Haoyang Weng (@ElijahGalahad)
2026-01-20 | โค๏ธ 307 | ๐ 47
Introducing vla-scratch: a modular, performant and efficient stack for VLAs. https://t.co/OJQTui7ls9
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://t.co/999ZcEP5qV
๋ฏธ๋์ด
