{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:42Z","timestamp":1777865442239,"version":"3.51.4"},"reference-count":37,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02001","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21547-21556","source":"Crossref","is-referenced-by-count":0,"title":["Constructing Ophthalmic MLLM for Positioning-Diagnosis Collaboration Through Clinical Cognitive Chain Reasoning"],"prefix":"10.1109","author":[{"given":"Xinyao","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diping","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Aptos 2019 blindness detection","year":"2025"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Biomedlm: A 2.7 b parameter language model trained on biomedical text","author":"Bolton","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Gmai-mmbench: A comprehensive multimodal evaluation benchmark towards general medical ai","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref11","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref12","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"Meddr: Diagnosisguided bootstrapping for large-scale medical vision-language learning","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref15","volume-title":"PAPILA","author":"Kovalyk","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03139-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i28.39485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3598734"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000454"},{"key":"ref23","volume-title":"Chatgpt","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300221"},{"key":"ref26","article-title":"Eyeclip: A visual-language foundation model for multi-modal ophthalmic image analysis","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref29","article-title":"Interpretable bilingual multimodal large language model for diverse biomedical tasks","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Common and rare fundus diseases identification using vision-language foundation model with knowledge of over 400 diseases","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_67"},{"key":"ref33","article-title":"Medtrinity- 25 m: A large-scale multimodal dataset with multigranular annotations for medicine","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Vilref: An expert knowledge enabled vision-language retinal foundation model","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.11.7.12"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref37","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11445515.pdf?arnumber=11445515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:33:46Z","timestamp":1777530826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02001","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}