image.png

Contact me:

<aside> <img src="/icons/mail_gray.svg" alt="/icons/mail_gray.svg" width="40px" /> Email

</aside>

<aside> <img src="/icons/graduate_gray.svg" alt="/icons/graduate_gray.svg" width="40px" /> Google Scholar

</aside>

<aside> <img src="/icons/git_gray.svg" alt="/icons/git_gray.svg" width="40px" /> Github

</aside>

News:

<aside>

</aside>

I'm Hao Zhu ("朱浩" in Chinese), currently a first-year Ph.D. candidate in the Key Laboratory of High Confidence Software Technologies (Ministry of Education) at the School of Computer Science, Peking University, Beijing, China. I'm fortunate to work under the supervision of Prof. Ge Li. My undergraduate degree is in Software Engineering from Soochow University.

My research focuses on code security analysis (vulnerability detection, secure code generation) and intelligent software development, including Large Language Models (LLMs) for code.

Publications

( * : equal contribution, † : corresponding author )


<aside> 💡

aiXcoder Series: My Contributions to State-of-the-Art Code Completion Models

aiXcoder is currently a SOTA (state-of-the-art) llm model for code completion tasks. This model was pretrained from scratch and after post-training, version 2.0 was released. In this project, I participated in the pretraining of aiXcoder from scratch, and was primarily responsible for the post-training of aiXcoder 2.0.

</aside>

aiXcoder-7B-v2: Training LLMs to Fully Utilize the Long Context in Repository-level Code Completion

Jia Li*, Hao Zhu*, Huanyu Liu*, Xianjie Shi, He Zong, Yihong Dong, Kechi Zhang, Siyuan Jiang, Zhi Jin, Ge Li†

arXiv preprint. 2025.

[Paper][Code][🤗Model]

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†

ICSE 2025

[Paper][Code][🤗Model]

FANformer: Improving Large Language Models Through Effective Periodicity Modeling

Yihong Dong, Ge Li†, Xue Jiang, Yongding Tao, Kechi Zhang, Hao Zhu, Huanyu Liu, Jiazheng Ding, Jia Li, Jinliang Deng, Hong Mei

Under Review, 2025

[Paper][Code][🤗Model]

DevEval: Evaluating Code Generation in Practical Software Projects

Jia Li, Ge Li† , Yunfei Zhao, Yongmin Li, Zhi Jin, Hao Zhu, Huanyu Liu, Kaibo Liu, Lecheng Wang, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yihong Dong, Yuqi Zhu, Bin Gu, Mengfei Yang

ACL 2024

[Paper][Code][🤗Dataset]

Generating Equivalent Representations of Code By A Self-Reflection Approach

Jia Li, Ge Li† , Lecheng Wang, Hao Zhu, Zhi Jin

arXiv preprint. 2024.

[Paper]