Jul 2026
Masked Visual Actions for Unified World Modeling
Masked Visual Actions is introduced, a pixel-space control interface that expresses action as a partially revealed trajectory of an arbitrary entity in a video that supports inverse modeling by synthesizing robot motion from desired object motion.
Hadi Alzayer, Wenlong Huang, Haonan Chen et al.
· arXiv.org · 3 citations
· ⚡1