I am a PhD student in Computer Science and Engineering at the University of Michigan, advised by Prof. Silviu Pitis. My research interests include natural language processing, large language models, RLHF, reward hacking, fine-grained reward modeling, and LLM reasoning.

Before joining UMich, I completed an MPhil in Computer Science and Technology at Sun Yat-Sen University, advised by Prof. Xiaojun Quan, and a BEng in Computer Science and Technology at Lanzhou University.

Research Focus

My work studies how language models learn from preferences and feedback, with an emphasis on reward modeling, policy optimization, and reasoning. Recent projects include prefix-value learning for distribution-level optimization, token-level reward models, advantage-guided distillation for preference alignment, and edit-wise preference optimization for grammatical error correction.

Education

• University of Michigan, PhD in Computer Science and Engineering, Sep 2026 - Jun 2030 (Expected)
• Sun Yat-Sen University, MPhil in Computer Science and Technology, Sep 2023 - Jun 2026
• Lanzhou University, BEng in Computer Science and Technology, Sep 2019 - Jul 2023

Publications

Also on Google Scholar. Click a title for details and BibTeX.

Academic Service

• Reviewer: NeurIPS 2026, EMNLP 2026
• Teaching Assistant: Artificial Neural Networks and Mathematical Principles of Reinforcement Learning, Sun Yat-Sen University (2025)

CV

A PDF version of my CV is available here (updated Aug 2026). The web version is on the CV page.

Contact

I can be reached at shiping@umich.edu or rungao2001@outlook.com.