All datasets / visual-abstention

visual-abstention/VisTA-Train

127 downloads in 30 days0 likesLast modified 6 Oct 2026View on Hugging Face

Permissive or share-alike

The declared licence (apache-2.0) is classified as permissive.

Declared licence: apache-2.0, from the tagEvidence: README.md at 312fa72
Licence files: No licence file at the top level of the repositoryEvidence: file list at 312fa72
Declared sources: None listed in the card metadata
Access gated on Hugging Face: No

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

image-to-image

Citation text from the card

@article{shi2026visual,
  title   = {Visual Abstention in Unified Multimodal Models},
  author  = {Shi, Chufan and Yang, Cheng and Yang, Tiannuo and White, Isadora and Chen, Yiwei and Berg-Kirkpatrick, Taylor and Ma, Xuezhe},
  journal = {arXiv preprint arXiv:<ARXIV_ID>},
  year    = {2026}
}

@inproceedings{han2026unireditbench,
  title     = {UniREditBench: A Unified Reasoning-based Image Editing Benchmark},
  author    = {Han, Feng and Wang, Yibin and Li, Chenglin and Liang, Zheming and Wang, Dianyi and Jiao, Yang and Wei, Zhipeng and Gong, Chao and Jin, Cheng and Wang, Jiaqi},
  booktitle = {European Conference on Computer Vision},
  pages     = {287--304},
  year      = {2026}
}

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "visual-abstention/VisTA-Train" })
signal: "permissive"
stated_licence: "apache-2.0"
sources: 0