I’m a final-year Ph.D. candidate in the School of Computer Science and Technology at Harbin Institute of Technology, Shenzhen (HIT), advised by Prof. Cuiyun Gao. I am currently visiting Singapore Management University (SMU), supervised by Prof. David Lo. I received both my Master’s and Bachelor’s degrees from HIT.

I am actively seeking postdoctoral opportunities in AI for software engineering. I also welcome research collaborations and visiting opportunities. Please feel free to contact me if you are interested!

Research Interests

My research focuses on AI4SE, particularly large language models for code, code intelligence, and AI agents for software engineering.

News

• 2026.09 💥💥 One Paper “ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination” is accepted by NeurIPS 2026!
• 2026.09 💥💥 One Paper “What Makes Effective Knowledge Distillation for Large Language Models in Code Generation?” is accepted by TSE 2026!
• 2026.08 💥💥 One Paper “Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation” is accepted by EMNLP 2026!
• 2026.04 💥💥 🏆 Distinguished Paper Award, ICSE 2026 Industry Challenge Track
• 2026.02 💥💥 One Paper “From Function to Repository: Towards Repository-Level Evaluation of Software Vulnerability Detection” is accepted by TSE 2026!
• 2026.01 💥💥 One Paper “LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search” is accepted by ICSE-Inch 2026!
• 2025.10 💥💥 One Paper “Multi-view Leaderboard: Towards Evaluating the Code Intelligence of LLMs From Multiple Views” is accepted by APSEC-ToolDemo 2025! 🏆 Best Paper Award of the Track
• 2025.09 💥💥 One Paper “Automated Prompt Generation for Code Intelligence: An Empirical Study and Experience in WeChat” is accepted by ASE-Industry 2025!
• 2025.04 💥💥 One Paper “Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs” is accepted by FSE 2025!
• 2025.03 💥💥 One Paper “Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware” is accepted by FSE-Industry 2025!
• 2025.03 💥💥 One Paper “AutoReview: An LLM-based Multi-Agent System for Security Issue-Oriented Code Review” is accepted by FSE-SRC 2025!