Publications

Preprint

2025

• [ICSE’25] Search-Based LLMs for Code Optimization (CCF-A)
  Shuzheng Gao, Cuiyun Gao, Wenchao Gu and Michael R. Lyu
  The 47th International Conference on Software Engineering, April 27- May 3, 2025, Ottawa, Ontario, Canada
  [Arxiv] | [code] | ACM SIGSOFT Distinguished Paper Award

• [FSE’25] Beyond PEFT: Layer-Wise Optimization for More Effective and Efficient Large Code Model Tuning (CCF-A)
  Chaozheng Wang, Jia Feng, Shuzheng Gao, Cuiyun Gao, Zongjie Li, Ting Peng, Hailiang Huang, Yuetang Deng, and Michael R. Lyu
  The ACM International Conference on the Foundations of Software Engineering, Mon 23 - Fri 27 June 2025 Trondheim, Norway

• [FSE’25 Industry] RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry
  Chaozheng Wang, Zezhou Yang, Shuzheng Gao, Cuiyun Gao, Ting Peng, Hailiang Huang, Yuetang Deng, and Michael R. Lyu
  The ACM International Conference on the Foundations of Software Engineering (Industry Track), Mon 23 - Fri 27 June 2025 Trondheim, Norway

• [Under Review] The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
  Shuzheng Gao, Chaozheng Wang, Cuiyun Gao, Xiaoqian Jiao, Chun Yong Chong, Shan Gao and Michael R. Lyu
  [Arxiv]

2024

• [ASE’24] A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How. (CCF-A)
  Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Wenxuan Wang, Chun Yong Chong, Shan Gao and Michael R. Lyu
  The 39th IEEE/ACM International Conference on Automated Software Engineering, October 27-November 1, 2024, Sacramento, California, United States [Arxiv]

• [ISSTA’24] SCALE: Constructing Symbolic Comment Trees for Software Vulnerability Detection (CCF-A)
  Xin-Cheng Wen, Cuiyun Gao, Shuzheng Gao, Yang Xiao and Michael R. Lyu
  The 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, September 16-20, 2024, Vienna, Austria
  [Arxiv] | [Code]

• [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
  The 46th International Conference on Software Engineering, April 14-20, 2024, Lisbon, Portugal
  [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
  The 46th International Conference on Software Engineering, April 14-20, 2024, Lisbon, Portugal
  [Arxiv] | [Code] | Accept Rate 6.6%

2023

• [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
  The 38th International Conference on Automated Software Engineering, September 11-15, 2023, Kirchberg, Luxembourg
  [Arxiv] | [Code]

• [ASE’23 Industry Challenge] REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes
  Chaozheng Wang, Zongjie Li, Yun Peng, Shuzheng Gao, Sirong Chen, Shuai Wang, Cuiyun Gao and Michael R. Lyu
  The 38th International Conference on Automated Software Engineering (Industry Challenge Track), September 11-15, 2023, Kirchberg, Luxembourg
  [Arxiv] | [Code] | Distinguished Paper Award

• [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
  The 45th International Conference on Software Engineering, May 14-20, 2023, Melbourne, Australia
  [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
  The 45th International Conference on Software Engineering, May 14-20, 2023, Melbourne, Australia
  [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
  ACM Transactions on Software Engineering and Methodology
  [Arxiv] | [Code] | Presented as a journal-first paper at ASE 2022

2022

• [TNNLS’22] Label-Aware Distribution Calibration for Long-tailed Classification (CCF-B)
  Chaozheng Wang*, Shuzheng Gao*, Cuiyun Gao, Pengyun Wang, Wenjie Pei, Lujia Pan and Zenglin Xu
  IEEE Transactions on Neural Networks and Learning Systems
  [Arxiv]

• [ACAIT’22] Improving Long-Tailed Classification Via Decoupling and Regularization
  Shuzheng Gao*, Chaozheng Wang*, Cuiyun Gao, Wenjian Luo, Peiyi Han and Qing Liao
  The 6th Asian Conference on Artificial Intelligence Technology, December 9-11, 2022, Changzhou, China
  | Best student paper award

• [TRel’22] Dynamically Relative Position Encoding-Based Transformer for Automatic Code Edit (JCR Q1)
  Shiyi Qi, Yaoxian Li, Cuiyun Gao, Xiaohong Su, Shuzheng Gao, Zibin Zheng and Chuanyi Liu
  IEEE Transactions on Reliability

(* denotes equal contribution.)