I am a staff AI research scientist in Meta Superintelligence Lab. I mainly work on media foundation models (emu, movie gen, autoregressive image-gen). I lead the Emu text-to-image foundation model training, was a core contributor to MovieGen and multimodal image generation.

I previously worked on depth estimation, on-device computer vision and human perception-inspired computational vision. Prior to Meta, I obtained my Ph.D. from Harvard University advised by Prof. Todd Zickler, and my B.A.Sc from the University of Toronto advised by Prof. Sven Dickinson and Prof. Sanja Fidler.


Contact:   jialiangwang05@gmail.com /  LinkedIn  /  CV  /  Google Scholar