Ropedia W0: One World Model Trained on 10,000 Hours of Egocentric Human Video for Any Robot
liuziwei7 · x · 2026-10-19
Day 1 of Ropedia Super Week introduces Ropedia W0, a world model trained on roughly 10,000 hours of first-person (egocentric) human video. A single model predicts how the physical world evolves for different embodiments—a human, a robot arm, or other robots—under the thesis "different robots, one world model."
Related event: Ropedia Unveils W0 World Model for Robot Action Prediction(2 posts)→
More from Embodied
- MolmoAct2 lead Duan Jiafei joins NUS with multimillion-dollar robotics grant — DJiafei · 2026-10-19
- PixVerse R2 acts like a world model: WASD movement and text inputs reshape a live game world — hey_abusiddik · 2026-10-19
- Robotics writer admits he was wrong: Physical Intelligence just shipped a model API — binarybits · 2026-10-19
- Why testing robot models is even harder than testing LLMs — the RoboDojo catch — binarybits · 2026-10-19
- What should a robot model predict? Four paradigms compared on the same robot data — GlenBerseth · 2026-10-19
- Shenzhen has built 1,200+ landing pads for passenger flying cars already operating in the city — LoganGrasby · 2026-10-19