About

I am an incoming fifth-year Ph.D. candidate at Penn State University, advised by Prof. Necdet Serhat Aybat. Before joining Penn State University, I obtained my Bachelor’s degree in Mathematics from Lanzhou University. Previously, I was a research intern at Machine Learning group, Microsoft Research, advised by Dr. Lei Song.

My research interests include large language models, reinforcement learning, convex optimization and non-convex optimization.

News

  • [May 2025] I joined X, The Moonshot Factory (Formerly Google X Lab) as an AI Resident in May 2025, working on Tapestry project utilizing the power of LLMs and RL.
  • [May 2025] Our paper Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning is accepted by ICML 2025.
  • [May 2024] I joined Microsoft Research as a Research Intern, working on in-context learning and offline reinforcement learning.

Experience

  • AI Resident, X, The Moonshot Factory (Formerly Google X Lab).
    • 05/2025 - Now
  • Research Intern, Microsoft Research.
    • 05/2024 - 08/2024
  • Research Assistant, Penn State University.
    • 08/2021 - Now

Selected Publications

(* indicates equal contribution)

Invited Talks

  • INFORMS 2024, INFORMS 2023, MOPTA 2023. Title: A stochastic gda method with backtracking for solving nonconvex (strongly) concave minimax problems.

Service

  • Journal Reviewer: Mathematics of Computation
  • Conference Reviewer: AAAI 2024, NeurIPS 2024, AISTATS 2025

Teaching

  • Deterministic Models in Operations Research
    • Teaching Assistant, The Pennsylvania State University, 2025 Spring
  • Deterministic Models in Operations Research
    • Teaching Assistant, The Pennsylvania State University, 2024 Fall
  • Manufacturing Systems Design and Analysis
    • Teaching Assistant, The Pennsylvania State University, 2024 Fall
  • Linear Algebra
    • Instructor, The Pennsylvania State University, 2023 Summer Bootcamp