Vision Language Action Dreaming

Predict robot actions through a perception-prediction-action loop: forecast dynamic regions, depth, and semantic features from visual observations, then generate action sequences via diffusion transformers.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 77f7c4893d

Frequently asked questions

npx get-skill add adu2021/vision-language-action-dreaming