About
Reinforcement learning · Planning · Reasoning
I am a PhD student in the Department of Electrical & Computer Engineering at Texas A&M University, supervised by Prof. Le Xie and co-advised by Prof. Chao Tian.
My research focuses on search-augmented reinforcement learning: turning search guided by learned models and value functions into efficient and reliable policy improvement, from continuous control to reasoning agents.
I received my master’s degree from the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University, advised by Prof. Yang Gao, and my bachelor’s degree in Electrical Engineering from Tsinghua, where I worked with Prof. Qirong Jiang and Prof. Haiwang Zhong.
News
- 09/2026Iterative Gumbel Planning for Continuous Control accepted to NeurIPS 2026, continuing our work on search-based reinforcement learning in the EfficientZero family.
- 09/2026Our Amazon internship work, Improving Math Reasoning through Value-Guided Informative Search, accepted to the NeurIPS 2026 MATH-AI Workshop.
- 09/2026Completed my Applied Scientist internship at Amazon (June–September 2026), working on search-augmented agentic reinforcement learning, mentored by Yuning Wu.
- 03/2026Released EfficientZero-Multitask (EZ-M), exploring task scaling and shared world models for sample-efficient humanoid control.
Selected Research
All publications
Iterative Gumbel Planning for Continuous Control
Aligning search and policy representations for continuous control, addressing variance inflation through iterative Gumbel planning with factorized categorical policies.
Improving Math Reasoning through Value-Guided Informative Search
Turning value-guided search improvements into informative learning signals for mathematical reasoning with verifiable rewards.
Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
Scaling tasks rather than samples: shared world models enable sample-efficient multi-task learning for humanoid control.
Beyond Research
I spent over 15 years as a student athlete, playing for YALI High School and the Tsinghua University Men’s Soccer Team. I play midfield and am a fan of Messi, FC Barcelona, and Argentina.