{"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":0,"n_unverified":4,"n_pointer_only":0}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":38,"tagged_in_all":81,"items":[{"url":"/paper/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":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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","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":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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":6,"n_unverified":6,"n_pointer_only":12}},{"url":"/paper/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","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_unverified":5,"n_pointer_only":11}},{"url":"/paper/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":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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_unverified":4,"n_pointer_only":14}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","title":"Towards Versatile Embodied Navigation","date":"2022-10-30","arxiv_id":"2210.16822","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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_unverified":0,"n_pointer_only":3}},{"url":"/paper/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","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","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_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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}],"syntology_records":12,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}