{"url":"/dataset/r1-onevision","name":"R1-Onevision","full_name":null,"description_markdown":"The R1-Onevision dataset is a meticulously crafted resource designed to empower models with advanced multimodal reasoning capabilities. Aimed at bridging the gap between visual and textual understanding, this dataset provides rich, context-aware reasoning tasks across diverse domains, including natural scenes, science, mathematical problems, OCR-based content, and complex charts.\r\n\r\nIt combines high-quality data from LLaVA-OneVision with domain-specific datasets, each carefully selected and filtered to provide a solid foundation for complex visual reasoning tasks. With a focus on enabling deep reasoning and accurate model predictions, R1-Onevision equips models to handle a variety of visual and textual inputs, tackling intricate reasoning challenges with precision.","description_withheld":null,"homepage":"https://huggingface.co/datasets/Fancy-MLLM/R1-Onevision","introduced_date":"2025-02-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/r1-onevision-an-open-source-multimodal-large","title":"R1-Onevision：An Open-Source Multimodal Large Language Model Capable of Deep Reasoning","first_author":"Yi Yang*","url":null},"license":{"name":"apache-2.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multimodal Reasoning","url":"/task/multimodal-reasoning","datasets_with_task":"/datasets/task/multimodal-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["R1-Onevision"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}