World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks
Embodied video world models typically capture both scene evolution and the robot's behavior, which we refer to as the \emph{world} and the \emph{ego}, respectively. The world and the ego exhibit different underlying dynamics: world prediction relies primarily on visual history and emphasizes scene stability, whereas ego prediction relies more strongly on the current instruction and emphasizes accurate instruction following. Modeling both components within a single generation stream can entangle these different dependencies, making it difficult to specialize the prediction of either component. Consequently, it becomes difficult to simultaneously maintain scene consistency and accurate inst...
| Authors | Zuyao Lin, Jianhui Zhang, Peidong Jia et al. |
|---|---|
| Primary category | cs.CV |
| Published | 19 May 2026 |
| Last updated at source | 8 October 2026 |
Models and datasets referencing this paper
- Zoorao/HTEWorldDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.