Robbyant Releases LingBot-VLA 2.0: An Open-Source 6B Vision-Language-Action (VLA) Model for Cross-Embodiment Robot Manipulation

Short summary

Ant Group's Robbyant released LingBot-VLA 2.0, an Apache-2.0 licensed 6B vision-language-action model for cross-embodiment robot manipulation. Pretrained on 60,000 hours of data across 20 robot configurations, it maps all embodiments into a single 55-dimensional action space using a MoE action expert. It outperforms π0.5 and its predecessor on the GM-100 benchmark.

• •Open-source 6B VLA model for cross-embodiment robot manipulation (Apache-2.0)
• •Pretrained on 60K hours spanning 50K robot trajectories and 10K hours egocentric video
• •Outperforms π0.5 and LingBot-VLA-1.0 on GM-100 generalist benchmark

Generated with AI, which can make mistakes.