I'm a

3rd

year Ph.D. student at the University of Hong Kong, advised by Prof. Tao Yu. Previously I got my bachelor's degree of Computer Science and Technology at Tsinghua University 

My research focuses on Digital Agents (Computer-Use Agents), Large-Scale Agentic Reinforcement Learning, and Synthetic Data. I am particularly interested in (1) post-training computer-use agents to raise the ceiling of multimodal intelligence, so they can take on real personal and professional work^[1,2,3,4]; (2) building frontier agentic RL infrastructure and algorithms efficiently enough to support large-scale multi-task RL^[5,6]; and (3) using models to synthesize tasks and environments at scale^[1], to break the data bottleneck in frontier domains and raise the ceiling on recursive self-improvement (RSI).

I have primarily worked on computer-use agents (CUA), developing open foundations through mid-training and post-training and building open-sourced CUA models^[7,8,9,10].