Article

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

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.

Part of the event: DirectWAM: A Single-Step De-Diffusion World-Action Model

This page provides a summary and source link only.