Insight tag
5 related stories.
Meta released V-JEPA 2 on June 11, 2025, pairing a video-trained world model with physical-reasoning benchmarks and reported zero-shot robot-planning experiments.
Read analysisWayve announced GAIA-2 on March 26, 2025, a video-generative world model for assisted and automated-driving development with controlled road, agent and environmental inputs.
Read analysisNVIDIA launched Cosmos on January 6, 2025, combining world foundation models, tokenizers and data processing for robotics and autonomous-vehicle development.
Read analysisGoogle DeepMind announced Genie 3 in August 2025 as a limited research preview for real-time interactive world generation, while documenting duration and accuracy limitations.
Read analysisMicrosoft Research introduced Muse on February 19, 2025, publishing a World and Human Action Model for gameplay ideation with a bounded game-data setting.
Read analysis
