robotics
The World Model Starts Writing Reusable Skills
AW-0 couples code, future video and robot actions so predicted behavior can become a reusable program.
Summary
AW-0 couples code, future video and robot actions so predicted behavior can become a reusable program.
AW-0 models code, video and actions as three linked generative streams. A code expert produces parameterized routines and control logic while video and action experts predict future states and motor commands. An automated pipeline labels human and robot trajectories with programs and consolidates repeated routines into a skill library. Evaluations on RoboTwin 2.0 and physical bimanual tasks report gains over compared vision-language-action and world-action baselines. Those results are specific to the tested tasks, but they connect visual prediction with compositional execution.
Why it matters
AW-0 couples code, future video and robot actions so predicted behavior can become a reusable program.
Limits and context
No additional limitation was separately recorded.
Key claims
AW-0 couples code, future video and robot actions so predicted behavior can become a reusable program.
Evidence: source-2026-10-22-003
Sources
- arXiv preprint 2610.30136, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.