{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:35:25Z","timestamp":1770845725991,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFC3308304"],"award-info":[{"award-number":["2024YFC3308304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476241"],"award-info":[{"award-number":["62476241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LZ23F020008"],"award-info":[{"award-number":["LZ23F020008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1109\/bibm66473.2025.11357141","type":"proceedings-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:19:40Z","timestamp":1769721580000},"page":"865-871","source":"Crossref","is-referenced-by-count":0,"title":["Med-GLIP: Advancing Medical Language-Image Pre-Training with Large-Scale Grounded Dataset"],"prefix":"10.1109","author":[{"given":"Ziye","family":"Deng","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihan","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Intelligence Science and Technology,Zhuhai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijie","family":"Meng","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songtao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuozhu","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref2","article-title":"Medrg: Medical report grounding with multi-modal large language model","author":"Zou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.221"},{"key":"ref5","article-title":"Medmoe: Mixture of domain-specific experts for lightweight medical visionlanguage models","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Omniv-med: Scaling medical vision-language model for universal visual understanding","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Hulu-med: A transparent generalist model towards holistic medical vision-language understanding","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00641"},{"key":"ref10","article-title":"R-llava: Improving med-vqa understanding through visual region of interest","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Fair-moe: Fairnessoriented mixture of experts in vision-language models","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Joint visual and text prompting for improved object-centric perception with multimodal large language models","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04971-1_62"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.962"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.583"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3311333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34075"},{"key":"ref18","volume-title":"Med-u1: Incentivizing unified medical reasoning in llms via large-scale reinforcement learning","author":"Zhang","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2025.3531360"},{"key":"ref21","article-title":"Tsnet: Integrating dental position prior and symptoms for tooth segmentation from cbct images","author":"Tong","year":"2023","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100825"},{"key":"ref23","article-title":"Medtrinity-25m: A large-scale multimodal dataset with multigranular annotations for medicine","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1148\/rg.220098"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref31","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01941"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref36","article-title":"Pathvqa: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.00968","volume-title":"Enhanced contrastive learning with multi-view longitudinal data for chest x-ray report generation","author":"Liu","year":"2025"},{"key":"ref39","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"event":{"name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Wuhan, China","start":{"date-parts":[[2025,12,15]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11355913\/11355975\/11357141.pdf?arnumber=11357141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:51:31Z","timestamp":1770843091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11357141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/bibm66473.2025.11357141","relation":{},"subject":[],"published":{"date-parts":[[2025,12,15]]}}}