OmniParser ‘tokenizes’ UI screenshots from pixel spaces into structured elements in the screenshot that are interpretable by LLMs. This enables the LLMs to do retrieval based next action prediction given a set of parsed interactable elements.
Subscribe
Sign in
Microsoft Research has unveiled their own Computer Use model trained on a ton of labeled screenshots.
The v2 achieves a 60% improvement in latency compared to V1 (avg latency: 0.6s/frame on A100, 0.8s on single 4090).
Really cool! Hopefully it will be ported to more languages soon!
Shram
Congrats on the launch and lots of wins to the team :)