
Ruben Villegas
My main research focuses on generative modeling, self-supervised learning and multimodal learning in the video domain. I am interested in effectively incorporating the time dimension to learn more general representations towards the goal of compositional generalization.Visit my personal website for more details and publications.
Research Areas
Authored Publications
Sort By
Google
Phenaki: Variable length video generation from open domain textual descriptions
Mohammad Babaeizadeh
Han Zhang
Mohammad Taghi Saffar
Santiago Castro
Julius Kunze
ICLR (2023)
Learning Latent Dynamics for Planning from Pixels
Danijar Hafner
Timothy Lillicrap
Ian Fischer
David Ha
Honglak Lee
James Davidson
International Conference on Machine Learning (2019)