{
 "id": "EmbodiedCity/EmbodiedNav-Bench",
 "owner": "EmbodiedCity",
 "name": "EmbodiedNav-Bench",
 "downloads": 596,
 "likes": 1,
 "last_modified": "2026-08-19T07:15:08.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering",
  "reinforcement-learning"
 ],
 "citation": "@inproceedings{10.1145/3770855.3817501,\n      author = {Zhao, Baining and Wang, Ziyou and Fang, Jianjie and Zhou, Zile and Xu, Yanggang and Ji, Yatai and Xu, Jiacheng and Zhang, Qian and Zhang, Weichen and Gao, Chen and Chen, Xinlei},\n      title = {How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace},\n      year = {2026},\n      isbn = {9798400722592},\n      publisher = {Association for Computing Machinery},\n      address = {New York, NY, USA},\n      url = {https://doi.org/10.1145/3770855.3817501},\n      doi = {10.1145/3770855.3817501},\n      booktitle = {Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2},\n      pages = {10326–10337},\n      numpages = {12},\n      keywords = {embodied intelligence, foundation model, urban airspace},\n      location = {Republic of Korea},\n      series = {KDD '26}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "af674dde5ab14f22792907299ec3ed6ffa21e0c9",
 "stated_evidence": "https://huggingface.co/datasets/EmbodiedCity/EmbodiedNav-Bench/blob/af674dde5ab14f22792907299ec3ed6ffa21e0c9/README.md",
 "file_evidence": "https://huggingface.co/datasets/EmbodiedCity/EmbodiedNav-Bench/tree/af674dde5ab14f22792907299ec3ed6ffa21e0c9",
 "card_nc": false
}