{"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-language-navigation","name":"Vision-Language Navigation","slug":"vision-language-navigation","description_markdown":"Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Learning to Navigate Unseen Environments:\r\nBack Translation with Environmental Dropout](https://arxiv.org/pdf/1904.04195v1.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"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":81,"papers_with_code":38,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":9,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/vision-language-navigation-on-room2room","slug":"vision-language-navigation-on-room2room","dataset":"Room2Room","dataset_url":"/dataset/room-to-room","rows_in_archive":3,"metrics":["spl"],"first_row_in_archive_order":{"model":"R2R+EnvDrop","paper_title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","paper_url":"/paper/learning-to-navigate-unseen-environments-back","paper_date":"2019-04-08","arxiv_id":"1904.04195","code_links":[{"title":"airsplay/R2R-EnvDrop","url":"https://github.com/airsplay/R2R-EnvDrop"}],"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/learning-to-navigate-unseen-environments-back#ran","syntology_url":"https://syntology.ai/paper/1904.04195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04195"}},"official":{"repos":["airsplay/R2R-EnvDrop"],"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"]}}}}],"datasets":[{"url":"/dataset/room-to-room","name":"R2R","full_name":"Room-to-Room","num_papers_in_archive":174},{"url":"/dataset/teach","name":"TEACh","full_name":"Task-driven Embodied Agents that Chat","num_papers_in_archive":36},{"url":"/dataset/talk-the-walk","name":"Talk the Walk","full_name":"","num_papers_in_archive":11},{"url":"/dataset/reascan","name":"ReaSCAN","full_name":"ReaSCAN: Compositional Reasoning in Language Grounding","num_papers_in_archive":10},{"url":"/dataset/bnb","name":"BnB","full_name":"","num_papers_in_archive":3},{"url":"/dataset/sdn","name":"SDN","full_name":"Situated Dialogue Navigation","num_papers_in_archive":3},{"url":"/dataset/xl-r2r","name":"XL-R2R","full_name":"Cross-lingual Room-to-Room","num_papers_in_archive":2},{"url":"/dataset/pinned","name":"PInNED","full_name":"Personalized Instance-based Navigation Embodied Dataset","num_papers_in_archive":1},{"url":"/dataset/realfred","name":"ReALFRED","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/vision-language-action","name":"Vision-Language-Action"}],"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":1,"rows_per_page":100,"shown":81,"of":81,"of_with_code":38,"tagged_in_all":81,"counts":{"archive_papers_tagged":81,"with_a_code_link":38,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":81,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":11,"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/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/cross-lingual-vision-language-navigation-1","slug":"cross-lingual-vision-language-navigation-1","title":"Cross-Lingual Vision-Language Navigation","date":"2019-10-24","arxiv_id":"1910.11301","repositories_listed":2,"syntology":null},{"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/vln-r1-vision-language-navigation-via","slug":"vln-r1-vision-language-navigation-via","title":"VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning","date":"2025-06-20","arxiv_id":"2506.17221","repositories_listed":1,"syntology":null},{"url":"/paper/unseen-from-seen-rewriting-observation","slug":"unseen-from-seen-rewriting-observation","title":"Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation","date":"2025-03-23","arxiv_id":"2503.18065","repositories_listed":1,"syntology":null},{"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/doscenes-an-autonomous-driving-dataset-with","slug":"doscenes-an-autonomous-driving-dataset-with","title":"doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation","date":"2024-12-08","arxiv_id":"2412.05893","repositories_listed":1,"syntology":null},{"url":"/paper/disco-embodied-navigation-and-interaction-via","slug":"disco-embodied-navigation-and-interaction-via","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","date":"2024-07-20","arxiv_id":"2407.14758","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disco-embodied-navigation-and-interaction-via#ran","syntology_url":"https://syntology.ai/paper/2407.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14758"}},"official":{"repos":["allenxuuu/disco"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/correctable-landmark-discovery-via-large","slug":"correctable-landmark-discovery-via-large","title":"Correctable Landmark Discovery via Large Models for Vision-Language Navigation","date":"2024-05-29","arxiv_id":"2405.18721","repositories_listed":1,"syntology":null},{"url":"/paper/open-set-3d-semantic-instance-maps-for-vision","slug":"open-set-3d-semantic-instance-maps-for-vision","title":"Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIM","date":"2024-04-27","arxiv_id":"2404.17922","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/volumetric-environment-representation-for","slug":"volumetric-environment-representation-for","title":"Volumetric Environment Representation for Vision-Language Navigation","date":"2024-03-21","arxiv_id":"2403.14158","repositories_listed":1,"syntology":null},{"url":"/paper/planning-as-in-painting-a-diffusion-based","slug":"planning-as-in-painting-a-diffusion-based","title":"Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty","date":"2023-12-02","arxiv_id":"2312.01097","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/planning-as-in-painting-a-diffusion-based#ran","syntology_url":"https://syntology.ai/paper/2312.01097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01097"}},"official":{"repos":["joeyy5588/planning-as-inpainting"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","slug":"an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-embodied-generalist-agent-in-3d-world#ran","syntology_url":"https://syntology.ai/paper/2311.12871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12871"}},"official":{"repos":["embodied-generalist/embodied-generalist"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bird-s-eye-view-scene-graph-for-vision","slug":"bird-s-eye-view-scene-graph-for-vision","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","date":"2023-08-09","arxiv_id":"2308.04758","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"10 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/bird-s-eye-view-scene-graph-for-vision#ran","syntology_url":"https://syntology.ai/paper/2308.04758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04758"}},"official":{"repos":["defaultrui/bev-scene-graph"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/etpnav-evolving-topological-planning-for","slug":"etpnav-evolving-topological-planning-for","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","date":"2023-04-06","arxiv_id":"2304.03047","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":0,"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/etpnav-evolving-topological-planning-for#ran","syntology_url":"https://syntology.ai/paper/2304.03047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03047"}},"official":{"repos":["marsaki/etpnav"],"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/adaptive-zone-aware-hierarchical-planner-for","slug":"adaptive-zone-aware-hierarchical-planner-for","title":"Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-versatile-embodied-navigation","slug":"towards-versatile-embodied-navigation","title":"Towards Versatile Embodied Navigation","date":"2022-10-30","arxiv_id":"2210.16822","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/towards-versatile-embodied-navigation#ran","syntology_url":"https://syntology.ai/paper/2210.16822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16822"}},"official":{"repos":["hanqingwangai/vxn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/danli-deliberative-agent-for-following","slug":"danli-deliberative-agent-for-following","title":"DANLI: Deliberative Agent for Following Natural Language Instructions","date":"2022-10-22","arxiv_id":"2210.12485","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/danli-deliberative-agent-for-following#ran","syntology_url":"https://syntology.ai/paper/2210.12485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12485"}},"official":{"repos":["sled-group/danli"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/target-driven-structured-transformer-planner","slug":"target-driven-structured-transformer-planner","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","date":"2022-07-19","arxiv_id":"2207.11201","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/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/counterfactual-cycle-consistent-learning-for","slug":"counterfactual-cycle-consistent-learning-for","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","date":"2022-03-30","arxiv_id":"2203.16586","repositories_listed":1,"syntology":null},{"url":"/paper/visual-language-navigation-pretraining-via-1","slug":"visual-language-navigation-pretraining-via-1","title":"Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration","date":"2022-03-08","arxiv_id":"2203.04006","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-mobile-app-navigation-with","slug":"interactive-mobile-app-navigation-with","title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","date":"2022-02-04","arxiv_id":"2202.02312","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interactive-mobile-app-navigation-with#ran","syntology_url":"https://syntology.ai/paper/2202.02312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02312"}},"official":{"repos":["aburns4/MoTIF"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-instruction-trajectory-learning","slug":"contrastive-instruction-trajectory-learning","title":"Contrastive Instruction-Trajectory Learning for Vision-Language Navigation","date":"2021-12-08","arxiv_id":"2112.04138","repositories_listed":1,"syntology":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/vision-language-navigation-with-random","slug":"vision-language-navigation-with-random","title":"Vision-Language Navigation with Random Environmental Mixup","date":"2021-06-15","arxiv_id":"2106.07876","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vision-language-navigation-with-random#ran","syntology_url":"https://syntology.ai/paper/2106.07876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07876"}},"official":{"repos":["lcfractal/vlnrem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-cross-modal-alignment-in-vision","slug":"improving-cross-modal-alignment-in-vision","title":"Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information","date":"2021-04-19","arxiv_id":"2104.09580","repositories_listed":1,"syntology":null},{"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/structured-scene-memory-for-vision-language","slug":"structured-scene-memory-for-vision-language","title":"Structured Scene Memory for Vision-Language Navigation","date":"2021-03-05","arxiv_id":"2103.03454","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/structured-scene-memory-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2103.03454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03454"}},"official":{"repos":["HanqingWangAI/SSM-VLN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-modular-vision-language-navigation-and","slug":"a-modular-vision-language-navigation-and","title":"A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment","date":"2021-01-19","arxiv_id":"2101.07891","repositories_listed":1,"syntology":null},{"url":"/paper/active-visual-information-gathering-for","slug":"active-visual-information-gathering-for","title":"Active Visual Information Gathering for Vision-Language Navigation","date":"2020-07-15","arxiv_id":"2007.08037","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/active-visual-information-gathering-for#ran","syntology_url":"https://syntology.ai/paper/2007.08037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08037"}},"official":{"repos":["HanqingWangAI/Active_VLN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/environment-agnostic-multitask-learning-for","slug":"environment-agnostic-multitask-learning-for","title":"Environment-agnostic Multitask Learning for Natural Language Grounded Navigation","date":"2020-03-01","arxiv_id":"2003.00443","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-navigate-unseen-environments-back","slug":"learning-to-navigate-unseen-environments-back","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","date":"2019-04-08","arxiv_id":"1904.04195","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/learning-to-navigate-unseen-environments-back#ran","syntology_url":"https://syntology.ai/paper/1904.04195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04195"}},"official":{"repos":["airsplay/R2R-EnvDrop"],"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/tactical-rewind-self-correction-via","slug":"tactical-rewind-self-correction-via","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","date":"2019-03-06","arxiv_id":"1903.02547","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tactical-rewind-self-correction-via#ran","syntology_url":"https://syntology.ai/paper/1903.02547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02547"}},"official":{"repos":["Kelym/FAST"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-regretful-navigation-agent-for-vision-and","slug":"the-regretful-navigation-agent-for-vision-and","title":"The Regretful Navigation Agent for Vision-and-Language Navigation","date":"2019-03-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/look-before-you-leap-bridging-model-free-and","slug":"look-before-you-leap-bridging-model-free-and","title":"Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation","date":"2018-03-21","arxiv_id":"1803.07729","repositories_listed":1,"syntology":null},{"url":null,"slug":"se-vln-a-self-evolving-vision-language","title":"SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models","date":"2025-07-17","arxiv_id":"2507.13152","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-vision-language-navigation-for-uavs","title":"Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding","date":"2025-06-12","arxiv_id":"2506.10756","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-vision-language-navigation","title":"Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations","date":"2025-06-10","arxiv_id":"2506.08566","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-test-time-vision-language-navigation","title":"Active Test-time Vision-Language Navigation","date":"2025-06-07","arxiv_id":"2506.06630","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolvenav-self-improving-embodied-reasoning","title":"EvolveNav: Self-Improving Embodied Reasoning for LLM-Based Vision-Language Navigation","date":"2025-06-02","arxiv_id":"2506.01551","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-data-curation-using-gps-nlp-to","title":"Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasets","date":"2025-05-06","arxiv_id":"2505.03174","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-vln-end-to-end-vision-language-guided","title":"UAV-VLN: End-to-End Vision Language guided Navigation for UAVs","date":"2025-04-30","arxiv_id":"2504.21432","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasongrounder-lvlm-guided-hierarchical","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning","date":"2025-03-30","arxiv_id":"2503.23297","repositories_listed":0,"syntology":null},{"url":null,"slug":"openfly-a-versatile-toolchain-and-large-scale","title":"OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation","date":"2025-02-25","arxiv_id":"2502.18041","repositories_listed":0,"syntology":null},{"url":null,"slug":"travel-training-free-retrieval-and-alignment","title":"TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation","date":"2025-02-11","arxiv_id":"2502.07306","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-nav-real-time-vision-language-navigation","title":"VL-Nav: Real-time Vision-Language Navigation with Spatial Reasoning","date":"2025-02-02","arxiv_id":"2502.00931","repositories_listed":0,"syntology":null},{"url":null,"slug":"navcon-a-cognitively-inspired-and","title":"NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation","date":"2024-12-17","arxiv_id":"2412.13026","repositories_listed":0,"syntology":null},{"url":null,"slug":"constraint-aware-zero-shot-vision-language","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","date":"2024-12-13","arxiv_id":"2412.10137","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-long-horizon-vision-language","title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method","date":"2024-12-12","arxiv_id":"2412.09082","repositories_listed":0,"syntology":null},{"url":null,"slug":"unitedvln-generalizable-gaussian-splatting","title":"UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation","date":"2024-11-25","arxiv_id":"2411.16053","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl-slam-for-oc-vln-natural-language-grounded","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","date":"2024-11-12","arxiv_id":"2411.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-navigation-with-energy-based","title":"Vision-Language Navigation with Energy-Based Policy","date":"2024-10-18","arxiv_id":"2410.14250","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-realistic-uav-vision-language","title":"Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology","date":"2024-10-09","arxiv_id":"2410.07087","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-the-nuances-a-fine-grained","title":"Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation","date":"2024-09-25","arxiv_id":"2409.17313","repositories_listed":0,"syntology":null},{"url":null,"slug":"asma-an-adaptive-safety-margin-algorithm-for","title":"ASMA: An Adaptive Safety Margin Algorithm for Vision-Language Drone Navigation via Scene-Aware Control Barrier Functions","date":"2024-09-16","arxiv_id":"2409.10283","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-is-believing-enhancing-vision-language","title":"Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations","date":"2024-09-09","arxiv_id":"2409.05552","repositories_listed":0,"syntology":null},{"url":null,"slug":"cog-ga-a-large-language-models-based","title":"Cog-GA: A Large Language Models-based Generative Agent for Vision-Language Navigation in Continuous Environments","date":"2024-09-04","arxiv_id":"2409.02522","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-navigation-with-continual","title":"Vision-Language Navigation with Continual Learning","date":"2024-09-04","arxiv_id":"2409.02561","repositories_listed":0,"syntology":null},{"url":null,"slug":"malicious-path-manipulations-via-exploitation","title":"Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems","date":"2024-07-10","arxiv_id":"2407.07392","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordances-oriented-planning-using","title":"Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation","date":"2024-07-08","arxiv_id":"2407.05890","repositories_listed":0,"syntology":null},{"url":null,"slug":"tina-think-interaction-and-action-framework","title":"TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation","date":"2024-03-13","arxiv_id":"2403.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-navigation-with-embodied","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","date":"2024-02-22","arxiv_id":"2402.14304","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-near-room-locality-learning-for","title":"What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environments","date":"2023-09-10","arxiv_id":"2309.05036","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamwalker-mental-planning-for-continuous","title":"DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation","date":"2023-08-14","arxiv_id":"2308.07498","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-semantic-localization-with-graph","title":"Active Semantic Localization with Graph Neural Embedding","date":"2023-05-10","arxiv_id":"2305.06141","repositories_listed":0,"syntology":null},{"url":null,"slug":"accessible-instruction-following-agent","title":"Accessible Instruction-Following Agent","date":"2023-05-08","arxiv_id":"2305.06358","repositories_listed":0,"syntology":null},{"url":null,"slug":"actional-atomic-concept-learning-for","title":"Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation","date":"2023-02-13","arxiv_id":"2302.06072","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","repositories_listed":0,"syntology":null},{"url":null,"slug":"anticipating-the-unseen-discrepancy-for","title":"Anticipating the Unseen Discrepancy for Vision and Language Navigation","date":"2022-09-10","arxiv_id":"2209.04725","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapt-vision-language-navigation-with","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","date":"2022-05-31","arxiv_id":"2205.15509","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-importance-of-karaka-framework-in","title":"On the Importance of Karaka Framework in Multi-modal Grounding","date":"2022-04-09","arxiv_id":"2204.04347","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-language-navigation-pretraining-via","title":"Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-and-language-navigation-a-survey-and","title":"Vision-Language Navigation: A Survey and Taxonomy","date":"2021-08-26","arxiv_id":"2108.11544","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-graph-attention-network-for-complex","title":"Modular Graph Attention Network for Complex Visual Relational Reasoning","date":"2020-11-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-stop-a-simple-yet-effective","slug":"learning-to-stop-a-simple-yet-effective","title":"Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation","date":"2020-09-28","arxiv_id":"2009.13112","repositories_listed":0,"syntology":null},{"url":"/paper/vision-language-navigation-with-self","slug":"vision-language-navigation-with-self","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","date":"2019-11-18","arxiv_id":"1911.07883","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-natural-language-grounded","title":"Generalized Natural Language Grounded Navigation via Environment-agnostic Multitask Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/reinforced-cross-modal-matching-and-self","slug":"reinforced-cross-modal-matching-and-self","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","date":"2018-11-25","arxiv_id":"1811.10092","repositories_listed":0,"syntology":null}],"syntology_records":16,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/vision-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":"ran","page":1,"of":1,"url":"/task/vision-language-navigation/papers/ran/1","json":"/task/vision-language-navigation/papers/ran/1.json","rows":15}],"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":"b0b0ae835d27930ce2733c8768242fa2b34960c8c764a7a8ff9c26977a5accaa","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}