LingBot-VLA v2.0 Released

AdinaYakup · x · 2026-07-08

An Ant Group related team has released LingBot-VLA v2.0, a new Vision-Language-Action model. Details shared include: the model has a scale of 6B, is open-sourced under the Apache 2.0 license, and was pre-trained on approximately 60,000 hours of data covering 20 robot configurations.

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

Original post →

More from Embodied

Embodied channel →