{"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/visual-navigation","name":"Visual Navigation","slug":"visual-navigation","description_markdown":"**Visual Navigation** is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.\n\n\n<span class=\"description-source\">Source: [Vision-based Navigation Using Deep Reinforcement Learning ](https://arxiv.org/abs/1908.03627)</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":316,"papers_with_code":132,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":19,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/visual-navigation-on-cooperative-vision-and-1","slug":"visual-navigation-on-cooperative-vision-and-1","dataset":"Cooperative Vision-and-Dialogue Navigation","dataset_url":null,"rows_in_archive":19,"metrics":["dist_to_end_reduction","spl"],"first_row_in_archive_order":{"model":"NaviLLM","paper_title":"Towards Learning a Generalist Model for Embodied Navigation","paper_url":"/paper/towards-learning-a-generalist-model-for","paper_date":"2023-12-04","arxiv_id":"2312.02010","code_links":[{"title":"zd11024/NaviLLM","url":"https://github.com/zd11024/NaviLLM"},{"title":"lavi-lab/navillm","url":"https://github.com/lavi-lab/navillm"}],"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/towards-learning-a-generalist-model-for#ran","syntology_url":"https://syntology.ai/paper/2312.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02010"}},"official":{"repos":["lavi-lab/navillm","zd11024/NaviLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-navigation-on-room-to-room-1","slug":"visual-navigation-on-room-to-room-1","dataset":"R2R","dataset_url":"/dataset/room-to-room","rows_in_archive":11,"metrics":["spl"],"first_row_in_archive_order":{"model":"SUSA","paper_title":"Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation","paper_url":"/paper/agent-journey-beyond-rgb-unveiling-hybrid","paper_date":"2024-12-09","arxiv_id":"2412.06465","code_links":[{"title":"HCI-LMC/VLN-SUSA","url":"https://github.com/HCI-LMC/VLN-SUSA"}],"syntology":null}},{"leaderboard":"/sota/visual-navigation-on-soon-test","slug":"visual-navigation-on-soon-test","dataset":"SOON Test","dataset_url":null,"rows_in_archive":6,"metrics":["Nav-SPL","SR"],"first_row_in_archive_order":{"model":"AutoVLN","paper_title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","paper_url":"/paper/learning-from-unlabeled-3d-environments-for","paper_date":"2022-08-24","arxiv_id":"2208.11781","code_links":[{"title":"cshizhe/HM3DAutoVLN","url":"https://github.com/cshizhe/HM3DAutoVLN"}],"syntology":null}},{"leaderboard":"/sota/visual-navigation-on-ai2-thor","slug":"visual-navigation-on-ai2-thor","dataset":"AI2-THOR","dataset_url":"/dataset/ai2-thor","rows_in_archive":2,"metrics":["SPL (All)","SPL (L≥5)","Success Rate (All)","Success Rate (L≥5)"],"first_row_in_archive_order":{"model":"MVV-IN","paper_title":"Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning","paper_url":"/paper/multimodal-aggregation-approach-for-memory","paper_date":"2020-09-01","arxiv_id":"2009.00402","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-navigation-on-dmlab-30","slug":"visual-navigation-on-dmlab-30","dataset":"Dmlab-30","dataset_url":null,"rows_in_archive":1,"metrics":["Medium Human-Normalized Score"],"first_row_in_archive_order":{"model":"PopArt-IMPALA","paper_title":"Multi-task Deep Reinforcement Learning with PopArt","paper_url":"/paper/multi-task-deep-reinforcement-learning-with","paper_date":"2018-09-12","arxiv_id":"1809.04474","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"aluscher/torchbeastpopart","url":"https://github.com/aluscher/torchbeastpopart"}],"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":2,"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/multi-task-deep-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1809.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.04474"}},"official":null}}},{"leaderboard":"/sota/visual-navigation-on-help-anna-hanna-1","slug":"visual-navigation-on-help-anna-hanna-1","dataset":"Help, Anna! (HANNA)","dataset_url":"/dataset/help","rows_in_archive":1,"metrics":["spl"],"first_row_in_archive_order":{"model":"Prevalent","paper_title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","paper_url":"/paper/towards-learning-a-generic-agent-for-vision","paper_date":"2020-02-25","arxiv_id":"2002.10638","code_links":[{"title":"weituo12321/PREVALENT","url":"https://github.com/weituo12321/PREVALENT"}],"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/towards-learning-a-generic-agent-for-vision#ran","syntology_url":"https://syntology.ai/paper/2002.10638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10638"}},"official":{"repos":["weituo12321/PREVALENT"],"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"]}}}}],"datasets":[{"url":"/dataset/replica","name":"Replica","full_name":"","num_papers_in_archive":414},{"url":"/dataset/ai2-thor","name":"AI2-THOR","full_name":"AI2-THOR","num_papers_in_archive":243},{"url":"/dataset/suncg","name":"SUNCG","full_name":"SUNCG","num_papers_in_archive":186},{"url":"/dataset/room-to-room","name":"R2R","full_name":"Room-to-Room","num_papers_in_archive":174},{"url":"/dataset/2d-3d-s","name":"2D-3D-S","full_name":"2D-3D-Semantic","num_papers_in_archive":147},{"url":"/dataset/help","name":"HELP","full_name":"","num_papers_in_archive":30},{"url":"/dataset/avd","name":"AVD","full_name":"Active Vision Dataset","num_papers_in_archive":29},{"url":"/dataset/minos","name":"MINOS","full_name":"MINOS","num_papers_in_archive":22},{"url":"/dataset/hm3dsem","name":"HM3DSem","full_name":"","num_papers_in_archive":13},{"url":"/dataset/house3d-environment","name":"House3D Environment","full_name":"","num_papers_in_archive":11},{"url":"/dataset/talk-the-walk","name":"Talk the Walk","full_name":"","num_papers_in_archive":11},{"url":"/dataset/iquad","name":"IQUAD","full_name":"Interactive Question Answering Dataset","num_papers_in_archive":7},{"url":"/dataset/minerl","name":"MineRL","full_name":"MineRL","num_papers_in_archive":3},{"url":"/dataset/baseprod","name":"BASEPROD","full_name":"The Bardenas Semi-Desert Planetary Rover Dataset","num_papers_in_archive":2},{"url":"/dataset/midgard","name":"MIDGARD","full_name":"MIDGARD","num_papers_in_archive":2},{"url":"/dataset/talk2nav","name":"Talk2Nav","full_name":"","num_papers_in_archive":2},{"url":"/dataset/image-goal-nav-dataset","name":"image-goal-nav-dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/luna-1","name":"Luna-1","full_name":"","num_papers_in_archive":1},{"url":"/dataset/uav-multiview-navigation","name":"UAV Multiview Navigation","full_name":"UAV Multiview Navigation","num_papers_in_archive":1}],"subtasks":[{"url":"/task/objectgoal-navigation","name":"ObjectGoal Navigation"}],"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":4,"rows_per_page":100,"shown":100,"of":316,"of_with_code":132,"tagged_in_all":316,"counts":{"archive_papers_tagged":316,"with_a_code_link":132,"where_syntology_ran_a_sample":37,"not_listed_spam_title":0,"listed":316,"listed_where_code_ran":37,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/cognitive-mapping-and-planning-for-visual","slug":"cognitive-mapping-and-planning-for-visual","title":"Cognitive Mapping and Planning for Visual Navigation","date":"2017-02-13","arxiv_id":"1702.03920","repositories_listed":6,"syntology":null},{"url":"/paper/think-locally-act-globally-federated-learning","slug":"think-locally-act-globally-federated-learning","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","date":"2020-01-06","arxiv_id":"2001.01523","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 4 unverified","sample_list":"/paper/think-locally-act-globally-federated-learning#ran","syntology_url":"https://syntology.ai/paper/2001.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01523"}},"official":{"repos":["pliang279/LG-FedAvg"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/are-we-making-real-progress-in-simulated","slug":"are-we-making-real-progress-in-simulated","title":"Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?","date":"2019-12-13","arxiv_id":"1912.06321","repositories_listed":4,"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/are-we-making-real-progress-in-simulated#ran","syntology_url":"https://syntology.ai/paper/1912.06321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06321"}},"official":null}},{"url":"/paper/popgym-benchmarking-partially-observable","slug":"popgym-benchmarking-partially-observable","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","date":"2023-03-03","arxiv_id":"2303.01859","repositories_listed":3,"syntology":null},{"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/visual-representations-for-semantic-target","slug":"visual-representations-for-semantic-target","title":"Visual Representations for Semantic Target Driven Navigation","date":"2018-05-15","arxiv_id":"1805.06066","repositories_listed":3,"syntology":null},{"url":"/paper/a-64mw-dnn-based-visual-navigation-engine-for","slug":"a-64mw-dnn-based-visual-navigation-engine-for","title":"A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones","date":"2018-05-04","arxiv_id":"1805.01831","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-64mw-dnn-based-visual-navigation-engine-for#ran","syntology_url":"https://syntology.ai/paper/1805.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01831"}},"official":{"repos":["pulp-platform/pulp-dronet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-learning-a-generalist-model-for","slug":"towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","arxiv_id":"2312.02010","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/towards-learning-a-generalist-model-for#ran","syntology_url":"https://syntology.ai/paper/2312.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02010"}},"official":{"repos":["lavi-lab/navillm","zd11024/NaviLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"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/soundspaces-2-0-a-simulation-platform-for","slug":"soundspaces-2-0-a-simulation-platform-for","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","date":"2022-06-16","arxiv_id":"2206.08312","repositories_listed":2,"syntology":null},{"url":"/paper/towards-real-world-navigation-with-deep","slug":"towards-real-world-navigation-with-deep","title":"Towards real-world navigation with deep differentiable planners","date":"2021-08-08","arxiv_id":"2108.05713","repositories_listed":2,"syntology":null},{"url":"/paper/teaching-agents-how-to-map-spatial-reasoning","slug":"teaching-agents-how-to-map-spatial-reasoning","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","date":"2021-07-13","arxiv_id":"2107.06011","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teaching-agents-how-to-map-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2107.06011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06011"}},"official":{"repos":["PierreMarza/teaching_agents_how_to_map"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/end-to-end-egospheric-spatial-memory","slug":"end-to-end-egospheric-spatial-memory","title":"End-to-End Egospheric Spatial Memory","date":"2021-02-15","arxiv_id":"2102.07764","repositories_listed":2,"syntology":null},{"url":"/paper/visual-navigation-in-real-world-indoor","slug":"visual-navigation-in-real-world-indoor","title":"Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning","date":"2020-10-21","arxiv_id":"2010.10903","repositories_listed":2,"syntology":null},{"url":"/paper/explore-then-execute-adapting-without-rewards","slug":"explore-then-execute-adapting-without-rewards","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","date":"2020-08-06","arxiv_id":"2008.02790","repositories_listed":2,"syntology":null},{"url":"/paper/side-tuning-network-adaptation-via-additive-1","slug":"side-tuning-network-adaptation-via-additive-1","title":"Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks","date":"2019-12-31","arxiv_id":"1912.13503","repositories_listed":2,"syntology":null},{"url":"/paper/audio-visual-embodied-navigation","slug":"audio-visual-embodied-navigation","title":"SoundSpaces: Audio-Visual Navigation in 3D Environments","date":"2019-12-24","arxiv_id":"1912.11474","repositories_listed":2,"syntology":null},{"url":"/paper/vusfavariational-universal-successor-features","slug":"vusfavariational-universal-successor-features","title":"VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation","date":"2019-08-18","arxiv_id":"1908.06376","repositories_listed":2,"syntology":null},{"url":"/paper/vision-and-dialog-navigation","slug":"vision-and-dialog-navigation","title":"Vision-and-Dialog Navigation","date":"2019-07-10","arxiv_id":"1907.04957","repositories_listed":2,"syntology":null},{"url":"/paper/an-open-source-and-open-hardware-deep","slug":"an-open-source-and-open-hardware-deep","title":"An Open Source and Open Hardware Deep Learning-powered Visual Navigation Engine for Autonomous Nano-UAVs","date":"2019-05-10","arxiv_id":"1905.04166","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-and-benchmarking-self-supervised","slug":"scaling-and-benchmarking-self-supervised","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","date":"2019-05-03","arxiv_id":"1905.01235","repositories_listed":2,"syntology":null},{"url":"/paper/learning-exploration-policies-for-navigation","slug":"learning-exploration-policies-for-navigation","title":"Learning Exploration Policies for Navigation","date":"2019-03-05","arxiv_id":"1903.01959","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/learning-to-learn-how-to-learn-self-adaptive","slug":"learning-to-learn-how-to-learn-self-adaptive","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","date":"2018-12-03","arxiv_id":"1812.00971","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-learn-how-to-learn-self-adaptive#ran","syntology_url":"https://syntology.ai/paper/1812.00971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00971"}},"official":{"repos":["allenai/savn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/target-driven-visual-navigation-in-indoor","slug":"target-driven-visual-navigation-in-indoor","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","date":"2016-09-16","arxiv_id":"1609.05143","repositories_listed":2,"syntology":null},{"url":"/paper/2505-11409","slug":"2505-11409","title":"Visual Planning: Let's Think Only with Images","date":"2025-05-16","arxiv_id":"2505.11409","repositories_listed":1,"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":0,"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/2505-11409#ran","syntology_url":"https://syntology.ai/paper/2505.11409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11409"}},"official":{"repos":["yix8/visualplanning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/task-oriented-communications-for-visual","slug":"task-oriented-communications-for-visual","title":"Task-Oriented Communications for Visual Navigation with Edge-Aerial Collaboration in Low Altitude Economy","date":"2025-04-25","arxiv_id":"2504.18317","repositories_listed":1,"syntology":null},{"url":"/paper/navidiffusor-cost-guided-diffusion-model-for","slug":"navidiffusor-cost-guided-diffusion-model-for","title":"NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation","date":"2025-04-14","arxiv_id":"2504.10003","repositories_listed":1,"syntology":null},{"url":"/paper/prior-does-matter-visual-navigation-via","slug":"prior-does-matter-visual-navigation-via","title":"Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models","date":"2025-04-14","arxiv_id":"2504.10041","repositories_listed":1,"syntology":null},{"url":"/paper/endomamba-an-efficient-foundation-model-for","slug":"endomamba-an-efficient-foundation-model-for","title":"EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training","date":"2025-02-26","arxiv_id":"2502.19090","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/same-learning-generic-language-guided-visual","slug":"same-learning-generic-language-guided-visual","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05552","repositories_listed":1,"syntology":null},{"url":"/paper/navigation-world-models","slug":"navigation-world-models","title":"Navigation World Models","date":"2024-12-04","arxiv_id":"2412.03572","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/navigation-world-models#ran","syntology_url":"https://syntology.ai/paper/2412.03572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03572"}},"official":null}},{"url":"/paper/lscenellm-enhancing-large-3d-scene","slug":"lscenellm-enhancing-large-3d-scene","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","date":"2024-12-02","arxiv_id":"2412.01292","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lscenellm-enhancing-large-3d-scene#ran","syntology_url":"https://syntology.ai/paper/2412.01292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01292"}},"official":{"repos":["Hoyyyaard/LSceneLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/citywalker-learning-embodied-urban-navigation","slug":"citywalker-learning-embodied-urban-navigation","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","date":"2024-11-26","arxiv_id":"2411.17820","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/citywalker-learning-embodied-urban-navigation#ran","syntology_url":"https://syntology.ai/paper/2411.17820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17820"}},"official":{"repos":["ai4ce/CityWalker"],"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/personalized-instance-based-navigation-toward","slug":"personalized-instance-based-navigation-toward","title":"Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments","date":"2024-10-23","arxiv_id":"2410.18195","repositories_listed":1,"syntology":null},{"url":"/paper/visual-navigation-of-digital-libraries","slug":"visual-navigation-of-digital-libraries","title":"Visual Navigation of Digital Libraries: Retrieval and Classification of Images in the National Library of Norway's Digitised Book Collection","date":"2024-10-19","arxiv_id":"2410.14969","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-the-challenges-of-loop-detection","slug":"addressing-the-challenges-of-loop-detection","title":"Addressing the challenges of loop detection in agricultural environments","date":"2024-08-28","arxiv_id":"2408.15761","repositories_listed":1,"syntology":null},{"url":"/paper/spin-spacecraft-imagery-for-navigation","slug":"spin-spacecraft-imagery-for-navigation","title":"SPIN: Spacecraft Imagery for Navigation","date":"2024-06-11","arxiv_id":"2406.07500","repositories_listed":1,"syntology":null},{"url":"/paper/xfeat-accelerated-features-for-lightweight","slug":"xfeat-accelerated-features-for-lightweight","title":"XFeat: Accelerated Features for Lightweight Image Matching","date":"2024-04-30","arxiv_id":"2404.19174","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/xfeat-accelerated-features-for-lightweight#ran","syntology_url":"https://syntology.ai/paper/2404.19174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19174"}},"official":null}},{"url":"/paper/motor-focus-ego-motion-prediction-with-all","slug":"motor-focus-ego-motion-prediction-with-all","title":"Motor Focus: Fast Ego-Motion Prediction for Assistive Visual Navigation","date":"2024-04-25","arxiv_id":"2404.17031","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/goat-bench-a-benchmark-for-multi-modal","slug":"goat-bench-a-benchmark-for-multi-modal","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","date":"2024-04-09","arxiv_id":"2404.06609","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/goat-bench-a-benchmark-for-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2404.06609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06609"}},"official":{"repos":["Ram81/goat-bench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visualization-of-thought-elicits-spatial","slug":"visualization-of-thought-elicits-spatial","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","date":"2024-04-04","arxiv_id":"2404.03622","repositories_listed":1,"syntology":null},{"url":"/paper/visiongpt-llm-assisted-real-time-anomaly","slug":"visiongpt-llm-assisted-real-time-anomaly","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","date":"2024-03-19","arxiv_id":"2403.12415","repositories_listed":1,"syntology":null},{"url":"/paper/gaussnav-gaussian-splatting-for-visual","slug":"gaussnav-gaussian-splatting-for-visual","title":"GaussNav: Gaussian Splatting for Visual Navigation","date":"2024-03-18","arxiv_id":"2403.11625","repositories_listed":1,"syntology":null},{"url":"/paper/openocc-open-vocabulary-3d-scene","slug":"openocc-open-vocabulary-3d-scene","title":"OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation","date":"2024-03-18","arxiv_id":"2403.11796","repositories_listed":1,"syntology":null},{"url":"/paper/vanp-learning-where-to-see-for-navigation","slug":"vanp-learning-where-to-see-for-navigation","title":"VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training","date":"2024-03-12","arxiv_id":"2403.08109","repositories_listed":1,"syntology":null},{"url":"/paper/tta-nav-test-time-adaptive-reconstruction-for","slug":"tta-nav-test-time-adaptive-reconstruction-for","title":"TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions","date":"2024-03-04","arxiv_id":"2403.01977","repositories_listed":1,"syntology":null},{"url":"/paper/memonav-working-memory-model-for-visual","slug":"memonav-working-memory-model-for-visual","title":"MemoNav: Working Memory Model for Visual Navigation","date":"2024-02-29","arxiv_id":"2402.19161","repositories_listed":1,"syntology":null},{"url":"/paper/an-interactive-navigation-method-with-effect","slug":"an-interactive-navigation-method-with-effect","title":"An Interactive Navigation Method with Effect-oriented Affordance","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/world-map-misalignment-detection-for-visual","slug":"world-map-misalignment-detection-for-visual","title":"World-Map Misalignment Detection for Visual Navigation Systems","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/what-you-see-is-what-you-get-experience","slug":"what-you-see-is-what-you-get-experience","title":"What you see is what you get: Experience ranking with deep neural dataset-to-dataset similarity for topological localisation","date":"2023-10-20","arxiv_id":"2310.13622","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-object-goal-visual-navigation-with","slug":"zero-shot-object-goal-visual-navigation-with","title":"Zero-Shot Object Goal Visual Navigation With Class-Independent Relationship Network","date":"2023-10-15","arxiv_id":"2310.09883","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-instance-image-goal-navigation","slug":"end-to-end-instance-image-goal-navigation","title":"End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon","date":"2023-09-28","arxiv_id":"2309.16634","repositories_listed":1,"syntology":null},{"url":"/paper/camp-causal-multi-policy-planning-for","slug":"camp-causal-multi-policy-planning-for","title":"CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/camp-causal-multi-policy-planning-for-1","slug":"camp-causal-multi-policy-planning-for-1","title":"CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi3drefer-grounding-text-description-to","slug":"multi3drefer-grounding-text-description-to","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","date":"2023-09-11","arxiv_id":"2309.05251","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/multi3drefer-grounding-text-description-to#ran","syntology_url":"https://syntology.ai/paper/2309.05251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05251"}},"official":{"repos":["3dlg-hcvc/M3DRef-CLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/language-enhanced-rnr-map-querying-renderable","slug":"language-enhanced-rnr-map-querying-renderable","title":"Language-enhanced RNR-Map: Querying Renderable Neural Radiance Field maps with natural language","date":"2023-08-17","arxiv_id":"2308.08854","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-planning-and-environment-aware","slug":"context-aware-planning-and-environment-aware","title":"Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents","date":"2023-08-14","arxiv_id":"2308.07241","repositories_listed":1,"syntology":null},{"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/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/online-self-supervised-thermal-water","slug":"online-self-supervised-thermal-water","title":"Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles","date":"2023-07-18","arxiv_id":"2307.09027","repositories_listed":1,"syntology":null},{"url":"/paper/the-drunkard-s-odometry-estimating-camera","slug":"the-drunkard-s-odometry-estimating-camera","title":"The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes","date":"2023-06-29","arxiv_id":"2306.16917","repositories_listed":1,"syntology":null},{"url":"/paper/vint-a-foundation-model-for-visual-navigation","slug":"vint-a-foundation-model-for-visual-navigation","title":"ViNT: A Foundation Model for Visual Navigation","date":"2023-06-26","arxiv_id":"2306.14846","repositories_listed":1,"syntology":null},{"url":"/paper/habicrowd-a-high-performance-simulator-for","slug":"habicrowd-a-high-performance-simulator-for","title":"HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation","date":"2023-06-20","arxiv_id":"2306.11377","repositories_listed":1,"syntology":null},{"url":"/paper/sonicverse-a-multisensory-simulation-platform","slug":"sonicverse-a-multisensory-simulation-platform","title":"Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear","date":"2023-06-01","arxiv_id":"2306.00923","repositories_listed":1,"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/sonicverse-a-multisensory-simulation-platform#ran","syntology_url":"https://syntology.ai/paper/2306.00923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00923"}},"official":{"repos":["stanfordvl/sonicverse"],"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/renderable-neural-radiance-map-for-visual","slug":"renderable-neural-radiance-map-for-visual","title":"Renderable Neural Radiance Map for Visual Navigation","date":"2023-03-01","arxiv_id":"2303.00304","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"7 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/renderable-neural-radiance-map-for-visual#ran","syntology_url":"https://syntology.ai/paper/2303.00304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00304"}},"official":null}},{"url":"/paper/offline-reinforcement-learning-for-visual","slug":"offline-reinforcement-learning-for-visual","title":"Offline Reinforcement Learning for Visual Navigation","date":"2022-12-16","arxiv_id":"2212.08244","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/last-mile-embodied-visual-navigation","slug":"last-mile-embodied-visual-navigation","title":"Last-Mile Embodied Visual Navigation","date":"2022-11-21","arxiv_id":"2211.11746","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/last-mile-embodied-visual-navigation#ran","syntology_url":"https://syntology.ai/paper/2211.11746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11746"}},"official":{"repos":["jbwasse2/sling"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/vinl-visual-navigation-and-locomotion-over","slug":"vinl-visual-navigation-and-locomotion-over","title":"ViNL: Visual Navigation and Locomotion Over Obstacles","date":"2022-10-26","arxiv_id":"2210.14791","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/visual-pre-training-for-navigation-what-can","slug":"visual-pre-training-for-navigation-what-can","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","date":"2022-06-30","arxiv_id":"2207.00052","repositories_listed":1,"syntology":null},{"url":"/paper/good-time-to-ask-a-learning-framework-for","slug":"good-time-to-ask-a-learning-framework-for","title":"Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation","date":"2022-06-20","arxiv_id":"2206.10606","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-navigation-agents-learn-about-their-1","slug":"what-do-navigation-agents-learn-about-their-1","title":"What do navigation agents learn about their environment?","date":"2022-06-17","arxiv_id":"2206.08500","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/what-do-navigation-agents-learn-about-their-1#ran","syntology_url":"https://syntology.ai/paper/2206.08500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08500"}},"official":{"repos":["allenai/isee"],"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/zero-shot-object-goal-visual-navigation","slug":"zero-shot-object-goal-visual-navigation","title":"Zero-shot object goal visual navigation","date":"2022-06-15","arxiv_id":"2206.07423","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":1,"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/zero-shot-object-goal-visual-navigation#ran","syntology_url":"https://syntology.ai/paper/2206.07423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07423"}},"official":{"repos":["pioneer-innovation/zero-shot-object-navigation"],"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/contrastive-learning-for-image-registration","slug":"contrastive-learning-for-image-registration","title":"Contrastive Learning for Image Registration in Visual Teach and Repeat Navigation","date":"2022-04-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-visual-navigation-perspective-for-category","slug":"a-visual-navigation-perspective-for-category","title":"A Visual Navigation Perspective for Category-Level Object Pose Estimation","date":"2022-03-25","arxiv_id":"2203.13572","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-visual-navigation-perspective-for-category#ran","syntology_url":"https://syntology.ai/paper/2203.13572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13572"}},"official":{"repos":["wrld/visual_navigation_pose_estimation"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simulation-benchmark-for-vision-based","slug":"a-simulation-benchmark-for-vision-based","title":"Benchmarking Visual Localization for Autonomous Navigation","date":"2022-03-24","arxiv_id":"2203.13048","repositories_listed":1,"syntology":null},{"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/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/sound-adversarial-audio-visual-navigation-1","slug":"sound-adversarial-audio-visual-navigation-1","title":"Sound Adversarial Audio-Visual Navigation","date":"2022-02-22","arxiv_id":"2202.10910","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sound-adversarial-audio-visual-navigation-1#ran","syntology_url":"https://syntology.ai/paper/2202.10910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10910"}},"official":{"repos":["yyf17/saavn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rara-zero-shot-sim2real-visual-navigation","slug":"rara-zero-shot-sim2real-visual-navigation","title":"RARA: Zero-shot Sim2Real Visual Navigation with Following Foreground Cues","date":"2022-01-08","arxiv_id":"2201.02798","repositories_listed":1,"syntology":null},{"url":"/paper/towards-disturbance-free-visual-mobile","slug":"towards-disturbance-free-visual-mobile","title":"Towards Disturbance-Free Visual Mobile Manipulation","date":"2021-12-17","arxiv_id":"2112.12612","repositories_listed":1,"syntology":null},{"url":"/paper/catch-me-if-you-hear-me-audio-visual","slug":"catch-me-if-you-hear-me-audio-visual","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","date":"2021-11-29","arxiv_id":"2111.14843","repositories_listed":1,"syntology":null},{"url":"/paper/goal-aware-cross-entropy-for-multi-target","slug":"goal-aware-cross-entropy-for-multi-target","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12985","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/goal-aware-cross-entropy-for-multi-target#ran","syntology_url":"https://syntology.ai/paper/2110.12985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12985"}},"official":{"repos":["kibeomkim/gace-gdan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sgolam-simultaneous-goal-localization-and","slug":"sgolam-simultaneous-goal-localization-and","title":"SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation","date":"2021-10-14","arxiv_id":"2110.07171","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/sgolam-simultaneous-goal-localization-and#ran","syntology_url":"https://syntology.ai/paper/2110.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07171"}},"official":{"repos":["eunsunlee/sgolam"],"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/seannet-semantic-understanding-network-for","slug":"seannet-semantic-understanding-network-for","title":"SeanNet: Semantic Understanding Network for Localization Under Object Dynamics","date":"2021-10-05","arxiv_id":"2110.02276","repositories_listed":1,"syntology":null},{"url":"/paper/waypoint-models-for-instruction-guided-1","slug":"waypoint-models-for-instruction-guided-1","title":"Waypoint Models for Instruction-guided Navigation in Continuous Environments","date":"2021-10-05","arxiv_id":"2110.02207","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/waypoint-models-for-instruction-guided-1#ran","syntology_url":"https://syntology.ai/paper/2110.02207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02207"}},"official":{"repos":["jacobkrantz/VLN-CE"],"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/towards-autonomous-crop-agnostic-visual","slug":"towards-autonomous-crop-agnostic-visual","title":"Towards Autonomous Crop-Agnostic Visual Navigation in Arable Fields","date":"2021-09-24","arxiv_id":"2109.11936","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-visual-navigation","slug":"collaborative-visual-navigation","title":"Collaborative Visual Navigation","date":"2021-07-02","arxiv_id":"2107.01151","repositories_listed":1,"syntology":null},{"url":"/paper/robustnav-towards-benchmarking-robustness-in","slug":"robustnav-towards-benchmarking-robustness-in","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","date":"2021-06-08","arxiv_id":"2106.04531","repositories_listed":1,"syntology":null},{"url":"/paper/out-of-the-box-embodied-navigation-in-the","slug":"out-of-the-box-embodied-navigation-in-the","title":"Out of the Box: Embodied Navigation in the Real World","date":"2021-05-12","arxiv_id":"2105.05873","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/out-of-the-box-embodied-navigation-in-the#ran","syntology_url":"https://syntology.ai/paper/2105.05873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05873"}},"official":{"repos":["aimagelab/LoCoNav"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pushing-it-out-of-the-way-interactive-visual","slug":"pushing-it-out-of-the-way-interactive-visual","title":"Pushing it out of the Way: Interactive Visual Navigation","date":"2021-04-28","arxiv_id":"2104.14040","repositories_listed":1,"syntology":null},{"url":"/paper/visual-navigation-with-spatial-attention","slug":"visual-navigation-with-spatial-attention","title":"Visual Navigation with Spatial Attention","date":"2021-04-20","arxiv_id":"2104.09807","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-navigation-with-spatial-attention#ran","syntology_url":"https://syntology.ai/paper/2104.09807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09807"}},"official":null}},{"url":"/paper/simultaneous-navigation-and-construction","slug":"simultaneous-navigation-and-construction","title":"Simultaneous Navigation and Construction Benchmarking Environments","date":"2021-03-31","arxiv_id":"2103.16732","repositories_listed":1,"syntology":null}],"syntology_records":33,"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":37,"papers_where_code_ran_first_page":"/task/visual-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":4,"url":"/task/visual-navigation/papers/2","json":"/task/visual-navigation/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/visual-navigation/papers/3","json":"/task/visual-navigation/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/visual-navigation/papers/4","json":"/task/visual-navigation/papers/4.json","rows":16},{"order":"ran","page":1,"of":1,"url":"/task/visual-navigation/papers/ran/1","json":"/task/visual-navigation/papers/ran/1.json","rows":37}],"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":"c787fefe5fbc6df5c334c3fb30396a542d1b3084d1a546ec0a13bb53a81a7e16","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}