{"url":"/dataset/infinity-mm","name":"Infinity-MM","full_name":null,"description_markdown":"We collect, organize and open-source the large-scale multimodal instruction dataset, Infinity-MM, consisting of tens of millions of samples. Through quality filtering and deduplication, the dataset has high quality and diversity. We propose a synthetic data generation method based on open-source models and labeling system, using detailed image annotations and diverse question generation.","description_withheld":null,"homepage":"https://huggingface.co/datasets/BAAI/Infinity-MM","introduced_date":"2024-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/infinity-mm-scaling-multimodal-performance","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","first_author":"Shuhao Gu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Visual Grounding","url":"/task/visual-grounding","datasets_with_task":"/datasets/task/visual-grounding"},{"name":"Object Discovery","url":"/task/object-discovery","datasets_with_task":"/datasets/task/object-discovery"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Infinity-MM"],"data_loaders":[],"num_papers_in_archive":5,"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":"2026-09-25T09:33:49+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."}