Qinbo Li

I will be joining Luma AI as a Research Scientist, working on image/video foundation models, multimodal models, and physical AI.

Previously, I worked at Snap, where I led the RLHF direction for video generation. Before Snap, I was a Research Scientist at Meta, working on 3D vision and diffusion models. I received my PhD from Texas A&M University, where I was advised by Dr. Yoonsuck Choe.

Email  /  CV  /  Google Scholar  /  Linkedin

We present a practical method for reconstructing and optimizing textured meshes of large, unbounded real-world scenes that offer high visual and geometric fidelity.

We propose a pose-guided diffusion model to generate a consistent long-term video of novel views from a single image.

Synthesize light fields from a single image on general scene. Introduced a light field dataset that includes indoor and outdoor scene.

We introduce an Audio-Visual Aggregation Network (AVAN) to aggregate multiple facial and voice information to improve face recognition performance.

Template from Jon Barron,
Last updated JUN 2026.