I joined the ByteDance ICVG Group as a Research Scientist in 2022. Before that, I was a researcher from the Visual Computing Group of Microsoft Research Asia since late 2017, right after receiving both my B.S and PhD degrees from the School of Software, Tsinghua University.

Currently I am interested in three aspects: the applications of large language models and large multi-modal models and the fully automatic generation of 3d content.


3D rendering and avatars

Pretrainings for applications

Face forgery and face forensics

Face parsing, face landmarks and face editing

Single-view 3D reconstruction