{
 "id": "Cognitive-Lab/NayanaOCR_Corpus_2025",
 "owner": "Cognitive-Lab",
 "name": "NayanaOCR_Corpus_2025",
 "downloads": 8752,
 "likes": 19,
 "last_modified": "2026-05-25T16:45:43.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": "nayana-ocr-research-license",
 "licence_link": "LICENSE.md",
 "file_licence": "cc-by-nc-4.0",
 "licence_files": [
  "LICENSE.md"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text",
  "visual-question-answering",
  "image-text-to-text"
 ],
 "citation": "@inproceedings{kolavi2025nayanaocr,\n  title     = {Nayana {OCR}: A Scalable Framework for Document {OCR} in Low-Resource Languages},\n  author    = {Kolavi, Adithya S. and Samarth, P. and Jain, Vyoman},\n  booktitle = {Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC)},\n  year      = {2025},\n  pages     = {86--103},\n  url       = {https://aclanthology.org/2025.lm4uc-1.11/}\n}\n\n@inproceedings{kolavi2025nayana,\n  title     = {Nayana: A Foundation for Document-Centric Vision-Language Models via Multi-Task, Multimodal, and Multilingual Data Synthesis},\n  author    = {Kolavi, Adithya S. and Samarth, P. and Jain, Vyoman},\n  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) -- CV4DC},\n  year      = {2025},\n  pages     = {1678--1687},\n  url       = {https://openaccess.thecvf.com/content/ICCV2025W/CV4DC/html/Kolavi_Nayana_A_Foundation_for_Document-Centric_Vision-Language_Models_via_Multi-Task_Multimodal_ICCVW_2025_paper.html}\n}\n\n@misc{kolavi2025m3dr,\n  title         = {{M3DR}: Towards Universal Multilingual Multimodal Document Retrieval},\n  author        = {Kolavi, Adithya S. and Jain, Vyoman},\n  year          = {2025},\n  eprint        = {2512.03514},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.IR},\n  url           = {https://arxiv.org/abs/2512.03514}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions."
}