About me

I am a Senior Research Fellow at Lero, the Irish software research center, directed by Prof. Lionel C. Briand.

At Lero I am the Technical Lead and primary academic contact for the €550K Lero × Genesys industry project on hallucination detection, safety compliance, and runtime guardrails for LLM customer-service agents. I co-wrote its funding proposal and line-manage the project's Research Fellow. CXBench, developed in this project, is used by Genesys to test its AI virtual agent.

I obtained my Ph.D. from the Chinese University of Hong Kong, Shenzhen in 2025, supervised by Prof. Pinjia He.

My research focuses on trustworthy AI, coding agents, and automated testing. I proposed Retromorphic Testing, a technique for automatically constructing test oracles. My work has appeared at ICML, ICSE, ISSTA, ESEC/FSE, and ACL.

My recent work on UTBoost and SWE-ABS investigates how weaknesses in benchmark tests can inflate the measured success of coding agents. Earlier work develops automated testing methods for image captioning and named entity recognition, and examines the trade-offs between classical and deep learning models for log anomaly detection.

Research and community

• Complete publications
• Academic service and reviewing
• Talks
• Teaching & supervision