Google Research

Ruben Villegas


My main research focuses on building models that understand the spatiotemporal dynamics in raw video through self-supervised and multimodal learning. I have published works on video prediction involving object interactions, highly articulated motion, and partially observable data. I am also interested in and have worked on model based reinforcement learning, modeling human motion and character animation. Visit my personal website for more details and publications.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work