Kexin is an Assistant Professor of computer science. His research lies at the intersection of Security, Software Engineering, and Machine Learning, focusing on developing data-driven program analysis approaches to improve the security and reliability of traditional and AI-based software systems. He gets most excited about developing machine learning models that can reason about program structure and behavior to precisely and efficiently analyze, detect, and fix software bugs and vulnerabilities.
His research has received the Best Paper Award in SOSP, a Distinguished Artifact Award, been featured in CACM Research Highlight, and won CSAW Applied Research Competition Runner-Up. He works with Learning for Code team at Google DeepMind, building program analysis tools based on large language models. Kexin received his Ph.D. in Computer Science from Columbia University.
Focus Areas: Machine Learning for Code, Program Analysis, Software Security and Reliability
