Robbyant releases LingBot-VA 2.0, a new foundation model for embodied AI and physical world control

financialpost.com

Robbyant released LingBot-VA 2.0, the first embodied-native video-action world model for physical control. This new model is built from scratch for robotics, focusing on dynamic modeling and real-time execution, unlike previous models adapted from digital content. LingBot-VA 2.0 uses a novel architecture for efficient, accurate physical world understanding and action, achieving 150 Hz inference speed.


With a significance score of 3.3, this news ranks in the top 9.2% of today's 33168 analyzed articles.

Get summaries of news with significance over 5.5 (usually ~10 stories per week). Read by 10,000+ subscribers: