|
I am a Senior Researcher at Tencent's LLM Department, working on AI-native systems at the intersection of applied reinforcement learning and large language model post-training.
My work focuses on building trustworthy decision intelligence systems that can perceive, reason, learn, and act reliably in complex real-world environments. I develop applied reinforcement learning agents and large language model post-training methods, including agent memory, tool-use policies, reward modeling, supervised fine-tuning, RLHF, preference optimization, and data-centric evaluation. I am particularly interested in turning learning algorithms into capable, robust, and dependable systems for real-world deployment.
I received my Ph.D. in Electrical and Computer Engineering from The University of Texas at Austin in 2021, advised by Prof. Constantine Caramanis. I received my B.E. in Electronic Engineering from Tsinghua University in 2016.
|