Apps · PROJECT NOTES
UI-Vision
An offline desktop GUI benchmark with publicly released element-grounding and layout-grounding screenshots, annotations and evaluation code.
What can you do with it?
Evaluate target localization and spatial/layout understanding on screenshots from desktop software.
What should you know before using it?
The public release covers grounding; the paper's action-prediction component still has a 'Coming soon' placeholder. This is static screenshot evaluation, not a desktop execution environment. The public dataset card declares MIT and evaluation use; native OS support is not established by the artifact.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Dataset + benchmark
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation