KORMo-VL/Ko-Screenspot
Dataset · https://huggingface.co/datasets/KORMo-VL/Ko-Screenspot
🇰🇷 Ko-Screenspot A Korean GUI grounding benchmark, built manually by native Korean annotators. 📋 3,319 samples · 🌐 142 websites · ✍️ ~480 annotator-hours · 🎯 GUI grounding 📌 Overview Ko-Screenspot is a single-image GUI grounding benchmark for Korean websites. It contains 3,319 screenshot–instruction pairs across 142 websites, derived from 540 human-recorded tasks. Instructions are written in Korean, and each sample includes an annotated target element. The… See the full description on the dataset page: https://huggingface.co/datasets/KORMo-VL/Ko-Screenspot.
First seen by Oriel on .
No saved summary available.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Datasets: 17, latest observation ; +6 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Datasets: 0, latest observation ; 0 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Datasets | KORMo-VL/Ko-Screenspot | https://huggingface.co/datasets/KORMo-VL/Ko-Screenspot Read discussion |