He Ye | Assistant Professor at UCL

This is Ye! I am a Lecturer (equivalent to Assistant Professor) in the Department of Computer Science at University College London. My research in multimodal agentic coding focuses on making programming more efficient and accessible. Specifically, I work on large language models (LLMs) for code generation, test generation, and GitHub issue repair. Previously, I was a postdoctoral researcher at Carnegie Mellon University (2023-2025), where I worked with Prof. Claire Le Goues. I completed my Ph.D. at KTH Royal Institute of Technology, advised by Prof. Martin Monperrus and Prof. Benoit Baudry, and completed my B.S. degree from Sichuan University.

We are organizing the LMPL@SPLASH 2025 workshop and the APR@ICSE 2025 workshop, we look forward to your submissions!

News

• 🎉 01/2025, our work LWDIFF was accepted to the ICSE 2025 research track!
• 🎉 01/2025, I will serve on the Program Committee of ICSE 2026, ASE 2025, SDLC 2025, SWGeno 2025, please consider submitting your papers!
• 🎉 03/2024, we received a GPU grant Berzelius-2024-131 from The National Academic Infrastructure for Supercomputing in Sweden (NAISS).
• 🎉 01/2024, my PhD dissertation received The Best Thesis of The Year Award (one recipient per year among five Swedish Universities affiliated with WASP)!
• 🎉 11/2023, I was invited to attend Dagstuhl Seminar on “Automated Programming and Program Repair”, excited to see you at Schloss Dagstuhl in October 2024!
• 🎉 09/2023, our work PreciseBugCollector received IEEE Distinguished Paper Award in ASE Industry Challenge Competition!

Publications

Please check my full publication list in Google Scholar.

• [ICSE 2025] Shiyao Zhou, Jincheng Wang, He Ye, Hao Zhou, Claire Le Goues, Xiapu Luo. LWDIFF: An LLM-Assisted Differential Testing Framework for WebAssembly Runtimes [Paper]
• [Preprint] Aidan Z.H. Yang, Haoye Tian, He Ye, Ruben Martins, Claire Le Goues. Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models [Paper]
• [ICSE 2024] He Ye, and Martin Monperrus. ITER: Iterative Neural Repair for Multi-Location Patches. Accepted to the 46th International Conference on Software Engineering, 2024.[Paper] [Data]
• [AAAI 2024] Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, Yanlin Wang. MemoryBank: Enhancing Large Language Models with Long-Term Memory. Proceedings of the 38th AAAI Conference on Artificial Intelligence, 2024. [Paper][Code]
• [ASE 2023 Industry Challenge] He Ye, Zimin Chen, Claire Le Goues. PreciseBugCollector: Extensible, Executable and Precise Bug-fix Collection. Accepted to the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) Industry Challenge Competition, 2023. [Paper] [Code] Distinguished Paper Award 🏆
• [FSE 2023] Kunsong Zhao, Zihao Li, Jianfeng Li, He Ye, Xiapu Luo, Ting Chen. DeepInfer: Deep Type Inference from Smart Contract Bytecode. Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2023. [Paper][Code]
• [ASE 2022] He Ye, Matias Martinez, Xiapu Luo, Tao Zhang, and Martin Monperrus. SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics. In Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering. Article 92, pages 1–13, 2022. [Paper] [Code]
• [ICSE 2022] He Ye, Matias Martinez, and Martin Monperrus. Neural Program Repair with Execution-based Backpropagation. In Proceedings of the 44th International Conference on Software Engineering, pages 1506–1518, 2022. [Paper] [Code]
• [TSE 2022, FSE 2022 Journal-first] He Ye, Jian Gu, Matias Martinez, Thomas Durieux and Martin Monperrus. Automated Classification of Overfitting Patches With Statically Extracted Code Features. In IEEE Transactions on Software Engineering, vol. 48, no. 8, pages 2920-2938. 2022. [Paper][Code]
• [EMSE 2021, FSE 2021 Journal-first] He Ye, Matias Martinez, and Martin Monperrus. Automated Patch Assessment for Program Repair at Scale. Empirical Software Engineering, Volume 26, No. 2, 38 pages, 2021. [Paper] [Code]
• [JSS 2021, SANER IBF 2019] He Ye, Matias Martinez, Thomas Durieux, Martin Monperrus. A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmark. Journal of Systems and Software (JSS), Volume 171, 2021. [Paper] [Code] Best Paper Award 🏆
• [IEEE Software 2021] Benoit Baudry, Zimin Chen, Khashayar Etemadi, Han Fu, Davide Ginelli, Steve Kommrusch, Matias Martinez, Martin Monperrus, Javier Ron, He Ye, Zhongxing Yu (Equal Contribution, Sorted by Alphabetical Order). A software-repair robot based on continual learning. IEEE Software, Volume 4, pages 28-35, 2021.

Contact

• Email: he[DOT]ye[AT]ucl[DOT]ac[DOT]uk

Grants

• WASP International Academic Visit Grant 2021-2022, 100,000 SEK (Solo PI).
• 2023 NAISS GPU Grant Berzelius-2023-175 - NVIDIA SuperPOD consisting of 94 DGX-A100 nodes (PI).
• 2024 NAISS GPU Grant Berzelius-2024-131 - NVIDIA SuperPOD consisting of 94 DGX-A100 nodes (PI).
• SIGSOFT CAPS travel grant to attend ICSE 2024 Conference.

Awards and Honors

• 3rd place at ICSE 2024 Automated Program Repair Competition in the Java bug AI track.
• Best Thesis of The Year Award in 2023 (one recipient per year among 5 Swedish Universities affiliated with WASP).
• Distinguished Paper Award by IEEE ASE 2023 Industry Challenge Competition, earning a prize of 7,000 EURO.
• Best Paper Award by IEEE SANER International Bug Fixing (IBF) in 2019.

Services

Program Committee:

• ICSE Research Track (2025,2026);
• FSE Research Track (2026)
• ASE Research Track (2024,2025)
• MSR Technical Track (2024);
• SANER Demo Track (2023)

Journal Reviewer:

• TSE (2022,2023,2024); TOSEM (2023,2024); TDSC (2022,2023,2024); EMSE(2024)
• Elsevier SCP (2023); Elsevier IST (2023); ASE Journal (2024)

Organizing Committee:

• Program Co-chair of LMPL@SPLASH 2025 workshop
• Program Co-chair of APR@ICSE 2025 workshop
• Proceedings Co-chair of Internetware 2024.
• Publicity Co-chair of APSEC 2024.

PhD Defense

I will always be grateful to my supervisors: Martin, Benoit and Matias, and to my jury committee:

• Prof. Baishakhi Ray (Columbia University),
• Prof. Nicole Novielli (University of Bari),
• Prof. Robert Feldt (Chalmers University of Technology in Gothenburg),
• Prof. Sergey Mechtaev (University College London).

Thank you all for making it happen!