{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/visual-grounding","name":"Visual Grounding","slug":"visual-grounding","description_markdown":"Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence, or even a multi-round dialogue. There are three main challenges in\r\nVG: \r\n\r\n* What is the main focus in a query? \r\n* How to understand an image? \r\n* How to locate an object?","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":571,"papers_with_code":299,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":11,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/visual-grounding-on-refcoco-testa","slug":"visual-grounding-on-refcoco-testa","dataset":"RefCOCO+ testA","dataset_url":"/dataset/refcoco","rows_in_archive":7,"metrics":["Accuracy (%)","IoU"],"first_row_in_archive_order":{"model":"Florence-2-large-ft","paper_title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","paper_url":"/paper/florence-2-advancing-a-unified-representation","paper_date":"2023-11-10","arxiv_id":"2311.06242","code_links":[{"title":"retkowsky/florence-2","url":"https://github.com/retkowsky/florence-2"}],"syntology":null}},{"leaderboard":"/sota/visual-grounding-on-refcoco-test-b","slug":"visual-grounding-on-refcoco-test-b","dataset":"RefCOCO+ test B","dataset_url":"/dataset/refcoco","rows_in_archive":6,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Florence-2-large-ft","paper_title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","paper_url":"/paper/florence-2-advancing-a-unified-representation","paper_date":"2023-11-10","arxiv_id":"2311.06242","code_links":[{"title":"retkowsky/florence-2","url":"https://github.com/retkowsky/florence-2"}],"syntology":null}},{"leaderboard":"/sota/visual-grounding-on-refcoco-val","slug":"visual-grounding-on-refcoco-val","dataset":"RefCOCO+ val","dataset_url":"/dataset/refcoco","rows_in_archive":6,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Florence-2-large-ft","paper_title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","paper_url":"/paper/florence-2-advancing-a-unified-representation","paper_date":"2023-11-10","arxiv_id":"2311.06242","code_links":[{"title":"retkowsky/florence-2","url":"https://github.com/retkowsky/florence-2"}],"syntology":null}},{"leaderboard":"/sota/visual-grounding-on-refcoco-testa-1","slug":"visual-grounding-on-refcoco-testa-1","dataset":"RefCOCO testA","dataset_url":"/dataset/refcoco","rows_in_archive":1,"metrics":["IoU"],"first_row_in_archive_order":{"model":"HYDRA","paper_title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","paper_url":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","paper_date":"2024-03-19","arxiv_id":"2403.12884","code_links":[{"title":"ControlNet/HYDRA","url":"https://github.com/ControlNet/HYDRA"}],"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hydra-a-hyper-agent-for-dynamic-compositional#ran","syntology_url":"https://syntology.ai/paper/2403.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12884"}},"official":{"repos":["ControlNet/HYDRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/refcoco","name":"RefCOCO","full_name":"","num_papers_in_archive":439},{"url":"/dataset/rsvgd","name":"DIOR-RSVG","full_name":"","num_papers_in_archive":25},{"url":"/dataset/mrr-benchmark","name":"MRR-Benchmark","full_name":"Multi-Modal Reading Benchmark","num_papers_in_archive":11},{"url":"/dataset/infinity-mm","name":"Infinity-MM","full_name":"","num_papers_in_archive":5},{"url":"/dataset/skyeye-968k","name":"SkyEye-968k","full_name":"","num_papers_in_archive":5},{"url":"/dataset/a-game-of-sorts","name":"A Game Of Sorts","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mono3drefer","name":"Mono3DRefer","full_name":"","num_papers_in_archive":3},{"url":"/dataset/vizwiz-answer-grounding","name":"VizWiz Answer Grounding","full_name":"","num_papers_in_archive":3},{"url":"/dataset/sk-vg","name":"SK-VG","full_name":"","num_papers_in_archive":2},{"url":"/dataset/automotiveui-bench-4k","name":"AutomotiveUI-Bench-4K","full_name":"","num_papers_in_archive":1},{"url":"/dataset/visargs","name":"VisArgs","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-visual-grounding","name":"3D visual grounding"},{"url":"/task/person-centric-visual-grounding","name":"Person-centric Visual Grounding"},{"url":"/task/phrase-extraction-and-grounding-peg","name":"Phrase Extraction and Grounding (PEG)"}],"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":6,"rows_per_page":100,"shown":100,"of":571,"of_with_code":299,"tagged_in_all":571,"counts":{"archive_papers_tagged":571,"with_a_code_link":299,"where_syntology_ran_a_sample":111,"not_listed_spam_title":0,"listed":571,"listed_where_code_ran":111,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":94,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":94,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","repositories_listed":11,"syntology":{"n":34,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":24,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}},"official":null}},{"url":"/paper/multimodal-compact-bilinear-pooling-for","slug":"multimodal-compact-bilinear-pooling-for","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","date":"2016-06-06","arxiv_id":"1606.01847","repositories_listed":10,"syntology":null},{"url":"/paper/viewrefer-grasp-the-multi-view-knowledge-for","slug":"viewrefer-grasp-the-multi-view-knowledge-for","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","date":"2023-03-29","arxiv_id":"2303.16894","repositories_listed":7,"syntology":{"n":12,"n_ran":8,"n_constructed":2,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":12,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/viewrefer-grasp-the-multi-view-knowledge-for#ran","syntology_url":"https://syntology.ai/paper/2303.16894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16894"}},"official":{"repos":["ivan-tang-3d/viewrefer3d","ziyuguo99/viewrefer3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}},"official":{"repos":["ashkamath/mdetr"],"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-visual-grounding-a-survey","slug":"towards-visual-grounding-a-survey","title":"Towards Visual Grounding: A Survey","date":"2024-12-28","arxiv_id":"2412.20206","repositories_listed":4,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-visual-grounding-a-survey#ran","syntology_url":"https://syntology.ai/paper/2412.20206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20206"}},"official":null}},{"url":"/paper/set-of-mark-prompting-unleashes-extraordinary","slug":"set-of-mark-prompting-unleashes-extraordinary","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","date":"2023-10-17","arxiv_id":"2310.11441","repositories_listed":4,"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/set-of-mark-prompting-unleashes-extraordinary#ran","syntology_url":"https://syntology.ai/paper/2310.11441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11441"}},"official":{"repos":["microsoft/SoM"],"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/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}},"official":{"repos":["alibaba/AliceMind"],"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/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","repositories_listed":4,"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"official":{"repos":["ofa-sys/ofa"],"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/orionbench-a-benchmark-for-chart-and-human","slug":"orionbench-a-benchmark-for-chart-and-human","title":"OrionBench: A Benchmark for Chart and Human-Recognizable Object Detection in Infographics","date":"2025-05-23","arxiv_id":"2505.17473","repositories_listed":3,"syntology":null},{"url":"/paper/vrsbench-a-versatile-vision-language","slug":"vrsbench-a-versatile-vision-language","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","date":"2024-06-18","arxiv_id":"2406.12384","repositories_listed":3,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vrsbench-a-versatile-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.12384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12384"}},"official":{"repos":["lx709/vrsbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/docgenome-an-open-large-scale-scientific","slug":"docgenome-an-open-large-scale-scientific","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11633","repositories_listed":3,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/docgenome-an-open-large-scale-scientific#ran","syntology_url":"https://syntology.ai/paper/2406.11633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11633"}},"official":{"repos":["UniModal4Reasoning/DocGenome"],"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":["listed","official"]}}},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/clip-vg-self-paced-curriculum-adapting-of","slug":"clip-vg-self-paced-curriculum-adapting-of","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","date":"2023-05-15","arxiv_id":"2305.08685","repositories_listed":3,"syntology":null},{"url":"/paper/eda-explicit-text-decoupling-and-dense","slug":"eda-explicit-text-decoupling-and-dense","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","date":"2022-09-29","arxiv_id":"2209.14941","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eda-explicit-text-decoupling-and-dense#ran","syntology_url":"https://syntology.ai/paper/2209.14941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14941"}},"official":{"repos":["yanmin-wu/eda"],"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/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/collaborative-transformers-for-grounded","slug":"collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","arxiv_id":"2203.16518","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/collaborative-transformers-for-grounded#ran","syntology_url":"https://syntology.ai/paper/2203.16518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16518"}},"official":{"repos":["jhcho99/coformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/seqtr-a-simple-yet-universal-network-for","slug":"seqtr-a-simple-yet-universal-network-for","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","date":"2022-03-30","arxiv_id":"2203.16265","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seqtr-a-simple-yet-universal-network-for#ran","syntology_url":"https://syntology.ai/paper/2203.16265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16265"}},"official":{"repos":["sean-zhuh/seqtr"],"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/word-discovery-in-visually-grounded-self","slug":"word-discovery-in-visually-grounded-self","title":"Word Discovery in Visually Grounded, Self-Supervised Speech Models","date":"2022-03-28","arxiv_id":"2203.15081","repositories_listed":3,"syntology":null},{"url":"/paper/jointly-learning-to-see-ask-and-guesswhat","slug":"jointly-learning-to-see-ask-and-guesswhat","title":"Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat","date":"2018-09-10","arxiv_id":"1809.03408","repositories_listed":3,"syntology":null},{"url":"/paper/revisiting-visual-question-answering","slug":"revisiting-visual-question-answering","title":"Revisiting Visual Question Answering Baselines","date":"2016-06-27","arxiv_id":"1606.08390","repositories_listed":3,"syntology":null},{"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/enhancing-visual-grounding-for-gui-agents-via","slug":"enhancing-visual-grounding-for-gui-agents-via","title":"Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning","date":"2025-05-18","arxiv_id":"2505.12370","repositories_listed":2,"syntology":null},{"url":"/paper/fixing-imbalanced-attention-to-mitigate-in","slug":"fixing-imbalanced-attention-to-mitigate-in","title":"PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model","date":"2025-01-21","arxiv_id":"2501.12206","repositories_listed":2,"syntology":null},{"url":"/paper/interpreting-object-level-foundation-models","slug":"interpreting-object-level-foundation-models","title":"Interpreting Object-level Foundation Models via Visual Precision Search","date":"2024-11-25","arxiv_id":"2411.16198","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-grounded-multimodal-named-entity","slug":"advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","slug":"f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lexicon-level-contrastive-visual-grounding","slug":"lexicon-level-contrastive-visual-grounding","title":"Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling","date":"2024-03-21","arxiv_id":"2403.14551","repositories_listed":2,"syntology":null},{"url":"/paper/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/seeing-is-believing-mitigating-hallucination#ran","syntology_url":"https://syntology.ai/paper/2402.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15300"}},"official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/llms-as-bridges-reformulating-grounded","slug":"llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/one-model-to-rule-them-all-towards-universal","slug":"one-model-to-rule-them-all-towards-universal","title":"One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts","date":"2023-12-28","arxiv_id":"2312.17183","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-model-to-rule-them-all-towards-universal#ran","syntology_url":"https://syntology.ai/paper/2312.17183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17183"}},"official":{"repos":["zhaoziheng/sat-ds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-and-prompting-everything-all-at-once","slug":"aligning-and-prompting-everything-all-at-once","title":"Aligning and Prompting Everything All at Once for Universal Visual Perception","date":"2023-12-04","arxiv_id":"2312.02153","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/aligning-and-prompting-everything-all-at-once#ran","syntology_url":"https://syntology.ai/paper/2312.02153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02153"}},"official":{"repos":["shenyunhang/ape"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/infmllm-a-unified-framework-for-visual","slug":"infmllm-a-unified-framework-for-visual","title":"InfMLLM: A Unified Framework for Visual-Language Tasks","date":"2023-11-12","arxiv_id":"2311.06791","repositories_listed":2,"syntology":null},{"url":"/paper/visual-grounding-helps-learn-word-meanings-in","slug":"visual-grounding-helps-learn-word-meanings-in","title":"Visual Grounding Helps Learn Word Meanings in Low-Data Regimes","date":"2023-10-20","arxiv_id":"2310.13257","repositories_listed":2,"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/visual-grounding-helps-learn-word-meanings-in#ran","syntology_url":"https://syntology.ai/paper/2310.13257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13257"}},"official":{"repos":["EvLab-MIT/LexiContrastiveGrd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/target-grounded-graph-aware-transformer-for","slug":"target-grounded-graph-aware-transformer-for","title":"Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation","date":"2023-08-22","arxiv_id":"2308.11561","repositories_listed":2,"syntology":null},{"url":"/paper/kosmos-2-grounding-multimodal-large-language","slug":"kosmos-2-grounding-multimodal-large-language","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","date":"2023-06-26","arxiv_id":"2306.14824","repositories_listed":2,"syntology":null},{"url":"/paper/syllable-discovery-and-cross-lingual","slug":"syllable-discovery-and-cross-lingual","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","date":"2023-05-19","arxiv_id":"2305.11435","repositories_listed":2,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/syllable-discovery-and-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2305.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11435"}},"official":{"repos":["jasonppy/syllable-discovery"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cpt-colorful-prompt-tuning-for-pre-trained","slug":"cpt-colorful-prompt-tuning-for-pre-trained","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","date":"2021-09-24","arxiv_id":"2109.11797","repositories_listed":2,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cpt-colorful-prompt-tuning-for-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2109.11797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11797"}},"official":{"repos":["thunlp/cpt"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/transvg-end-to-end-visual-grounding-with","slug":"transvg-end-to-end-visual-grounding-with","title":"TransVG: End-to-End Visual Grounding with Transformers","date":"2021-04-17","arxiv_id":"2104.08541","repositories_listed":2,"syntology":{"n":20,"n_ran":18,"n_constructed":0,"n_ran_checked":10,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":8,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transvg-end-to-end-visual-grounding-with#ran","syntology_url":"https://syntology.ai/paper/2104.08541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08541"}},"official":{"repos":["djiajunustc/TransVG"],"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/refer-it-in-rgbd-a-bottom-up-approach-for-3d","slug":"refer-it-in-rgbd-a-bottom-up-approach-for-3d","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","date":"2021-03-14","arxiv_id":"2103.07894","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":10,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"11 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/refer-it-in-rgbd-a-bottom-up-approach-for-3d#ran","syntology_url":"https://syntology.ai/paper/2103.07894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07894"}},"official":null}},{"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/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","repositories_listed":2,"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":2,"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/x-lxmert-paint-caption-and-answer-questions#ran","syntology_url":"https://syntology.ai/paper/2009.11278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11278"}},"official":{"repos":["allenai/x-lxmert"],"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/learning-cross-modal-context-graph-for-visual-1","slug":"learning-cross-modal-context-graph-for-visual-1","title":"Learning Cross-modal Context Graph for Visual Grounding","date":"2019-11-20","arxiv_id":"1911.09042","repositories_listed":2,"syntology":null},{"url":"/paper/a-fast-and-accurate-one-stage-approach-to","slug":"a-fast-and-accurate-one-stage-approach-to","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","date":"2019-08-18","arxiv_id":"1908.06354","repositories_listed":2,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":3,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-fast-and-accurate-one-stage-approach-to#ran","syntology_url":"https://syntology.ai/paper/1908.06354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06354"}},"official":{"repos":["zyang-ur/onestage_grounding"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-attention-networks-for-visual-reference","slug":"dual-attention-networks-for-visual-reference","title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","date":"2019-02-25","arxiv_id":"1902.09368","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dual-attention-networks-for-visual-reference#ran","syntology_url":"https://syntology.ai/paper/1902.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09368"}},"official":{"repos":["gicheonkang/DAN-VisDial"],"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/gta1-gui-test-time-scaling-agent","slug":"gta1-gui-test-time-scaling-agent","title":"GTA1: GUI Test-time Scaling Agent","date":"2025-07-08","arxiv_id":"2507.05791","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"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; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gta1-gui-test-time-scaling-agent#ran","syntology_url":"https://syntology.ai/paper/2507.05791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.05791"}},"official":{"repos":["yan98/gta1"],"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/high-resolution-visual-reasoning-via-multi","slug":"high-resolution-visual-reasoning-via-multi","title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","date":"2025-07-08","arxiv_id":"2507.05920","repositories_listed":1,"syntology":null},{"url":"/paper/denseworld-1m-towards-detailed-dense-grounded","slug":"denseworld-1m-towards-detailed-dense-grounded","title":"DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World","date":"2025-06-30","arxiv_id":"2506.24102","repositories_listed":1,"syntology":null},{"url":"/paper/drishtikon-multi-granular-visual-grounding","slug":"drishtikon-multi-granular-visual-grounding","title":"DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images","date":"2025-06-26","arxiv_id":"2506.21316","repositories_listed":1,"syntology":null},{"url":"/paper/revisit-what-you-see-disclose-language-prior","slug":"revisit-what-you-see-disclose-language-prior","title":"Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs","date":"2025-06-11","arxiv_id":"2506.09522","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-compositional-ability-gap-in","slug":"unveiling-the-compositional-ability-gap-in","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","date":"2025-05-26","arxiv_id":"2505.19406","repositories_listed":1,"syntology":null},{"url":"/paper/cxreasonbench-a-benchmark-for-evaluating","slug":"cxreasonbench-a-benchmark-for-evaluating","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","date":"2025-05-23","arxiv_id":"2505.18087","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cxreasonbench-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2505.18087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18087"}},"official":{"repos":["ttumyche/cxreasonbench"],"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/gui-g1-understanding-r1-zero-like-training","slug":"gui-g1-understanding-r1-zero-like-training","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","date":"2025-05-21","arxiv_id":"2505.15810","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gui-g1-understanding-r1-zero-like-training#ran","syntology_url":"https://syntology.ai/paper/2505.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15810"}},"official":{"repos":["yuqi-zhou/gui-g1"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/instructsam-a-training-free-framework-for","slug":"instructsam-a-training-free-framework-for","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","date":"2025-05-21","arxiv_id":"2505.15818","repositories_listed":1,"syntology":null},{"url":"/paper/unimoco-unified-modality-completion-for","slug":"unimoco-unified-modality-completion-for","title":"UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings","date":"2025-05-17","arxiv_id":"2505.11815","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11454","slug":"2505-11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","date":"2025-05-16","arxiv_id":"2505.11454","repositories_listed":1,"syntology":null},{"url":"/paper/extending-large-vision-language-model-for","slug":"extending-large-vision-language-model-for","title":"Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving","date":"2025-05-13","arxiv_id":"2505.08725","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-vision-language-models-for-visual","slug":"leveraging-vision-language-models-for-visual","title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","date":"2025-05-09","arxiv_id":"2505.05895","repositories_listed":1,"syntology":null},{"url":"/paper/as3d-2d-assisted-cross-modal-understanding","slug":"as3d-2d-assisted-cross-modal-understanding","title":"AS3D: 2D-Assisted Cross-Modal Understanding with Semantic-Spatial Scene Graphs for 3D Visual Grounding","date":"2025-05-07","arxiv_id":"2505.04058","repositories_listed":1,"syntology":null},{"url":"/paper/ges3vig-incorporating-pointing-gestures-into","slug":"ges3vig-incorporating-pointing-gestures-into","title":"Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","date":"2025-04-13","arxiv_id":"2504.09623","repositories_listed":1,"syntology":null},{"url":"/paper/vlm-r1-a-stable-and-generalizable-r1-style","slug":"vlm-r1-a-stable-and-generalizable-r1-style","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","date":"2025-04-10","arxiv_id":"2504.07615","repositories_listed":1,"syntology":null},{"url":"/paper/sting-bee-towards-vision-language-model-for","slug":"sting-bee-towards-vision-language-model-for","title":"STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection","date":"2025-04-03","arxiv_id":"2504.02823","repositories_listed":1,"syntology":null},{"url":"/paper/mb-ores-a-multi-branch-object-reasoner-for","slug":"mb-ores-a-multi-branch-object-reasoner-for","title":"MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing","date":"2025-03-31","arxiv_id":"2503.24219","repositories_listed":1,"syntology":null},{"url":"/paper/refchartqa-grounding-visual-answer-on-chart","slug":"refchartqa-grounding-visual-answer-on-chart","title":"RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning","date":"2025-03-29","arxiv_id":"2503.23131","repositories_listed":1,"syntology":null},{"url":"/paper/visual-position-prompt-for-mllm-based-visual","slug":"visual-position-prompt-for-mllm-based-visual","title":"Visual Position Prompt for MLLM based Visual Grounding","date":"2025-03-19","arxiv_id":"2503.15426","repositories_listed":1,"syntology":null},{"url":"/paper/led-llm-enhanced-open-vocabulary-object","slug":"led-llm-enhanced-open-vocabulary-object","title":"LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation","date":"2025-03-18","arxiv_id":"2503.13794","repositories_listed":1,"syntology":null},{"url":"/paper/deepperception-advancing-r1-like-cognitive","slug":"deepperception-advancing-r1-like-cognitive","title":"DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding","date":"2025-03-17","arxiv_id":"2503.12797","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepperception-advancing-r1-like-cognitive#ran","syntology_url":"https://syntology.ai/paper/2503.12797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12797"}},"official":{"repos":["thunlp/deepperception"],"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/himtok-learning-hierarchical-mask-tokens-for","slug":"himtok-learning-hierarchical-mask-tokens-for","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","date":"2025-03-17","arxiv_id":"2503.13026","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/himtok-learning-hierarchical-mask-tokens-for#ran","syntology_url":"https://syntology.ai/paper/2503.13026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13026"}},"official":{"repos":["yayafengzi/LMM-HiMTok"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/how-do-multimodal-large-language-models","slug":"how-do-multimodal-large-language-models","title":"How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game","date":"2025-03-13","arxiv_id":"2503.10042","repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding-1","slug":"segagent-exploring-pixel-understanding-1","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":"2503.08625","repositories_listed":1,"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":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) · 1 unverified","sample_list":"/paper/segagent-exploring-pixel-understanding-1#ran","syntology_url":"https://syntology.ai/paper/2503.08625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08625"}},"official":{"repos":["aim-uofa/SegAgent"],"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":["official"]}}},{"url":"/paper/swimvg-step-wise-multimodal-fusion-and","slug":"swimvg-step-wise-multimodal-fusion-and","title":"SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding","date":"2025-02-24","arxiv_id":"2502.16786","repositories_listed":1,"syntology":null},{"url":"/paper/text-guided-sparse-voxel-pruning-for","slug":"text-guided-sparse-voxel-pruning-for","title":"Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding","date":"2025-02-14","arxiv_id":"2502.10392","repositories_listed":1,"syntology":null},{"url":"/paper/evolving-symbolic-3d-visual-grounder-with","slug":"evolving-symbolic-3d-visual-grounder-with","title":"Evolving Symbolic 3D Visual Grounder with Weakly Supervised Reflection","date":"2025-02-03","arxiv_id":"2502.01401","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/evolving-symbolic-3d-visual-grounder-with#ran","syntology_url":"https://syntology.ai/paper/2502.01401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01401"}},"official":{"repos":["openrobotlab/ease"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/naver-a-neuro-symbolic-compositional","slug":"naver-a-neuro-symbolic-compositional","title":"NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning","date":"2025-02-01","arxiv_id":"2502.00372","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/naver-a-neuro-symbolic-compositional#ran","syntology_url":"https://syntology.ai/paper/2502.00372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00372"}},"official":{"repos":["controlnet/naver"],"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/when-language-and-vision-meet-road-safety","slug":"when-language-and-vision-meet-road-safety","title":"When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis","date":"2025-01-17","arxiv_id":"2501.10604","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-aerial-detection-baseline-of","slug":"a-simple-aerial-detection-baseline-of","title":"A Simple Aerial Detection Baseline of Multimodal Language Models","date":"2025-01-16","arxiv_id":"2501.09720","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-visual-grounding-with-coarse-to","slug":"multi-task-visual-grounding-with-coarse-to","title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","date":"2025-01-12","arxiv_id":"2501.06710","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-task-visual-grounding-with-coarse-to#ran","syntology_url":"https://syntology.ai/paper/2501.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06710"}},"official":{"repos":["dmmm1997/c3vg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/open-eyes-then-reason-fine-grained-visual","slug":"open-eyes-then-reason-fine-grained-visual","title":"Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs","date":"2025-01-11","arxiv_id":"2501.06430","repositories_listed":1,"syntology":null},{"url":"/paper/ursa-understanding-and-verifying-chain-of","slug":"ursa-understanding-and-verifying-chain-of","title":"URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics","date":"2025-01-08","arxiv_id":"2501.04686","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ursa-understanding-and-verifying-chain-of#ran","syntology_url":"https://syntology.ai/paper/2501.04686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04686"}},"official":{"repos":["URSA-MATH/URSA-MATH"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-vlms-ready-for-autonomous-driving-an","slug":"are-vlms-ready-for-autonomous-driving-an","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","date":"2025-01-07","arxiv_id":"2501.04003","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/are-vlms-ready-for-autonomous-driving-an#ran","syntology_url":"https://syntology.ai/paper/2501.04003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04003"}},"official":{"repos":["opendrivelab/drivelm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ges3vig-incorporating-pointing-gestures-into-1","slug":"ges3vig-incorporating-pointing-gestures-into-1","title":"Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-object-hallucinations-in-large-2","slug":"mitigating-object-hallucinations-in-large-2","title":"Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-to-attend-try-to-understand-how-seg","slug":"reasoning-to-attend-try-to-understand-how-seg","title":"Reasoning to Attend: Try to Understand How <SEG> Token Works","date":"2024-12-23","arxiv_id":"2412.17741","repositories_listed":1,"syntology":null},{"url":"/paper/cof-coarse-to-fine-grained-image","slug":"cof-coarse-to-fine-grained-image","title":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models","date":"2024-12-22","arxiv_id":"2412.16869","repositories_listed":1,"syntology":null},{"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/deepseek-vl2-mixture-of-experts-vision","slug":"deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepseek-vl2-mixture-of-experts-vision#ran","syntology_url":"https://syntology.ai/paper/2412.10302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10302"}},"official":{"repos":["deepseek-ai/deepseek-vl2"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/progressive-multi-granular-alignments-for","slug":"progressive-multi-granular-alignments-for","title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","date":"2024-12-11","arxiv_id":"2412.08125","repositories_listed":1,"syntology":null},{"url":"/paper/taco-learning-multi-modal-action-models-with","slug":"taco-learning-multi-modal-action-models-with","title":"TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action","date":"2024-12-07","arxiv_id":"2412.05479","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-d-a-multimodal-multilingual-and-multitask","slug":"m-3-d-a-multimodal-multilingual-and-multitask","title":"M$^{3}$D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction","date":"2024-12-05","arxiv_id":"2412.04026","repositories_listed":1,"syntology":null},{"url":"/paper/bip3d-bridging-2d-images-and-3d-perception","slug":"bip3d-bridging-2d-images-and-3d-perception","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","date":"2024-11-22","arxiv_id":"2411.14869","repositories_listed":1,"syntology":null},{"url":"/paper/solving-zero-shot-3d-visual-grounding-as","slug":"solving-zero-shot-3d-visual-grounding-as","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","date":"2024-11-21","arxiv_id":"2411.14594","repositories_listed":1,"syntology":null},{"url":"/paper/visual-contexts-clarify-ambiguous-expressions","slug":"visual-contexts-clarify-ambiguous-expressions","title":"Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset","date":"2024-11-21","arxiv_id":"2411.14137","repositories_listed":1,"syntology":null},{"url":"/paper/geoground-a-unified-large-vision-language","slug":"geoground-a-unified-large-vision-language","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","date":"2024-11-16","arxiv_id":"2411.11904","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-decoupling-cross-modal-hierarchical","slug":"phrase-decoupling-cross-modal-hierarchical","title":"Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding","date":"2024-10-31","arxiv_id":"2410.23570","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-multimodal-explanation-for-visual","slug":"few-shot-multimodal-explanation-for-visual","title":"Few-Shot Multimodal Explanation for Visual Question Answering","date":"2024-10-28","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":42,"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":3,"papers_placed":1,"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/visual-grounding-on-refcoco-testa","since_archive":"/sota/visual-grounding-on-refcoco-testa#since-judged","papers_judged":3,"placed":1},{"leaderboard":"/sota/visual-grounding-on-refcoco-test-b","since_archive":"/sota/visual-grounding-on-refcoco-test-b#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/visual-grounding-on-refcoco-val","since_archive":"/sota/visual-grounding-on-refcoco-val#since-judged","papers_judged":3,"placed":1}]},"papers_where_code_ran":111,"papers_where_code_ran_first_page":"/task/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":"archive","page":2,"of":6,"url":"/task/visual-grounding/papers/2","json":"/task/visual-grounding/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/visual-grounding/papers/3","json":"/task/visual-grounding/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/visual-grounding/papers/4","json":"/task/visual-grounding/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/visual-grounding/papers/5","json":"/task/visual-grounding/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/visual-grounding/papers/6","json":"/task/visual-grounding/papers/6.json","rows":71},{"order":"ran","page":1,"of":2,"url":"/task/visual-grounding/papers/ran/1","json":"/task/visual-grounding/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/visual-grounding/papers/ran/2","json":"/task/visual-grounding/papers/ran/2.json","rows":11}],"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":"1c3eb97984600a7a3f5efe29fb952fd885d4b6a679a43c9efb189f7cc74ef28d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}