About this Event
Jack Parker-Holder, Ashley Edwards and Yuge (Jimmy) Shi from Google DeepMind will present Genie: Generative Interactive Environments.
Join us in person in the Function Space at 90HH or online on zoom. There will be refreshments after the talk.
Abstract:
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of actioncontrollable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.
Event Venue & Nearby Stays
90 High Holborn, 90 High Holborn, London, United Kingdom
USD 0.00