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
- Dexmal's open-source VLA model DM0.5 lands in LeRobot, tops RoboColiseum — AdinaYakup · 2026-10-23
- A classic world model (s, a → s′) acting as a neural MuJoCo simulator — yshan2u · 2026-10-23
- Gen-HumanWholeBody: open 600-hour whole-body manipulation dataset for robots — AdinaYakup · 2026-10-23
- Stanford releases free 520-page robot autonomy course book and lectures — lukas_m_ziegler · 2026-10-23
- Pony.ai and inDrive target Kazakhstan robotaxis by 2027 as Nvidia GPU deployments expand — VectorWireAI · 2026-10-23
- MambaAct cuts VLA robot policy latency up to 59% while lifting success rates — MBZUAI · 2026-10-23