2026Ant Group Robbyantopen source
LingBot-VLA
v1.0
LingBot-VLA is a Vision-Language-Action (VLA) foundation model developed by Ant Group Robbyant, designed to enhance real-world robotic manipulation. Trained on approximately 20,000 hours of teleoperated bimanual data from nine dual-arm robot configurations, it demonstrates strong cross-morphology generalization and data-efficient post-training capabilities.
Trained on 20,000 hours of real-world dual-arm robot data
Evaluated on the GM-100 benchmark across three platforms
High training throughput on commodity GPU clusters
pricingOpen source under the Apache 2.0 license
version1.0