{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/vision-and-language-navigation","name":"Vision and Language Navigation","slug":"vision-and-language-navigation","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":223,"papers_with_code":114,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":13,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/vision-and-language-navigation-on-vln","slug":"vision-and-language-navigation-on-vln","dataset":"VLN Challenge","dataset_url":null,"rows_in_archive":145,"metrics":["success","length","error","oracle success","spl"],"first_row_in_archive_order":{"model":"human","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/vision-and-language-navigation-on-touchdown","slug":"vision-and-language-navigation-on-touchdown","dataset":"Touchdown Dataset","dataset_url":"/dataset/touchdown-dataset","rows_in_archive":12,"metrics":["Task Completion (TC)"],"first_row_in_archive_order":{"model":"FLAME","paper_title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","paper_url":"/paper/flame-learning-to-navigate-with-multimodal","paper_date":"2024-08-20","arxiv_id":"2408.11051","code_links":[{"title":"xyz9911/FLAME","url":"https://github.com/xyz9911/FLAME"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flame-learning-to-navigate-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.11051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11051"}},"official":{"repos":["xyz9911/FLAME"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","slug":"vision-and-language-navigation-on-rxr","dataset":"RxR","dataset_url":"/dataset/rxr","rows_in_archive":6,"metrics":["ndtw"],"first_row_in_archive_order":{"model":"MARVAL","paper_title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","paper_url":"/paper/a-new-path-scaling-vision-and-language","paper_date":"2022-10-06","arxiv_id":"2210.03112","code_links":[],"syntology":null}},{"leaderboard":"/sota/vision-and-language-navigation-on-map2seq","slug":"vision-and-language-navigation-on-map2seq","dataset":"map2seq","dataset_url":"/dataset/map2seq","rows_in_archive":5,"metrics":["Task Completion (TC)"],"first_row_in_archive_order":{"model":"FLAME","paper_title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","paper_url":"/paper/flame-learning-to-navigate-with-multimodal","paper_date":"2024-08-20","arxiv_id":"2408.11051","code_links":[{"title":"xyz9911/FLAME","url":"https://github.com/xyz9911/FLAME"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flame-learning-to-navigate-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.11051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11051"}},"official":{"repos":["xyz9911/FLAME"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/vision-and-language-navigation-on-robo-vln","slug":"vision-and-language-navigation-on-robo-vln","dataset":"robo-vln","dataset_url":"/dataset/robo-vln","rows_in_archive":1,"metrics":["SPL (Sucess Weighted by Path Length)"],"first_row_in_archive_order":{"model":"Hierarchical Cross-Modal Agent","paper_title":"Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation","paper_url":"/paper/hierarchical-cross-modal-agent-for-robotics","paper_date":"2021-04-21","arxiv_id":"2104.10674","code_links":[{"title":"GT-RIPL/robo-vln","url":"https://github.com/GT-RIPL/robo-vln"}],"syntology":null}}],"datasets":[{"url":"/dataset/rxr","name":"RxR","full_name":"Room-across-Room","num_papers_in_archive":54},{"url":"/dataset/streetlearn","name":"StreetLearn","full_name":"","num_papers_in_archive":30},{"url":"/dataset/minos","name":"MINOS","full_name":"MINOS","num_papers_in_archive":22},{"url":"/dataset/touchdown-dataset","name":"Touchdown Dataset","full_name":null,"num_papers_in_archive":19},{"url":"/dataset/talk-the-walk","name":"Talk the Walk","full_name":"","num_papers_in_archive":11},{"url":"/dataset/chalet","name":"CHALET","full_name":"Cornell House Agent Learning Environment","num_papers_in_archive":10},{"url":"/dataset/weblinx","name":"WebLINX","full_name":"Real-World Website Navigation with Multi-Turn","num_papers_in_archive":6},{"url":"/dataset/map2seq","name":"map2seq","full_name":"","num_papers_in_archive":5},{"url":"/dataset/run","name":"RUN","full_name":"The RUN Dataset","num_papers_in_archive":5},{"url":"/dataset/arramon","name":"ArraMon","full_name":"","num_papers_in_archive":3},{"url":"/dataset/fine-grained-r2r","name":"Fine-Grained R2R","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/robo-vln","name":"robo-vln","full_name":"Robotics Vision-and-Language Navigation","num_papers_in_archive":2},{"url":"/dataset/talk2nav","name":"Talk2Nav","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":223,"of_with_code":114,"tagged_in_all":223,"counts":{"archive_papers_tagged":223,"with_a_code_link":114,"where_syntology_ran_a_sample":52,"not_listed_spam_title":0,"listed":223,"listed_where_code_ran":52,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":48,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":48,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/vision-and-language-navigation-interpreting","slug":"vision-and-language-navigation-interpreting","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","date":"2017-11-20","arxiv_id":"1711.07280","repositories_listed":8,"syntology":null},{"url":"/paper/beyond-the-nav-graph-vision-and-language","slug":"beyond-the-nav-graph-vision-and-language","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","date":"2020-04-06","arxiv_id":"2004.02857","repositories_listed":5,"syntology":null},{"url":"/paper/how-much-can-clip-benefit-vision-and-language","slug":"how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","arxiv_id":"2107.06383","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-much-can-clip-benefit-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.06383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06383"}},"official":{"repos":["clip-vil/CLIP-ViL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/retouchdown-adding-touchdown-to-streetlearn","slug":"retouchdown-adding-touchdown-to-streetlearn","title":"Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View","date":"2020-01-10","arxiv_id":"2001.03671","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retouchdown-adding-touchdown-to-streetlearn#ran","syntology_url":"https://syntology.ai/paper/2001.03671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.03671"}},"official":{"repos":["google-research/valan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/touchdown-natural-language-navigation-and","slug":"touchdown-natural-language-navigation-and","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","date":"2018-11-29","arxiv_id":"1811.12354","repositories_listed":4,"syntology":null},{"url":"/paper/room-across-room-multilingual-vision-and","slug":"room-across-room-multilingual-vision-and","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","date":"2020-10-15","arxiv_id":"2010.07954","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/room-across-room-multilingual-vision-and#ran","syntology_url":"https://syntology.ai/paper/2010.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07954"}},"official":{"repos":["google-research-datasets/RxR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-regretful-agent-heuristic-aided","slug":"the-regretful-agent-heuristic-aided","title":"The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation","date":"2019-03-05","arxiv_id":"1903.01602","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-regretful-agent-heuristic-aided#ran","syntology_url":"https://syntology.ai/paper/1903.01602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.01602"}},"official":{"repos":["chihyaoma/regretful-agent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hierarchical-spatial-proximity-reasoning-for","slug":"hierarchical-spatial-proximity-reasoning-for","title":"Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation","date":"2024-03-18","arxiv_id":"2403.11541","repositories_listed":2,"syntology":null},{"url":"/paper/weblinx-real-world-website-navigation-with","slug":"weblinx-real-world-website-navigation-with","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","date":"2024-02-08","arxiv_id":"2402.05930","repositories_listed":2,"syntology":{"n":27,"n_ran":21,"n_constructed":0,"n_ran_checked":12,"n_instrument":9,"n_unverified":6,"n_honours":2,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/weblinx-real-world-website-navigation-with#ran","syntology_url":"https://syntology.ai/paper/2402.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05930"}},"official":{"repos":["McGill-NLP/weblinx","McGill-NLP/webllama"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navgpt-explicit-reasoning-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.16986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16986"}},"official":{"repos":["gengzezhou/navgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/airbert-in-domain-pretraining-for-vision-and","slug":"airbert-in-domain-pretraining-for-vision-and","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","date":"2021-08-20","arxiv_id":"2108.09105","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/airbert-in-domain-pretraining-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2108.09105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09105"}},"official":{"repos":["airbert-vln/airbert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-monitoring-navigation-agent-via","slug":"self-monitoring-navigation-agent-via","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","date":"2019-01-10","arxiv_id":"1901.03035","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-monitoring-navigation-agent-via#ran","syntology_url":"https://syntology.ai/paper/1901.03035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.03035"}},"official":{"repos":["chihyaoma/selfmonitoring-agent"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/navmorph-a-self-evolving-world-model-for","slug":"navmorph-a-self-evolving-world-model-for","title":"NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments","date":"2025-06-30","arxiv_id":"2506.23468","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navmorph-a-self-evolving-world-model-for#ran","syntology_url":"https://syntology.ai/paper/2506.23468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.23468"}},"official":{"repos":["feliciaxyao/navmorph"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2506-10172","slug":"2506-10172","title":"A Navigation Framework Utilizing Vision-Language Models","date":"2025-06-11","arxiv_id":"2506.10172","repositories_listed":1,"syntology":null},{"url":"/paper/cross-from-left-to-right-brain-adaptive-text","slug":"cross-from-left-to-right-brain-adaptive-text","title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","date":"2025-05-27","arxiv_id":"2505.20897","repositories_listed":1,"syntology":null},{"url":"/paper/flightgpt-towards-generalizable-and","slug":"flightgpt-towards-generalizable-and","title":"FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models","date":"2025-05-19","arxiv_id":"2505.12835","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11383","slug":"2505-11383","title":"Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation","date":"2025-05-16","arxiv_id":"2505.11383","repositories_listed":1,"syntology":null},{"url":"/paper/citynavagent-aerial-vision-and-language","slug":"citynavagent-aerial-vision-and-language","title":"CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory","date":"2025-05-08","arxiv_id":"2505.05622","repositories_listed":1,"syntology":null},{"url":"/paper/navrag-generating-user-demand-instructions","slug":"navrag-generating-user-demand-instructions","title":"NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM","date":"2025-02-16","arxiv_id":"2502.11142","repositories_listed":1,"syntology":null},{"url":"/paper/general-scene-adaptation-for-vision-and","slug":"general-scene-adaptation-for-vision-and","title":"General Scene Adaptation for Vision-and-Language Navigation","date":"2025-01-29","arxiv_id":"2501.17403","repositories_listed":1,"syntology":{"n":14,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/general-scene-adaptation-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2501.17403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.17403"}},"official":{"repos":["honghd16/gsa-vln"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-journey-beyond-rgb-unveiling-hybrid","slug":"agent-journey-beyond-rgb-unveiling-hybrid","title":"Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation","date":"2024-12-09","arxiv_id":"2412.06465","repositories_listed":1,"syntology":null},{"url":"/paper/g3d-lf-generalizable-3d-language-feature","slug":"g3d-lf-generalizable-3d-language-feature","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","date":"2024-11-26","arxiv_id":"2411.17030","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/g3d-lf-generalizable-3d-language-feature#ran","syntology_url":"https://syntology.ai/paper/2411.17030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17030"}},"official":{"repos":["MrZihan/g3D-LF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spatially-aware-speaker-for-vision-and","slug":"spatially-aware-speaker-for-vision-and","title":"Spatially-Aware Speaker for Vision-and-Language Navigation Instruction Generation","date":"2024-09-09","arxiv_id":"2409.05583","repositories_listed":1,"syntology":null},{"url":"/paper/flame-learning-to-navigate-with-multimodal","slug":"flame-learning-to-navigate-with-multimodal","title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","date":"2024-08-20","arxiv_id":"2408.11051","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flame-learning-to-navigate-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.11051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11051"}},"official":{"repos":["xyz9911/FLAME"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/narrowing-the-gap-between-vision-and-action","slug":"narrowing-the-gap-between-vision-and-action","title":"Narrowing the Gap between Vision and Action in Navigation","date":"2024-08-19","arxiv_id":"2408.10388","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21452","slug":"2407-21452","title":"Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments","date":"2024-07-31","arxiv_id":"2407.21452","repositories_listed":1,"syntology":null},{"url":"/paper/navgpt-2-unleashing-navigational-reasoning","slug":"navgpt-2-unleashing-navigational-reasoning","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","date":"2024-07-17","arxiv_id":"2407.12366","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/navgpt-2-unleashing-navigational-reasoning#ran","syntology_url":"https://syntology.ai/paper/2407.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12366"}},"official":{"repos":["gengzezhou/navgpt-2"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pret-planning-with-directed-fidelity","slug":"pret-planning-with-directed-fidelity","title":"PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation","date":"2024-07-16","arxiv_id":"2407.11487","repositories_listed":1,"syntology":null},{"url":"/paper/vision-and-language-navigation-today-and","slug":"vision-and-language-navigation-today-and","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","date":"2024-07-09","arxiv_id":"2407.07035","repositories_listed":1,"syntology":null},{"url":"/paper/into-the-unknown-generating-geospatial","slug":"into-the-unknown-generating-geospatial","title":"Into the Unknown: Generating Geospatial Descriptions for New Environments","date":"2024-06-28","arxiv_id":"2406.19967","repositories_listed":1,"syntology":null},{"url":"/paper/human-aware-vision-and-language-navigation","slug":"human-aware-vision-and-language-navigation","title":"Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions","date":"2024-06-27","arxiv_id":"2406.19236","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/human-aware-vision-and-language-navigation#ran","syntology_url":"https://syntology.ai/paper/2406.19236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19236"}},"official":{"repos":["lpercc/ha3d_simulator"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/magic-meta-ability-guided-interactive-chain","slug":"magic-meta-ability-guided-interactive-chain","title":"MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation","date":"2024-06-25","arxiv_id":"2406.17960","repositories_listed":1,"syntology":null},{"url":"/paper/citynav-language-goal-aerial-navigation","slug":"citynav-language-goal-aerial-navigation","title":"CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information","date":"2024-06-20","arxiv_id":"2406.14240","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/citynav-language-goal-aerial-navigation#ran","syntology_url":"https://syntology.ai/paper/2406.14240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14240"}},"official":null}},{"url":"/paper/sim-to-real-transfer-via-3d-feature-fields","slug":"sim-to-real-transfer-via-3d-feature-fields","title":"Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation","date":"2024-06-14","arxiv_id":"2406.09798","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sim-to-real-transfer-via-3d-feature-fields#ran","syntology_url":"https://syntology.ai/paper/2406.09798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09798"}},"official":{"repos":["MrZihan/Sim2Real-VLN-3DFF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/why-only-text-empowering-vision-and-language","slug":"why-only-text-empowering-vision-and-language","title":"Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts","date":"2024-06-04","arxiv_id":"2406.02208","repositories_listed":1,"syntology":null},{"url":"/paper/augmented-commonsense-knowledge-for-remote","slug":"augmented-commonsense-knowledge-for-remote","title":"Augmented Commonsense Knowledge for Remote Object Grounding","date":"2024-06-03","arxiv_id":"2406.01256","repositories_listed":1,"syntology":null},{"url":"/paper/vision-and-language-navigation-via-causal","slug":"vision-and-language-navigation-via-causal","title":"Vision-and-Language Navigation via Causal Learning","date":"2024-04-16","arxiv_id":"2404.10241","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":2,"n_ran_checked":3,"n_instrument":9,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vision-and-language-navigation-via-causal#ran","syntology_url":"https://syntology.ai/paper/2404.10241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10241"}},"official":{"repos":["crystalsixone/vln-goat"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/delan-dual-level-alignment-for-vision-and","slug":"delan-dual-level-alignment-for-vision-and","title":"DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning","date":"2024-04-02","arxiv_id":"2404.01994","repositories_listed":1,"syntology":null},{"url":"/paper/lookahead-exploration-with-neural-radiance","slug":"lookahead-exploration-with-neural-radiance","title":"Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation","date":"2024-04-02","arxiv_id":"2404.01943","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lookahead-exploration-with-neural-radiance#ran","syntology_url":"https://syntology.ai/paper/2404.01943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01943"}},"official":{"repos":["mrzihan/hnr-vln"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/navcot-boosting-llm-based-vision-and-language","slug":"navcot-boosting-llm-based-vision-and-language","title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","date":"2024-03-12","arxiv_id":"2403.07376","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/navcot-boosting-llm-based-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2403.07376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07376"}},"official":{"repos":["expectorlin/navcot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/navhint-vision-and-language-navigation-agent","slug":"navhint-vision-and-language-navigation-agent","title":"NavHint: Vision and Language Navigation Agent with a Hint Generator","date":"2024-02-04","arxiv_id":"2402.02559","repositories_listed":1,"syntology":null},{"url":"/paper/webvln-vision-and-language-navigation-on","slug":"webvln-vision-and-language-navigation-on","title":"WebVLN: Vision-and-Language Navigation on Websites","date":"2023-12-25","arxiv_id":"2312.15820","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/webvln-vision-and-language-navigation-on#ran","syntology_url":"https://syntology.ai/paper/2312.15820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15820"}},"official":{"repos":["webvln/webvln"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/test-time-adaptive-vision-and-language","slug":"test-time-adaptive-vision-and-language","title":"Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation","date":"2023-11-22","arxiv_id":"2311.13209","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/test-time-adaptive-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2311.13209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13209"}},"official":{"repos":["feliciaxyao/icml2024-fstta"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-entity-landmark-adaptive-pre","slug":"grounded-entity-landmark-adaptive-pre","title":"Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation","date":"2023-08-24","arxiv_id":"2308.12587","repositories_listed":1,"syntology":{"n":30,"n_ran":23,"n_constructed":14,"n_ran_checked":20,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":30,"phrase":"23 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/grounded-entity-landmark-adaptive-pre#ran","syntology_url":"https://syntology.ai/paper/2308.12587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12587"}},"official":{"repos":["csir1996/vln-gela"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":14,"n_ran_no_instrument_failure":20,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/march-in-chat-interactive-prompting-for","slug":"march-in-chat-interactive-prompting-for","title":"March in Chat: Interactive Prompting for Remote Embodied Referring Expression","date":"2023-08-20","arxiv_id":"2308.10141","repositories_listed":1,"syntology":null},{"url":"/paper/vln-petl-parameter-efficient-transfer","slug":"vln-petl-parameter-efficient-transfer","title":"VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation","date":"2023-08-20","arxiv_id":"2308.10172","repositories_listed":1,"syntology":null},{"url":"/paper/aerialvln-vision-and-language-navigation-for","slug":"aerialvln-vision-and-language-navigation-for","title":"AerialVLN: Vision-and-Language Navigation for UAVs","date":"2023-08-13","arxiv_id":"2308.06735","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/aerialvln-vision-and-language-navigation-for#ran","syntology_url":"https://syntology.ai/paper/2308.06735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06735"}},"official":{"repos":["airvln/airvln"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-data-generation-in-vision-and","slug":"scaling-data-generation-in-vision-and","title":"Scaling Data Generation in Vision-and-Language Navigation","date":"2023-07-28","arxiv_id":"2307.15644","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-data-generation-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2307.15644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15644"}},"official":{"repos":["wz0919/scalevln"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kefa-a-knowledge-enhanced-and-fine-grained","slug":"kefa-a-knowledge-enhanced-and-fine-grained","title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation","date":"2023-07-25","arxiv_id":"2307.13368","repositories_listed":1,"syntology":null},{"url":"/paper/gridmm-grid-memory-map-for-vision-and","slug":"gridmm-grid-memory-map-for-vision-and","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","date":"2023-07-24","arxiv_id":"2307.12907","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gridmm-grid-memory-map-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2307.12907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12907"}},"official":{"repos":["mrzihan/gridmm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-navigational-visual-representations","slug":"learning-navigational-visual-representations","title":"Learning Navigational Visual Representations with Semantic Map Supervision","date":"2023-07-23","arxiv_id":"2307.12335","repositories_listed":1,"syntology":null},{"url":"/paper/learning-vision-and-language-navigation-from","slug":"learning-vision-and-language-navigation-from","title":"Learning Vision-and-Language Navigation from YouTube Videos","date":"2023-07-22","arxiv_id":"2307.11984","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-vision-and-language-navigation-from#ran","syntology_url":"https://syntology.ai/paper/2307.11984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11984"}},"official":{"repos":["jeremylinky/youtube-vln"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/behavioral-analysis-of-vision-and-language-1","slug":"behavioral-analysis-of-vision-and-language-1","title":"Behavioral Analysis of Vision-and-Language Navigation Agents","date":"2023-07-20","arxiv_id":"2307.10790","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/behavioral-analysis-of-vision-and-language-1#ran","syntology_url":"https://syntology.ai/paper/2307.10790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10790"}},"official":{"repos":["yoark/vln-behave"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/velma-verbalization-embodiment-of-llm-agents","slug":"velma-verbalization-embodiment-of-llm-agents","title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View","date":"2023-07-12","arxiv_id":"2307.06082","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/velma-verbalization-embodiment-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2307.06082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06082"}},"official":{"repos":["raphael-sch/velma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/geovln-learning-geometry-enhanced-visual-1","slug":"geovln-learning-geometry-enhanced-visual-1","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","date":"2023-05-26","arxiv_id":"2305.17102","repositories_listed":1,"syntology":null},{"url":"/paper/a-dual-semantic-aware-recurrent-global","slug":"a-dual-semantic-aware-recurrent-global","title":"A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation","date":"2023-05-05","arxiv_id":"2305.03602","repositories_listed":1,"syntology":{"n":24,"n_ran":10,"n_constructed":5,"n_ran_checked":6,"n_instrument":4,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/a-dual-semantic-aware-recurrent-global#ran","syntology_url":"https://syntology.ai/paper/2305.03602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03602"}},"official":{"repos":["crystalsixone/dsrg"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/kerm-knowledge-enhanced-reasoning-for-vision","slug":"kerm-knowledge-enhanced-reasoning-for-vision","title":"KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation","date":"2023-03-28","arxiv_id":"2303.15796","repositories_listed":1,"syntology":{"n":10,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/kerm-knowledge-enhanced-reasoning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2303.15796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15796"}},"official":{"repos":["xiangyangli20/kerm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/esceme-vision-and-language-navigation-with","slug":"esceme-vision-and-language-navigation-with","title":"ESceme: Vision-and-Language Navigation with Episodic Scene Memory","date":"2023-03-02","arxiv_id":"2303.01032","repositories_listed":1,"syntology":null},{"url":"/paper/mlanet-multi-level-attention-network-with-sub","slug":"mlanet-multi-level-attention-network-with-sub","title":"MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation","date":"2023-03-02","arxiv_id":"2303.01396","repositories_listed":1,"syntology":null},{"url":"/paper/vln-trans-translator-for-the-vision-and","slug":"vln-trans-translator-for-the-vision-and","title":"VLN-Trans: Translator for the Vision and Language Navigation Agent","date":"2023-02-18","arxiv_id":"2302.09230","repositories_listed":1,"syntology":null},{"url":"/paper/bevbert-topo-metric-map-pre-training-for","slug":"bevbert-topo-metric-map-pre-training-for","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","date":"2022-12-08","arxiv_id":"2212.04385","repositories_listed":1,"syntology":null},{"url":"/paper/dorothie-spoken-dialogue-for-handling","slug":"dorothie-spoken-dialogue-for-handling","title":"DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents","date":"2022-10-22","arxiv_id":"2210.12511","repositories_listed":1,"syntology":null},{"url":"/paper/uln-towards-underspecified-vision-and","slug":"uln-towards-underspecified-vision-and","title":"ULN: Towards Underspecified Vision-and-Language Navigation","date":"2022-10-18","arxiv_id":"2210.10020","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-multi-granularity-map","slug":"weakly-supervised-multi-granularity-map","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","date":"2022-10-14","arxiv_id":"2210.07506","repositories_listed":1,"syntology":null},{"url":"/paper/lovis-learning-orientation-and-visual-signals","slug":"lovis-learning-orientation-and-visual-signals","title":"LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation","date":"2022-09-26","arxiv_id":"2209.12723","repositories_listed":1,"syntology":null},{"url":"/paper/ground-then-navigate-language-guided","slug":"ground-then-navigate-language-guided","title":"Ground then Navigate: Language-guided Navigation in Dynamic Scenes","date":"2022-09-24","arxiv_id":"2209.11972","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-unlabeled-3d-environments-for","slug":"learning-from-unlabeled-3d-environments-for","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","date":"2022-08-24","arxiv_id":"2208.11781","repositories_listed":1,"syntology":null},{"url":"/paper/a-priority-map-for-vision-and-language","slug":"a-priority-map-for-vision-and-language","title":"A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cues","date":"2022-07-24","arxiv_id":"2207.11717","repositories_listed":1,"syntology":null},{"url":"/paper/clear-improving-vision-language-navigation","slug":"clear-improving-vision-language-navigation","title":"CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations","date":"2022-07-05","arxiv_id":"2207.02185","repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solutions-for-rxr-habitat-vision","slug":"1st-place-solutions-for-rxr-habitat-vision","title":"1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)","date":"2022-06-23","arxiv_id":"2206.11610","repositories_listed":1,"syntology":null},{"url":"/paper/local-slot-attention-for-vision-and-language","slug":"local-slot-attention-for-vision-and-language","title":"Local Slot Attention for Vision-and-Language Navigation","date":"2022-06-17","arxiv_id":"2206.08645","repositories_listed":1,"syntology":null},{"url":"/paper/foam-a-follower-aware-speaker-model-for","slug":"foam-a-follower-aware-speaker-model-for","title":"FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation","date":"2022-06-09","arxiv_id":"2206.04294","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-object-relation-alignment-for-vision-1","slug":"explicit-object-relation-alignment-for-vision-1","title":"Explicit Object Relation Alignment for Vision and Language Navigation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-structured-state-evolution-for","slug":"reinforced-structured-state-evolution-for","title":"Reinforced Structured State-Evolution for Vision-Language Navigation","date":"2022-04-20","arxiv_id":"2204.09280","repositories_listed":1,"syntology":null},{"url":"/paper/simple-and-effective-synthesis-of-indoor-3d","slug":"simple-and-effective-synthesis-of-indoor-3d","title":"Simple and Effective Synthesis of Indoor 3D Scenes","date":"2022-04-06","arxiv_id":"2204.02960","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-and-effective-synthesis-of-indoor-3d#ran","syntology_url":"https://syntology.ai/paper/2204.02960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02960"}},"official":{"repos":["google-research/se3ds"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/envedit-environment-editing-for-vision-and","slug":"envedit-environment-editing-for-vision-and","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","date":"2022-03-29","arxiv_id":"2203.15685","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/envedit-environment-editing-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2203.15685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15685"}},"official":{"repos":["jialuli-luka/envedit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fedvln-privacy-preserving-federated-vision","slug":"fedvln-privacy-preserving-federated-vision","title":"FedVLN: Privacy-preserving Federated Vision-and-Language Navigation","date":"2022-03-28","arxiv_id":"2203.14936","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fedvln-privacy-preserving-federated-vision#ran","syntology_url":"https://syntology.ai/paper/2203.14936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14936"}},"official":{"repos":["eric-ai-lab/fedvln"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-generalization-of-vision-and","slug":"analyzing-generalization-of-vision-and","title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","date":"2022-03-25","arxiv_id":"2203.13838","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analyzing-generalization-of-vision-and#ran","syntology_url":"https://syntology.ai/paper/2203.13838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13838"}},"official":{"repos":["raphael-sch/map2seq_vln"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hop-history-and-order-aware-pre-training-for","slug":"hop-history-and-order-aware-pre-training-for","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","date":"2022-03-22","arxiv_id":"2203.11591","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hop-history-and-order-aware-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2203.11591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11591"}},"official":{"repos":["yanyuanqiao/hop-vln"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-and-language-navigation-a-survey-of-1","slug":"vision-and-language-navigation-a-survey-of-1","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","date":"2022-03-22","arxiv_id":"2203.12667","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-map-learning-for-vision-and","slug":"cross-modal-map-learning-for-vision-and","title":"Cross-modal Map Learning for Vision and Language Navigation","date":"2022-03-10","arxiv_id":"2203.05137","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/cross-modal-map-learning-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2203.05137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05137"}},"official":{"repos":["ggeorgak11/cm2"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-gap-between-learning-in-discrete","slug":"bridging-the-gap-between-learning-in-discrete","title":"Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation","date":"2022-03-05","arxiv_id":"2203.02764","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-the-gap-between-learning-in-discrete#ran","syntology_url":"https://syntology.ai/paper/2203.02764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02764"}},"official":{"repos":["yiconghong/discrete-continuous-vln"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/think-global-act-local-dual-scale-graph","slug":"think-global-act-local-dual-scale-graph","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","date":"2022-02-23","arxiv_id":"2202.11742","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/think-global-act-local-dual-scale-graph#ran","syntology_url":"https://syntology.ai/paper/2202.11742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.11742"}},"official":null}},{"url":"/paper/one-step-at-a-time-long-horizon-vision-and","slug":"one-step-at-a-time-long-horizon-vision-and","title":"One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones","date":"2022-02-14","arxiv_id":"2202.07028","repositories_listed":1,"syntology":null},{"url":"/paper/landmark-rxr-solving-vision-and-language","slug":"landmark-rxr-solving-vision-and-language","title":"Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-transformer-with-variable-length","slug":"multimodal-transformer-with-variable-length","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","date":"2021-11-10","arxiv_id":"2111.05759","repositories_listed":1,"syntology":null},{"url":"/paper/history-aware-multimodal-transformer-for","slug":"history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","arxiv_id":"2110.13309","repositories_listed":1,"syntology":{"n":15,"n_ran":7,"n_constructed":3,"n_ran_checked":7,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/history-aware-multimodal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2110.13309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13309"}},"official":null}},{"url":"/paper/sasra-semantically-aware-spatio-temporal","slug":"sasra-semantically-aware-spatio-temporal","title":"SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments","date":"2021-08-26","arxiv_id":"2108.11945","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sasra-semantically-aware-spatio-temporal#ran","syntology_url":"https://syntology.ai/paper/2108.11945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11945"}},"official":null}},{"url":"/paper/adversarial-reinforced-instruction-attacker","slug":"adversarial-reinforced-instruction-attacker","title":"Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation","date":"2021-07-23","arxiv_id":"2107.11252","repositories_listed":1,"syntology":null},{"url":"/paper/neighbor-view-enhanced-model-for-vision-and","slug":"neighbor-view-enhanced-model-for-vision-and","title":"Neighbor-view Enhanced Model for Vision and Language Navigation","date":"2021-07-15","arxiv_id":"2107.07201","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/neighbor-view-enhanced-model-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2107.07201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07201"}},"official":{"repos":["MarSaKi/NvEM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visitron-visual-semantics-aligned","slug":"visitron-visual-semantics-aligned","title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator","date":"2021-05-25","arxiv_id":"2105.11589","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visitron-visual-semantics-aligned#ran","syntology_url":"https://syntology.ai/paper/2105.11589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11589"}},"official":{"repos":["alexa/visitron"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pathdreamer-a-world-model-for-indoor","slug":"pathdreamer-a-world-model-for-indoor","title":"Pathdreamer: A World Model for Indoor Navigation","date":"2021-05-18","arxiv_id":"2105.08756","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pathdreamer-a-world-model-for-indoor#ran","syntology_url":"https://syntology.ai/paper/2105.08756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08756"}},"official":{"repos":["google-research/pathdreamer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/episodic-transformer-for-vision-and-language","slug":"episodic-transformer-for-vision-and-language","title":"Episodic Transformer for Vision-and-Language Navigation","date":"2021-05-13","arxiv_id":"2105.06453","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/episodic-transformer-for-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2105.06453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06453"}},"official":{"repos":["alexpashevich/E.T."],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/know-what-and-know-where-an-object-and-room","slug":"know-what-and-know-where-an-object-and-room","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","date":"2021-04-09","arxiv_id":"2104.04167","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-vision-and-language-navigation","slug":"diagnosing-vision-and-language-navigation","title":"Diagnosing Vision-and-Language Navigation: What Really Matters","date":"2021-03-30","arxiv_id":"2103.16561","repositories_listed":1,"syntology":null},{"url":"/paper/a-recurrent-vision-and-language-bert-for","slug":"a-recurrent-vision-and-language-bert-for","title":"A Recurrent Vision-and-Language BERT for Navigation","date":"2020-11-26","arxiv_id":"2011.13922","repositories_listed":1,"syntology":null},{"url":"/paper/sim-to-real-transfer-for-vision-and-language","slug":"sim-to-real-transfer-for-vision-and-language","title":"Sim-to-Real Transfer for Vision-and-Language Navigation","date":"2020-11-07","arxiv_id":"2011.03807","repositories_listed":1,"syntology":null},{"url":"/paper/language-and-visual-entity-relationship-graph","slug":"language-and-visual-entity-relationship-graph","title":"Language and Visual Entity Relationship Graph for Agent Navigation","date":"2020-10-19","arxiv_id":"2010.09304","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-text-style-transfer-for-outdoor","slug":"multimodal-text-style-transfer-for-outdoor","title":"Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation","date":"2020-07-01","arxiv_id":"2007.00229","repositories_listed":1,"syntology":null},{"url":"/paper/babywalk-going-farther-in-vision-and-language","slug":"babywalk-going-farther-in-vision-and-language","title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","date":"2020-05-10","arxiv_id":"2005.04625","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/babywalk-going-farther-in-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2005.04625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04625"}},"official":{"repos":["Sha-Lab/babywalk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"syntology_records":45,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","since_archive":"/sota/vision-and-language-navigation-on-rxr#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":52,"papers_where_code_ran_first_page":"/task/vision-and-language-navigation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/vision-and-language-navigation/papers/2","json":"/task/vision-and-language-navigation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/vision-and-language-navigation/papers/3","json":"/task/vision-and-language-navigation/papers/3.json","rows":23},{"order":"ran","page":1,"of":1,"url":"/task/vision-and-language-navigation/papers/ran/1","json":"/task/vision-and-language-navigation/papers/ran/1.json","rows":52}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"73fca93123bfd61d83831904d04166cbd8e6d27d594172e8456d38bb4945e4dd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}