Evolution of world models
Selected primary-source milestones from latent environment representations to interactive video, driving, and spatial world generation.
World Models
The 2018 paper presented agents learning compact environment models for control.
Primary sourceDreamerV3
DreamerV3 unified latent imagination across diverse reinforcement-learning domains.
Primary sourceV-JEPA 2
Meta connected predictive video representations with robot planning experiments.
Primary sourceCosmos 3
NVIDIA published the Cosmos 3 technical report and open development artifacts.
Primary source