PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
Adds lightweight physical dynamics tokens to a vision-language-action model, avoiding slow video generation in the loop.
Explainer · on the wire
The explainer for this story is still on the wire.
The claim, the mechanism, and the figures land here once generated.
Source · arXiv wire
arxiv.org/abs/2610.37381cs.RO · cs.CV · cs.LG