{"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/referring-expression-comprehension","name":"Referring Expression Comprehension","slug":"referring-expression-comprehension","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":167,"papers_with_code":98,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/refcoco","name":"RefCOCO","full_name":"","num_papers_in_archive":439},{"url":"/dataset/google-refexp","name":"Google Refexp","full_name":"","num_papers_in_archive":46},{"url":"/dataset/talk2car","name":"Talk2Car","full_name":"","num_papers_in_archive":45},{"url":"/dataset/clevr-ref","name":"CLEVR-Ref+","full_name":"","num_papers_in_archive":17},{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/description-detection-dataset","name":"Description Detection Dataset","full_name":"Description Detection Dataset","num_papers_in_archive":10},{"url":"/dataset/coloninst-v1","name":"ColonINST-v1","full_name":"","num_papers_in_archive":8},{"url":"/dataset/coloninst-v1-seen","name":"ColonINST-v1 (Seen)","full_name":"","num_papers_in_archive":8},{"url":"/dataset/coloninst-v1-uneen","name":"ColonINST-v1 (Unseen)","full_name":"","num_papers_in_archive":8},{"url":"/dataset/a-game-of-sorts","name":"A Game Of Sorts","full_name":"","num_papers_in_archive":4},{"url":"/dataset/vqdv1","name":"VQDv1","full_name":"Visual Query Detection v1","num_papers_in_archive":2},{"url":"/dataset/finecops-ref","name":"FineCops-Ref","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":2,"rows_per_page":100,"shown":100,"of":167,"of_with_code":98,"tagged_in_all":167,"counts":{"archive_papers_tagged":167,"with_a_code_link":98,"where_syntology_ran_a_sample":50,"not_listed_spam_title":0,"listed":167,"listed_where_code_ran":50,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":46,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":46,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"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/grounding-dino-marrying-dino-with-grounded","slug":"grounding-dino-marrying-dino-with-grounded","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","date":"2023-03-09","arxiv_id":"2303.05499","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/grounding-dino-marrying-dino-with-grounded#ran","syntology_url":"https://syntology.ai/paper/2303.05499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05499"}},"official":{"repos":["idea-research/groundingdino"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/compositional-attention-networks-for-machine","slug":"compositional-attention-networks-for-machine","title":"Compositional Attention Networks for Machine Reasoning","date":"2018-03-08","arxiv_id":"1803.03067","repositories_listed":10,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/compositional-attention-networks-for-machine#ran","syntology_url":"https://syntology.ai/paper/1803.03067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03067"}},"official":{"repos":["stanfordnlp/mac-network"],"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/improved-baselines-with-visual-instruction","slug":"improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","arxiv_id":"2310.03744","repositories_listed":9,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improved-baselines-with-visual-instruction#ran","syntology_url":"https://syntology.ai/paper/2310.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03744"}},"official":null}},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"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/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/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/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/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}},"official":{"repos":["jackroos/VL-BERT"],"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/clevr-ref-diagnosing-visual-reasoning-with","slug":"clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}},{"url":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mini-gemini-mining-the-potential-of-multi#ran","syntology_url":"https://syntology.ai/paper/2403.18814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18814"}},"official":{"repos":["dvlab-research/minigemini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"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/an-open-and-comprehensive-pipeline-for","slug":"an-open-and-comprehensive-pipeline-for","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","date":"2024-01-04","arxiv_id":"2401.02361","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-open-and-comprehensive-pipeline-for#ran","syntology_url":"https://syntology.ai/paper/2401.02361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02361"}},"official":{"repos":["open-mmlab/mmdetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"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/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/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reclip-a-strong-zero-shot-baseline-for-1","slug":"reclip-a-strong-zero-shot-baseline-for-1","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","date":"2022-04-12","arxiv_id":"2204.05991","repositories_listed":2,"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/reclip-a-strong-zero-shot-baseline-for-1#ran","syntology_url":"https://syntology.ai/paper/2204.05991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05991"}},"official":{"repos":["allenai/reclip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/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/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-collaborative-network-for-joint","slug":"multi-task-collaborative-network-for-joint","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","date":"2020-03-19","arxiv_id":"2003.08813","repositories_listed":2,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/multi-task-collaborative-network-for-joint#ran","syntology_url":"https://syntology.ai/paper/2003.08813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08813"}},"official":{"repos":["luogen1996/MCN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"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/a-joint-speaker-listener-reinforcer-model-for","slug":"a-joint-speaker-listener-reinforcer-model-for","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","date":"2016-12-30","arxiv_id":"1612.09542","repositories_listed":2,"syntology":null},{"url":"/paper/textregion-text-aligned-region-tokens-from","slug":"textregion-text-aligned-region-tokens-from","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","date":"2025-05-29","arxiv_id":"2505.23769","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/new-dataset-and-methods-for-fine-grained","slug":"new-dataset-and-methods-for-fine-grained","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","date":"2025-02-27","arxiv_id":"2502.20104","repositories_listed":1,"syntology":null},{"url":"/paper/refdrone-a-challenging-benchmark-for","slug":"refdrone-a-challenging-benchmark-for","title":"RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes","date":"2025-02-01","arxiv_id":"2502.00392","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/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/frontiers-in-intelligent-colonoscopy","slug":"frontiers-in-intelligent-colonoscopy","title":"Frontiers in Intelligent Colonoscopy","date":"2024-10-22","arxiv_id":"2410.17241","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/frontiers-in-intelligent-colonoscopy#ran","syntology_url":"https://syntology.ai/paper/2410.17241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17241"}},"official":{"repos":["ai4colonoscopy/intelliscope"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/griffon-g-bridging-vision-language-and-vision","slug":"griffon-g-bridging-vision-language-and-vision","title":"Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models","date":"2024-10-21","arxiv_id":"2410.16163","repositories_listed":1,"syntology":null},{"url":"/paper/simvg-a-simple-framework-for-visual-grounding","slug":"simvg-a-simple-framework-for-visual-grounding","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","date":"2024-09-26","arxiv_id":"2409.17531","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/simvg-a-simple-framework-for-visual-grounding#ran","syntology_url":"https://syntology.ai/paper/2409.17531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17531"}},"official":{"repos":["dmmm1997/simvg"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uni-med-a-unified-medical-generalist","slug":"uni-med-a-unified-medical-generalist","title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","date":"2024-09-26","arxiv_id":"2409.17508","repositories_listed":1,"syntology":null},{"url":"/paper/finecops-ref-a-new-dataset-and-task-for-fine","slug":"finecops-ref-a-new-dataset-and-task-for-fine","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","date":"2024-09-23","arxiv_id":"2409.14750","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finecops-ref-a-new-dataset-and-task-for-fine#ran","syntology_url":"https://syntology.ai/paper/2409.14750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14750"}},"official":{"repos":["liujunzhuo/FineCops-Ref"],"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","unlocated"]}}},{"url":"/paper/mapper-multimodal-prior-guided-parameter","slug":"mapper-multimodal-prior-guided-parameter","title":"MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension","date":"2024-09-20","arxiv_id":"2409.13609","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mapper-multimodal-prior-guided-parameter#ran","syntology_url":"https://syntology.ai/paper/2409.13609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13609"}},"official":{"repos":["liuting20/mapper"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-wrapper-black-box-semantic-aware","slug":"llm-wrapper-black-box-semantic-aware","title":"LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension","date":"2024-09-18","arxiv_id":"2409.11919","repositories_listed":1,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"9 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; 8 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/llm-wrapper-black-box-semantic-aware#ran","syntology_url":"https://syntology.ai/paper/2409.11919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11919"}},"official":{"repos":["valeoai/LLM_wrapper"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/lightmdetr-a-lightweight-approach-for-low","slug":"lightmdetr-a-lightweight-approach-for-low","title":"A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training","date":"2024-08-20","arxiv_id":"2408.10787","repositories_listed":1,"syntology":null},{"url":"/paper/multi-branch-collaborative-learning-network","slug":"multi-branch-collaborative-learning-network","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","date":"2024-07-07","arxiv_id":"2407.05363","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-referring-expression-comprehension","slug":"revisiting-referring-expression-comprehension","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models","date":"2024-06-24","arxiv_id":"2406.16866","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/revisiting-referring-expression-comprehension#ran","syntology_url":"https://syntology.ai/paper/2406.16866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16866"}},"official":{"repos":["jierunchen/ref-l4"],"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/talk2radar-bridging-natural-language-with-4d","slug":"talk2radar-bridging-natural-language-with-4d","title":"Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension","date":"2024-05-21","arxiv_id":"2405.12821","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-for-visual-grounding","slug":"adversarial-robustness-for-visual-grounding","title":"Adversarial Robustness for Visual Grounding of Multimodal Large Language Models","date":"2024-05-16","arxiv_id":"2405.09981","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-robustness-for-visual-grounding#ran","syntology_url":"https://syntology.ai/paper/2405.09981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09981"}},"official":{"repos":["KuofengGao/MLLM-Grounding-Robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/elysium-exploring-object-level-perception-in","slug":"elysium-exploring-object-level-perception-in","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","date":"2024-03-25","arxiv_id":"2403.16558","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/elysium-exploring-object-level-perception-in#ran","syntology_url":"https://syntology.ai/paper/2403.16558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16558"}},"official":{"repos":["hon-wong/elysium"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dettoolchain-a-new-prompting-paradigm-to","slug":"dettoolchain-a-new-prompting-paradigm-to","title":"DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM","date":"2024-03-19","arxiv_id":"2403.12488","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-multimodal-learning-from-data","slug":"efficient-multimodal-learning-from-data","title":"Efficient Multimodal Learning from Data-centric Perspective","date":"2024-02-18","arxiv_id":"2402.11530","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-multimodal-learning-from-data#ran","syntology_url":"https://syntology.ai/paper/2402.11530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11530"}},"official":{"repos":["baai-dcai/bunny"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-counterfactual-problems-in","slug":"revisiting-counterfactual-problems-in","title":"Revisiting Counterfactual Problems in Referring Expression Comprehension","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tune-an-ellipse-clip-has-potential-to-find","slug":"tune-an-ellipse-clip-has-potential-to-find","title":"Tune-An-Ellipse: CLIP Has Potential to Find What You Want","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mobilevlm-a-fast-reproducible-and-strong","slug":"mobilevlm-a-fast-reproducible-and-strong","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","date":"2023-12-28","arxiv_id":"2312.16886","repositories_listed":1,"syntology":null},{"url":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}},"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-referring-expression-comprehension","slug":"zero-shot-referring-expression-comprehension","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","date":"2023-11-28","arxiv_id":"2311.17048","repositories_listed":1,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":3,"n_no_contract":6,"n_pointer_only":10,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 3 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/zero-shot-referring-expression-comprehension#ran","syntology_url":"https://syntology.ai/paper/2311.17048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17048"}},"official":{"repos":["show-han/zeroshot_rec"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/continual-referring-expression-comprehension","slug":"continual-referring-expression-comprehension","title":"Continual Referring Expression Comprehension via Dual Modular Memorization","date":"2023-11-25","arxiv_id":"2311.14909","repositories_listed":1,"syntology":null},{"url":"/paper/griffon-spelling-out-all-object-locations-at","slug":"griffon-spelling-out-all-object-locations-at","title":"Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models","date":"2023-11-24","arxiv_id":"2311.14552","repositories_listed":1,"syntology":null},{"url":"/paper/genome-generative-neuro-symbolic-visual","slug":"genome-generative-neuro-symbolic-visual","title":"GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs","date":"2023-11-08","arxiv_id":"2311.04901","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/genome-generative-neuro-symbolic-visual#ran","syntology_url":"https://syntology.ai/paper/2311.04901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04901"}},"official":null}},{"url":"/paper/instructdet-diversifying-referring-object","slug":"instructdet-diversifying-referring-object","title":"InstructDET: Diversifying Referring Object Detection with Generalized Instructions","date":"2023-10-08","arxiv_id":"2310.05136","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instructdet-diversifying-referring-object#ran","syntology_url":"https://syntology.ai/paper/2310.05136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05136"}},"official":{"repos":["jyfenggogo/instructdet"],"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/collecting-visually-grounded-dialogue-with-a-1","slug":"collecting-visually-grounded-dialogue-with-a-1","title":"Collecting Visually-Grounded Dialogue with A Game Of Sorts","date":"2023-09-10","arxiv_id":"2309.05162","repositories_listed":1,"syntology":null},{"url":"/paper/grec-generalized-referring-expression","slug":"grec-generalized-referring-expression","title":"GREC: Generalized Referring Expression Comprehension","date":"2023-08-30","arxiv_id":"2308.16182","repositories_listed":1,"syntology":null},{"url":"/paper/hubo-vlm-unified-vision-language-model","slug":"hubo-vlm-unified-vision-language-model","title":"HuBo-VLM: Unified Vision-Language Model designed for HUman roBOt interaction tasks","date":"2023-08-24","arxiv_id":"2308.12537","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-for-3d-point-cloud-visual","slug":"a-unified-framework-for-3d-point-cloud-visual","title":"A Unified Framework for 3D Point Cloud Visual Grounding","date":"2023-08-23","arxiv_id":"2308.11887","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-unified-framework-for-3d-point-cloud-visual#ran","syntology_url":"https://syntology.ai/paper/2308.11887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11887"}},"official":{"repos":["leon1207/3dreftr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/refego-referring-expression-comprehension","slug":"refego-referring-expression-comprehension","title":"RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D","date":"2023-08-23","arxiv_id":"2308.12035","repositories_listed":1,"syntology":null},{"url":"/paper/whether-you-can-locate-or-not-interactive","slug":"whether-you-can-locate-or-not-interactive","title":"Whether you can locate or not? Interactive Referring Expression Generation","date":"2023-08-19","arxiv_id":"2308.09977","repositories_listed":1,"syntology":null},{"url":"/paper/described-object-detection-liberating-object-1","slug":"described-object-detection-liberating-object-1","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","date":"2023-07-24","arxiv_id":"2307.12813","repositories_listed":1,"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/described-object-detection-liberating-object-1#ran","syntology_url":"https://syntology.ai/paper/2307.12813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12813"}},"official":{"repos":["shikras/d-cube"],"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/language-adaptive-weight-generation-for-multi-1","slug":"language-adaptive-weight-generation-for-multi-1","title":"Language Adaptive Weight Generation for Multi-task Visual Grounding","date":"2023-06-06","arxiv_id":"2306.04652","repositories_listed":1,"syntology":null},{"url":"/paper/referring-expression-comprehension-using","slug":"referring-expression-comprehension-using","title":"Referring Expression Comprehension Using Language Adaptive Inference","date":"2023-06-06","arxiv_id":"2306.04451","repositories_listed":1,"syntology":null},{"url":"/paper/llava-med-training-a-large-language-and","slug":"llava-med-training-a-large-language-and","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","date":"2023-06-01","arxiv_id":"2306.00890","repositories_listed":1,"syntology":null},{"url":"/paper/ns3d-neuro-symbolic-grounding-of-3d-objects","slug":"ns3d-neuro-symbolic-grounding-of-3d-objects","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","date":"2023-03-23","arxiv_id":"2303.13483","repositories_listed":1,"syntology":null},{"url":"/paper/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}},"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ck-transformer-commonsense-knowledge-enhanced","slug":"ck-transformer-commonsense-knowledge-enhanced","title":"CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension","date":"2023-02-17","arxiv_id":"2302.09027","repositories_listed":1,"syntology":null},{"url":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}},"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dq-detr-dual-query-detection-transformer-for","slug":"dq-detr-dual-query-detection-transformer-for","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","date":"2022-11-28","arxiv_id":"2211.15516","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-oriented-reffering-expression","slug":"scene-text-oriented-reffering-expression","title":"Scene-Text Oriented Reffering Expression Comprehension","date":"2022-11-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/toist-task-oriented-instance-segmentation","slug":"toist-task-oriented-instance-segmentation","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","date":"2022-10-19","arxiv_id":"2210.10775","repositories_listed":1,"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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/toist-task-oriented-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2210.10775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10775"}},"official":{"repos":["air-discover/toist"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/volta-vision-language-transformer-with-weakly","slug":"volta-vision-language-transformer-with-weakly","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","date":"2022-10-09","arxiv_id":"2210.04135","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/volta-vision-language-transformer-with-weakly#ran","syntology_url":"https://syntology.ai/paper/2210.04135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04135"}},"official":{"repos":["ShramanPramanick/VoLTA"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/exploring-modulated-detection-transformer-as","slug":"exploring-modulated-detection-transformer-as","title":"Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos","date":"2022-09-21","arxiv_id":"2209.10126","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-evaluate-performance-of-multi","slug":"learning-to-evaluate-performance-of-multi","title":"Learning to Evaluate Performance of Multi-modal Semantic Localization","date":"2022-09-14","arxiv_id":"2209.06515","repositories_listed":1,"syntology":null},{"url":"/paper/correspondence-matters-for-video-referring","slug":"correspondence-matters-for-video-referring","title":"Correspondence Matters for Video Referring Expression Comprehension","date":"2022-07-21","arxiv_id":"2207.10400","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-grounding-by-encouraging","slug":"improving-visual-grounding-by-encouraging","title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations","date":"2022-06-30","arxiv_id":"2206.15462","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-to-fine-vision-language-pre-training","slug":"coarse-to-fine-vision-language-pre-training","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","date":"2022-06-15","arxiv_id":"2206.07643","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coarse-to-fine-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2206.07643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07643"}},"official":{"repos":["microsoft/fiber"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-goes-beyond-multi-modal-fusion-in-one","slug":"what-goes-beyond-multi-modal-fusion-in-one","title":"A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension","date":"2022-04-17","arxiv_id":"2204.07913","repositories_listed":1,"syntology":null},{"url":"/paper/looking-outside-the-box-to-ground-language-in","slug":"looking-outside-the-box-to-ground-language-in","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","date":"2021-12-16","arxiv_id":"2112.08879","repositories_listed":1,"syntology":null},{"url":"/paper/towards-language-guided-visual-recognition","slug":"towards-language-guided-visual-recognition","title":"Towards Language-guided Visual Recognition via Dynamic Convolutions","date":"2021-10-17","arxiv_id":"2110.08797","repositories_listed":1,"syntology":null},{"url":"/paper/referring-transformer-a-one-step-approach-to","slug":"referring-transformer-a-one-step-approach-to","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","date":"2021-06-06","arxiv_id":"2106.03089","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/referring-transformer-a-one-step-approach-to#ran","syntology_url":"https://syntology.ai/paper/2106.03089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03089"}},"official":{"repos":["ubc-vision/RefTR"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-better-visual-dialog-agents-with","slug":"learning-better-visual-dialog-agents-with","title":"Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation","date":"2021-05-24","arxiv_id":"2105.11541","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-synonymous-referring","slug":"understanding-synonymous-referring","title":"Understanding Synonymous Referring Expressions via Contrastive Features","date":"2021-04-20","arxiv_id":"2104.10156","repositories_listed":1,"syntology":null},{"url":"/paper/mdetr-modulated-detection-for-end-to-end-1","slug":"mdetr-modulated-detection-for-end-to-end-1","title":"MDETR - Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/trar-routing-the-attention-spans-in","slug":"trar-routing-the-attention-spans-in","title":"TRAR: Routing the Attention Spans in Transformer for Visual Question Answering","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-conditioned-feature-pyramids-for","slug":"language-conditioned-feature-pyramids-for","title":"Language-Conditioned Feature Pyramids for Visual Selection Tasks","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cosine-meets-softmax-a-tough-to-beat-baseline","slug":"cosine-meets-softmax-a-tough-to-beat-baseline","title":"Cosine meets Softmax: A tough-to-beat baseline for visual grounding","date":"2020-09-13","arxiv_id":"2009.06066","repositories_listed":1,"syntology":null},{"url":"/paper/attngrounder-talking-to-cars-with-attention","slug":"attngrounder-talking-to-cars-with-attention","title":"AttnGrounder: Talking to Cars with Attention","date":"2020-09-11","arxiv_id":"2009.05684","repositories_listed":1,"syntology":null},{"url":"/paper/give-me-something-to-eat-referring-expression","slug":"give-me-something-to-eat-referring-expression","title":"Give Me Something to Eat: Referring Expression Comprehension with Commonsense Knowledge","date":"2020-06-02","arxiv_id":"2006.01629","repositories_listed":1,"syntology":null},{"url":"/paper/a-real-time-global-inference-network-for-one","slug":"a-real-time-global-inference-network-for-one","title":"A Real-time Global Inference Network for One-stage Referring Expression Comprehension","date":"2019-12-07","arxiv_id":"1912.03478","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-real-time-global-inference-network-for-one#ran","syntology_url":"https://syntology.ai/paper/1912.03478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.03478"}},"official":{"repos":["luogen1996/Real-time-Global-Inference-Network"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/talk2car-taking-control-of-your-self-driving","slug":"talk2car-taking-control-of-your-self-driving","title":"Talk2Car: Taking Control of Your Self-Driving Car","date":"2019-09-24","arxiv_id":"1909.10838","repositories_listed":1,"syntology":null},{"url":"/paper/language-conditioned-graph-networks-for","slug":"language-conditioned-graph-networks-for","title":"Language-Conditioned Graph Networks for Relational Reasoning","date":"2019-05-10","arxiv_id":"1905.04405","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/language-conditioned-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1905.04405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04405"}},"official":null}},{"url":"/paper/explainable-neural-computation-via-stack","slug":"explainable-neural-computation-via-stack","title":"Explainable Neural Computation via Stack Neural Module Networks","date":"2018-07-23","arxiv_id":"1807.08556","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/explainable-neural-computation-via-stack#ran","syntology_url":"https://syntology.ai/paper/1807.08556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.08556"}},"official":null}},{"url":"/paper/mattnet-modular-attention-network-for","slug":"mattnet-modular-attention-network-for","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","date":"2018-01-24","arxiv_id":"1801.08186","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-object-retrieval","slug":"natural-language-object-retrieval","title":"Natural Language Object Retrieval","date":"2015-11-13","arxiv_id":"1511.04164","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/natural-language-object-retrieval#ran","syntology_url":"https://syntology.ai/paper/1511.04164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.04164"}},"official":null}},{"url":null,"slug":"referring-expression-instance-retrieval-and-a","title":"Referring Expression Instance Retrieval and A Strong End-to-End Baseline","date":"2025-06-23","arxiv_id":"2506.18246","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-visual-genome-1","title":"Synthetic Visual Genome","date":"2025-06-09","arxiv_id":"2506.07643","repositories_listed":0,"syntology":null}],"syntology_records":51,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":50,"papers_where_code_ran_first_page":"/task/referring-expression-comprehension/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":2,"url":"/task/referring-expression-comprehension/papers/2","json":"/task/referring-expression-comprehension/papers/2.json","rows":67},{"order":"ran","page":1,"of":1,"url":"/task/referring-expression-comprehension/papers/ran/1","json":"/task/referring-expression-comprehension/papers/ran/1.json","rows":50}],"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":"ffba98642b3b0afcc18a13b8d5b0d173725f0ad1d1a980003beac74647c896bb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}