{"url":"/dataset/rxr","name":"RxR","full_name":"Room-across-Room","description_markdown":"Room-Across-Room (RxR) is a multilingual dataset for Vision-and-Language Navigation (VLN) for Matterport3D environments. In contrast to related datasets such as Room-to-Room (R2R), RxR is 10x larger, multilingual (English, Hindi and Telugu), with longer and more variable paths, and it includes and fine-grained visual groundings that relate each word to pixels/surfaces in the environment.\r\n\r\nSource: [Room-Across-Room (RxR) Dataset](https://github.com/google-research-datasets/RxR)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/RxR","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/room-across-room-multilingual-vision-and","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","first_author":"Alexander Ku","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Vision and Language Navigation","url":"/task/vision-and-language-navigation","datasets_with_task":"/datasets/task/vision-and-language-navigation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Telugu","url":"/datasets/language/telugu"}],"variants":["RxR"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/RxR","url":"https://github.com/google-research-datasets/RxR","frameworks":["tf"]}],"num_papers_in_archive":54,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","task":"Vision and Language Navigation","dataset_variant":"RxR","rows":6,"metrics":["ndtw"],"first_row_in_archive_order":{"model":"MARVAL","paper":"/paper/a-new-path-scaling-vision-and-language","metrics":{"ndtw":"66.76"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-new-path-scaling-vision-and-language","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","date":"2022-10-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/envedit-environment-editing-for-vision-and","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":7,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/room-across-room-multilingual-vision-and","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","date":"2020-10-15","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":34,"samples_ran":15,"samples_unverified":19,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":1,"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."}