{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/room-across-room-multilingual-vision-and","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","arxiv_id":"2010.07954","date":"2020-10-15","proceeding":"EMNLP 2020 11","authors":["Alexander Ku","Peter Anderson","Roma Patel","Eugene Ie","Jason Baldridge"],"abstract":"We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes the role of language in VLN by addressing known biases in paths and eliciting more references to visible entities. Furthermore, each word in an instruction is time-aligned to the virtual poses of instruction creators and validators. We establish baseline scores for monolingual and multilingual settings and multitask learning when including Room-to-Room annotations. We also provide results for a model that learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations. The size, scope and detail of RxR dramatically expands the frontier for research on embodied language agents in simulated, photo-realistic environments.","url_abs":"https://arxiv.org/abs/2010.07954v1","url_pdf":"https://arxiv.org/pdf/2010.07954v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"room-across-room-multilingual-vision-and","repo_url":"https://github.com/google-research-datasets/RxR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"room-across-room-multilingual-vision-and","repo_url":"https://github.com/VegB/Diagnose_VLN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"room-across-room-multilingual-vision-and","repo_url":"https://github.com/jacobkrantz/VLN-CE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[],"datasets_introduced":[{"slug":"rxr","name":"RxR","full_name":"Room-across-Room"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","task":"Vision and Language Navigation","dataset":"RxR","model":"Monolingual Baseline","rank_in_archive_order":5,"of":6,"metrics":{"ndtw":"41.05"},"uses_additional_data":false},{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","task":"Vision and Language Navigation","dataset":"RxR","model":"Multilingual Baseline","rank_in_archive_order":6,"of":6,"metrics":{"ndtw":"36.81"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.07954","atlas_url":"https://app.syntology.ai/?focus=2010.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07954"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacobkrantz/VLN-CE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VegB/Diagnose_VLN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research-datasets/RxR","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7b5b4685db18fbca","entry":"compute_bleu","repo":"VegB/Diagnose_VLN","repo_kind":"listed","path":"rxr/model/CLIP-ViL-VLN/r2r_src/bleu.py","file_url":"https://github.com/VegB/Diagnose_VLN/blob/HEAD/rxr/model/CLIP-ViL-VLN/r2r_src/bleu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b5b4685db18fbca"}},{"code_sha256_prefix":"57e01d248c7840a8","entry":"get_label_for_setting","repo":"VegB/Diagnose_VLN","repo_kind":"listed","path":"r2r/model/Recurrent-VLN-BERT/r2r_src/utils.py","file_url":"https://github.com/VegB/Diagnose_VLN/blob/HEAD/r2r/model/Recurrent-VLN-BERT/r2r_src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57e01d248c7840a8"}},{"code_sha256_prefix":"e3a90df1a875a38e","entry":"load_nav_graphs","repo":"VegB/Diagnose_VLN","repo_kind":"listed","path":"r2r/model/Recurrent-VLN-BERT/r2r_src/utils.py","file_url":"https://github.com/VegB/Diagnose_VLN/blob/HEAD/r2r/model/Recurrent-VLN-BERT/r2r_src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3a90df1a875a38e"}},{"code_sha256_prefix":"6468f9e62900b58c","entry":"read_tsv","repo":"VegB/Diagnose_VLN","repo_kind":"listed","path":"rxr/model/CLIP-ViL-VLN/precomute_imagenet_views.py","file_url":"https://github.com/VegB/Diagnose_VLN/blob/HEAD/rxr/model/CLIP-ViL-VLN/precomute_imagenet_views.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6468f9e62900b58c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}