About Me

I am a third-year undergraduate student at the School of Data Science and Engineering, East China Normal University, advised by Prof. Xiang Li in the PLANING Lab. My current research focuses on large language model post-training, particularly reinforcement learning and on-policy distillation, including multi-teacher approaches. More broadly, I am interested in multimodal understanding and reasoning, especially how models integrate information across modalities to understand and reason about the world.

I value simplicity and clarity in research. I enjoy breaking down complex problems to uncover their underlying structure.

Outside research, I am interested in value investing. I also enjoy exchanging ideas with people across academia and industry. Feel free to reach out for a chat or to explore potential collaborations!

🔥 News

• 2026.09 🎊🎊 A recent work S²D-OPD has been released on ArXiv!
• 2026.08 🔥🔥 Our work MERIT is accepted by EMNLP 2026, see you in Budapest!
• 2026.05 🎊🎊 A recent work MERIT has been released on ArXiv!
• 2026.04 🔥🔥 Our work RATE is accepted by ACL 2026, see you in San Diego!
• 2026.01 🎊🎊 Happy New Year! A recent work RATE has been released on ArXiv!

📑 Publications

(* denotes equal contribution.)

• ACL 2026 RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems,
  Weicong Liu*, Zixuan Yang*, Yibo Zhao, Xiang Li.
• EMNLP 2026 MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment,
  Zixuan Yang, Yibo Zhao, Weicong Liu, Xiang Li.

📜 Preprints

• Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD,
  Yibo Zhao*, Zixuan Yang*, Yunshi Lan, Xiang Li.

📖 Educations

• 2024.09 - now, Undergraduate student, Data Science and Engineering, East China Normal University

🔍 Service

• I have served as a reviewer for the following venue:
  • ICLR 2027

Everything should be made as simple as possible, but not simpler.