REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
- Apple: 36 events in the last 90 days
- Previous: earlier the same day · Upcoming changes to Rosetta support for Intel-based macOS apps
What happened
Most current vision-language-action (VLA) models—such as OpenVLA, π0, RT-2, and RDT-1B—are “monolithic.” This means they generate raw motor…
Summary assembled by rule from the sources below
Why it's spreading
Sources
Official
- REFACTOR-VLA: Unsupervised Library Learning of Typed Motor ProgramsApple Machine Learning