Scholar
Jialiang Wang
Google Scholar ID: R8vOkZYAAAAJ
Research Scientist, Meta AI
Citations & Impact
Citations
1,144
H-index
14
i10-index
16
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published multiple papers, including 'Improving Chain-of-Thought Efficiency for Autoregressive Image Generation' and 'LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity', in top conferences like CVPR and ICML.
Research Experience
- Works as an AI research scientist at Meta Superintelligence Labs, contributing to the development and training of various media foundation models such as emu and MovieGen.
Education
- Ph.D. from Harvard University, advised by Prof. Todd Zickler; B.A.Sc from the University of Toronto, advised by Prof. Sven Dickinson and Prof. Sanja Fidler.
Background
- A staff AI research scientist at Meta Superintelligence Labs, a core contributor to training Meta's media foundation models including emu, MovieGen, and multimodal image generations. Also works on personalized media generation. Previously worked on depth estimation, 3D computer vision, on-device computer vision, and human perception-inspired computational vision.
Miscellany
- Contact: jialiangwang05@gmail.com / LinkedIn / Google Scholar