alt Hacker NewsOpenVLA is basically a slightly modified, fine-tuned llama2. I found the launch/intro talk by lead author to be quite accessible: https://www.youtube.com/watch?v=-0s0v3q7mBk
Replies
KoolKat23 • 06/25/2025
In the paper at the bottom of googles page, this VLA says it is built on the foundations of Gemini 2.0 (hence my quotations). They'd be using Gemini 2.0 rather than llama.
A more modern one, smolVLA is similar and uses a VLM but skips a few layers and uses an action adapter for outputs. Both are from HF and run on LeRobot.
https://arxiv.org/abs/2506.01844
Explanation by PhosphoAI: https://www.youtube.com/watch?v=00A6j02v450