RUBEN VILLEGAS
  • About
  • News

Ruben Villegas

Senior Staff Research Scientist

Google DeepMind

rubville [at] google [dot] com

Biography

I am a Senior Staff Research Scientist at Google DeepMind where I work on generative models of video. My primary goal is to develop models that learn to understand and generate the intricate dynamics of the real world from massive amounts of video data. These world models should be capable of interpreting the dynamics within a given video, forecast future events based on past observations, and to recombine learned concepts into novel, simulated versions of reality. I received my PhD from the Computer Science & Engineering Department at the University of Michigan, Ann Arbor under the supervision of Professor Honglak Lee. During my PhD, I mainly focused on building models for future frame prediction using self-supervised and supervised approaches. I also contributed to building world models successfully applied in model-based reinforcement learning.

Fun Facts: I played for my national basketball team (I am originally from Ecuador). I was also second best scorer in the nation in a national championship I played back in the day. I was part of a team that beat the media's projected champion during a championship in Quito (the guy that was best scorer in the national championship played for the other team :P). Let's have a Curry-range 3-point shootout. Ok, I'll stop now ...

News

  • 08/2025: Our general purpose world model, Genie 3, was announced to the public.
  • 05/2025: Our state-of-the-art audio and video generation model, Veo 3, was announced at Google I/O 2025, and made avaiable through Gemini Ultra.
  • 12/2024: Our state-of-the-art video generation model, Veo 2, was announced and made available to a selected group of users.
  • 05/2024: Our most capable video generation model to date, Veo, was announced at Google I/O 2024. Stay tuned for our official model release!.
  • 05/2023: Our text-to-video model, Phenaki, was highlighted at Google I/O 2023.
  • 03/2023: Honored to be giving a talk on Generative Models at Khipu2023, taking place in Montevideo, Uruguay.
  • 02/2023: Our paper "Phenaki: Variable Length Video Generation From Open Domain Textual Description" has been accepted to ICLR 2023.

© Ruben Villegas · Powered by the Academic theme for Hugo.

Cite

Copy Download