LingBot-Video Foundation Model Released

_akhaliq · x · 2026-07-09

LingBot-Video has been released on Hugging Face as a MoE video foundation model designed for embodied AI. The model has a total parameter count of 30B, activating only 3B parameters during inference.

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

Original post →

More from Embodied

Embodied channel →