Summary
Junming Chen is a machine learning researcher and engineer with nine years of experience focused on multimodal generative models, world models, and computer vision applications. A UC Berkeley MEng graduate, he has driven video generation and 3D-controllable human animation research at institutions including BAIR, Fudan, and Université Laval, and contributed practical systems from HDR lighting estimation to inverse rendering. His open-source Video Gen repository has attracted wide attention (5K stars), reflecting a knack for building reproducible research that the community uses. Currently based in San Jose, he blends academic rigor with industry impact as a Member of Technical Staff on multimodal research and is actively pursuing roles in research, computer vision, and ML engineering for Summer 2025.
10 years of coding experience