GAIA-2 is a controllable latent diffusion world model that produces spatiotemporally consistent multi-view videos for autonomous driving simulation across diverse geographies.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
GAIA-1 generates controllable realistic driving scenarios by casting world modeling as next-token prediction on tokenized video, text, and action sequences.
citing papers explorer
-
GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
GAIA-2 is a controllable latent diffusion world model that produces spatiotemporally consistent multi-view videos for autonomous driving simulation across diverse geographies.
-
GAIA-1: A Generative World Model for Autonomous Driving
GAIA-1 generates controllable realistic driving scenarios by casting world modeling as next-token prediction on tokenized video, text, and action sequences.