Yun Peng

Dr. Yun Peng is an Assistant Professor in the Department of Computer Science and Engineering at The Chinese University of Hong Kong, specializing in software engineering with a focus on intelligent code analysis, automatic program repair, and software ecosystems. With an active research profile, Dr. Peng serves on program committees for major conferences including ASE and ESEC/FSE.

Dr. Peng's educational background includes doctoral training focused on programming languages and software engineering, though specific institutions aren't detailed in the available information. Their research primarily addresses challenges in type inference, code analysis, and the application of large language models to software engineering tasks.

Research interests center on intelligent code analysis techniques, particularly in type inference systems for dynamic languages like Python. Dr. Peng has pioneered hybrid approaches combining static analysis with deep learning, as demonstrated in their influential ICSE 2022 paper on HiTyper. Recent work has shifted toward leveraging large language models for code review, program repair, and API recommendation, reflecting the field's evolution. Current projects examine LLM applications in secure code review, code efficiency optimization, and vulnerability detection in smart contracts.

Dr. Peng's publication record shows a clear progression from foundational type inference research toward cutting-edge LLM applications in software engineering. The work spans multiple dimensions of code quality including security, performance, and maintainability, with tools like HiTyper, TypeGen, and APIBench making significant contributions to the research community.

As a program committee member for top-tier conferences, Dr. Peng actively contributes to the software engineering research community. Their work has been recognized through publication in premier venues including ICSE, ASE, and ESEC/FSE, demonstrating consistent high-impact contributions to the field.

Dr. Peng maintains an active research group focused on advancing the state of the art in intelligent code analysis, with current projects exploring the intersection of large language models and traditional program analysis techniques. The research has practical applications in developer productivity tools, security analysis systems, and software maintenance automation.