{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:16:05Z","timestamp":1776888965577,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680834","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3122-3130","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7664-8582","authenticated-orcid":false,"given":"Jiawei","family":"Chen","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-5671","authenticated-orcid":false,"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0267-672X","authenticated-orcid":false,"given":"Yue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6244-6081","authenticated-orcid":false,"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2636-4220","authenticated-orcid":false,"given":"Jinjie","family":"Wei","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1054-419X","authenticated-orcid":false,"given":"Xiaolu","family":"Hou","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-4347","authenticated-orcid":false,"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"CIT Lab, Institute of Meta-Medical, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tom Brown Benjamin Mann Ryder et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_2_1","volume-title":"Can LLMs' Tuning Methods Work in Medical Multimodal Domain? arXiv preprint arXiv:2403.06407","author":"Chen Jiawei","year":"2024","unstructured":"Jiawei Chen, Yue Jiang, Dingkang Yang, Mingcheng Li, Jinjie Wei, Ziyun Qian, and Lihua Zhang. 2024. Can LLMs' Tuning Methods Work in Medical Multimodal Domain? arXiv preprint arXiv:2403.06407 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"MISS: A Generative Pretraining and Finetuning Approach for Med-VQA. arXiv preprint arXiv:2401.05163","author":"Chen Jiawei","year":"2024","unstructured":"Jiawei Chen, Dingkang Yang, Yue Jiang, et al. 2024. MISS: A Generative Pretraining and Finetuning Approach for Med-VQA. arXiv preprint arXiv:2401.05163 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Zhihong Chen Yuhao Du Hu et al. 2022. Multi-modal masked autoencoders for medical vision-and-language pre-training. In MICCAI. Springer 679--689.","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"e_1_3_2_1_5_1","volume-title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv","author":"Dai W","year":"2023","unstructured":"W Dai, J Li, D Li, AMH Tiong, J Zhao, W Wang, B Li, P Fung, and S Hoi. [n.,d.]. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv 2023. arXiv preprint arXiv:2305.06500 ( [n.,d.])."},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Lee, et al. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Tuong Do Binh X. Nguyen et al. 2021. Multiple Meta-model Quantifying for Medical Visual Question Answering. In MICCAI. Cham 64--74.","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"e_1_3_2_1_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3185008"},{"key":"e_1_3_2_1_10_1","volume-title":"Sai Qian Zhang, et al","author":"Han Zeyu","year":"2024","unstructured":"Zeyu Han, Chao Gao, Jinyang Liu, Sai Qian Zhang, et al. 2024. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey. arXiv preprint arXiv:2403.14608 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25160"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Jastrzebski, et al. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_13_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Shen, et al. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00281"},{"key":"e_1_3_2_1_15_1","volume-title":"a de-identified publicly available database of chest radiographs with free-text reports. Scientific data","author":"Johnson Alistair EW","year":"2019","unstructured":"Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, Vol. 6, 1 (2019), 317."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Jason J Lau Gayen et al. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data Vol. 5 1 (2018) 1--10.","DOI":"10.1038\/sdata.2018.251"},{"key":"e_1_3_2_1_17_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Cliff Wong, Zhang, et al. 2023. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICCV. 12888--12900.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Xiong, et al. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICCV. 12888--12900."},{"key":"e_1_3_2_1_21_1","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Gotmare, et al. 2021. Align before fuse: Vision and language representation learning with momentum distillation. NIPS, Vol. 34 (2021), 9694--9705.","journal-title":"NIPS"},{"key":"e_1_3_2_1_22_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"e_1_3_2_1_24_1","volume-title":"Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In 2021 ISBI. 1650--1654.","author":"Liu Bo","year":"2021","unstructured":"Bo Liu, Li-Ming Zhan, Xu, et al. 2021. Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In 2021 ISBI. 1650--1654."},{"key":"e_1_3_2_1_25_1","unstructured":"Haotian Liu Chunyuan Li Wu et al. 2023. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Kwang-Ting Cheng, and Min-Hung Chen.","author":"Liu Shih-Yang","year":"2024","unstructured":"Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, and Min-Hung Chen. 2024. DoRA: Weight-Decomposed Low-Rank Adaptation. arXiv preprint arXiv:2402.09353 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Xiao Liu Yanan Zheng Zhengxiao Du Ding et al. 2023. GPT understands too. AI Open (2023).","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Binh D. Nguyen Thanh-Toan Do Binh X Nguyen et al. 2019. Overcoming Data Limitation in Medical Visual Question Answering. In MICCAI. Cham 522--530.","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Hallacy, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_30_1","volume-title":"Lucy Lu Wang et al","author":"Sanjay Subramanian Sachin Mehta","year":"2020","unstructured":"Sachin Mehta Sanjay Subramanian, Lucy Lu Wang et al. 2020. MedICaT: A Dataset of Medical Images, Captions, and Textual References. In Findings of EMNLP."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_32_1","volume-title":"Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Jorma Laaksonen, and Fahad Shahbaz Khan.","author":"Thawkar Omkar","year":"2023","unstructured":"Omkar Thawkar, Abdelrahman Shaker, Sahal Shaji Mullappilly, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Jorma Laaksonen, and Fahad Shahbaz Khan. 2023. Xraygpt: Chest radiographs summarization using medical vision-language models. arXiv preprint arXiv:2306.07971 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Haixin","year":"2024","unstructured":"Haixin Wang, Xinlong Yang, Jianlong Chang, Dian Jin, Jinan Sun, Shikun Zhang, Xiao Luo, and Qi Tian. 2024. Parameter-efficient tuning of large-scale multimodal foundation model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_3_2_1_35_1","volume-title":"Xiaohui Tao, and Fu Lee Wang.","author":"Xu Lingling","year":"2023","unstructured":"Lingling Xu, Haoran Xie, Si-Zhao Joe Qin, Xiaohui Tao, and Fu Lee Wang. 2023. Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment. arXiv preprint arXiv:2312.12148 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"The expressive power of low-rank adaptation. arXiv preprint arXiv:2310.17513","author":"Zeng Yuchen","year":"2023","unstructured":"Yuchen Zeng and Kangwook Lee. 2023. The expressive power of low-rank adaptation. arXiv preprint arXiv:2310.17513 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Jiaming Han, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Peng Gao, and Yu Qiao. 2023. Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Tuning LayerNorm in Attention: Towards efficient multi-modal llm finetuning. arXiv preprint arXiv:2312.11420","author":"Zhao Bingchen","year":"2023","unstructured":"Bingchen Zhao, Haoqin Tu, Chen Wei, Jieru Mei, and Cihang Xie. 2023. Tuning LayerNorm in Attention: Towards efficient multi-modal llm finetuning. arXiv preprint arXiv:2312.11420 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680834","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":39,"alternative-id":["10.1145\/3664647.3680834","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680834","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}