Ropedia W0: one kinematic interface transfers loco-manipulation across embodiments
liuziwei7 · x · 2026-10-20
Ropedia W0 is an egocentric world foundation model (latent video diffusion; dense 5B and 14B-active MoE variants) trained on 10k hours of human experience to learn loco-manipulation and transfer across embodiments — from robot arms to humanoids, grippers to dexterous hands — via one kinematic interface.
- Interface: locomotion as camera poses (dense Plücker-ray maps relative to the first frame), manipulation as projected hand skeletons; explicit, pixel-aligned signals any human or robot body can render in the same format
- Training: human pre-training → human-robot mid-training → optional post-training on a target robot
- Code open-sourced on GitHub (Apache-2.0) with a 5B inference script
Related event: Ropedia Open-Sources W0 World Model Trained on 10k Hours of Human Video(5 posts)→
More from Embodied
- Surgeons Complete 100+ Cataract Surgeries Using Apple Vision Pro and ClearSphere App — asymco · 2026-10-20
- What makes human video generation good for robot manipulation? A constrained-optimization analysis — mangahomanga · 2026-10-20
- Figure's F.03 humanoid walks 348 miles and 1.2M steps over 9 straight days on a treadmill — adcock_brett · 2026-10-20
- NVIDIA joins Gemma hardware hackathon with 30 Jetson kits at AGI House on Oct 24 — agihouse_org · 2026-10-20
- Tesla shows Optimus V3 render in investor letter, Musk touts an 'Amazing Abundance' era — JOBhakdi · 2026-10-20
- UCSD PhD Nicklas Hansen joins NYU as postdoc with LeCun and Pinto on world models + robots — LerrelPinto · 2026-10-20