Hi. I’m Jie Wu, a second-year M.S. student at Tsinghua with Prof. Yang.

I am working for Code AGI, under the advice of Xin Zhang.

Education

• Aug. 2024 - Jun. 2027 M.Sc., SIGS, Tsinghua University, Shenzhen, China.

• Sep. 2020 - Jun. 2024 B.Sc., School of Computer Science, Wuhan Univeristy, China.
  GPA: 3.98/4.0, Rank: 1/226

Publications

🧑‍💻 Code-focused Works

• [Preprint 2025 (#1 Paper of the day)] PRG: A Repository Planning Graph for Unified and Scalable Codebase Generation
  Jane Luo*, Xin Zhang*, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang
  📝 Generating your repository from scratch with repository planning graph.

• [Preprint 2025 (#1 Paper of the day)] ASE: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code [code]
  Keke Lian*, Bin Wang*, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Jiazheng Quan, Yilu Zhong, Chenhao He, Zichuan Chen, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang
  🛡️ A repository-level benchmark for comprehensively and reliably assessing the security of AI-generated code.

• [EMNLP 2025 Main] Teaching Your Models to Understand Code via Focal Preference Alignment [code]
  Jie Wu, Haoling Li*, Xin Zhang*, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li
  🔧 Leveraging the idea of iterative debugging to refine Code LLM through focused alignment on critical error tokens.

• [ICML 2025] EpiCoder: Encompassing Diversity and Complexity in Code Generation [code]
  Yaoxiang Wang*, Haoling Li*, Xin Zhang*, Jie Wu, Xiao Liu, Wenxiang Hu, Zhongxin Guo, Yangyu Huang, Ying Xin, Yujiu Yang, Jinsong Su, Qi Chen, Scarlett Li
  🌳 A novel feature tree-based synthesis framework for generating diverse and complex code instruction data.

🤝 Collaborative Works

• [EMNLP 2025 Main] ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models [code]
  Jiani Guo*, Jie Wu*, Zuchao Li, Qianren Wang, Yun Li, Lefei Zhang, Hai Zhao, Yujiu Yang

• [NeurIPS 2025] PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning [code]
  Yizhen Zhang*, Yang Ding*, Shuoshuo Zhang*, Xinchen Zhang, Haoling Li, Zhong-zhi Li, Peijie Wang, Jie Wu, Lei Ji, Yelong Shen, Yujiu Yang, Yeyun Gong

• [NeurIPS 2024 LMC (oral)] Efficiently Building Large Language Models through Merging
  Yizhen Zhang, Yang Ding, Jie Wu, Yujiu Yang

• [Multimedia 2024 MIS (oral)] Multi-modal Fake News Detection via Decision Uncertainty [code]
  Jie Wu, Danni Xu*, Wenxuan Liu, Joey Zhou, Yew Ong, Siyuan Hu, Hongyuan Zhu, Zheng Wang

Experience

• (Nov. 2024 - Present) Research Intern, Microsoft Asia, Beijing, China.
  Mentor: Independent Researcher Xin Zhang
  Working on post-training for Code LLMs.

• (June. 2024 - Sep. 2024) Research Intern, Myth Lab, Wuhan University, Wuhan, China.
  Advisor: Assoc. Prof. Zuchao Li
  Working on improving reasoning capability of LLMs in multi-doc reasoning.

• (Apri. 2023 - May. 2024) Research Intern, AIM Lab, Wuhan University, Wuhan, China.
  Advisor: Prof. Zheng Wang
  Working on effective detection for multi-modal misinformation.

Competitions

• (Nov. 2024) 1st Place (1/150) in NeurIPS 2024 LLM Merging Competition.
• (Nov. 2024) 4th Place (4/53) in Kingsoft Office Chineses Grammar Correction Competition.

Honors & Awards

• Top 1% Graduate, Wuhan University, 2024
• Outstanding Graduate Thesis, Wuhan University, 2024
• National Scholarship, Ministry of Education, China, 2023