AW-0 pretrained on 3,000 hours of demos, distilling 50 reusable skill programs
trevordarrell · x · 2026-10-27
Part 4/8 of the AW-0 thread: turning demonstrations into reusable skill programs. An automated annotation pipeline expresses observed manipulation as Code-as-Policies-style programs, aligns program slices with demonstration segments, and distills recurring behaviors into reusable skills. AW-0 is pretrained on roughly 3,000 hours of robot and egocentric human demonstrations with 50 reusable skills, then fine-tuned per task with the same pipeline.
More from Embodied
- StackChan robot performs an AI-generated skit, orchestrated by Hermes Agent via JSON script — alexcovo_eth · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27