UMI diffusion policy hits 100/100 cube-stacking success with slowed demos
DominiqueCAPaul · x · 2026-11-13
ginokreis shares first results training UMI diffusion policies for cube stacking: v1, trained on human-speed demos collected 1.6x faster than teleop, achieved 91/100 success while running 2.4x faster than the teleop policy; v2, trained on demos slowed to teleop speed, reached 100/100. A follow-up thread covers ACT and delta policies.
More from Embodied
- Video shows an autonomous parking robot handling the full parking job on its own — DavidWells · 2026-11-13
- BoSS benchmark released: 180K+ stellarators, 3TB of simulation data for generative models — ZhongingAlong · 2026-11-13
- Fly brain hooked up to a synth learns to sing Bad Apple — Bedrovelsen · 2026-11-13
- CoRL takeaways: SuperMimic steals the show, dexterity and tactile sensing improve, human data still a bottleneck — KyleMorgenstein · 2026-11-13
- Outworld Labs launches simulation platform with new physics engine for robot learning — ycombinator · 2026-11-13
- YC-backed Mantle launches AI-native maintenance service for robots with 250+ technicians — ycombinator · 2026-11-13