{"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-question-answering/papers/2","list_of":"/task/visual-question-answering","task":"Visual Question Answering (VQA)","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":22,"rows_per_page":100,"rows":[101,200],"of":2167,"counts":{"archive_papers_tagged":2167,"with_a_code_link":1039,"where_syntology_ran_a_sample":359,"not_listed_spam_title":0,"listed":2167,"listed_where_code_ran":359,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":287,"every_run_a_failure_of_syntologys_instrument":72,"listed_with_a_run_with_no_instrument_failure":287,"listed_every_run_a_failure_of_syntologys_instrument":72,"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"},"first_page":"/task/visual-question-answering","prev":"/task/visual-question-answering","next":"/task/visual-question-answering/papers/3","papers":[{"url":"/paper/conceptual-12m-pushing-web-scale-image-text","slug":"conceptual-12m-pushing-web-scale-image-text","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","date":"2021-02-17","arxiv_id":"2102.08981","repositories_listed":3,"syntology":null},{"url":"/paper/lrta-a-transparent-neural-symbolic-reasoning","slug":"lrta-a-transparent-neural-symbolic-reasoning","title":"LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering","date":"2020-11-21","arxiv_id":"2011.10731","repositories_listed":3,"syntology":null},{"url":"/paper/docvqa-a-dataset-for-vqa-on-document-images","slug":"docvqa-a-dataset-for-vqa-on-document-images","title":"DocVQA: A Dataset for VQA on Document Images","date":"2020-07-01","arxiv_id":"2007.00398","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/docvqa-a-dataset-for-vqa-on-document-images#ran","syntology_url":"https://syntology.ai/paper/2007.00398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00398"}},"official":null}},{"url":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}},"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ludwig-a-type-based-declarative-deep-learning","slug":"ludwig-a-type-based-declarative-deep-learning","title":"Ludwig: a type-based declarative deep learning toolbox","date":"2019-09-17","arxiv_id":"1909.07930","repositories_listed":3,"syntology":null},{"url":"/paper/dont-take-the-easy-way-out-ensemble-based","slug":"dont-take-the-easy-way-out-ensemble-based","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","date":"2019-09-09","arxiv_id":"1909.03683","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dont-take-the-easy-way-out-ensemble-based#ran","syntology_url":"https://syntology.ai/paper/1909.03683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03683"}},"official":{"repos":["chrisc36/debias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"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/attention-on-attention-architectures-for","slug":"attention-on-attention-architectures-for","title":"Attention on Attention: Architectures for Visual Question Answering (VQA)","date":"2018-03-21","arxiv_id":"1803.07724","repositories_listed":3,"syntology":null},{"url":"/paper/a-dataset-and-architecture-for-visual","slug":"a-dataset-and-architecture-for-visual","title":"A Dataset and Architecture for Visual Reasoning with a Working Memory","date":"2018-03-16","arxiv_id":"1803.06092","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-and-architecture-for-visual#ran","syntology_url":"https://syntology.ai/paper/1803.06092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06092"}},"official":{"repos":["google/cog"],"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":["listed","official"]}}},{"url":"/paper/a-simple-loss-function-for-improving-the","slug":"a-simple-loss-function-for-improving-the","title":"A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models","date":"2017-08-02","arxiv_id":"1708.00584","repositories_listed":3,"syntology":null},{"url":"/paper/shapeworld-a-new-test-methodology-for","slug":"shapeworld-a-new-test-methodology-for","title":"ShapeWorld - A new test methodology for multimodal language understanding","date":"2017-04-14","arxiv_id":"1704.04517","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/exploring-models-and-data-for-image-question","slug":"exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","date":"2015-05-08","arxiv_id":"1505.02074","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/exploring-models-and-data-for-image-question#ran","syntology_url":"https://syntology.ai/paper/1505.02074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.02074"}},"official":{"repos":["renmengye/imageqa-public"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-foundation-models-for-3d-vision-how","slug":"towards-foundation-models-for-3d-vision-how","title":"Towards Foundation Models for 3D Vision: How Close Are We?","date":"2024-10-14","arxiv_id":"2410.10799","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":0,"n_ran_checked":19,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/towards-foundation-models-for-3d-vision-how#ran","syntology_url":"https://syntology.ai/paper/2410.10799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10799"}},"official":{"repos":["princeton-vl/uniqa-3d"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mediconfusion-can-you-trust-your-ai","slug":"mediconfusion-can-you-trust-your-ai","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","date":"2024-09-23","arxiv_id":"2409.15477","repositories_listed":2,"syntology":{"n":28,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":16,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":28,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/mediconfusion-can-you-trust-your-ai#ran","syntology_url":"https://syntology.ai/paper/2409.15477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15477"}},"official":{"repos":["mshahabsepehri/mediconfusion","AIF4S/MediConfusion"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":16,"ran_from_kinds":["official"]}}},{"url":"/paper/e-bench-subjective-aligned-benchmark-suite","slug":"e-bench-subjective-aligned-benchmark-suite","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","date":"2024-08-21","arxiv_id":"2408.11481","repositories_listed":2,"syntology":null},{"url":"/paper/llava-onevision-easy-visual-task-transfer","slug":"llava-onevision-easy-visual-task-transfer","title":"LLaVA-OneVision: Easy Visual Task Transfer","date":"2024-08-06","arxiv_id":"2408.03326","repositories_listed":2,"syntology":null},{"url":"/paper/frechet-video-motion-distance-a-metric-for","slug":"frechet-video-motion-distance-a-metric-for","title":"Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","date":"2024-07-23","arxiv_id":"2407.16124","repositories_listed":2,"syntology":{"n":23,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":18,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/frechet-video-motion-distance-a-metric-for#ran","syntology_url":"https://syntology.ai/paper/2407.16124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16124"}},"official":{"repos":["ljh0v0/fmd-frechet-motion-distance"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/from-the-least-to-the-most-building-a-plug","slug":"from-the-least-to-the-most-building-a-plug","title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis","date":"2024-06-28","arxiv_id":"2406.19934","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"8 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; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-the-least-to-the-most-building-a-plug#ran","syntology_url":"https://syntology.ai/paper/2406.19934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19934"}},"official":{"repos":["steven-ccq/visualreasoner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}},"official":{"repos":["evolvinglmms-lab/longva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/learnable-in-context-vector-for-visual","slug":"learnable-in-context-vector-for-visual","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","date":"2024-06-19","arxiv_id":"2406.13185","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"3 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learnable-in-context-vector-for-visual#ran","syntology_url":"https://syntology.ai/paper/2406.13185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13185"}},"official":{"repos":["forjadeforest/live-learnable-in-context-vector"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ovis-structural-embedding-alignment-for","slug":"ovis-structural-embedding-alignment-for","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","date":"2024-05-31","arxiv_id":"2405.20797","repositories_listed":2,"syntology":null},{"url":"/paper/viocrvqa-novel-benchmark-dataset-and-vision","slug":"viocrvqa-novel-benchmark-dataset-and-vision","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","date":"2024-04-29","arxiv_id":"2404.18397","repositories_listed":2,"syntology":null},{"url":"/paper/moe-tinymed-mixture-of-experts-for-tiny","slug":"moe-tinymed-mixture-of-experts-for-tiny","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","date":"2024-04-16","arxiv_id":"2404.10237","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 5 unverified","sample_list":"/paper/moe-tinymed-mixture-of-experts-for-tiny#ran","syntology_url":"https://syntology.ai/paper/2404.10237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10237"}},"official":{"repos":["jiangsongtao/med-moe","jiangsongtao/tinymed"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vitextvqa-a-large-scale-visual-question","slug":"vitextvqa-a-large-scale-visual-question","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset for Evaluating Vietnamese Text Comprehension in Images","date":"2024-04-16","arxiv_id":"2404.10652","repositories_listed":2,"syntology":null},{"url":"/paper/design-as-desired-utilizing-visual-question","slug":"design-as-desired-utilizing-visual-question","title":"Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training","date":"2024-03-30","arxiv_id":"2404.00226","repositories_listed":2,"syntology":null},{"url":"/paper/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/screenai-a-vision-language-model-for-ui-and","slug":"screenai-a-vision-language-model-for-ui-and","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","date":"2024-02-07","arxiv_id":"2402.04615","repositories_listed":2,"syntology":null},{"url":"/paper/tinygpt-v-efficient-multimodal-large-language","slug":"tinygpt-v-efficient-multimodal-large-language","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","date":"2023-12-28","arxiv_id":"2312.16862","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tinygpt-v-efficient-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.16862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16862"}},"official":{"repos":["dlyuangod/tinygpt-v"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"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/advancing-surgical-vqa-with-scene-graph","slug":"advancing-surgical-vqa-with-scene-graph","title":"Advancing Surgical VQA with Scene Graph Knowledge","date":"2023-12-15","arxiv_id":"2312.10251","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/advancing-surgical-vqa-with-scene-graph#ran","syntology_url":"https://syntology.ai/paper/2312.10251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10251"}},"official":{"repos":["camma-public/ssg-qa","camma-public/ssg-vqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quilt-llava-visual-instruction-tuning-by","slug":"quilt-llava-visual-instruction-tuning-by","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","date":"2023-12-07","arxiv_id":"2312.04746","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quilt-llava-visual-instruction-tuning-by#ran","syntology_url":"https://syntology.ai/paper/2312.04746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04746"}},"official":null}},{"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/mplug-owl2-revolutionizing-multi-modal-large","slug":"mplug-owl2-revolutionizing-multi-modal-large","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","date":"2023-11-07","arxiv_id":"2311.04257","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-owl2-revolutionizing-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2311.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04257"}},"official":{"repos":["x-plug/mplug-owl"],"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":["unlocated"]}}},{"url":"/paper/3d-aware-visual-question-answering-about-1","slug":"3d-aware-visual-question-answering-about-1","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","date":"2023-10-27","arxiv_id":"2310.17914","repositories_listed":2,"syntology":{"n":28,"n_ran":22,"n_constructed":0,"n_ran_checked":21,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":14,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/3d-aware-visual-question-answering-about-1#ran","syntology_url":"https://syntology.ai/paper/2310.17914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17914"}},"official":{"repos":["xingruiwang/3d-aware-vqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lxmert-model-compression-for-visual-question","slug":"lxmert-model-compression-for-visual-question","title":"LXMERT Model Compression for Visual Question Answering","date":"2023-10-23","arxiv_id":"2310.15325","repositories_listed":2,"syntology":null},{"url":"/paper/halle-switch-rethinking-and-controlling","slug":"halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","arxiv_id":"2310.01779","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/halle-switch-rethinking-and-controlling#ran","syntology_url":"https://syntology.ai/paper/2310.01779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01779"}},"official":{"repos":["bronyayang/HallE_Switch","bronyayang/halle_control"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/uni-nlx-unifying-textual-explanations-for","slug":"uni-nlx-unifying-textual-explanations-for","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","date":"2023-08-17","arxiv_id":"2308.09033","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-nlx-unifying-textual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/2308.09033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09033"}},"official":{"repos":["fawazsammani/uni-nlx","fawazsammani/nlxgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pro-cap-leveraging-a-frozen-vision-language","slug":"pro-cap-leveraging-a-frozen-vision-language","title":"Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection","date":"2023-08-16","arxiv_id":"2308.08088","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/pro-cap-leveraging-a-frozen-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.08088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08088"}},"official":{"repos":["social-ai-studio/pro-cap"],"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":["official"]}}},{"url":"/paper/openflamingo-an-open-source-framework-for","slug":"openflamingo-an-open-source-framework-for","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","date":"2023-08-02","arxiv_id":"2308.01390","repositories_listed":2,"syntology":null},{"url":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}},"official":{"repos":["baaivision/emu"],"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/sas-video-qa-self-adaptive-sampling-for","slug":"sas-video-qa-self-adaptive-sampling-for","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","date":"2023-07-09","arxiv_id":"2307.04192","repositories_listed":2,"syntology":null},{"url":"/paper/causalvlr-a-toolbox-and-benchmark-for-visual","slug":"causalvlr-a-toolbox-and-benchmark-for-visual","title":"CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning","date":"2023-06-30","arxiv_id":"2306.17462","repositories_listed":2,"syntology":null},{"url":"/paper/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llavar-enhanced-visual-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17107"}},"official":{"repos":["SALT-NLP/LLaVAR"],"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","unlocated"]}}},{"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/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":29,"n_instrument":6,"n_unverified":7,"n_honours":2,"n_violates":1,"n_no_contract":26,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 1 violated, 26 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/getting-vit-in-shape-scaling-laws-for-compute","slug":"getting-vit-in-shape-scaling-laws-for-compute","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","date":"2023-05-22","arxiv_id":"2305.13035","repositories_listed":2,"syntology":null},{"url":"/paper/surgical-vqla-transformer-with-gated-vision","slug":"surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","arxiv_id":"2305.11692","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surgical-vqla-transformer-with-gated-vision#ran","syntology_url":"https://syntology.ai/paper/2305.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11692"}},"official":{"repos":["longbai1006/surgical-vqla"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/pmc-vqa-visual-instruction-tuning-for-medical","slug":"pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10415","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pmc-vqa-visual-instruction-tuning-for-medical#ran","syntology_url":"https://syntology.ai/paper/2305.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10415"}},"official":{"repos":["xiaoman-zhang/PMC-VQA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-text-prompted-semantic","slug":"towards-robust-text-prompted-semantic","title":"Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment","date":"2023-04-28","arxiv_id":"2304.14672","repositories_listed":2,"syntology":null},{"url":"/paper/pmc-clip-contrastive-language-image-pre","slug":"pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","date":"2023-03-13","arxiv_id":"2303.07240","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"9 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; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pmc-clip-contrastive-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2303.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07240"}},"official":{"repos":["WeixiongLin/PMC-CLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/palm-e-an-embodied-multimodal-language-model","slug":"palm-e-an-embodied-multimodal-language-model","title":"PaLM-E: An Embodied Multimodal Language Model","date":"2023-03-06","arxiv_id":"2303.03378","repositories_listed":2,"syntology":null},{"url":"/paper/prismer-a-vision-language-model-with-an","slug":"prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","arxiv_id":"2303.02506","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-opinion-unaware-video-quality","slug":"exploring-opinion-unaware-video-quality","title":"Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion","date":"2023-02-26","arxiv_id":"2302.13269","repositories_listed":2,"syntology":null},{"url":"/paper/can-pre-trained-vision-and-language-models","slug":"can-pre-trained-vision-and-language-models","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","date":"2023-02-23","arxiv_id":"2302.11713","repositories_listed":2,"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/can-pre-trained-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2302.11713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11713"}},"official":{"repos":["edchengg/infoseek_eval"],"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/open-domain-visual-entity-recognition-towards","slug":"open-domain-visual-entity-recognition-towards","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","date":"2023-02-22","arxiv_id":"2302.11154","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/open-domain-visual-entity-recognition-towards#ran","syntology_url":"https://syntology.ai/paper/2302.11154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11154"}},"official":{"repos":["edchengg/oven_eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/uniadapter-unified-parameter-efficient","slug":"uniadapter-unified-parameter-efficient","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","date":"2023-02-13","arxiv_id":"2302.06605","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"8 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniadapter-unified-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2302.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06605"}},"official":{"repos":["rerv/uniadapter","uniadapter/uniadapter"],"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/upop-unified-and-progressive-pruning-for","slug":"upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","date":"2023-01-31","arxiv_id":"2301.13741","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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/upop-unified-and-progressive-pruning-for#ran","syntology_url":"https://syntology.ai/paper/2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"official":{"repos":["sdc17/upop"],"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/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","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":0,"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/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}},"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/super-clevr-a-virtual-benchmark-to-diagnose","slug":"super-clevr-a-virtual-benchmark-to-diagnose","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","date":"2022-12-01","arxiv_id":"2212.00259","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/super-clevr-a-virtual-benchmark-to-diagnose#ran","syntology_url":"https://syntology.ai/paper/2212.00259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00259"}},"official":{"repos":["lizw14/super-clevr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-vision-language-pretraining","slug":"self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","arxiv_id":"2211.13594","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-supervised-vision-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2211.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13594"}},"official":{"repos":["pengfeiliheu/m2i2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/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/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 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) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"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/linearly-mapping-from-image-to-text-space","slug":"linearly-mapping-from-image-to-text-space","title":"Linearly Mapping from Image to Text Space","date":"2022-09-30","arxiv_id":"2209.15162","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linearly-mapping-from-image-to-text-space#ran","syntology_url":"https://syntology.ai/paper/2209.15162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15162"}},"official":{"repos":["jmerullo/limber"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","repositories_listed":2,"syntology":null},{"url":"/paper/cross-modal-causal-relational-reasoning-for","slug":"cross-modal-causal-relational-reasoning-for","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","date":"2022-07-26","arxiv_id":"2207.12647","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-modal-causal-relational-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2207.12647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12647"}},"official":{"repos":["hcplab-sysu/cmcir","yangliu9208/cmcir"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lst-ladder-side-tuning-for-parameter-and","slug":"lst-ladder-side-tuning-for-parameter-and","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","date":"2022-06-13","arxiv_id":"2206.06522","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lst-ladder-side-tuning-for-parameter-and#ran","syntology_url":"https://syntology.ai/paper/2206.06522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06522"}},"official":{"repos":["ylsung/ladder-side-tuning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/all-you-may-need-for-vqa-are-image-captions-1","slug":"all-you-may-need-for-vqa-are-image-captions-1","title":"All You May Need for VQA are Image Captions","date":"2022-05-04","arxiv_id":"2205.01883","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/all-you-may-need-for-vqa-are-image-captions-1#ran","syntology_url":"https://syntology.ai/paper/2205.01883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01883"}},"official":{"repos":["google-research-datasets/maverics"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/end-to-end-document-recognition-and","slug":"end-to-end-document-recognition-and","title":"End-to-end Document Recognition and Understanding with Dessurt","date":"2022-03-30","arxiv_id":"2203.16618","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-document-recognition-and#ran","syntology_url":"https://syntology.ai/paper/2203.16618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16618"}},"official":{"repos":["herobd/dessurt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/searching-the-search-space-of-vision-1","slug":"searching-the-search-space-of-vision-1","title":"Searching the Search Space of Vision Transformer","date":"2021-11-29","arxiv_id":"2111.14725","repositories_listed":2,"syntology":null},{"url":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","repositories_listed":2,"syntology":null},{"url":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","repositories_listed":2,"syntology":null},{"url":"/paper/vivqa-vietnamese-visual-question-answering","slug":"vivqa-vietnamese-visual-question-answering","title":"ViVQA: Vietnamese Visual Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/label-descriptive-patterns-and-their","slug":"label-descriptive-patterns-and-their","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","date":"2021-10-18","arxiv_id":"2110.09599","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/label-descriptive-patterns-and-their#ran","syntology_url":"https://syntology.ai/paper/2110.09599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09599"}},"official":{"repos":["uds-lsv/premise"],"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/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}},"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/weakly-supervised-visual-retriever-reader-for","slug":"weakly-supervised-visual-retriever-reader-for","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","date":"2021-09-09","arxiv_id":"2109.04014","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weakly-supervised-visual-retriever-reader-for#ran","syntology_url":"https://syntology.ai/paper/2109.04014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04014"}},"official":{"repos":["luomancs/retriever_reader_for_okvqa"],"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":["official","unlocated"]}}},{"url":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","repositories_listed":2,"syntology":{"n":37,"n_ran":22,"n_constructed":8,"n_ran_checked":16,"n_instrument":6,"n_unverified":15,"n_honours":1,"n_violates":3,"n_no_contract":12,"n_pointer_only":32,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"official":null}},{"url":"/paper/blindly-assess-quality-of-in-the-wild-videos","slug":"blindly-assess-quality-of-in-the-wild-videos","title":"Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception","date":"2021-08-19","arxiv_id":"2108.08505","repositories_listed":2,"syntology":null},{"url":"/paper/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/separating-skills-and-concepts-for-novel-1","slug":"separating-skills-and-concepts-for-novel-1","title":"Separating Skills and Concepts for Novel Visual Question Answering","date":"2021-07-19","arxiv_id":"2107.09106","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/separating-skills-and-concepts-for-novel-1#ran","syntology_url":"https://syntology.ai/paper/2107.09106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09106"}},"official":{"repos":["SpencerWhitehead/novelvqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/zero-shot-visual-question-answering-using","slug":"zero-shot-visual-question-answering-using","title":"Zero-shot Visual Question Answering using Knowledge Graph","date":"2021-07-12","arxiv_id":"2107.05348","repositories_listed":2,"syntology":null},{"url":"/paper/multiple-meta-model-quantifying-for-medical","slug":"multiple-meta-model-quantifying-for-medical","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","date":"2021-05-19","arxiv_id":"2105.08913","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 3 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-meta-model-quantifying-for-medical#ran","syntology_url":"https://syntology.ai/paper/2105.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08913"}},"official":{"repos":["aioz-ai/MICCAI21_MMQ"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/next-qa-next-phase-of-question-answering-to","slug":"next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","date":"2021-05-18","arxiv_id":"2105.08276","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/next-qa-next-phase-of-question-answering-to#ran","syntology_url":"https://syntology.ai/paper/2105.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08276"}},"official":{"repos":["doc-doc/NExT-QA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-general-purpose-vision-systems","slug":"towards-general-purpose-vision-systems","title":"Towards General Purpose Vision Systems","date":"2021-04-01","arxiv_id":"2104.00743","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-general-purpose-vision-systems#ran","syntology_url":"https://syntology.ai/paper/2104.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00743"}},"official":{"repos":["allenai/gpv-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-generation-of-contrast-sets-from","slug":"automatic-generation-of-contrast-sets-from","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","date":"2021-03-17","arxiv_id":"2103.09591","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/automatic-generation-of-contrast-sets-from#ran","syntology_url":"https://syntology.ai/paper/2103.09591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09591"}},"official":{"repos":["yonatanbitton/AutoGenOfContrastSetsFromSceneGraphs"],"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/slake-a-semantically-labeled-knowledge","slug":"slake-a-semantically-labeled-knowledge","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","date":"2021-02-18","arxiv_id":"2102.09542","repositories_listed":2,"syntology":null},{"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/study-on-the-assessment-of-the-quality-of","slug":"study-on-the-assessment-of-the-quality-of","title":"Study on the Assessment of the Quality of Experience of Streaming Video","date":"2020-12-08","arxiv_id":"2012.04623","repositories_listed":2,"syntology":null},{"url":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"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/mutant-a-training-paradigm-for-out-of","slug":"mutant-a-training-paradigm-for-out-of","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","date":"2020-09-18","arxiv_id":"2009.08566","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":9,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}},"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/structured-multimodal-attentions-for-textvqa","slug":"structured-multimodal-attentions-for-textvqa","title":"Structured Multimodal Attentions for TextVQA","date":"2020-06-01","arxiv_id":"2006.00753","repositories_listed":2,"syntology":null},{"url":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","repositories_listed":2,"syntology":null},{"url":"/paper/towards-ground-truth-evaluation-of-visual","slug":"towards-ground-truth-evaluation-of-visual","title":"Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI","date":"2020-03-16","arxiv_id":"2003.07258","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-ground-truth-evaluation-of-visual#ran","syntology_url":"https://syntology.ai/paper/2003.07258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07258"}},"official":{"repos":["ahmedmagdiosman/clevr-xai","ahmedmagdiosman/simply-clevr-dataset"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"3ee41b37d747b3f58750c09d2e196e5142057f7e12ff5cd3fb4161e868ebaef0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}