Ropedia W0 world model tops all robot baselines, trained on 10k hours of human video
liuziwei7 · x · 2026-10-20
Ropedia released Ropedia W0, an open-source egocentric world foundation model that learns loco-manipulation from 10k hours of human experience and transfers across embodiments (robot arms, humanoids, grippers, dexterous hands) via one kinematic interface of camera poses and projected skeletons.
- Built on the Wan2.2-TI2V-5B DiT backbone with 96-dim Plücker camera and 48-dim skeleton conditioning; 5B pre/mid-trained checkpoints are live on Hugging Face, A14B to follow
- Benchmark charts show W0 (A14B) leading DreamDojo, Ψ0, ω-HOME, AgiBot Bench and Xp-Teleop from zero-shot to full-data post-training, ahead of Cosmos 3-Nano/3-Super and DreamDojo
- Use cases: robot policy evaluation, imagined rollouts, real-time VR teleoperation, improved robot learning
- Code, weights, and the Xp-Teleop dataset are all open (cc-by-nc-4.0)
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