🦾 SyncWorld — a zero-shot robot simulator

SyncWorld shows that a pretrained video world model becomes a usable robot simulator once you visually calibrate it: prepend a short clip of the arm sweeping each degree of freedom, and the model infers the unseen camera↔robot mapping on the fly — no per-scene finetuning.

Pick a calibrated scene, then either replay the robot's own actions or drive the arm yourself with a per-step end-effector twist, and watch the model render what happens next.

Model: yyuncong/SyncWorld (16B Cosmos-3 mixture-of-transformers, Wan2.2 video VAE). Scenes and calibration clips are the authors' own evaluation episodes from yyuncong/SyncWorld-Evaluation (OpenMDW-1.1).

Calibrated scene
0 271
Actions

Commanded end-effector twist — used in Drive the arm myself mode. Held constant for every predicted step (the calibration sweeps cover roughly ±3 cm/step and ±3 °/step).

-3 3
-3 3
-3 3
-3 3
-3 3
-3 3
Gripper
1 3
Examples