Jia Li (李佳)
Portrait

I am the tenure-track 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. Nowadays, I am working closely with Prof. Shi-Min Hu and Fitten Code.

I lead the Tsinghua Intelligent Software Engineering (TISE) Lab. Our lab explores AI techniques (such as Code LLMs and Coding Agents) for automating software engineering, especially for industrial large-scale software projects. We are dedicated to producing useful research that brings real-world economic benefits.

I am looking for highly-motivated interns to join my research group. In our research group, you can encounter real-world problems, and your research may have the opportunity to be applied practical products and used by millions of developers worldwide. Feel free to email me with your resume attached.

Google Scholar GitHub Twitter ORCID
News
2025
Our paper (DAVSP) has been accepted by AAAI 2026.
Nov 08
Our paper (AdapTrack) has been accepted by ICSE 2026.
Oct 16
Our paper (M2CVD) has been accepted by TOSEM 2025.
Oct 09
Our paper (aiXcoder-7B-v2) has been accepted by ASE 2025.
Sep 26
Congratulations! Four of our papers were accepted by NeurIPS 2025, including one Spotlight and three Poster papers!
Sep 19
I joined the College of AI at Tsinghua University as an assistant professor!
Aug 01
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.
Feb 28
Selected Publications (view all )
SATURN: SAT-based Reinforcement Learning to Unleash Language Model Reasoning

Huanyu Liu, Jia Li, Hao Zhu, Yihong Dong, Kechi Zhang, Ge Li

The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Just Accepted, 2025 Spotlight (3.2%)

[Paper] [Code]

SATURN: SAT-based Reinforcement Learning to Unleash Language Model Reasoning

Huanyu Liu, Jia Li, Hao Zhu, Yihong Dong, Kechi Zhang, Ge Li

The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Just Accepted, 2025 Spotlight (3.2%)

[Paper] [Code]

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), Pages 215-226, 2025 Oral

[Paper] [Code]

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), Pages 215-226, 2025 Oral

[Paper] [Code]

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

[Paper] [Data]

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

[Paper] [Data]

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

[Paper]

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

[Paper]

All publications