I am a final-year undergraduate student in Computer Science at Sichuan University, Chengdu. I expect to graduate in 2026/06.
Currently, I am a Research Intern at Beijing Academy of Artificial Intelligence(BAAI), advised by Prof. Chaozhuo Li.
My broader research interests include:
- Post-training
- Self-Evolving
- Trustworthy AI
🚩 Seeking Opportunities: I am exploring 2027 Fall PhD positions across the US/Singapore/Hong Kong. I am particularly open to remote RA opportunities to build early connections and foster research partnerships. If my background aligns with your group's interests, please feel free to reach out. I would welcome the chance to discuss potential synergies!
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Sichuan UniversityChengdu, Sichuan
B.Eng. in Computer ScienceSep. 2022 - Jun. 2026 (Expected)
Research Experience
-
Beijing Academy of Artificial Intelligence (BAAI)Research Intern
Trustworthy AI GroupDec. 2025 - Present
Honors & Awards
-
International Collegiate Programming Contest Asia Regional ContestDec. 2023
-
China Collegiate Programming ContestNov. 2023
-
International Collegiate Programming Contest Asia Regional ContestNov. 2023
Selected Publications (view all )
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
Dengchun Li, Naizheng Wang, Zihao Zhang, Haoyang Yin, Lei Duan, Meng Xiao, Mingjie Tang
arXiv preprint 2504.00661
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
Dengchun Li, Naizheng Wang, Zihao Zhang, Haoyang Yin, Lei Duan, Meng Xiao, Mingjie Tang
arXiv preprint 2504.00661
Enhancing Code LLMs with Reinforcement Learning in Code Generation
Junqiao Wang, Zeng Zhang, Yangfan He, Zihao Zhang, etal.
ICLR 2026 Workshop LLM Reasoning
Enhancing Code LLMs with Reinforcement Learning in Code Generation
Junqiao Wang, Zeng Zhang, Yangfan He, Zihao Zhang, etal.
ICLR 2026 Workshop LLM Reasoning