# Video-Point Model learns 4D world through point trajectory prediction, improving robot manipulation success rate

- Source: HuggingFace Daily Papers
- Published: 2026-10-20T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/agljhembnjn5utv4zpisowzg3
- Original: https://huggingface.co/papers/2610.28594

## Summary

The paper proposes Video-Point Model (VPM), a world model that conditions on multi-view video histories and language instructions to jointly predict future videos from arbitrary viewpoints and the 3D trajectories of persistent scene points. The authors add camera-conditioned multi-view processing and a trajectory prediction head to a pretrained world model, and build the VPM-Data simulation corpus and the VP-WorldBench benchmark; they further add robot actions as a token modality in the generator, so that the policy shares the point-supervised backbone.