Wenchao GU ☕️
Wenchao GU

Postdoctoral Fellow

About Me

Wenchao Gu is a postdoctoral fellow at the TUM School of Computation, Information and Technology at Technische Universität München (TUM), working with Prof. Chunyang Chen. He received his PhD from The Chinese University of Hong Kong (CUHK) in early 2024, under the supervision of Prof. Michael R. Lyu. From July 2021 to January 2022, he interned at Microsoft Research Asia (MSRA), where he was supervised by Prof. Yanlin Wang. Prior to his time at CUHK, he was a master’s student at the Graduate School of Information Sciences at Tohoku University from 2015 to 2017, supervised by Prof. Konyo Masashi. Before his master’s degree, he completed his bachelor’s degree in the Department of Mechanical and Aerospace Engineering at Tohoku University from 2012 to 2015 and earned the qualification for early graduation.

His primary research interests include Artificial Intelligence for Software Engineering, particularly large language models, source code understanding and analysis, code generation, and vulnerability detection.

Download CV
Interests
  • Artificial Intelligence
  • Software Engineering
  • Computational Linguistics
  • Information Retrieval
Education
  • PhD Computer Science and Engineering

    The Chinese University of Hong Kong

  • Msc Information Science

    Tohoku University

  • B.Eng Mechanical and Aerospace Engineering

    Tohoku University

📚 My Research

My research interests lie at the intersection of Artificial Intelligence and Software Engineering, with a focus on leveraging large language models to advance the field. I work on applying AI techniques to automate and enhance software development processes, making production more efficient and reliable. I am particularly interested in using large language models to assist in writing code, documenting projects, and debugging. Additionally, I develop tools for better understanding and analyzing source code, which helps in maintaining and improving software systems. My research also includes generating new, functional code snippets or entire programs based on high-level specifications. Ensuring software security is another critical aspect of my work; I create AI-driven methods to detect vulnerabilities, helping to identify and mitigate potential security risks. Throughout my academic journey, I have aimed to bridge the gap between theoretical research and practical applications, striving to make software engineering more intelligent, automated, and secure.

Please reach out to collaborate 😃

Featured Publications
Recent Publications
(2024). XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection. In ACL 2024.
(2023). CoCoSoDa: Effective Contrastive Learning for Code Search. In ICSE 2023.
(2023). A transformer‐based approach for improving app review response generation. SPE.
(2022). Accelerating code search with deep hashing and code classification. In ACL 2022.
(2022). Source Code Summarization with Structural Relative Position Guided Transformer. In SANER 2022.
Recent News