Hacker News
- OmniParser V2 – A simple screen parsing tool towards pure vision based GUI agent https://github.com/microsoft/OmniParser 4 comments
Linking pages
Linked pages
- OmniParser https://microsoft.github.io/OmniParser/ 34 comments
- The MIT License | Open Source Initiative https://opensource.org/licenses/MIT 15 comments
- [2408.00203] OmniParser for Pure Vision Based GUI Agent https://arxiv.org/abs/2408.00203 0 comments
- Windows Agent Arena: Evaluating Multi-modal OS Agents at Scale https://microsoft.github.io/WindowsAgentArena/ 0 comments
- microsoft/OmniParser · Hugging Face https://huggingface.co/microsoft/OmniParser 0 comments
- OmniParser V2: Turning Any LLM into a Computer Use Agent - Microsoft Research https://www.microsoft.com/en-us/research/articles/omniparser-v2-turning-any-llm-into-a-computer-use-agent/ 0 comments
Related searches:
Search whole site: site:github.com
Search title: GitHub - microsoft/OmniParser: A simple screen parsing tool towards pure vision based GUI agent
See how to search.