{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T13:32:22Z","timestamp":1784035942743,"version":"3.55.0"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1109\/bibm66473.2025.11357048","type":"proceedings-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:19:40Z","timestamp":1769721580000},"page":"2754-2759","source":"Crossref","is-referenced-by-count":2,"title":["Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Shi","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s20185097"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1430984"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref5","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref6","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":"ar Xiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref8","article-title":"Tinyllava: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Tinyllava factory: A modularized codebase for small-scale large multimodal models","author":"Jia","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","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":"ref11","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume-title":"Machine Learning for Health (ML4H)","author":"Moor","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref13","article-title":"Gmai-vl & gmai-vl-5.5 m: A large vision-language model and a comprehensive multimodal dataset towards general medical ai","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_6"},{"key":"ref15","article-title":"M3d: Advancing 3d medical image analysis with multi-modal large language models","author":"Bai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Developing generalist foundation models from a multimodal dataset for 3d computed tomography","author":"Hamamci","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"3d-ct-gpt: Generating 3d radiology reports through integration of large vision-language models","author":"Chen","year":"2024","journal-title":"ar Xiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04981-0_14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57426-0"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref22","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"ar Xiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref24","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11357048.pdf?arnumber=11357048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:51:44Z","timestamp":1770843104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11357048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/bibm66473.2025.11357048","relation":{},"subject":[],"published":{"date-parts":[[2025,12,15]]}}}