Kaiyao Ke 柯凯耀

I am a first year Ph.D. student in Computer Science at the University of California, Berkeley, where I work with Prof. Koushik Sen as a member of the Berkeley Sky Computing Lab. My research interest lies in AI for software engineering, particularly in the integration of large language models for automatic program repair and code translation.

Before joining Berkeley, I obtained my M.S. in Computer Science from the University of Illinois Urbana-Champaign, where I worked on software testing with Prof. Darko Marinov, focusing on flaky tests and test case prioritization.
I also worked with Prof. Reyhaneh Jabbarvand on neuro-symbolic models for software engineering, particularly on code translation.

You can view my publications page for more details about my research and academic work.

Outside research, I’m interested in the intersection of programming languages and AI, and I enjoy exploring new tools that improve developer productivity and software reliability.

📄 Download my CV

news

Nov 26, 2025	Our new work TRAM has been arXived.
May 14, 2025	Graduated from the University of Illinois Urbana-Champaign. A great 6-year journey!
Mar 10, 2025	Our work pytest-ranking has been accepted at FSE ‘25 Demo Track
Jan 22, 2025	Our work NIODebugger has been accepted at ICSE ‘25

selected publications

Kaiyao Ke, Ali Reza Ibrahimzada, Rangeet Pan, Saurabh Sinha, Reyhaneh Jabbarvand

Advancing Automated In-Isolation Validation in Repository-Level Code Translation

arXiv preprint arXiv:2511.21878

[link] [PDF]
Kaiyao Ke

NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent

Proceedings of the IEEE/ACM 47th International Conference on Software Engineering (ICSE 2025)

Acceptance Rate: 21.30% (245/1150)

[link] [PDF] [Slides]
Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid, Rangeet Pan, Saurabh Sinha, Reyhaneh Jabbarvand

AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering (FSE 2025)

Acceptance Rate: 22.06% (135/612)

[link] [PDF] [Slides]
Runxiang Cheng, Kaiyao Ke, Darko Marinov

pytest-ranking: A Regression Test Prioritization Tool for Python

Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, Demo Track (FSE Demo 2025)

Acceptance Rate: 64.06% (41/64)

[link] [PDF] [Slides]
Kaiyao Ke, Darko Marinov

Evaluating NonDex for Modern Java Ecosystem

Proceedings of the 2nd IEEE/ACM International Flaky Tests Workshop (FTW 2025)

[link] [PDF] [Slides]