About Me

Hi! My name is Leyi Pan (潘乐怡). I am currently a 3rd-year Ph.D. student at Tsinghua University. Before that, I received my B.Eng. from Tsinghua University in 2024.

I am currently a member of the Top Talent Intern Program at Minimax, working in the Foundation Model Team, Reinforcement Learning Group, where I contribute to releases of the M-series LLMs, including MiniMax M3.1-Flash. From July 2025 to July 2026, I was a research intern on LLM reasoning and reinforcement learning at Tongyi Lab, Alibaba Group. Previously, I interned at Z.ai, where I contributed to the GLM-4.5V and GLM-4.1V-Thinking models.

My research interests mainly lie in:

  • LLM Reinforcement Learning (current focus)
  • Trustworthy AI

Feel free to reach out if you would like to discuss research or explore potential collaboration!

News

Education

Internships

  • 2026.07 - PresentMinimax, Top Talent Intern Program
  • Foundation Model Team, Reinforcement Learning Group. Contributing to releases of the M-series LLMs, including MiniMax M3.1-Flash. Focus on RL scaling and MOPD.
  • 2025.07 - 2026.07Tongyi Lab, Alibaba Group, Research Intern
  • Topic: LLM reasoning and reinforcement learning.
  • 2024.10 - 2025.06AI Lab, Z.ai, Research Intern
  • Topic: Reasoning and reinforcement learning for multimodal large language models. Contributed to GLM-4.5V and GLM-4.1V-Thinking.
  • 2024.06 - 2024.08CUHK MISC Lab, Research Assistant
  • Topic: Trustworthy AI.
  • 2023.06 - 2023.08KuaiShou Technology, Research Intern
  • Topic: Tool-integrated agent.

Projects

MiniMax M3.1-Flash project image
MiniMax M3.1-Flash (Contributor: RL scaling, MOPD)
MiniMax's next-generation Flash model, delivering a generational leap in agentic tasks, coding, Computer Use, and cybersecurity, with nearly 3× faster online inference and 70% lower usage cost.
GLM-4.5V and GLM-4.1V-Thinking project image
Open-source multimodal reasoning models trained with scalable reinforcement learning, with strong visual understanding, coding, STEM, and GUI-agent capabilities.
MarkLLM project image
MarkLLM (Project Lead & First Contributor)
An open-source toolkit for LLM watermarking, covering watermark generation, detection, evaluation, visualization, and extensible algorithm implementations.
MarkDiffusion project image
MarkDiffusion (Project Lead & First Contributor)
An open-source toolkit for generative watermarking of latent diffusion models, designed for reproducible evaluation and easy integration of watermarking methods.

Selected Publications & Preprints

A full publication list is available on my Google Scholar page. (* denotes equal contribution)

LLM Reinforcement Learning (current focus)

Trustworthy AI

Service

  • Reviewer: ACL ARR, NeurIPS, ICLR.

Honors and Awards

  • 2026   Tsinghua Excellent First-class Scholarship / 清华大学综合优秀一等奖学金.
  • 2025   Tsinghua Excellent First-class Scholarship / 清华大学综合优秀一等奖学金.
  • 2024   Outstanding Graduate of Beijing / 北京市优秀毕业生.
  • 2024   Outstanding Graduate of Tsinghua / 清华大学优良毕业生.
  • 2024   Tsinghua Outstanding Graduation Project / 清华大学优秀毕业设计.
  • 2021-2023   Tsinghua Excellent Student Award / 清华大学综合优秀奖学金.

Contact