AdaDex turns short human demos into adaptable dexterous skills
One policy trains on motion tracking and noised goal environments, then transfers to real robots.
2 stories, newest first · one card per story
One policy trains on motion tracking and noised goal environments, then transfers to real robots.
A flow-matching student distilled by DAgger runs on proprioception alone and was tested on the Unitree-G1.
Today 1.2K readers · 1.8K views · 1.4K reads · all time 160K views