DriftWorld: Fast World Modeling through Drifting

Published
Source
arXiv
Paper number
645
Field
Robotics
arXiv ID
2607.15065

Key points

  • It is the first application of a drifting generative model, which generates in a single forward pass, to a robotic world model and achieves 30-plus fps, 17 times faster than diffusion.
  • It proposes three adaptations: an action-conditioned drifting field, a loss in the DINOv2 feature space, and frame-wise action conditioning.
  • On Push-T, it raises IoU from 0.635 to 0.781, which greatly improves action-exploration quality, and it shows consistent gains across 5 environments.
  • It is also valid as an offline policy-evaluation metric and achieves a Pearson correlation of 0.92 to 0.99 with actual performance.
  • It proves that fast and accurate imagination directly helps both robot planning and policy evaluation.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)