AI Briefing#robot-learning
The latest AI and developer news about #robot-learning, with the original source and a short summary.
The latest AI and developer news about #robot-learning, with the original source and a short summary.
OpenWAM is an open framework for composable world-action models that achieves 98.6% success on the LIBERO benchmark using a Mixture-of-Transformers architecture trained on 14.64k hours of robot video data.
The 6B parameter model was trained on approximately 2,500 hours of real robot data and supports parallel grippers and dexterous hands.
Figure achieves an average household task success rate of 56% across 30 unseen homes by pre-training on human behavior data
Unitree has released UnifoLM-WLA-1.0, a 6B parameter model for humanoid manipulation.
Rhoda AI experimentally demonstrated that scaling the size of web video pre-training models and expanding computing resources increases the completion rate of real-world industrial robot tasks.
Xiaomi validated VLA scaling using 100,000 hours of manipulation data collected without robots.
LG AI Research summarized the World Model research trends and EDA application potential from CVPR 2026.
An open-source system called Grabette has been released that lets anyone easily collect manipulation data and build training datasets without needing a robot.
Generalist has secured $400 million in new investment to accelerate the development of physical AGI.