{"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/natural-language-visual-grounding","name":"Natural Language Visual Grounding","slug":"natural-language-visual-grounding","description_markdown":null,"categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":32,"papers_with_code":30,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/natural-language-visual-grounding-on","slug":"natural-language-visual-grounding-on","dataset":"ScreenSpot","dataset_url":"/dataset/screenspot","rows_in_archive":18,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"UGround-V1-7B","paper_title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","paper_url":"/paper/navigating-the-digital-world-as-humans-do","paper_date":"2024-10-07","arxiv_id":"2410.05243","code_links":[{"title":"OSU-NLP-Group/UGround","url":"https://github.com/OSU-NLP-Group/UGround"}],"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/navigating-the-digital-world-as-humans-do#ran","syntology_url":"https://syntology.ai/paper/2410.05243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05243"}},"official":{"repos":["OSU-NLP-Group/UGround"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}}],"datasets":[{"url":"/dataset/referit3d","name":"ReferIt3D","full_name":"","num_papers_in_archive":104},{"url":"/dataset/screenspot","name":"ScreenSpot","full_name":"","num_papers_in_archive":47},{"url":"/dataset/google-refexp","name":"Google Refexp","full_name":"","num_papers_in_archive":46},{"url":"/dataset/mad","name":"MAD","full_name":"","num_papers_in_archive":36},{"url":"/dataset/spot-the-diff","name":"Spot-the-diff","full_name":"","num_papers_in_archive":35},{"url":"/dataset/imagecode","name":"ImageCoDe","full_name":"Image Retrieval from Contextual Descriptions","num_papers_in_archive":11},{"url":"/dataset/metu-viref-dataset","name":"METU-VIREF Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":32,"of":32,"of_with_code":30,"tagged_in_all":32,"counts":{"archive_papers_tagged":32,"with_a_code_link":30,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":32,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/alfred-a-benchmark-for-interpreting-grounded","slug":"alfred-a-benchmark-for-interpreting-grounded","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","date":"2019-12-03","arxiv_id":"1912.01734","repositories_listed":11,"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/alfred-a-benchmark-for-interpreting-grounded#ran","syntology_url":"https://syntology.ai/paper/1912.01734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01734"}},"official":{"repos":["askforalfred/alfred"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/qwen2-vl-enhancing-vision-language-model-s","slug":"qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","arxiv_id":"2409.12191","repositories_listed":8,"syntology":{"n":12,"n_ran":12,"n_constructed":1,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":4,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qwen2-vl-enhancing-vision-language-model-s#ran","syntology_url":"https://syntology.ai/paper/2409.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12191"}},"official":{"repos":["qwenlm/qwen2-vl"],"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":["listed","official"]}}},{"url":"/paper/cogagent-a-visual-language-model-for-gui","slug":"cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","arxiv_id":"2312.08914","repositories_listed":3,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"12 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; 8 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/cogagent-a-visual-language-model-for-gui#ran","syntology_url":"https://syntology.ai/paper/2312.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08914"}},"official":{"repos":["THUDM/CogAgent","thudm/cogvlm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/grounding-of-textual-phrases-in-images-by","slug":"grounding-of-textual-phrases-in-images-by","title":"Grounding of Textual Phrases in Images by Reconstruction","date":"2015-11-12","arxiv_id":"1511.03745","repositories_listed":3,"syntology":null},{"url":"/paper/os-atlas-a-foundation-action-model-for","slug":"os-atlas-a-foundation-action-model-for","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","date":"2024-10-30","arxiv_id":"2410.23218","repositories_listed":2,"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":0,"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/os-atlas-a-foundation-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2410.23218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23218"}},"official":{"repos":["OS-Copilot/OS-Atlas"],"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/minigpt-v2-large-language-model-as-a-unified","slug":"minigpt-v2-large-language-model-as-a-unified","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","date":"2023-10-14","arxiv_id":"2310.09478","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":1,"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/minigpt-v2-large-language-model-as-a-unified#ran","syntology_url":"https://syntology.ai/paper/2310.09478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09478"}},"official":null}},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","arxiv_id":"2308.12966","repositories_listed":2,"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/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}},"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/composing-pick-and-place-tasks-by-grounding","slug":"composing-pick-and-place-tasks-by-grounding","title":"Composing Pick-and-Place Tasks By Grounding Language","date":"2021-02-16","arxiv_id":"2102.08094","repositories_listed":2,"syntology":null},{"url":"/paper/alfworld-aligning-text-and-embodied","slug":"alfworld-aligning-text-and-embodied","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","date":"2020-10-08","arxiv_id":"2010.03768","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":4,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/alfworld-aligning-text-and-embodied#ran","syntology_url":"https://syntology.ai/paper/2010.03768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03768"}},"official":{"repos":["alfworld/alfworld"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":4,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-monitoring-navigation-agent-via","slug":"self-monitoring-navigation-agent-via","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","date":"2019-01-10","arxiv_id":"1901.03035","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-monitoring-navigation-agent-via#ran","syntology_url":"https://syntology.ai/paper/1901.03035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.03035"}},"official":{"repos":["chihyaoma/selfmonitoring-agent"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/aria-ui-visual-grounding-for-gui-instructions","slug":"aria-ui-visual-grounding-for-gui-instructions","title":"Aria-UI: Visual Grounding for GUI Instructions","date":"2024-12-20","arxiv_id":"2412.16256","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/aria-ui-visual-grounding-for-gui-instructions#ran","syntology_url":"https://syntology.ai/paper/2412.16256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16256"}},"official":null}},{"url":"/paper/aguvis-unified-pure-vision-agents-for","slug":"aguvis-unified-pure-vision-agents-for","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","date":"2024-12-05","arxiv_id":"2412.04454","repositories_listed":1,"syntology":null},{"url":"/paper/showui-one-vision-language-action-model-for","slug":"showui-one-vision-language-action-model-for","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","date":"2024-11-26","arxiv_id":"2411.17465","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/showui-one-vision-language-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.17465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17465"}},"official":{"repos":["showlab/showui"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-gui-grounding-via-iterative","slug":"improved-gui-grounding-via-iterative","title":"Improved GUI Grounding via Iterative Narrowing","date":"2024-11-18","arxiv_id":"2411.13591","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-the-digital-world-as-humans-do","slug":"navigating-the-digital-world-as-humans-do","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","date":"2024-10-07","arxiv_id":"2410.05243","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/navigating-the-digital-world-as-humans-do#ran","syntology_url":"https://syntology.ai/paper/2410.05243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05243"}},"official":{"repos":["OSU-NLP-Group/UGround"],"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/omniparser-for-pure-vision-based-gui-agent","slug":"omniparser-for-pure-vision-based-gui-agent","title":"OmniParser for Pure Vision Based GUI Agent","date":"2024-08-01","arxiv_id":"2408.00203","repositories_listed":1,"syntology":null},{"url":"/paper/guicourse-from-general-vision-language-models","slug":"guicourse-from-general-vision-language-models","title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","date":"2024-06-17","arxiv_id":"2406.11317","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":10,"n_instrument":5,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":16,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/guicourse-from-general-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.11317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11317"}},"official":{"repos":["yiye3/guicourse"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/groma-localized-visual-tokenization-for","slug":"groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","date":"2024-04-19","arxiv_id":"2404.13013","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":2,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/groma-localized-visual-tokenization-for#ran","syntology_url":"https://syntology.ai/paper/2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"official":{"repos":["FoundationVision/Groma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/seeclick-harnessing-gui-grounding-for","slug":"seeclick-harnessing-gui-grounding-for","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","date":"2024-01-17","arxiv_id":"2401.10935","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/seeclick-harnessing-gui-grounding-for#ran","syntology_url":"https://syntology.ai/paper/2401.10935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10935"}},"official":{"repos":["njucckevin/seeclick"],"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/localizing-moments-in-long-video-via","slug":"localizing-moments-in-long-video-via","title":"Localizing Moments in Long Video Via Multimodal Guidance","date":"2023-02-26","arxiv_id":"2302.13372","repositories_listed":1,"syntology":null},{"url":"/paper/belief-revision-based-caption-re-ranker-with","slug":"belief-revision-based-caption-re-ranker-with","title":"Belief Revision based Caption Re-ranker with Visual Semantic Information","date":"2022-09-16","arxiv_id":"2209.08163","repositories_listed":1,"syntology":null},{"url":"/paper/tubedetr-spatio-temporal-video-grounding-with","slug":"tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","arxiv_id":"2203.16434","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"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 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/tubedetr-spatio-temporal-video-grounding-with#ran","syntology_url":"https://syntology.ai/paper/2203.16434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16434"}},"official":{"repos":["antoyang/TubeDETR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/calvin-a-benchmark-for-language-conditioned","slug":"calvin-a-benchmark-for-language-conditioned","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","date":"2021-12-06","arxiv_id":"2112.03227","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/calvin-a-benchmark-for-language-conditioned#ran","syntology_url":"https://syntology.ai/paper/2112.03227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03227"}},"official":{"repos":["mees/calvin"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/panoptic-narrative-grounding","slug":"panoptic-narrative-grounding","title":"Panoptic Narrative Grounding","date":"2021-09-10","arxiv_id":"2109.04988","repositories_listed":1,"syntology":null},{"url":"/paper/panoptic-narrative-grounding-1","slug":"panoptic-narrative-grounding-1","title":"Panoptic Narrative Grounding","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-linguistic-analysis-of-visually-grounded","slug":"a-linguistic-analysis-of-visually-grounded","title":"A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions","date":"2020-10-07","arxiv_id":"2010.03127","repositories_listed":1,"syntology":null},{"url":"/paper/learning-cross-modal-context-graph-for-visual","slug":"learning-cross-modal-context-graph-for-visual","title":"Learning Cross-modal Context Graph for Visual Grounding","date":"2020-02-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-ambiguous-objects-in-videos","slug":"searching-for-ambiguous-objects-in-videos","title":"Searching for Ambiguous Objects in Videos using Relational Referring Expressions","date":"2019-08-03","arxiv_id":"1908.01189","repositories_listed":1,"syntology":null},{"url":"/paper/modularized-textual-grounding-for","slug":"modularized-textual-grounding-for","title":"Modularized Textual Grounding for Counterfactual Resilience","date":"2019-04-07","arxiv_id":"1904.03589","repositories_listed":1,"syntology":null},{"url":"/paper/viewpoint-invariant-change-captioning","slug":"viewpoint-invariant-change-captioning","title":"Robust Change Captioning","date":"2019-01-08","arxiv_id":"1901.02527","repositories_listed":1,"syntology":null},{"url":"/paper/visual-writing-prompts-character-grounded","slug":"visual-writing-prompts-character-grounded","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","date":"2023-01-20","arxiv_id":"2301.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-by-parsing-neural-module-tree","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","date":"2018-12-08","arxiv_id":"1812.03299","repositories_listed":0,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/natural-language-visual-grounding-on","since_archive":"/sota/natural-language-visual-grounding-on#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/task/natural-language-visual-grounding/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/natural-language-visual-grounding/papers/ran/1","json":"/task/natural-language-visual-grounding/papers/ran/1.json","rows":14}],"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":"5a2230d1649c99640fa429c718a6e5a8edf852d435e4383bb2c7526df584bce8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}