Jia Li (李佳)

I am the Assistant Professor of College of AI at Tsinghua University. I obtained my PhD degree from Peking University in 2025, supervised by Prof. Zhi Jin and Prof. Ge Li.

My goal is to make more secure AIware (the future software built by source code and AI). Specifically, my research directions include:

  • AI Safety, identifying and defending against the safety risks of AI in real-world applications, such as jailbreaking attacks, poisoning attacks, and safety alignment.
  • Software Security, leveraging AI to detect and repair the code defects and vulnerabilities of real-world software projects, such as test generation, fuzzing, and code vulnerability detection.

I am looking for highly-motivated interns to join my research group. Feel free to email me with your resume attached. 长期招收线上/线下科研实习生,可提供工位、定期一对一讨论,欢迎优秀本科生和研究生联系我,请附带上简历。


News
2025
I passed the defense of my PhD thesis!
May 22
Congratulation, our two papers are accepted by ACL 2025!
May 16
Our paper Line-level Semantic Structure Learning for Code Vulnerability Detection has been accepted by Internetware 2025.
Apr 16
Our paper Escalating LLM-based Code Translation Benchmarking into the Class-level Era has been accepted by ISSTA 2025.
Mar 02
Our paper Large Language Model-Aware In-Context Learning for Code Generation has been accepted by TOSEM 2025.
Jan 02
Selected Publications (view all )
aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing

Siyuan Jiang*, Jia Li*, He Zong, Huanyu Liu, Hao Zhu, Shukai Hu, Erlu Li, Jiazheng Ding, Yu Han, Wei Ning, Ge Li (* equal contribution)

The 47th International Conference on Software Engineering (ICSE 2025 SEIP Track), 2025 Oral

aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing

Siyuan Jiang*, Jia Li*, He Zong, Huanyu Liu, Hao Zhu, Shukai Hu, Erlu Li, Jiazheng Ding, Yu Han, Wei Ning, Ge Li (* equal contribution)

The 47th International Conference on Software Engineering (ICSE 2025 SEIP Track), 2025 Oral

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

Jia Li, Ge Li, Xuanming Zhang, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li

The 38th Conference on Neural Information Processing Systems (NeurIPS 2024 D&B Track), 2024

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

Jia Li, Ge Li, Xuanming Zhang, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li

The 38th Conference on Neural Information Processing Systems (NeurIPS 2024 D&B Track), 2024

Structured Chain-of-Thought Prompting for Code Generation

Jia Li, Ge Li, Yongmin Li, Zhi Jin

ACM Transactions on Software Engineering and Methodology (TOSEM), Volume 34, Issue 2, Pages 1-23, 21 January 2025

Structured Chain-of-Thought Prompting for Code Generation

Jia Li, Ge Li, Yongmin Li, Zhi Jin

ACM Transactions on Software Engineering and Methodology (TOSEM), Volume 34, Issue 2, Pages 1-23, 21 January 2025

All publications