LingBot-VLA 2.0 Released

Scobleizer · x · 2026-07-08

Robbyant has released LingBot-VLA 2.0, a vision-language-action model trained on 50,000 hours of real robot data and 10,000 hours of everyday human operation videos.

The model unifies 20 different robot embodiments into a single action space, allowing a single model to drive various robots.

Related event: Ant Lingbo Open-Sources LingBot-VLA 2.0 for Multi-Robot Generalization(18 posts)→

Original post →

More from Embodied

Embodied channel →