{"url":"/dataset/luma","name":"LUMA","full_name":"Learning from Uncertain and Multimodal Data","description_markdown":"LUMA is a multimodal dataset that consists of audio, image, and text modalities. It allows controlled injection of uncertainties into the data and is mainly intended for studying uncertainty quantification in multimodal classification settings. \r\nThis repository provides the Audio and Text modalities. The image modality consists of images from [CIFAR-10/100](https://www.cs.toronto.edu/~kriz/cifar.html) datasets. \r\nTo download the image modality and compile the dataset with a specified amount of uncertainties, please use the [LUMA compilation tool](https://github.com/bezirganyan/LUMA).","description_withheld":null,"homepage":"https://huggingface.co/datasets/bezirganyan/LUMA","introduced_date":"2024-06-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/luma-a-benchmark-dataset-for-learning-from","title":"LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data","first_author":"Grigor Bezirganyan","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Multimodal Deep Learning","url":"/task/multimodal-deep-learning","datasets_with_task":"/datasets/task/multimodal-deep-learning"},{"name":"Decision Making Under Uncertainty","url":"/task/decision-making-under-uncertainty","datasets_with_task":"/datasets/task/decision-making-under-uncertainty"},{"name":"Uncertainty Quantification","url":"/task/uncertainty-quantification","datasets_with_task":"/datasets/task/uncertainty-quantification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LUMA"],"data_loaders":[{"repo":"https://github.com/bezirganyan/luma","url":"https://github.com/bezirganyan/luma","frameworks":["pytorch"]}],"num_papers_in_archive":2,"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."}