{"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/medical-visual-question-answering","name":"Medical Visual Question Answering","slug":"medical-visual-question-answering","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":97,"papers_with_code":47,"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":11,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/vqa-rad","name":"VQA-RAD","full_name":"Visual Question Answering in Radiology","num_papers_in_archive":145},{"url":"/dataset/pathvqa","name":"PathVQA","full_name":"","num_papers_in_archive":89},{"url":"/dataset/slake","name":"SLAKE","full_name":"","num_papers_in_archive":63},{"url":"/dataset/pmc-vqa","name":"PMC-VQA","full_name":"","num_papers_in_archive":55},{"url":"/dataset/quilt-1m","name":"QUILT-1M","full_name":"","num_papers_in_archive":17},{"url":"/dataset/vqa-slake","name":"SLAKE-English","full_name":"","num_papers_in_archive":7},{"url":"/dataset/ovqa","name":"OVQA","full_name":"","num_papers_in_archive":4},{"url":"/dataset/kvasir-vqa","name":"Kvasir-VQA","full_name":"A Text-Image Pair GI Tract Dataset","num_papers_in_archive":3},{"url":"/dataset/mediconfusion","name":"MediConfusion","full_name":"","num_papers_in_archive":1},{"url":"/dataset/medpromptx-vqa","name":"MedPromptX-VQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/medtrinity-25m","name":"MedTrinity-25M","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":97,"of":97,"of_with_code":47,"tagged_in_all":97,"counts":{"archive_papers_tagged":97,"with_a_code_link":47,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":97,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":20,"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/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"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/large-scale-domain-specific-pretraining-for","slug":"large-scale-domain-specific-pretraining-for","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","date":"2023-03-02","arxiv_id":"2303.00915","repositories_listed":5,"syntology":null},{"url":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_constructed":6,"n_ran_checked":11,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":8,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}},"official":null}},{"url":"/paper/pathvqa-30000-questions-for-medical-visual","slug":"pathvqa-30000-questions-for-medical-visual","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","date":"2020-03-07","arxiv_id":"2003.10286","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pathvqa-30000-questions-for-medical-visual#ran","syntology_url":"https://syntology.ai/paper/2003.10286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10286"}},"official":null}},{"url":"/paper/med-flamingo-a-multimodal-medical-few-shot","slug":"med-flamingo-a-multimodal-medical-few-shot","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","date":"2023-07-27","arxiv_id":"2307.15189","repositories_listed":4,"syntology":null},{"url":"/paper/ehrxqa-a-multi-modal-question-answering-1","slug":"ehrxqa-a-multi-modal-question-answering-1","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","date":"2023-10-28","arxiv_id":"2310.18652","repositories_listed":3,"syntology":{"n":20,"n_ran":20,"n_constructed":0,"n_ran_checked":17,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ehrxqa-a-multi-modal-question-answering-1#ran","syntology_url":"https://syntology.ai/paper/2310.18652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18652"}},"official":{"repos":["baeseongsu/ehrxqa","baeseongsu/mimic-cxr-vqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"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":8,"n_instrument":4,"n_unverified":16,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":28,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 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":8,"n_unverified":16,"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":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 3 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":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"9 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; 5 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":4,"n_unverified":4,"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":0,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 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":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/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/overcoming-data-limitation-in-medical-visual","slug":"overcoming-data-limitation-in-medical-visual","title":"Overcoming Data Limitation in Medical Visual Question Answering","date":"2019-09-26","arxiv_id":"1909.11867","repositories_listed":2,"syntology":null},{"url":"/paper/medagentboard-benchmarking-multi-agent","slug":"medagentboard-benchmarking-multi-agent","title":"MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks","date":"2025-05-18","arxiv_id":"2505.12371","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/medagentboard-benchmarking-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2505.12371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12371"}},"official":{"repos":["yhzhu99/medagentboard"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/clinkd-cross-modal-clinical-knowledge","slug":"clinkd-cross-modal-clinical-knowledge","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","date":"2025-02-09","arxiv_id":"2502.05928","repositories_listed":1,"syntology":null},{"url":"/paper/medcot-medical-chain-of-thought-via","slug":"medcot-medical-chain-of-thought-via","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","date":"2024-12-18","arxiv_id":"2412.13736","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/medcot-medical-chain-of-thought-via#ran","syntology_url":"https://syntology.ai/paper/2412.13736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13736"}},"official":{"repos":["jxliu-ai/medcot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bimedix2-bio-medical-expert-lmm-for-diverse","slug":"bimedix2-bio-medical-expert-lmm-for-diverse","title":"BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities","date":"2024-12-10","arxiv_id":"2412.07769","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-medical-vision-and-language","slug":"a-survey-of-medical-vision-and-language","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","date":"2024-11-19","arxiv_id":"2411.12195","repositories_listed":1,"syntology":null},{"url":"/paper/mc-cot-a-modular-collaborative-cot-framework","slug":"mc-cot-a-modular-collaborative-cot-framework","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration","date":"2024-10-06","arxiv_id":"2410.04521","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mc-cot-a-modular-collaborative-cot-framework#ran","syntology_url":"https://syntology.ai/paper/2410.04521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04521"}},"official":{"repos":["thomaswei-cn/MC-CoT"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kvasir-vqa-a-text-image-pair-gi-tract-dataset","slug":"kvasir-vqa-a-text-image-pair-gi-tract-dataset","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","date":"2024-09-02","arxiv_id":"2409.01437","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/kvasir-vqa-a-text-image-pair-gi-tract-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.01437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01437"}},"official":{"repos":["simula/Kvasir-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/fedmeki-a-benchmark-for-scaling-medical","slug":"fedmeki-a-benchmark-for-scaling-medical","title":"FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection","date":"2024-08-17","arxiv_id":"2408.09227","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fedmeki-a-benchmark-for-scaling-medical#ran","syntology_url":"https://syntology.ai/paper/2408.09227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09227"}},"official":{"repos":["psudslab/FEDMEKI"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/med-pmc-medical-personalized-multi-modal","slug":"med-pmc-medical-personalized-multi-modal","title":"Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm","date":"2024-08-16","arxiv_id":"2408.08693","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/med-pmc-medical-personalized-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2408.08693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08693"}},"official":{"repos":["liuhc0428/med-pmc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/surgical-vqla-adversarial-contrastive","slug":"surgical-vqla-adversarial-contrastive","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","date":"2024-08-09","arxiv_id":"2408.04958","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surgical-vqla-adversarial-contrastive#ran","syntology_url":"https://syntology.ai/paper/2408.04958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04958"}},"official":{"repos":["longbai1006/surgical-vqlaplus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02900","slug":"2408-02900","title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine","date":"2024-08-06","arxiv_id":"2408.02900","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-02900#ran","syntology_url":"https://syntology.ai/paper/2408.02900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02900"}},"official":{"repos":["UCSC-VLAA/MedTrinity-25M"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03043","slug":"2408-03043","title":"Targeted Visual Prompting for Medical Visual Question Answering","date":"2024-08-06","arxiv_id":"2408.03043","repositories_listed":1,"syntology":null},{"url":"/paper/stllava-med-self-training-large-language-and","slug":"stllava-med-self-training-large-language-and","title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","date":"2024-06-28","arxiv_id":"2406.19973","repositories_listed":1,"syntology":{"n":19,"n_ran":9,"n_constructed":4,"n_ran_checked":5,"n_instrument":4,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 4 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) · 10 unverified","sample_list":"/paper/stllava-med-self-training-large-language-and#ran","syntology_url":"https://syntology.ai/paper/2406.19973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19973"}},"official":{"repos":["heliossun/stllava-med"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/worse-than-random-an-embarrassingly-simple","slug":"worse-than-random-an-embarrassingly-simple","title":"Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA","date":"2024-05-30","arxiv_id":"2405.20421","repositories_listed":1,"syntology":null},{"url":"/paper/lapa-latent-prompt-assist-model-for-medical","slug":"lapa-latent-prompt-assist-model-for-medical","title":"LaPA: Latent Prompt Assist Model For Medical Visual Question Answering","date":"2024-04-19","arxiv_id":"2404.13039","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"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) · 4 unverified","sample_list":"/paper/lapa-latent-prompt-assist-model-for-medical#ran","syntology_url":"https://syntology.ai/paper/2404.13039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13039"}},"official":{"repos":["garygutc/lapa_model"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/medpromptx-grounded-multimodal-prompting-for","slug":"medpromptx-grounded-multimodal-prompting-for","title":"MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis","date":"2024-03-22","arxiv_id":"2403.15585","repositories_listed":1,"syntology":null},{"url":"/paper/omnimedvqa-a-new-large-scale-comprehensive","slug":"omnimedvqa-a-new-large-scale-comprehensive","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","date":"2024-02-14","arxiv_id":"2402.09181","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"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) · 1 unverified","sample_list":"/paper/omnimedvqa-a-new-large-scale-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2402.09181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09181"}},"official":{"repos":["opengvlab/multi-modality-arena"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gemini-goes-to-med-school-exploring-the","slug":"gemini-goes-to-med-school-exploring-the","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","date":"2024-02-10","arxiv_id":"2402.07023","repositories_listed":1,"syntology":null},{"url":"/paper/hallucination-benchmark-in-medical-visual","slug":"hallucination-benchmark-in-medical-visual","title":"Hallucination Benchmark in Medical Visual Question Answering","date":"2024-01-11","arxiv_id":"2401.05827","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hallucination-benchmark-in-medical-visual#ran","syntology_url":"https://syntology.ai/paper/2401.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05827"}},"official":{"repos":["knowlab/halt-medvqa"],"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/miss-a-generative-pretraining-and-finetuning","slug":"miss-a-generative-pretraining-and-finetuning","title":"MISS: A Generative Pretraining and Finetuning Approach for Med-VQA","date":"2024-01-10","arxiv_id":"2401.05163","repositories_listed":1,"syntology":null},{"url":"/paper/pefomed-parameter-efficient-fine-tuning-on","slug":"pefomed-parameter-efficient-fine-tuning-on","title":"PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging","date":"2024-01-05","arxiv_id":"2401.02797","repositories_listed":1,"syntology":null},{"url":"/paper/expert-knowledge-aware-image-difference-graph","slug":"expert-knowledge-aware-image-difference-graph","title":"Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering","date":"2023-07-22","arxiv_id":"2307.11986","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/expert-knowledge-aware-image-difference-graph#ran","syntology_url":"https://syntology.ai/paper/2307.11986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11986"}},"official":{"repos":["holipori/mimic-diff-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/masked-vision-and-language-pre-training-with","slug":"masked-vision-and-language-pre-training-with","title":"Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering","date":"2023-07-11","arxiv_id":"2307.05314","repositories_listed":1,"syntology":null},{"url":"/paper/rad-restruct-a-novel-vqa-benchmark-and-method","slug":"rad-restruct-a-novel-vqa-benchmark-and-method","title":"Rad-ReStruct: A Novel VQA Benchmark and Method for Structured Radiology Reporting","date":"2023-07-11","arxiv_id":"2307.05766","repositories_listed":1,"syntology":null},{"url":"/paper/localized-questions-in-medical-visual","slug":"localized-questions-in-medical-visual","title":"Localized Questions in Medical Visual Question Answering","date":"2023-07-03","arxiv_id":"2307.01067","repositories_listed":1,"syntology":null},{"url":"/paper/biomedgpt-a-unified-and-generalist-biomedical","slug":"biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","arxiv_id":"2305.17100","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/biomedgpt-a-unified-and-generalist-biomedical#ran","syntology_url":"https://syntology.ai/paper/2305.17100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17100"}},"official":{"repos":["taokz/biomedgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/medblip-bootstrapping-language-image-pre","slug":"medblip-bootstrapping-language-image-pre","title":"MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts","date":"2023-05-18","arxiv_id":"2305.10799","repositories_listed":1,"syntology":null},{"url":"/paper/towards-medical-artificial-general","slug":"towards-medical-artificial-general","title":"Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining","date":"2023-04-26","arxiv_id":"2304.14204","repositories_listed":1,"syntology":null},{"url":"/paper/open-ended-medical-visual-question-answering","slug":"open-ended-medical-visual-question-answering","title":"Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models","date":"2023-03-10","arxiv_id":"2303.05977","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/open-ended-medical-visual-question-answering#ran","syntology_url":"https://syntology.ai/paper/2303.05977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05977"}},"official":{"repos":["tjvsonsbeek/open-ended-medical-vqa"],"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/a-dual-attention-learning-network-with-word","slug":"a-dual-attention-learning-network-with-word","title":"A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering","date":"2022-10-01","arxiv_id":"2210.00220","repositories_listed":1,"syntology":null},{"url":"/paper/vilmedic-a-framework-for-research-at-the","slug":"vilmedic-a-framework-for-research-at-the","title":"ViLMedic: a framework for research at the intersection of vision and language in medical AI","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-understanding-and-generation-for","slug":"multi-modal-understanding-and-generation-for","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","date":"2021-05-24","arxiv_id":"2105.11333","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-modal-understanding-and-generation-for#ran","syntology_url":"https://syntology.ai/paper/2105.11333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11333"}},"official":{"repos":["SuperSupermoon/MedViLL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-deep-multi-modal-network-for","slug":"hierarchical-deep-multi-modal-network-for","title":"Hierarchical Deep Multi-modal Network for Medical Visual Question Answering","date":"2020-09-27","arxiv_id":"2009.12770","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-pre-trained-vision-and","slug":"a-comparison-of-pre-trained-vision-and","title":"A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports","date":"2020-09-03","arxiv_id":"2009.01523","repositories_listed":1,"syntology":null},{"url":null,"slug":"barriers-in-integrating-medical-visual","title":"Barriers in Integrating Medical Visual Question Answering into Radiology Workflows: A Scoping Review and Clinicians' Insights","date":"2025-07-09","arxiv_id":"2507.08036","repositories_listed":0,"syntology":null},{"url":null,"slug":"smmile-an-expert-driven-benchmark-for","title":"SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning","date":"2025-06-26","arxiv_id":"2506.21355","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemex-thinkvg-towards-thinking-with-visual","title":"GEMeX-ThinkVG: Towards Thinking with Visual Grounding in Medical VQA via Reinforcement Learning","date":"2025-06-22","arxiv_id":"2506.17939","repositories_listed":0,"syntology":null},{"url":null,"slug":"capo-reinforcing-consistent-reasoning-in","title":"CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making","date":"2025-06-15","arxiv_id":"2506.12849","repositories_listed":0,"syntology":null},{"url":null,"slug":"kvasir-vqa-x1-a-multimodal-dataset-for","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","date":"2025-06-11","arxiv_id":"2506.09958","repositories_listed":0,"syntology":null},{"url":null,"slug":"medorch-medical-diagnosis-with-tool-augmented","title":"MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility","date":"2025-05-30","arxiv_id":"2506.00235","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-causal-approach-to-mitigate-modality","title":"A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering","date":"2025-05-22","arxiv_id":"2505.16209","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-effective-reinforcement-learning-fine","title":"Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models","date":"2025-05-20","arxiv_id":"2505.13973","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-causal-models-and-llms-integration","title":"Structure Causal Models and LLMs Integration in Medical Visual Question Answering","date":"2025-05-05","arxiv_id":"2505.02703","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-semantic-gaps-improving-medical","title":"Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets","date":"2025-04-16","arxiv_id":"2504.11777","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-modeling-for-medical-visual","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","date":"2025-04-04","arxiv_id":"2504.03135","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-amplified-semantic-entropy-for","title":"Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering","date":"2025-03-26","arxiv_id":"2503.20504","repositories_listed":0,"syntology":null},{"url":null,"slug":"din-diffusion-model-for-robust-medical-vqa","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","date":"2025-03-24","arxiv_id":"2503.18536","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignment-mining-and-fusion-representation","title":"Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gemex-a-large-scale-groundable-and","title":"GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis","date":"2024-11-25","arxiv_id":"2411.16778","repositories_listed":0,"syntology":null},{"url":null,"slug":"med-2e3-a-2d-enhanced-3d-medical-multimodal","title":"Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model","date":"2024-11-19","arxiv_id":"2411.12783","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-bilinear-attention-based-fusion-for","title":"Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering","date":"2024-10-28","arxiv_id":"2410.21000","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-llava-improving-med-vqa-understanding","title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","date":"2024-10-27","arxiv_id":"2410.20327","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-client-is-reliable-a-reliable-and","title":"Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering","date":"2024-10-23","arxiv_id":"2410.17484","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-ultra-large-chinese-language-and-vision","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","date":"2024-10-19","arxiv_id":"2410.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"zalm3-zero-shot-enhancement-of-vision","title":"ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue","date":"2024-09-26","arxiv_id":"2409.17610","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21368","title":"Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering","date":"2024-07-31","arxiv_id":"2407.21368","repositories_listed":0,"syntology":null},{"url":null,"slug":"tm-pathvqa-90000-textless-multilingual","title":"TM-PATHVQA:90000+ Textless Multilingual Questions for Medical Visual Question Answering","date":"2024-07-16","arxiv_id":"2407.11383","repositories_listed":0,"syntology":null},{"url":null,"slug":"tri-vqa-triangular-reasoning-medical-visual","title":"Tri-VQA: Triangular Reasoning Medical Visual Question Answering for Multi-Attribute Analysis","date":"2024-06-21","arxiv_id":"2406.15050","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-and-evaluating-medical","title":"Detecting and Evaluating Medical Hallucinations in Large Vision Language Models","date":"2024-06-14","arxiv_id":"2406.10185","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-in-focus-layernorm-as-a-catalyst","title":"Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models","date":"2024-04-25","arxiv_id":"2404.16385","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-of-domain-adapted-vision-and-language","title":"Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering","date":"2024-04-24","arxiv_id":"2404.16192","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-knowledge-enhanced-medical-vlp-for","title":"Grounded Knowledge-Enhanced Medical VLP for Chest X-Ray","date":"2024-04-23","arxiv_id":"2404.14750","repositories_listed":0,"syntology":null},{"url":null,"slug":"wanglab-at-mediqa-m3g-2024-multimodal-medical","title":"WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models","date":"2024-04-22","arxiv_id":"2404.14567","repositories_listed":0,"syntology":null},{"url":null,"slug":"medthink-explaining-medical-visual-question","title":"MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale","date":"2024-04-18","arxiv_id":"2404.12372","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-generalization-in-medical-visual","title":"Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation","date":"2024-03-05","arxiv_id":"2403.02707","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-personalized-federated-learning","title":"Prompt-based Personalized Federated Learning for Medical Visual Question Answering","date":"2024-02-15","arxiv_id":"2402.09677","repositories_listed":0,"syntology":null},{"url":null,"slug":"free-form-medical-visual-question-answering","title":"Free Form Medical Visual Question Answering in Radiology","date":"2024-01-23","arxiv_id":"2401.13081","repositories_listed":0,"syntology":null},{"url":null,"slug":"bestmvqa-a-benchmark-evaluation-system-for","title":"BESTMVQA: A Benchmark Evaluation System for Medical Visual Question Answering","date":"2023-12-13","arxiv_id":"2312.07867","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-gpt-4v-s-multimodal","title":"A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis","date":"2023-10-31","arxiv_id":"2310.20381","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-question-answering-in-the-medical","title":"Visual Question Answering in the Medical Domain","date":"2023-09-20","arxiv_id":"2309.11080","repositories_listed":0,"syntology":null},{"url":null,"slug":"uit-saviors-at-medvqa-gi-2023-improving","title":"UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering","date":"2023-07-06","arxiv_id":"2307.02783","repositories_listed":0,"syntology":null},{"url":null,"slug":"q2atransformer-improving-medical-vqa-via-an","title":"Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder","date":"2023-04-04","arxiv_id":"2304.01611","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-visual-question-answering-using-joint","title":"Medical visual question answering using joint self-supervised learning","date":"2023-02-25","arxiv_id":"2302.13069","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-medical-image-visual-question","title":"Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning","date":"2023-02-19","arxiv_id":"2302.09636","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniclam-contrastive-representation-learning","title":"UnICLAM:Contrastive Representation Learning with Adversarial Masking for Unified and Interpretable Medical Vision Question Answering","date":"2022-12-21","arxiv_id":"2212.10729","repositories_listed":0,"syntology":null},{"url":null,"slug":"mf2-mvqa-a-multi-stage-feature-fusion-method","title":"MF2-MVQA: A Multi-stage Feature Fusion method for Medical Visual Question Answering","date":"2022-11-11","arxiv_id":"2211.05991","repositories_listed":0,"syntology":null},{"url":null,"slug":"repsnet-combining-vision-with-language-for","title":"RepsNet: Combining Vision with Language for Automated Medical Reports","date":"2022-09-27","arxiv_id":"2209.13171","repositories_listed":0,"syntology":null},{"url":"/paper/ovqa-a-clinically-generated-visual-question","slug":"ovqa-a-clinically-generated-visual-question","title":"OVQA: A Clinically Generated Visual Question Answering Dataset","date":"2022-07-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"2112-13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","date":"2021-12-27","arxiv_id":"2112.13906","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-visual-question-answering-a-survey","title":"Medical Visual Question Answering: A Survey","date":"2021-11-19","arxiv_id":"2111.10056","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-learning-a-simple-efficient-decentralized","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","date":"2021-10-27","arxiv_id":"2110.14555","repositories_listed":0,"syntology":null},{"url":null,"slug":"muvam-a-multi-view-attention-based-model-for","title":"MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering","date":"2021-07-07","arxiv_id":"2107.03216","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-medical-visual-question-answering","title":"Leveraging Medical Visual Question Answering with Supporting Facts","date":"2019-05-28","arxiv_id":"1905.12008","repositories_listed":0,"syntology":null},{"url":"/paper/a-dataset-of-clinically-generated-visual","slug":"a-dataset-of-clinically-generated-visual","title":"A dataset of clinically generated visual questions and answers about radiology images","date":"2018-11-20","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":25,"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":24,"papers_where_code_ran_first_page":"/task/medical-visual-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/medical-visual-question-answering/papers/ran/1","json":"/task/medical-visual-question-answering/papers/ran/1.json","rows":24}],"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":"13aa4ea4b49beac0e9fb6dac84d8c6caab5e13f67b965e4c41b9045279eca7f0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}