{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T02:24:39Z","timestamp":1778725479927,"version":"3.51.4"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720857","type":"print"},{"value":"9783031720864","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72086-4_11","type":"book-chapter","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:34:45Z","timestamp":1727987685000},"page":"112-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Can LLMs\u2019 Tuning Methods Work in\u00a0Medical Multimodal Domain?"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yue","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jinjie","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Ziyun","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"11_CR1","first-page":"1877","volume":"33","author":"Language models are few-shot learners","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, et\u00a0al.: Language models are few-shot learners. Advances in neural information processing systems 33, 1877\u20131901 (2020)","journal-title":"Advances in neural information processing systems"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Yang, D., Jiang, Y., Li, M., Wei, J., Hou, X., Zhang, L.: Efficiency in focus: Layernorm as a catalyst for fine-tuning medical visual language pre-trained models. arXiv preprint arXiv:2404.16385 (2024)","DOI":"10.1145\/3664647.3680834"},{"key":"11_CR3","unstructured":"Chen, J., Yang, D., Jiang, Y., et\u00a0al.: Miss: A generative pretraining and finetuning approach for med-vqa. arXiv preprint arXiv:2401.05163 (2024)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Du, Y., Hu, et\u00a0al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: MICCAI. pp. 679\u2013689. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Cong, F., Xu, S., et\u00a0al.: Caption-aware medical vqa via semantic focusing and progressive cross-modality comprehension. In: ACM MM. pp. 3569\u20133577 (2022)","DOI":"10.1145\/3503161.3548122"},{"key":"11_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, et\u00a0al.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"11_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR8","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, et\u00a0al.: Parameter-efficient transfer learning for nlp. In: International Conference on Machine Learning. pp. 2790\u20132799. PMLR (2019)"},{"key":"11_CR9","unstructured":"Hu, E.J., Shen, et\u00a0al.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, et\u00a0al.: A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5(1), 1\u201310 (2018)","DOI":"10.1038\/sdata.2018.251"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"11_CR12","unstructured":"Li, C., Wong, C., Zhang, et\u00a0al.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"11_CR13","unstructured":"Li, J., Li, D., Xiong, et\u00a0al.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICCV. pp. 12888\u201312900 (2022)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., He, et\u00a0al.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: MICCAI. pp. 374\u2013383. Springer (2023)","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, et\u00a0al.: Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 ISBI. pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"11_CR17","unstructured":"Liu, H., Tam, D., Muqeeth, et\u00a0al.: Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems 35, 1950\u20131965 (2022)"},{"key":"11_CR18","unstructured":"Liu, H., Li, C., Wu, et\u00a0al.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"11_CR19","unstructured":"Liu, S.Y., Wang, C.Y., Yin, H., Molchanov, P., Wang, Y.C.F., Cheng, K.T., Chen, M.H.: Dora: Weight-decomposed low-rank adaptation. arXiv preprint arXiv:2402.09353 (2024)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Ji, K., Fu, Y., Tam, et\u00a0al.: P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Liu, X., Zheng, Y., Du, Z., Ding, et\u00a0al.: Gpt understands, too. AI Open (2023)","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"11_CR22","unstructured":"Radford, A., Kim, J.W., Hallacy, et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR23","unstructured":"Vaswani, A., Shazeer, N., Parmar, et\u00a0al.: Attention is all you need. NIPS 30 (2017)"},{"key":"11_CR24","unstructured":"Wei, J., Bosma, M., Zhao, V.Y., Guu, et\u00a0al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"11_CR25","unstructured":"Zhang, R., Han, J., Zhou, A., Hu, X., Yan, S., Lu, P., Li, H., Gao, P., Qiao, Y.: Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"11_CR26","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72086-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T02:27:07Z","timestamp":1732847227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72086-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720857","9783031720864"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72086-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 October 2024","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":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}