Machine Learning Algorithms & Natural Language Processing

Jul 23, 2026 · Artificial Intelligence

Painting Robot Actions into Video World Models for Bidirectional Inference (Fei‑Fei Li Co‑author)

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.