Open-Source Embodied Video Model: LingBot-Video

thetripathi58 · x · 2026-07-09

Robbyant has introduced LingBot-Video, an open-source MoE video foundation model for robotic embodied intelligence. Rather than generating entertainment videos, it serves as a foundational component for a robot's "brain," used for data engines, policy evaluation, and action planning. The model simulates physically accurate future state evolutions based on a starting image and a sequence of robot actions.

Related event: Ant Group Open-Sources LingBot-Video for Embodied AI(26 posts)→

Original post →

More from Embodied

Embodied channel →