Doppel: one open video world model for eight robot embodiments
CMU, Johns Hopkins and Toyota Research open-sourced Doppel, a factored action-conditioned video world model that unifies eight robot embodiments by first 3D-rendering the robot body from the camera view, then conditioning a shared video model on the render plus actions.
2026-11-19 ~ 2026-11-19 · 2 related posts
- Doppel world model renders the robot body and beats action-only baselines across 8 embodiments — mangahomanga · 2026-11-19
- Doppel open-sourced: one video world model unifies 8 robot embodiments — mangahomanga · 2026-11-19