Ambient Diffusion Policy accepted to CoRL 2026: training on suboptimal robot data
giannis_daras · x · 2026-09-05
Ambient Diffusion Policy has been accepted to CoRL 2026 in Austin. The method tackles the ubiquity of suboptimal data in robotics: data filtering is wasteful and co-training learns both good and bad features, whereas Ambient Diffusion Policy selectively learns useful features via noise-dependent data usage, offering a principled way to train policies from imperfect demonstration data.
More from Embodied
- Tesla Cybercab now on display at Domain showroom in North Austin, doors open to visitors — EricETesla · 2026-09-05
- Robot data startup XDOF in talks for Series B at $1.2B valuation, 3 months out of stealth — TechCrunch AI · 2026-09-05
- Auki hosts Hong Kong Robots & Beers meetup with stealth robotics startup demo — broodsugar · 2026-09-05
- Dev runs full local Physical AI stack on Jetson Thor: Nemotron agent sees the real world — chrismatthieu · 2026-09-05
- 3 Hours in Tesla's Cybercab Cost $92.51 vs $200 on Uber, and FSD V15 Won Him Over — xiaosun86 · 2026-09-05
- EU AI Act high-risk rules for humanoid robots now live, mandate audit logs — sierracatalina · 2026-09-05