About

I am a Staff Research Scientist at Google. My research interest mainly lies in computer vision and perception, with a focus on efficient foundation models and multimodal models.

Previously I was at Meta, working on various semantic perception models. I received a Ph.D. degree from the Department of Electrical & Computer Engineering (ECE) at Carnegie Mellon University (CMU), working with Prof. Marios Savvides from the CyLab Biometrics Center. My thesis title was "Towards Object Detection in the Real World". I also obtained an M.S. degree from CMU-ECE. Before coming to CMU, I got a B.S. degree in Electronic Information Science & Engineering from Nanjing University, China. 

[Google Scholar]