Jiayi Fu

Doctoral Student

About me: My name is Jiayi Fu, and I am a PhD student at INSAIT, starting in March 2026, where I am fortunate to be supervised by  Prof.Yuxia Wang. My research interests mainly focus on Artificial General Intelligence, including Large Language Model, Reinforcement Learning, and Diffusion Models. Before joining INSAIT, I received my Bachelor’s degree from Harbin Institute of Technology and my Master’s degree from Fudan University.

Google ScholarGoogle Scholar

HomePage:   HomePage

Education:

  • Fudan University – Master of Science in Computer Science – 2022.09-2025.06
  • Harbin Institute of Technology –  Bachelor of Engineering in Computer Science – 2018.08-2022.06

Representative Publications:

  • Reward Shaping to Mitigate Reward Hacking in RLHF, ICML2025  R2-FM Workshop
  • GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick, ACL 2024
  • P4: Plug-and-Play Discrete Prompting for Large Language Models Personalization, ACL 2024 Findings

Awards:

        Huawei Scholarship at Fudan University, 2024

Internships:

  • StepFun Inc. – Reinforcement Learning From Human Feedback – 2024.06-2025.02