ChenDL09's picture
add Goal-depth LDM
c816139
---
license: mit
---
# 3D-VLA: A 3D Vision-Language-Action Generative World Model
Model card for 3D-VLA
<img src="https://vis-www.cs.umass.edu/3dvla/static/video/3dvla_arch.mp4" alt="Logo" width="90%">