UMass-Foundation-Model/3D-VLA
[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model
Python
Issues
- 0
3D Embodied Instruction Tuning Dataset
#6 opened by zubair-irshad - 1
raise EnvironmentError( OSError: stabilityai/stable-diffusion-2 does not appear to have a file named scheduler_config.json
#5 opened by cjmdd - 0
- 0
Questions about the training cost
#3 opened by wxz1996 - 1
robot action coordinates
#2 opened by Todibo99 - 1
Release code time
#1 opened by Johnx69