Robbyant Releases Two Spatial AI Models

heyshrutimishra · x · 2026-07-09

Robbyant has released two notable spatial AI/robotics models: LingBot-Vision and LingBot-Depth 2.0. The former is an open-source 1B backbone model that outperforms 7B models in depth estimation. Its distilled 0.3B version also achieves near-7B depth performance while being much better suited for edge deployment.

Related event: Robbyant Releases LingBot-Vision: 1B Spatial Model Beats 7B(7 posts)→

Original post →

More from Embodied

Embodied channel →