Physical-world-model startup LiberAI has released Liber-0, a world action model pretrained on more than 2.2 million hours of human experience data. In 600 real-robot tests across 60 tasks randomly generated by GPT-6, the model achieved a 36% overall success rate without collecting robot demonstration data specifically for the test tasks. When combined with human manipulation data collected via data gloves, the model outperformed one trained only on full real-robot data even with 75% less real-robot data, LiberAI said.
LiberAI launches Liber-0 world action model
Related Articles
LiberAI raises pre-A++ round for world models
Boston Dynamics shows Atlas humanoid robot fitted with wheels
D-Robotics, Infinigence AI partner on open-source embodied AI infrastructure
Ant Lingbo to hold first developer conference on Nov. 16
Amazon forms home robot team to develop "unprecedented" product, report says
J.P. Morgan sees U.S. humanoid robot output reaching 300,000-400,000 units by 2030
GenRobot AI raises $100 mln in new funding round
Honor sets up robot subsidiary with 100 mln yuan capital
AGIBOT
Figure AI
UBTECH