{
 "id": "nyu-visionx/VSI-Bench",
 "owner": "nyu-visionx",
 "name": "VSI-Bench",
 "downloads": 12510,
 "likes": 74,
 "last_modified": "2026-10-08T00:09:17.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering"
 ],
 "citation": "@inproceedings{yang2025thinking,\n    title={{Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces}},\n    author={Yang, Jihan and Yang, Shusheng and Gupta, Anjali and Han, Rilyn and Fei-Fei, Li and Xie, Saining},\n    booktitle={CVPR},\n    year={2025},\n}\n\n@inproceedings{brown2026benchmark,\n    title={{Benchmark Designers Should ``Train on the Test Set'' to Expose Exploitable Non-Visual Shortcuts}},\n    author={Brown, Ellis and Yang, Jihan and Yang, Shusheng and Fergus, Rob and Xie, Saining},\n    booktitle={COLM},\n    year={2026},\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "3a6a1cf9ac54c403509b15260897cc6ddc41b408",
 "stated_evidence": "https://huggingface.co/datasets/nyu-visionx/VSI-Bench/blob/3a6a1cf9ac54c403509b15260897cc6ddc41b408/README.md",
 "file_evidence": "https://huggingface.co/datasets/nyu-visionx/VSI-Bench/tree/3a6a1cf9ac54c403509b15260897cc6ddc41b408",
 "card_nc": false
}