilingual Programming
P Zhenyu PanPan, Zhenyu Northwestern University Do Code LLMs Understand Design Patterns? (Virtual Talk)
Anand PatelPatel, Anand MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Chao PengPeng, Chao ByteDanceChina Session Chair of Paper Session 3 (part of LLM4Code)
Jinjun PengPeng, Jinjun Columbia University CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Jasper PhillipsPhillips, Jasper MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Irina PionkovskayaPionkovskaya, Irina Huawei Noah's Ark Lab YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
Sanyogita PiyaPiya, Sanyogita The University of Texas at Arlington Is More or Less Automation Better? An Investigation into the LLM4TDD Process (Virtual Talk)
Ofir PressPress, Ofir Princeton University Keynote 2: Towards Autonomous Language Model Systems (zoom talk)
Laura PuccioniPuccioni, Laura Spotify Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk)
Srivishnu PydaPyda, Srivishnu University of Maryland Understanding Code Properties: Is Code All You Need?
R Mona RahimiRahimi, Mona Dept. of Computer Science at the Northern Illinois University From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks (Virtual Talk)
Daniel RamosRamos, Daniel Carnegie Mellon University Are Large Language Models Memorizing Bug Benchmarks?
Sanka RasnayakaRasnayaka, Sanka National University of Singapore Analysis of Student-LLM Interaction in a Software Engineering Project
Baishakhi RayRay, Baishakhi Columbia UniversityUnited States CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Zachary RobinRobin, Zachary MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Scott RosenRosen, Scott MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
S Anahita SamadiSamadi, Anahita The University of Texas at Arlington Is More or Less Automation Better? An Investigation into the LLM4TDD Process (Virtual Talk)
Mariano ScazzarielloScazzariello, Mariano RISE Research Institutes of Sweden Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk) From Scientific Texts to Verifiable Code: Automating the Process with Transformers (Virtual Talk) Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Siggy ScottScott, Siggy MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Koushik SenSen, Koushik University of California at BerkeleyUnited States Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
Sanjit A. SeshiaSeshia, Sanjit A. University of California, BerkeleyUnited States Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
Sapan ShahShah, Sapan TCS Research Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs (Virtual Talk)
Ridwan Salihin ShariffdeenShariffdeen, Ridwan Salihin National University of SingaporeSingapore Analysis of Student-LLM Interaction in a Software Engineering Project
Manish ShettyShetty, Manish University of California, BerkeleyUnited States Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
André SilvaSilva, André KTH Royal Institute of TechnologySweden RepairBench: Leaderboard of Frontier Models for Program Repair
Linhai SongSong, Linhai The Pennsylvania State University SC-Bench: A Large-Scale Dataset for Smart Contract Auditing
Xuefeng SongSong, Xuefeng Northwestern University Do Code LLMs Understand Design Patterns? (Virtual Talk)
Arun SridharanSridharan, Arun MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Allison SullivanSullivan, Allison University of Texas at ArlingtonUnited States Is More or Less Automation Better? An Investigation into the LLM4TDD Process (Virtual Talk)
Mohammed Murtuza Shahzad SyedSyed, Mohammed Murtuza Shahzad Northern Illinois University From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks (Virtual Talk)
T Anika TabassumTabassum, Anika University of Dhaka LLM-ProS: Analyzing Large Language Models’ Performance in Competitive Problem Solving
Samruddhi ThakerThaker, Samruddhi MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
U Paul UrsinoUrsino, Paul MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
V Vishal VaddinaVaddina, Vishal Quantiphi Inc. Knowledge Graph Based Repository-Level Code Generation (Virtual Talk)
Aidar ValeevValeev, Aidar Innopolis University YABLoCo: Yet Another Benchmark for Long Context Code Generation (Virtual Talk)
W Changjie WangWang, Changjie KTH Royal Institute of Technology Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning (Virtual Talk) From Scientific Texts to Verifiable Code: Automating the Process with Transformers (Virtual Talk) Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Yunkun WangWang, Yunkun Zhejiang University Do Code LLMs Understand Design Patterns? (Virtual Talk)
Zijian WangWang, Zijian AWS AI Labs Session Chair of Opening / Keynote 1 / Paper Session 1 (part of LLM4Code) Opening
Doug WendtWendt, Doug MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Joseph WilsonWilson, Joseph Northern Illinois University From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks (Virtual Talk)
X Shihao XiaXia, Shihao The Pennsylvania State University SC-Bench: A Large-Scale Dataset for Smart Contract Auditing
Y Junfeng YangYang, Junfeng Columbia UniversityUnited States CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Shin YooYoo, Shin KAISTSouth Korea METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries COSMosFL: Ensemble of Small Language Models for Fault Localisation
Z Tarannum Shaila ZamanZaman, Tarannum Shaila University of Maryland Baltimore CountyUnited States LLM-ProS: Analyzing Large Language Models’ Performance in Competitive Problem Solving
Lingming ZhangZhang, Lingming University of Illinois at Urbana-Champaign Session Chair of Paper Session 4 / Virtual Talk / Award Session & Closing (part of LLM4Code) Opening
Yiying ZhangZhang, Yiying University of California San Diego SC-Bench: A Large-Scale Dataset for Smart Contract Auditing
Jacob ZimmerZimmer, Jacob MITRE Corporation Leveraging LLMs for Legacy Code Modernization: Evaluation of LLM-Generated Documentation (Virtual Talk)
Yifan ZongZong, Yifan University of Waterloo Mix-of-Language-Experts Architecture for Multilingual Programming