{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:52Z","timestamp":1777865332344,"version":"3.51.4"},"reference-count":57,"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":["62302354"],"award-info":[{"award-number":["62302354"]}],"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\/iccv51701.2025.01964","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21144-21154","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Liang","sequence":"first","affiliation":[{"name":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Warren Alpert Medical School, Brown University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronghan","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Yang","sequence":"additional","affiliation":[{"name":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume":"abs\/2404.14219","author":"Abdin","year":"2024","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"M3d: Advancing 3d medical image analysis with multi-modal large language models","volume":"abs\/2404.00578","author":"Bai","year":"2024","journal-title":"ArXiv"},{"key":"ref4","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref5","article-title":"Huatuogpt-vision, towards injecting medical visual knowledge into multimodal llms at scale","volume":"abs\/2406.19280","author":"Chen","year":"2024","journal-title":"ArXiv"},{"key":"ref6","article-title":"Cost-effective instruction learning for pathology vision and language analysis","volume":"abs\/2407.17734","author":"Chen","year":"2024","journal-title":"ArXiv"},{"key":"ref7","article-title":"Advancing high resolution vision-language models in biomedicine","volume":"abs\/2406.09454","author":"Chen","year":"2024","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3057"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10821785"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref12","article-title":"Ophglm: Training an ophthalmology large language-and-vision assistant based on instructions and dialogue","volume":"abs\/2306.12174","author":"Gao","year":"2023","journal-title":"ArXiv"},{"key":"ref13","article-title":"Pefomed: Parameter efficient fine-tuning of multimodal large language models for medical imaging","volume":"abs\/2401.02797","author":"He","year":"2024","journal-title":"ArXiv"},{"key":"ref14","article-title":"Pathvqa: 30000+ questions for medical visual question answering","volume":"abs\/2003.10286","author":"He","year":"2020","journal-title":"ArXiv"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","volume":"abs\/2207.12598","author":"Ho","year":"2022","journal-title":"ArXiv"},{"key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","volume":"abs\/2106.09685","author":"Hu","year":"2021","journal-title":"ArXiv"},{"key":"ref17","article-title":"Ciem: Contrastive instruction evaluation method for better instruction tuning","volume":"abs\/2309.02301","author":"Hu","year":"2023","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.221"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01185-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01316"},{"key":"ref24","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"abs\/2306.00890","author":"Li","year":"2023","journal-title":"ArXiv"},{"key":"ref25","article-title":"Self-supervised vision-language pretraining for medical visual question answering","volume":"abs\/2211.13594","author":"Li","year":"2022","journal-title":"ArXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681201"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref31","article-title":"A survey on hallucination in large vision-language models","volume":"abs\/2402.00253","author":"Liu","year":"2024","journal-title":"ArXiv"},{"key":"ref32","article-title":"Negative object presence evaluation (nope) to measure object hallucination in vision-language models","volume":"abs\/2310.05338","author":"Lovenia","year":"2023","journal-title":"ArXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac409"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref35","article-title":"Uncertainty estimation in autoregressive structured prediction","volume-title":"ICLR","author":"Malinin","year":"2021"},{"key":"ref36","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","author":"Moor","year":"2023","journal-title":"Machine Learning for Health@NeurIPS"},{"key":"ref37","article-title":"Gpt-4 technical report","volume-title":"ArXiv","volume":"abs\/2303.08774","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref40","author":"Education","year":"2020","journal-title":"Main page pathology education instructional resource"},{"key":"ref41","author":"Royer","year":"2024","journal-title":"Multimedeval: A benchmark and a toolkit for evaluating medical vision-language models. ArXiv, abs\/2402.09262"},{"key":"ref42","article-title":"Stay on topic with classifier-free guidance","volume":"abs\/2306.17806","author":"Sanchez","year":"2023","journal-title":"ArXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"ref45","article-title":"Cxpmrg-bench: Pre-training and benchmarking for x-ray medical report generation on chexpert plus dataset","volume":"abs\/2410.00379","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref46","article-title":"Towards generalist foundation model for radiology","volume":"abs\/2308.02463","author":"Wu","year":"2023","journal-title":"ArXiv"},{"key":"ref47","article-title":"Cares: A comprehensive benchmark of trustworthiness in medical vision language models","volume":"abs\/2406.06007","author":"Xia","year":"2024","journal-title":"ArXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"ref50","article-title":"Multimodal chatgpt for medical applications: an experimental study of gpt-4v","volume":"abs\/2310.19061","author":"Yan","year":"2023","journal-title":"ArXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611830"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03185-2"},{"key":"ref54","article-title":"Large-scale domainspecific pretraining for biomedical vision-language processing","volume":"abs\/2303.00915","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref55","article-title":"Pmc-vqa: Vi-sual instruction tuning for medical visual question answering","volume":"abs\/2305.10415","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01255"},{"key":"ref57","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume":"abs\/2310.00754","author":"Zhou","year":"2023","journal-title":"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\/11444989.pdf?arnumber=11444989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:25Z","timestamp":1777529845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01964","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}