# DirectWAM: Distilling Cascaded World-Action Models into Single-Step Action Prediction

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/kzpw10rfbnt8cj6lqrke9a1uc
- Original: https://arxiv.org/abs/2610.28122

## Summary

The paper proposes DirectWAM, which converts pretrained video and action experts into single-step predictors that require no stochastic sampling while retaining the explicit future-to-action cascade structure. After learning a single-step action model, the method trains the future predictor by decoding actions from its own predicted futures and backpropagating demonstration action error.