{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:06:42Z","timestamp":1783123602910,"version":"3.54.6"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82261138629,12326610,B0166"],"award-info":[{"award-number":["82261138629,12326610,B0166"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02109","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22718-22727","source":"Crossref","is-referenced-by-count":4,"title":["WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image"],"prefix":"10.1109","author":[{"given":"Yuci","family":"Liang","sequence":"first","affiliation":[{"name":"Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinheng","family":"Lyu","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenting","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meidan","family":"Ding","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[{"name":"University of Nottingham Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Xing","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Publicly available clinical bert embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1128\/jcm.00986-22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_51"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00484"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Who classification of tumours, breast tumours","author":"Dilani","year":"2019","journal-title":"Lyon: International Agency for Research on Cancer"},{"key":"ref8","article-title":"Longnet: Scaling transformers to 1,000,000,000 tokens","author":"Ding","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.711"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2147\/PLMI.S59826"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19209-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_18"},{"key":"ref13","article-title":"Pathvqa: 30000 questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.540"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s44222-025-00279-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2022.07.012"},{"key":"ref18","article-title":"A foundational multimodal vision language ai assistant for human pathology","author":"Ming","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Wsi-agents: A collaborative multi-agent system for multi-modal whole slide image analysis","author":"Lyu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08869-4"},{"key":"ref21","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"962","article-title":"Pathologybert-pre-trained vs. a new transformer language model for pathology domain","volume-title":"AMIA annual symposium proceedings","author":"Santos","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2024-205413"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2016.01.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"ref26","article-title":"Prism: A multi-modal generative foundation model for slide-level histopathology","author":"Shaikovski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102645"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07894-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2764"},{"key":"ref30","article-title":"Pathinsight: Instruction tuning of multimodal datasets and models for intelligence assisted diagnosis in histopathology","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08378-w"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1524-4741.2007.00393.x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445209.pdf?arnumber=11445209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:32:53Z","timestamp":1777530773000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02109","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}