SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
- Published
- Source
- arXiv
- Paper number
- 1074
- Field
- Computer Vision
- arXiv ID
- 2609.09155
Key points
- Videos of the robot moving along each control direction plus action logs serve as a calibration context, so the model learns how commands map to visual change in a given environment.
- At prediction time it uses the calibration context, recent observations, and the planned action together, requiring no additional training for a new environment.
- The authors show experiments simulating action outcomes in unseen environments and using these predictions to improve policy performance at evaluation time.
- This can cut the cost of retraining a simulator whenever the camera or robot placement changes.
- Trajectory prediction is unstable from extreme viewpoints, and out-of-distribution objects may appear blurred or misplaced.
Paper links
External research summaries. These are not HDATF publications or measured product results.