Research
Our research focuses on trustworthy automated programming — building reliable and secure software systems through AI. We work at the intersection of software engineering and artificial intelligence, combining formal reasoning with modern machine learning techniques to make software development safer and more productive.
Research Areas
Trustworthy LLMs for Code
Evaluating and improving the reliability, security, and correctness of large language models used for code synthesis and analysis.
Automated Program Repair
Developing AI-driven techniques for automated bug detection and repair, including patch correctness assessment and fault localization.
Software Security
Analyzing vulnerabilities in modern software systems, including vulnerability-fixing commit classification and security testing.
Software Engineering for AI
Applying software engineering principles to improve AI systems — testing, debugging, and formal verification of ML models.