Shuzheng Gao

Shuzheng Gao

The first year Ph.D. student @ARISE, CUHK, advised by Prof. Michael R. Lyu.

About Me

I’m a first-year Ph.D. student at the Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), advised by Prof. Michael R. Lyu. I got my Master’s degree from Harbin Institute of Technology Shenzhen in June 2023, under the supervision of Prof. Cuiyun Gao. Before that, I received my Bachelor’s degree from Harbin Institute of Technology Weihai in June 2021. My research interests mainly focus on software engineering and code intelligence.

My research mainly focuses on software engineering and code intelligence. Code Intelligence leverages artificial intelligence techniques to analyze and generate source code, which could benefit a variety of software engineering activities and tasks such as program repair, defect detection, code summarization, etc. Besides, I also have a wide interest in the development of code intelligence models in real-world scenarios and the development of Large Language Models (LLMs) for software engineering. Specifically, my research interest lies in the span of the following topics: 1. Code analysis and generation: code representation learning, code generation, static analysis 2. Code intelligence in real-world scenarios: robustness, data imbalance, continual learning 3. LLM for software engineering: in-context learning, chain of thought, tool using

News

  • 2024.3 🎉🎉 One Paper “SCALE: Constructing Symbolic Comment Trees for Software Vulnerability Detection” is accepted by ISSTA 2024!
  • 2023.12 🎉🎉 One Paper “Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code Models” is accepted by ICSE 2024!
  • 2023.07 🎉🎉 One Paper “What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?” is accepted by ASE 2023!
  • 2023.06 🎉🎉 One Paper “Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors” is accepted by ICSE 2024!
  • 2022.12 🎉🎉 Two papers “Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension” and “Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models” are accepted by ICSE 2023!

Selected Publications

  • [ICSE’24] Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code Models (CCF-A)
    Shuzheng Gao, Wenxin Mao, Cuiyun Gao, Li Li, Xing Hu, Xin Xia and Michael R. Lyu

  • [ASE’23] What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs? (CCF-A)
    Shuzheng Gao, Xin-Cheng Wen, Cuiyun Gao, Wenxuan Wang, Hongyu Zhang and Michael R. Lyu | [Arxiv] | [Code]

  • [ICSE’24] Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors (CCF-A)
    Yun Peng, Shuzheng Gao, Cuiyun Gao, Yintong Huo and Michael R. Lyu | [Arxiv] | [Code]

  • [ICSE’23] Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension (CCF-A)
    Shuzheng Gao, Cuiyun Gao, Chaozheng Wang, Jun Sun, David Lo and Yue Yu | [Arxiv] | [Code]

  • [ICSE’23] Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models (CCF-A)
    Shuzheng Gao, Hongyu Zhang, Cuiyun Gao and Chaozheng Wang | [Arxiv] | [Code]

  • [TOSEM’23] Code Structure Guided Transformer for Source Code Summarization (CCF-A)
    Shuzheng Gao, Cuiyun Gao, Yulan He, Jichuan Zeng, Lun Yiu Nie, Xin Xia and Michael R. Lyu | [Arxiv] | [Code]

Selected Awards

  • Postgraduate Studentship Award, CUHK, 2023
  • Distinguished Paper Award, ASE-Inch, 2023
  • Binxing Fang Scholarship, 2023
  • Best Student Paper Award, ACAIT, 2022
  • Outstanding Graduates of Harbin Institute of Technology, 2021
  • National Scholarship, Ministry of Education, 2019