Original Tweet
Introducing vla-scratch: a modular, performant and efficient stack for VLAs. https://github.com/EGalahad/vla-scratch
I started it because existing codebases were either slow, or hard to extend for co-training with clean data abstractions. This repo is a ground-up attempt to address both. https://x.com/ElijahGalahad/status/2013644966854357173/video/1
๐ ์๋ณธ ๋งํฌ
- https://github.com/EGalahad/vla-scratch
- https://x.com/ElijahGalahad/status/2013644966854357173/video/1
๋ฏธ๋์ด
๐ Related
- a-compact-04b-vision-language-action-model-that-finally-lets-robots-manipulate-m โ ์ฃผ์ : Vla
- dynamicvla โ ์ฃผ์ : Vla
- the-next-evolution-vla-models โ ์ฃผ์ : Vla
- video-models-serve-as-a-good-pretrained-backbone-for-robot-policies โ ์ฃผ์ : Vla
- what-if-your-robot-or-car-could-see-depth-more-clearly-than- โ ์ฃผ์ : Vla