🛠️ Steven Gong

Search

SearchSearch

Mar 17, 2025, 1 min read

Vision-Language Action Model (VLA)

This was first introduced through RT-2.

  • https://robotics-transformer2.github.io/

Models:

  • OpenVLA

Graph View

Backlinks

  • OpenVLA
  • RT-1-X
  • Vision-Language Model (VLM)

Created with Quartz, © 2025

  • Blog
  • LinkedIn
  • Twitter
  • GitHub