{"url":"/dataset/i2l-140k","name":"I2L-140K","full_name":null,"description_markdown":"Introduced by Singh, Sumeet S.. “Teaching Machines to Code: Neural Markup Generation with Visual Attention.” ArXiv abs/1802.05415 (2018): n. pag.\r\n\r\nA prebuilt dataset for OpenAI's task for image-2-latex system. Includes total of ~140k formulas and images splitted into train, validation and test sets. Superset of im2latex-100K dataset.","description_withheld":null,"homepage":"https://untrix.github.io/i2l/","introduced_date":"2018-02-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/teaching-machines-to-code-neural-markup","title":"Teaching Machines to Code: Neural Markup Generation with Visual Attention","first_author":"Sumeet S. Singh","url":null},"license":null,"modalities":[],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[],"variants":["I2L-140K"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/optical-character-recognition-on-i2l-140k","task":"Optical Character Recognition (OCR)","dataset_variant":"I2L-140K","rows":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"I2L-NOPOOL","paper":"/paper/teaching-machines-to-code-neural-markup","metrics":{"BLEU":"89.09%"},"code_links":[{"title":"untrix/im2latex","url":"https://github.com/untrix/im2latex"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/teaching-machines-to-code-neural-markup","title":"Teaching Machines to Code: Neural Markup Generation with Visual Attention","date":"2018-02-15","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}