Apps · PROJECT NOTES
GUI-World
A GUI video dataset and offline benchmark for understanding interface content, changes and operation sequences across desktop, mobile, web and XR recordings.
What can you do with it?
Train on annotated GUI videos and evaluate temporal understanding through the released question-answering splits and inference/judging code.
What should you know before using it?
Video question answering does not execute GUI actions or verify workflow completion. The dataset is public under CC BY 4.0; evaluation needs a chosen model and, for judged responses, a configured judge. GUI-Vid is the associated model, not a separate environment.
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
- Web, macOS, Windows, iOS, Android