The paper introduces Masked Visual Actions, a pixel‑mask representation of robot behavior that lets a 14B video model predict future outcomes and generate robot motions across unseen embodiments, achieving higher accuracy than traditional joint‑angle or pose inputs.
The paper introduces Masked Visual Actions, a method that renders robot motions as pixel‑level masks for video world models, enabling both forward prediction of environment changes and inverse generation of robot actions, achieving notable success‑rate gains and cross‑embodiment generalization.
The article reviews the Masked Visual Actions approach, which renders robot motion as pixel‑level masks for video world models, enabling both forward prediction of environment changes and inverse generation of robot actions, and demonstrates significant performance gains across multiple robotic tasks and embodiments.
A new world model called Masked Visual Actions uses just 15 hours of robot video to predict action outcomes and generate robot behavior by representing motions as spatiotemporal pixel masks, achieving cross‑embodiment generalization, higher task success rates, and strong correlation between video evaluation and real‑world performance.
