{"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/navigate","name":"Navigate","slug":"navigate","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1982,"papers_with_code":644,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":2,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","num_papers_in_archive":2}],"subtasks":[{"url":"/task/go-to-anything","name":"Go to AnyThing"},{"url":"/task/universal-navigation","name":"Universal Navigation"}],"parent_tasks":[{"url":"/task/logical-reasoning","name":"Logical Reasoning"}],"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":20,"rows_per_page":100,"shown":100,"of":1979,"of_with_code":644,"tagged_in_all":1982,"counts":{"archive_papers_tagged":1982,"with_a_code_link":644,"where_syntology_ran_a_sample":152,"not_listed_spam_title":3,"listed":1979,"listed_where_code_ran":152,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":122,"every_run_a_failure_of_syntologys_instrument":30,"listed_with_a_run_with_no_instrument_failure":122,"listed_every_run_a_failure_of_syntologys_instrument":30,"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/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","repositories_listed":27,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}},"official":{"repos":["allenai/bi-att-flow"],"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/decentralized-distributed-ppo-solving","slug":"decentralized-distributed-ppo-solving","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","date":"2019-11-01","arxiv_id":"1911.00357","repositories_listed":8,"syntology":null},{"url":"/paper/social-gan-socially-acceptable-trajectories","slug":"social-gan-socially-acceptable-trajectories","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","date":"2018-03-29","arxiv_id":"1803.10892","repositories_listed":8,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/social-gan-socially-acceptable-trajectories#ran","syntology_url":"https://syntology.ai/paper/1803.10892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10892"}},"official":{"repos":["agrimgupta92/sgan"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/go-for-a-walk-and-arrive-at-the-answer","slug":"go-for-a-walk-and-arrive-at-the-answer","title":"Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning","date":"2017-11-15","arxiv_id":"1711.05851","repositories_listed":8,"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/go-for-a-walk-and-arrive-at-the-answer#ran","syntology_url":"https://syntology.ai/paper/1711.05851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05851"}},"official":{"repos":["shehzaadzd/MINERVA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/crowd-robot-interaction-crowd-aware-robot","slug":"crowd-robot-interaction-crowd-aware-robot","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","date":"2018-09-24","arxiv_id":"1809.08835","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crowd-robot-interaction-crowd-aware-robot#ran","syntology_url":"https://syntology.ai/paper/1809.08835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08835"}},"official":{"repos":["vita-epfl/CrowdNav","vita-epfl/DyNav"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vizdoom-competitions-playing-doom-from-pixels","slug":"vizdoom-competitions-playing-doom-from-pixels","title":"ViZDoom Competitions: Playing Doom from Pixels","date":"2018-09-10","arxiv_id":"1809.03470","repositories_listed":7,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/vizdoom-competitions-playing-doom-from-pixels#ran","syntology_url":"https://syntology.ai/paper/1809.03470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.03470"}},"official":{"repos":["mwydmuch/ViZDoom"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","slug":"deblurgan-v2-deblurring-orders-of-magnitude","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","date":"2019-08-10","arxiv_id":"1908.03826","repositories_listed":6,"syntology":null},{"url":"/paper/motion-planning-among-dynamic-decision-making","slug":"motion-planning-among-dynamic-decision-making","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01956","repositories_listed":6,"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/motion-planning-among-dynamic-decision-making#ran","syntology_url":"https://syntology.ai/paper/1805.01956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01956"}},"official":{"repos":["mfe7/cadrl_ros"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/towards-mental-time-travel-a-hierarchical","slug":"towards-mental-time-travel-a-hierarchical","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","date":"2021-05-28","arxiv_id":"2105.14039","repositories_listed":5,"syntology":{"n":6,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-mental-time-travel-a-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2105.14039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14039"}},"official":{"repos":["deepmind/deepmind-research","deepmind/dm_fast_mapping"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/why-not-use-your-textbook-knowledge-enhanced","slug":"why-not-use-your-textbook-knowledge-enhanced","title":"Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos","date":"2024-03-05","arxiv_id":"2403.02782","repositories_listed":4,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/why-not-use-your-textbook-knowledge-enhanced#ran","syntology_url":"https://syntology.ai/paper/2403.02782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02782"}},"official":{"repos":["ravindu-yasas-nagasinghe/kepp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/wizmap-scalable-interactive-visualization-for","slug":"wizmap-scalable-interactive-visualization-for","title":"WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings","date":"2023-06-15","arxiv_id":"2306.09328","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wizmap-scalable-interactive-visualization-for#ran","syntology_url":"https://syntology.ai/paper/2306.09328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09328"}},"official":{"repos":["poloclub/wizmap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/melting-pot-2-0","slug":"melting-pot-2-0","title":"Melting Pot 2.0","date":"2022-11-24","arxiv_id":"2211.13746","repositories_listed":4,"syntology":null},{"url":"/paper/objective-robustness-in-deep-reinforcement","slug":"objective-robustness-in-deep-reinforcement","title":"Goal Misgeneralization in Deep Reinforcement Learning","date":"2021-05-28","arxiv_id":"2105.14111","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/objective-robustness-in-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14111"}},"official":{"repos":["JacobPfau/procgenAISC","jbkjr/train-procgen-pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/meta-learning-through-hebbian-plasticity-in","slug":"meta-learning-through-hebbian-plasticity-in","title":"Meta-Learning through Hebbian Plasticity in Random Networks","date":"2020-07-06","arxiv_id":"2007.02686","repositories_listed":4,"syntology":null},{"url":"/paper/learning-to-navigate-in-cities-without-a-map","slug":"learning-to-navigate-in-cities-without-a-map","title":"Learning to Navigate in Cities Without a Map","date":"2018-03-31","arxiv_id":"1804.00168","repositories_listed":4,"syntology":null},{"url":"/paper/embodied-question-answering","slug":"embodied-question-answering","title":"Embodied Question Answering","date":"2017-11-30","arxiv_id":"1711.11543","repositories_listed":4,"syntology":null},{"url":"/paper/webthinker-empowering-large-reasoning-models","slug":"webthinker-empowering-large-reasoning-models","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","date":"2025-04-30","arxiv_id":"2504.21776","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/webthinker-empowering-large-reasoning-models#ran","syntology_url":"https://syntology.ai/paper/2504.21776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21776"}},"official":{"repos":["ruc-nlpir/webthinker","sunnynexus/webthinker"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/patch-n-pack-navit-a-vision-transformer-for","slug":"patch-n-pack-navit-a-vision-transformer-for","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","date":"2023-07-12","arxiv_id":"2307.06304","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/patch-n-pack-navit-a-vision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2307.06304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06304"}},"official":null}},{"url":"/paper/rl4co-an-extensive-reinforcement-learning-for","slug":"rl4co-an-extensive-reinforcement-learning-for","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","date":"2023-06-29","arxiv_id":"2306.17100","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rl4co-an-extensive-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17100"}},"official":{"repos":["ai4co/rl4co","pytorch/rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/webshop-towards-scalable-real-world-web","slug":"webshop-towards-scalable-real-world-web","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","date":"2022-07-04","arxiv_id":"2207.01206","repositories_listed":3,"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/webshop-towards-scalable-real-world-web#ran","syntology_url":"https://syntology.ai/paper/2207.01206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01206"}},"official":{"repos":["princeton-nlp/WebShop"],"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/vectormapnet-end-to-end-vectorized-hd-map","slug":"vectormapnet-end-to-end-vectorized-hd-map","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","date":"2022-06-17","arxiv_id":"2206.08920","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/tph-yolov5-improved-yolov5-based-on","slug":"tph-yolov5-improved-yolov5-based-on","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","date":"2021-08-26","arxiv_id":"2108.11539","repositories_listed":3,"syntology":null},{"url":"/paper/extracting-a-knowledge-base-of-mechanisms","slug":"extracting-a-knowledge-base-of-mechanisms","title":"Extracting a Knowledge Base of Mechanisms from COVID-19 Papers","date":"2020-10-08","arxiv_id":"2010.03824","repositories_listed":3,"syntology":null},{"url":"/paper/autotrans-automating-transformer-design-via","slug":"autotrans-automating-transformer-design-via","title":"AutoTrans: Automating Transformer Design via Reinforced Architecture Search","date":"2020-09-04","arxiv_id":"2009.02070","repositories_listed":3,"syntology":null},{"url":"/paper/holmes-health-online-model-ensemble-serving","slug":"holmes-health-online-model-ensemble-serving","title":"HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units","date":"2020-08-10","arxiv_id":"2008.04063","repositories_listed":3,"syntology":null},{"url":"/paper/avp-slam-semantic-visual-mapping-and","slug":"avp-slam-semantic-visual-mapping-and","title":"AVP-SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot","date":"2020-07-03","arxiv_id":"2007.01813","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-real","slug":"deep-reinforcement-learning-for-real","title":"Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments","date":"2020-05-28","arxiv_id":"2005.13857","repositories_listed":3,"syntology":null},{"url":"/paper/jelly-bean-world-a-testbed-for-never-ending-1","slug":"jelly-bean-world-a-testbed-for-never-ending-1","title":"Jelly Bean World: A Testbed for Never-Ending Learning","date":"2020-02-15","arxiv_id":"2002.06306","repositories_listed":3,"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/jelly-bean-world-a-testbed-for-never-ending-1#ran","syntology_url":"https://syntology.ai/paper/2002.06306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06306"}},"official":{"repos":["eaplatanios/jelly-bean-world"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/virtual-to-real-deep-reinforcement-learning","slug":"virtual-to-real-deep-reinforcement-learning","title":"Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation","date":"2017-03-01","arxiv_id":"1703.00420","repositories_listed":3,"syntology":null},{"url":"/paper/personalized-federated-learning-via-feature","slug":"personalized-federated-learning-via-feature","title":"Personalized Federated Learning via Feature Distribution Adaptation","date":"2024-11-01","arxiv_id":"2411.00329","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/personalized-federated-learning-via-feature#ran","syntology_url":"https://syntology.ai/paper/2411.00329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00329"}},"official":{"repos":["cj-mclaughlin/pfedfda"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/event-based-stereo-depth-estimation-a-survey","slug":"event-based-stereo-depth-estimation-a-survey","title":"Event-based Stereo Depth Estimation: A Survey","date":"2024-09-26","arxiv_id":"2409.17680","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/event-based-stereo-depth-estimation-a-survey#ran","syntology_url":"https://syntology.ai/paper/2409.17680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17680"}},"official":null}},{"url":"/paper/oodis-anomaly-instance-segmentation-benchmark","slug":"oodis-anomaly-instance-segmentation-benchmark","title":"OoDIS: Anomaly Instance Segmentation Benchmark","date":"2024-06-17","arxiv_id":"2406.11835","repositories_listed":2,"syntology":null},{"url":"/paper/optimizing-instructions-and-demonstrations","slug":"optimizing-instructions-and-demonstrations","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","date":"2024-06-17","arxiv_id":"2406.11695","repositories_listed":2,"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/optimizing-instructions-and-demonstrations#ran","syntology_url":"https://syntology.ai/paper/2406.11695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11695"}},"official":{"repos":["stanfordnlp/dspy"],"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/lmvd-a-large-scale-multimodal-vlog-dataset","slug":"lmvd-a-large-scale-multimodal-vlog-dataset","title":"LMVD: A Large-Scale Multimodal Vlog Dataset for Depression Detection in the Wild","date":"2024-05-09","arxiv_id":"2407.00024","repositories_listed":2,"syntology":null},{"url":"/paper/swe-agent-agent-computer-interfaces-enable","slug":"swe-agent-agent-computer-interfaces-enable","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","date":"2024-05-06","arxiv_id":"2405.15793","repositories_listed":2,"syntology":null},{"url":"/paper/appagent-multimodal-agents-as-smartphone","slug":"appagent-multimodal-agents-as-smartphone","title":"AppAgent: Multimodal Agents as Smartphone Users","date":"2023-12-21","arxiv_id":"2312.13771","repositories_listed":2,"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/appagent-multimodal-agents-as-smartphone#ran","syntology_url":"https://syntology.ai/paper/2312.13771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13771"}},"official":{"repos":["mnotgod96/AppAgent"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/depicting-beyond-scores-advancing-image","slug":"depicting-beyond-scores-advancing-image","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","date":"2023-12-14","arxiv_id":"2312.08962","repositories_listed":2,"syntology":null},{"url":"/paper/nllg-quarterly-arxiv-report-09-23-what-are","slug":"nllg-quarterly-arxiv-report-09-23-what-are","title":"NLLG Quarterly arXiv Report 09/23: What are the most influential current AI Papers?","date":"2023-12-09","arxiv_id":"2312.05688","repositories_listed":2,"syntology":null},{"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/tree-of-attacks-jailbreaking-black-box-llms","slug":"tree-of-attacks-jailbreaking-black-box-llms","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","date":"2023-12-04","arxiv_id":"2312.02119","repositories_listed":2,"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/tree-of-attacks-jailbreaking-black-box-llms#ran","syntology_url":"https://syntology.ai/paper/2312.02119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02119"}},"official":{"repos":["ricommunity/tap"],"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/promptagent-strategic-planning-with-language","slug":"promptagent-strategic-planning-with-language","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","date":"2023-10-25","arxiv_id":"2310.16427","repositories_listed":2,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/promptagent-strategic-planning-with-language#ran","syntology_url":"https://syntology.ai/paper/2310.16427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16427"}},"official":{"repos":["xinyuanwangcs/promptagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/offline-prompt-evaluation-and-optimization","slug":"offline-prompt-evaluation-and-optimization","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","date":"2023-09-13","arxiv_id":"2309.06553","repositories_listed":2,"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/offline-prompt-evaluation-and-optimization#ran","syntology_url":"https://syntology.ai/paper/2309.06553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06553"}},"official":{"repos":["holarissun/prompt-oirl","vanderschaarlab/prompt-oirl"],"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/manipulating-embeddings-of-stable-diffusion","slug":"manipulating-embeddings-of-stable-diffusion","title":"Manipulating Embeddings of Stable Diffusion Prompts","date":"2023-08-23","arxiv_id":"2308.12059","repositories_listed":2,"syntology":null},{"url":"/paper/a-first-look-at-llm-powered-generative-news","slug":"a-first-look-at-llm-powered-generative-news","title":"ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models","date":"2023-05-11","arxiv_id":"2305.06566","repositories_listed":2,"syntology":null},{"url":"/paper/is-a-prompt-and-a-few-samples-all-you-need","slug":"is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","date":"2023-04-26","arxiv_id":"2304.13861","repositories_listed":2,"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/is-a-prompt-and-a-few-samples-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2304.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13861"}},"official":{"repos":["andersgiovanni/worker_vs_gpt","AGMoller/worker_vs_gpt"],"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/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","repositories_listed":2,"syntology":null},{"url":"/paper/sift-sparse-iso-flop-transformations-for","slug":"sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","arxiv_id":"2303.11525","repositories_listed":2,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sift-sparse-iso-flop-transformations-for#ran","syntology_url":"https://syntology.ai/paper/2303.11525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11525"}},"official":{"repos":["cerebrasresearch/sift","cerebrasresearch/sparse-ift"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dfr-fastmot-detection-failure-resistant","slug":"dfr-fastmot-detection-failure-resistant","title":"DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion","date":"2023-02-28","arxiv_id":"2302.14807","repositories_listed":2,"syntology":null},{"url":"/paper/aerial-vision-and-dialog-navigation","slug":"aerial-vision-and-dialog-navigation","title":"Aerial Vision-and-Dialog Navigation","date":"2022-05-24","arxiv_id":"2205.12219","repositories_listed":2,"syntology":null},{"url":"/paper/e-scooter-rider-detection-and-classification","slug":"e-scooter-rider-detection-and-classification","title":"E-Scooter Rider Detection and Classification in Dense Urban Environments","date":"2022-05-20","arxiv_id":"2205.10184","repositories_listed":2,"syntology":null},{"url":"/paper/mugen-a-playground-for-video-audio-text","slug":"mugen-a-playground-for-video-audio-text","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","date":"2022-04-17","arxiv_id":"2204.08058","repositories_listed":2,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/pedestrian-stop-and-go-forecasting-with","slug":"pedestrian-stop-and-go-forecasting-with","title":"Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion","date":"2022-03-04","arxiv_id":"2203.02489","repositories_listed":2,"syntology":null},{"url":"/paper/dialfred-dialogue-enabled-agents-for-embodied","slug":"dialfred-dialogue-enabled-agents-for-embodied","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","date":"2022-02-27","arxiv_id":"2202.13330","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialfred-dialogue-enabled-agents-for-embodied#ran","syntology_url":"https://syntology.ai/paper/2202.13330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13330"}},"official":{"repos":["anonrabit/dialfred","xfgao/dialfred"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/webgpt-browser-assisted-question-answering","slug":"webgpt-browser-assisted-question-answering","title":"WebGPT: Browser-assisted question-answering with human feedback","date":"2021-12-17","arxiv_id":"2112.09332","repositories_listed":2,"syntology":null},{"url":"/paper/simple-but-effective-clip-embeddings-for","slug":"simple-but-effective-clip-embeddings-for","title":"Simple but Effective: CLIP Embeddings for Embodied AI","date":"2021-11-18","arxiv_id":"2111.09888","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-but-effective-clip-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/2111.09888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09888"}},"official":{"repos":["allenai/embodied-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/airbert-in-domain-pretraining-for-vision-and","slug":"airbert-in-domain-pretraining-for-vision-and","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","date":"2021-08-20","arxiv_id":"2108.09105","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/airbert-in-domain-pretraining-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2108.09105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09105"}},"official":{"repos":["airbert-vln/airbert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/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/visual-room-rearrangement","slug":"visual-room-rearrangement","title":"Visual Room Rearrangement","date":"2021-03-30","arxiv_id":"2103.16544","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/visual-room-rearrangement#ran","syntology_url":"https://syntology.ai/paper/2103.16544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16544"}},"official":{"repos":["allenai/robothor-challenge"],"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":["official"]}}},{"url":"/paper/datalens-scalable-privacy-preserving-training","slug":"datalens-scalable-privacy-preserving-training","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","date":"2021-03-20","arxiv_id":"2103.11109","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-learning-of-lidar","slug":"self-supervised-learning-of-lidar","title":"Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation","date":"2020-12-10","arxiv_id":"2012.05897","repositories_listed":2,"syntology":null},{"url":"/paper/solving-the-lunar-lander-problem-under","slug":"solving-the-lunar-lander-problem-under","title":"Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learning","date":"2020-11-24","arxiv_id":"2011.11850","repositories_listed":2,"syntology":null},{"url":"/paper/where-are-you-localization-from-embodied","slug":"where-are-you-localization-from-embodied","title":"Where Are You? Localization from Embodied Dialog","date":"2020-11-16","arxiv_id":"2011.08277","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/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/one-explanation-does-not-fit-all-a-toolkit","slug":"one-explanation-does-not-fit-all-a-toolkit","title":"One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques","date":"2019-09-06","arxiv_id":"1909.03012","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/one-explanation-does-not-fit-all-a-toolkit#ran","syntology_url":"https://syntology.ai/paper/1909.03012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03012"}},"official":{"repos":["IBM/AIX360"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-multi-vehicle-interaction-scenarios","slug":"modeling-multi-vehicle-interaction-scenarios","title":"Modeling Multi-Vehicle Interaction Scenarios Using Gaussian Random Field","date":"2019-06-25","arxiv_id":"1906.10307","repositories_listed":2,"syntology":null},{"url":"/paper/cross-view-policy-learning-for-street","slug":"cross-view-policy-learning-for-street","title":"Cross-View Policy Learning for Street Navigation","date":"2019-06-13","arxiv_id":"1906.05930","repositories_listed":2,"syntology":null},{"url":"/paper/safe-reinforcement-learning-with-scene","slug":"safe-reinforcement-learning-with-scene","title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","date":"2019-04-25","arxiv_id":"1904.11483","repositories_listed":2,"syntology":null},{"url":"/paper/ai-imu-dead-reckoning","slug":"ai-imu-dead-reckoning","title":"AI-IMU Dead-Reckoning","date":"2019-04-12","arxiv_id":"1904.06064","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-follow-directions-in-street-view","slug":"learning-to-follow-directions-in-street-view","title":"Learning To Follow Directions in Street View","date":"2019-03-01","arxiv_id":"1903.00401","repositories_listed":2,"syntology":null},{"url":"/paper/universal-successor-features-approximators","slug":"universal-successor-features-approximators","title":"Universal Successor Features Approximators","date":"2018-12-18","arxiv_id":"1812.07626","repositories_listed":2,"syntology":null},{"url":"/paper/q-map-a-convolutional-approach-for-goal","slug":"q-map-a-convolutional-approach-for-goal","title":"Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks","date":"2018-10-06","arxiv_id":"1810.02927","repositories_listed":2,"syntology":null},{"url":"/paper/visceral-machines-reinforcement-learning-with","slug":"visceral-machines-reinforcement-learning-with","title":"Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological Rewards","date":"2018-05-25","arxiv_id":"1805.09975","repositories_listed":2,"syntology":null},{"url":"/paper/ai2-thor-an-interactive-3d-environment-for","slug":"ai2-thor-an-interactive-3d-environment-for","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","date":"2017-12-14","arxiv_id":"1712.05474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai2-thor-an-interactive-3d-environment-for#ran","syntology_url":"https://syntology.ai/paper/1712.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05474"}},"official":{"repos":["allenai/ai2thor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/minos-multimodal-indoor-simulator-for","slug":"minos-multimodal-indoor-simulator-for","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","date":"2017-12-11","arxiv_id":"1712.03931","repositories_listed":2,"syntology":null},{"url":"/paper/intention-net-integrating-planning-and-deep","slug":"intention-net-integrating-planning-and-deep","title":"Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation","date":"2017-10-16","arxiv_id":"1710.05627","repositories_listed":2,"syntology":null},{"url":"/paper/social-attention-modeling-attention-in-human","slug":"social-attention-modeling-attention-in-human","title":"Social Attention: Modeling Attention in Human Crowds","date":"2017-10-12","arxiv_id":"1710.04689","repositories_listed":2,"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/social-attention-modeling-attention-in-human#ran","syntology_url":"https://syntology.ai/paper/1710.04689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.04689"}},"official":null}},{"url":"/paper/self-supervised-deep-reinforcement-learning","slug":"self-supervised-deep-reinforcement-learning","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","date":"2017-09-29","arxiv_id":"1709.10489","repositories_listed":2,"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/self-supervised-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1709.10489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.10489"}},"official":{"repos":["gkahn13/gcg"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-tutorial-on-deep-learning-for-music","slug":"a-tutorial-on-deep-learning-for-music","title":"A Tutorial on Deep Learning for Music Information Retrieval","date":"2017-09-13","arxiv_id":"1709.04396","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-6dof-outdoor-visual-localization","slug":"benchmarking-6dof-outdoor-visual-localization","title":"Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions","date":"2017-07-28","arxiv_id":"1707.09092","repositories_listed":2,"syntology":null},{"url":"/paper/socially-aware-motion-planning-with-deep","slug":"socially-aware-motion-planning-with-deep","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","date":"2017-03-26","arxiv_id":"1703.08862","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-evolution-of-image-classifiers","slug":"large-scale-evolution-of-image-classifiers","title":"Large-Scale Evolution of Image Classifiers","date":"2017-03-03","arxiv_id":"1703.01041","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-scale-evolution-of-image-classifiers#ran","syntology_url":"https://syntology.ai/paper/1703.01041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01041"}},"official":null}},{"url":"/paper/structsense-a-task-agnostic-agentic-framework","slug":"structsense-a-task-agnostic-agentic-framework","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","date":"2025-07-04","arxiv_id":"2507.03674","repositories_listed":1,"syntology":null},{"url":"/paper/ai-research-agents-for-machine-learning","slug":"ai-research-agents-for-machine-learning","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","date":"2025-07-03","arxiv_id":"2507.02554","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ai-research-agents-for-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2507.02554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02554"}},"official":{"repos":["facebookresearch/aira-dojo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decide-less-communicate-more-on-the-construct","slug":"decide-less-communicate-more-on-the-construct","title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine","date":"2025-06-25","arxiv_id":"2506.20876","repositories_listed":1,"syntology":null},{"url":"/paper/the-decrypto-benchmark-for-multi-agent","slug":"the-decrypto-benchmark-for-multi-agent","title":"The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind","date":"2025-06-25","arxiv_id":"2506.20664","repositories_listed":1,"syntology":null},{"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/from-emergence-to-control-probing-and","slug":"from-emergence-to-control-probing-and","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","date":"2025-06-13","arxiv_id":"2506.12217","repositories_listed":1,"syntology":null},{"url":"/paper/2506-10172","slug":"2506-10172","title":"A Navigation Framework Utilizing Vision-Language Models","date":"2025-06-11","arxiv_id":"2506.10172","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-pitfalls-in-auditing-practices-of","slug":"addressing-pitfalls-in-auditing-practices-of","title":"Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia","date":"2025-06-10","arxiv_id":"2506.08846","repositories_listed":1,"syntology":null},{"url":"/paper/eifbench-extremely-complex-instruction","slug":"eifbench-extremely-complex-instruction","title":"EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models","date":"2025-06-10","arxiv_id":"2506.08375","repositories_listed":1,"syntology":null},{"url":"/paper/dualmap-online-open-vocabulary-semantic","slug":"dualmap-online-open-vocabulary-semantic","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes","date":"2025-06-02","arxiv_id":"2506.01950","repositories_listed":1,"syntology":null},{"url":"/paper/semnav-a-semantic-segmentation-driven","slug":"semnav-a-semantic-segmentation-driven","title":"SEMNAV: A Semantic Segmentation-Driven Approach to Visual Semantic Navigation","date":"2025-06-02","arxiv_id":"2506.01418","repositories_listed":1,"syntology":null},{"url":"/paper/socialeval-evaluating-social-intelligence-of","slug":"socialeval-evaluating-social-intelligence-of","title":"SocialEval: Evaluating Social Intelligence of Large Language Models","date":"2025-06-01","arxiv_id":"2506.00900","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/socialeval-evaluating-social-intelligence-of#ran","syntology_url":"https://syntology.ai/paper/2506.00900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00900"}},"official":{"repos":["thu-coai/socialeval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-structured-unplugged-approach-for","slug":"a-structured-unplugged-approach-for","title":"A Structured Unplugged Approach for Foundational AI Literacy in Primary Education","date":"2025-05-27","arxiv_id":"2505.21398","repositories_listed":1,"syntology":null},{"url":"/paper/cross-from-left-to-right-brain-adaptive-text","slug":"cross-from-left-to-right-brain-adaptive-text","title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","date":"2025-05-27","arxiv_id":"2505.20897","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-planning-a","slug":"large-language-models-for-planning-a","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","date":"2025-05-26","arxiv_id":"2505.19683","repositories_listed":1,"syntology":null},{"url":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in","slug":"when-ethics-and-payoffs-diverge-llm-agents-in","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","date":"2025-05-25","arxiv_id":"2505.19212","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in#ran","syntology_url":"https://syntology.ai/paper/2505.19212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19212"}},"official":{"repos":["sbackmann/moralsim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}}],"syntology_records":38,"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":152,"papers_where_code_ran_first_page":"/task/navigate/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":20,"url":"/task/navigate/papers/2","json":"/task/navigate/papers/2.json","rows":100},{"order":"archive","page":3,"of":20,"url":"/task/navigate/papers/3","json":"/task/navigate/papers/3.json","rows":100},{"order":"archive","page":4,"of":20,"url":"/task/navigate/papers/4","json":"/task/navigate/papers/4.json","rows":100},{"order":"archive","page":5,"of":20,"url":"/task/navigate/papers/5","json":"/task/navigate/papers/5.json","rows":100},{"order":"archive","page":6,"of":20,"url":"/task/navigate/papers/6","json":"/task/navigate/papers/6.json","rows":100},{"order":"archive","page":7,"of":20,"url":"/task/navigate/papers/7","json":"/task/navigate/papers/7.json","rows":100},{"order":"archive","page":8,"of":20,"url":"/task/navigate/papers/8","json":"/task/navigate/papers/8.json","rows":100},{"order":"archive","page":9,"of":20,"url":"/task/navigate/papers/9","json":"/task/navigate/papers/9.json","rows":100},{"order":"archive","page":10,"of":20,"url":"/task/navigate/papers/10","json":"/task/navigate/papers/10.json","rows":100},{"order":"archive","page":11,"of":20,"url":"/task/navigate/papers/11","json":"/task/navigate/papers/11.json","rows":100},{"order":"archive","page":12,"of":20,"url":"/task/navigate/papers/12","json":"/task/navigate/papers/12.json","rows":100},{"order":"archive","page":13,"of":20,"url":"/task/navigate/papers/13","json":"/task/navigate/papers/13.json","rows":100},{"order":"archive","page":14,"of":20,"url":"/task/navigate/papers/14","json":"/task/navigate/papers/14.json","rows":100},{"order":"archive","page":15,"of":20,"url":"/task/navigate/papers/15","json":"/task/navigate/papers/15.json","rows":100},{"order":"archive","page":16,"of":20,"url":"/task/navigate/papers/16","json":"/task/navigate/papers/16.json","rows":100},{"order":"archive","page":17,"of":20,"url":"/task/navigate/papers/17","json":"/task/navigate/papers/17.json","rows":100},{"order":"archive","page":18,"of":20,"url":"/task/navigate/papers/18","json":"/task/navigate/papers/18.json","rows":100},{"order":"archive","page":19,"of":20,"url":"/task/navigate/papers/19","json":"/task/navigate/papers/19.json","rows":100},{"order":"archive","page":20,"of":20,"url":"/task/navigate/papers/20","json":"/task/navigate/papers/20.json","rows":79},{"order":"ran","page":1,"of":2,"url":"/task/navigate/papers/ran/1","json":"/task/navigate/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/navigate/papers/ran/2","json":"/task/navigate/papers/ran/2.json","rows":52}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"40d0961cddb60e29e110c536d64841b55ac788c392c460cbdcb0aaafd35781fe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}