{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:26:12Z","timestamp":1759332372572,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060037","type":"print"},{"value":"9783032060044","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06004-4_29","type":"book-chapter","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:22:07Z","timestamp":1758561727000},"page":"290-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MedM-VL: What Makes a\u00a0Good Medical LVLM?"],"prefix":"10.1007","author":[{"given":"Yiming","family":"Shi","sequence":"first","affiliation":[]},{"given":"Shaoshuai","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xun","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiangling","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ji","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"issue":"9","key":"29_CR2","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","volume":"28","author":"JN Acosta","year":"2022","unstructured":"Acosta, J.N., Falcone, G.J., Rajpurkar, P., Topol, E.J.: Multimodal biomedical ai. Nat. Med. 28(9), 1773\u20131784 (2022)","journal-title":"Nat. Med."},{"key":"29_CR3","unstructured":"Bai, F., Du, Y., Huang, T., Meng, M.Q.H., Zhao, B.: M3d: advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578 (2024)"},{"key":"29_CR4","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"29_CR5","unstructured":"Bai, J., et al.: Qwen-vl: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"29_CR6","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: Vqa-med: overview of the medical visual question answering task at imageclef 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes. 9\u201312 September 2019 (2019)"},{"issue":"06","key":"29_CR7","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1097\/CM9.0000000000003489","volume":"138","author":"Y Bian","year":"2025","unstructured":"Bian, Y., Li, J., Ye, C., Jia, X., Yang, Q.: Artificial intelligence in medical imaging: from task-specific models to large-scale foundation models. Chin. Med. J. 138(06), 651\u2013663 (2025)","journal-title":"Chin. Med. J."},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Hamamci, I.E., et al.: Developing generalist foundation models from a multimodal dataset for 3d computed tomography (2024), https:\/\/arxiv.org\/abs\/2403.17834","DOI":"10.21203\/rs.3.rs-5271327\/v1"},{"key":"29_CR10","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Front. Artif. Intell. 7, 1430984 (2024)","journal-title":"Front. Artif. Intell."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"issue":"1","key":"29_CR12","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","volume":"3","author":"SC Huang","year":"2020","unstructured":"Huang, S.C., Pareek, A., Seyyedi, S., Banerjee, I., Lungren, M.P.: Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digit. Med. 3(1), 136 (2020)","journal-title":"NPJ Digit. Med."},{"key":"29_CR13","unstructured":"Jia, J., et\u00a0al.: Tinyllava factory: a modularized codebase for small-scale large multimodal models. arXiv preprint arXiv:2405.11788 (2024)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Jin, H., Che, H., Lin, Y., Chen, H.: Promptmrg: diagnosis-driven prompts for medical report generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2607\u20132615 (2024)","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"29_CR16","first-page":"28541","volume":"36","author":"C Li","year":"2023","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Adv. Neural. Inf. Process. Syst. 36, 28541\u201328564 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th international symposium on biomedical imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"29_CR18","unstructured":"Liu, G., et al.: Clinically accurate chest x-ray report generation. In: Machine Learning for Healthcare Conference, pp. 249\u2013269. PMLR (2019)"},{"key":"29_CR19","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR20","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"issue":"1","key":"29_CR21","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41746-024-01010-1","volume":"7","author":"T Savage","year":"2024","unstructured":"Savage, T., Nayak, A., Gallo, R., Rangan, E., Chen, J.H.: Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. NPJ Digit. Med. 7(1), 20 (2024)","journal-title":"NPJ Digit. Med."},{"key":"29_CR22","unstructured":"Shi, Y., Zhu, X., Hu, Y., Guo, C., Li, M., Wu, J.: Med-2e3: A 2d-enhanced 3d medical multimodal large language model. arXiv preprint arXiv:2411.12783 (2024)"},{"key":"29_CR23","doi-asserted-by":"publisher","unstructured":"Sopruchi, A., Anguzu, R., University\u00a0II, K.I.: The integration of ai-driven decision support systems in healthcare: enhancements, challenges, and future directions. Idosr J. Comput. Appl. Sci. 9, 17\u201325 (2024). https:\/\/doi.org\/10.59298\/JCAS\/2024\/92.1725","DOI":"10.59298\/JCAS\/2024\/92.1725"},{"key":"29_CR24","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"29_CR25","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Towards generalist foundation model for radiology. arXiv preprint arXiv:2308.02463 (2023)"},{"key":"29_CR26","unstructured":"Yang, A., et\u00a0al.: Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"issue":"1","key":"29_CR27","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","volume":"10","author":"J Yang","year":"2023","unstructured":"Yang, J., et al.: Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification. Sci. Data 10(1), 41 (2023)","journal-title":"Sci. Data"},{"key":"29_CR28","unstructured":"Yang, L., et\u00a0al.: Advancing multimodal medical capabilities of gemini. arXiv preprint arXiv:2405.03162 (2024)"},{"key":"29_CR29","unstructured":"Ye, J., et\u00a0al.: Sa-med2d-20m dataset: segment anything in 2d medical imaging with 20 million masks. arXiv preprint arXiv:2311.11969 (2023)"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"}],"container-title":["Lecture Notes in Computer Science","AI for Clinical Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06004-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:22:16Z","timestamp":1758561736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06004-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9783032060037","9783032060044"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06004-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"22 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CMLLMs","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multimodal Large Language Models in Clinical Practice","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmllms2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clinicalmllms.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}