{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language","title":"GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI","arxiv_id":"2411.14522","date":"2024-11-21","proceeding":null,"authors":["Tianbin Li","Yanzhou Su","Wei Li","Bin Fu","Zhe Chen","Ziyan Huang","Guoan Wang","Chenglong Ma","Ying Chen","Ming Hu","Yanjun Li","Pengcheng Chen","Xiaowei Hu","Zhongying Deng","Yuanfeng Ji","Jin Ye","Yu Qiao","Junjun He"],"abstract":"Despite significant advancements in general AI, its effectiveness in the medical domain is limited by the lack of specialized medical knowledge. To address this, we formulate GMAI-VL-5.5M, a multimodal medical dataset created by converting hundreds of specialized medical datasets with various annotations into high-quality image-text pairs. This dataset offers comprehensive task coverage, diverse modalities, and rich image-text data. Building upon this dataset, we develop GMAI-VL, a general medical vision-language model, with a three-stage training strategy that enhances the integration of visual and textual information. This approach significantly improves the model's ability to process multimodal data, supporting accurate diagnoses and clinical decision-making. Experiments show that GMAI-VL achieves state-of-the-art performance across various multimodal medical tasks, including visual question answering and medical image diagnosis.","url_abs":"https://arxiv.org/abs/2411.14522v2","url_pdf":"https://arxiv.org/pdf/2411.14522v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gmai-vl-gmai-vl-5-5m-a-large-vision-language","repo_url":"https://github.com/uni-medical/gmai-vl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.14522","atlas_url":"https://app.syntology.ai/?focus=2411.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14522"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uni-medical/gmai-vl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"53281c424cf5891f","entry":"find_all_linear_names","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/model/utils.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/model/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53281c424cf5891f"}},{"code_sha256_prefix":"dcdc7ef233f3e1e8","entry":"build_model","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/apis/model.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/apis/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dcdc7ef233f3e1e8"}},{"code_sha256_prefix":"f8035a195671164a","entry":"convert_state_dict_to_hf","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/model/llava.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/model/llava.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8035a195671164a"}},{"code_sha256_prefix":"269c10dd16c744e8","entry":"create_reference_model","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/model/dpo.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/model/dpo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"269c10dd16c744e8"}},{"code_sha256_prefix":"444b8623d0de4b5a","entry":"download_model_from_hub","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/_lite/auto.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/_lite/auto.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"444b8623d0de4b5a"}},{"code_sha256_prefix":"5d8fd42d109d9939","entry":"get_main_modality","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"demo/gmai_vl_demo/static/get_modality_num.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/demo/gmai_vl_demo/static/get_modality_num.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d8fd42d109d9939"}},{"code_sha256_prefix":"9356d2ed9b73134b","entry":"get_peft_model_state_dict","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/model/utils.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9356d2ed9b73134b"}},{"code_sha256_prefix":"501a90fb110e541b","entry":"load_json","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"demo/gmai_vl_demo/static/get_modality_num.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/demo/gmai_vl_demo/static/get_modality_num.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"501a90fb110e541b"}},{"code_sha256_prefix":"5fa73aa676ca240b","entry":"parse_samed2d_name","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"demo/gmai_vl_demo/static/get_modality_num.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/demo/gmai_vl_demo/static/get_modality_num.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5fa73aa676ca240b"}},{"code_sha256_prefix":"a0a407c2a1c1f7d3","entry":"reduce_mean","repo":"uni-medical/gmai-vl","repo_kind":"official","path":"xtuner/model/reward.py","file_url":"https://github.com/uni-medical/gmai-vl/blob/HEAD/xtuner/model/reward.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0a407c2a1c1f7d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}