Safety
Today we're announcing Praxis-1, an open-weight world action model that adapts to new robot embodiments with light finetuning. Video is eati…
Today we're announcing Praxis-1, an open-weight world action model that adapts to new robot embodiments with light finetuning. Video is eating the world Introducing Praxis-1, an open-weight World Acti
Today we're announcing Praxis-1, an open-weight world action model that adapts to new robot embodiments with light finetuning. Video is eating the world Introducing Praxis-1, an open-weight World Action Model that turns our video pre-training expertise into real world control for robots. Robot demonstration data is limited. But video data is infinite. Praxis-1 extends our bet that the best policy models will learn from video, and…
Related
- OSCAR: Omni-Embodiment Skeleton-Conditioned World Action Model for Robotics
- SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control
- XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?
- Action Images: End-to-End Policy Learning via Multiview Video Generation
Source: Cristobal Valenzuela (X) | 2026-09-30