{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:09:13Z","timestamp":1765343353908,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"Noncommunicable Chronic Diseases-National Science and Technology Major Project","award":["No. 2024ZD0522702"],"award-info":[{"award-number":["No. 2024ZD0522702"]}]},{"name":"Beijing Natural Science Foundation","award":["NO. L251072 and NO. 4252046"],"award-info":[{"award-number":["NO. L251072 and NO. 4252046"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754716","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"2693-2702","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Multi-task Learning Capability of Medical Generalist Foundation Model via Image-centric Multi-annotation Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8598-8748","authenticated-orcid":false,"given":"Xun","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0682-9095","authenticated-orcid":false,"given":"Fanbin","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8899-2360","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2902-4812","authenticated-orcid":false,"given":"Jiaxi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5335-2803","authenticated-orcid":false,"given":"Yiming","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8390-5398","authenticated-orcid":false,"given":"Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Post and Telecommunication, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1115-5580","authenticated-orcid":false,"given":"Chuang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China and Beijing Wuzi University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5672-7448","authenticated-orcid":false,"given":"Miao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6170-726X","authenticated-orcid":false,"given":"Ji","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China and College of AI, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.08.022"},{"key":"e_1_3_2_1_2_1","volume-title":"Minigpt-med: Large language model as a general interface for radiology diagnosis. arXiv preprint arXiv:2407.04106","author":"Alkhaldi Asma","year":"2024","unstructured":"Asma Alkhaldi, Raneem Alnajim, Layan Alabdullatef, Rawan Alyahya, Jun Chen, Deyao Zhu, Ahmed Alsinan, and Mohamed Elhoseiny. 2024. Minigpt-med: Large language model as a general interface for radiology diagnosis. arXiv preprint arXiv:2407.04106 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 694-702","author":"Karakida Ryo","year":"2019","unstructured":"Shun-ichi Amari, Ryo Karakida, and Masafumi Oizumi. 2019. Fisher information and natural gradient learning in random deep networks. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 694-702."},{"key":"e_1_3_2_1_4_1","first-page":"3867","article-title":"Ehrxqa: A multi-modal question answering dataset for electronic health records with chest x-ray images","volume":"36","author":"Bae Seongsu","year":"2023","unstructured":"Seongsu Bae, Daeun Kyung, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric Chang, Tackeun Kim, et al., 2023. Ehrxqa: A multi-modal question answering dataset for electronic health records with chest x-ray images. Advances in Neural Information Processing Systems, Vol. 36 (2023), 3867-3880.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","volume-title":"Max Q-H Meng, and Bo Zhao","author":"Bai Fan","year":"2024","unstructured":"Fan Bai, Yuxin Du, Tiejun Huang, Max Q-H Meng, and Bo Zhao. 2024. M3d: Advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578 (2024)."},{"key":"e_1_3_2_1_6_1","unstructured":"Juan Manuel Zambrano Chaves Shih-Cheng Huang Yanbo Xu Hanwen Xu Naoto Usuyama Sheng Zhang Fei Wang Yujia Xie Mahmoud Khademi Ziyi Yang et al. 2024. Training small multimodal models to bridge biomedical competency gap: A case study in radiology imaging. CoRR (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 2404-2420","author":"Chen Qiuhui","year":"2024","unstructured":"Qiuhui Chen and Yi Hong. 2024. Medblip: Bootstrapping language-image pre-training from 3d medical images and texts. In Proceedings of the Asian Conference on Computer Vision. 2404-2420."},{"key":"e_1_3_2_1_8_1","volume-title":"Dia-LLaMA: Towards large language model-driven ct report generation. arXiv preprint arXiv:2403.16386","author":"Chen Zhixuan","year":"2024","unstructured":"Zhixuan Chen, Luyang Luo, Yequan Bie, and Hao Chen. 2024a. Dia-LLaMA: Towards large language model-driven ct report generation. arXiv preprint arXiv:2403.16386 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Jeya Maria Jose Valanarasu, Alaa Youssef, Joseph Paul Cohen, Eduardo Pontes Reis, et al.","author":"Chen Zhihong","year":"2024","unstructured":"Zhihong Chen, Maya Varma, Jean-Benoit Delbrouck, Magdalini Paschali, Louis Blankemeier, Dave Van Veen, Jeya Maria Jose Valanarasu, Alaa Youssef, Joseph Paul Cohen, Eduardo Pontes Reis, et al., 2024b. Chexagent: Towards a foundation model for chest x-ray interpretation. arXiv preprint arXiv:2401.12208 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12053-4_2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"e_1_3_2_1_12_1","series-title":"Series A, containing papers of a mathematical or physical character","volume-title":"On the mathematical foundations of theoretical statistics. Philosophical transactions of the Royal Society of London","author":"Fisher Ronald A","year":"1922","unstructured":"Ronald A Fisher. 1922. On the mathematical foundations of theoretical statistics. Philosophical transactions of the Royal Society of London. Series A, containing papers of a mathematical or physical character, Vol. 222, 594-604 (1922), 309-368."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03358-1"},{"key":"e_1_3_2_1_14_1","volume-title":"Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley.","author":"Goldberger Ary L","year":"2000","unstructured":"Ary L Goldberger, Luis AN Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, Vol. 101, 23 (2000), e215-e220."},{"key":"e_1_3_2_1_15_1","volume-title":"X-ray: Overview of the CXR-LT challenge. Medical Image Analysis","author":"Holste Gregory","year":"2024","unstructured":"Gregory Holste, Yiliang Zhou, Song Wang, Ajay Jaiswal, Mingquan Lin, Sherry Zhuge, Yuzhe Yang, Dongkyun Kim, Trong-Hieu Nguyen-Mau, Minh-Triet Tran, et al., 2024. Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge. Medical Image Analysis (2024), 103224."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021190228"},{"key":"e_1_3_2_1_17_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_18_1","volume-title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine. arXiv preprint arXiv:2412.09278","author":"Huang Xiaoshuang","year":"2024","unstructured":"Xiaoshuang Huang, Lingdong Shen, Jia Liu, Fangxin Shang, Hongxiang Li, Haifeng Huang, and Yehui Yang. 2024. Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine. arXiv preprint arXiv:2412.09278 (2024)."},{"key":"e_1_3_2_1_19_1","unstructured":"Stephanie L Hyland Shruthi Bannur Kenza Bouzid Daniel C Castro Mercy Ranjit Anton Schwaighofer Fernando P\u00e9rez-Garc\u00eda Valentina Salvatelli Shaury Srivastav Anja Thieme et al. 2023. Maira-1: A specialised large multimodal model for radiology report generation. arXiv preprint arXiv:2311.13668 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042","author":"Johnson Alistair EW","year":"2019","unstructured":"Alistair EW Johnson, Tom J Pollard, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Yifan Peng, Zhiyong Lu, Roger G Mark, Seth J Berkowitz, and Steven Horng. 2019. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 1032-1041","author":"Karakida Ryo","year":"2019","unstructured":"Ryo Karakida, Shotaro Akaho, and Shun-ichi Amari. 2019. Universal statistics of fisher information in deep neural networks: Mean field approach. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 1032-1041."},{"key":"e_1_3_2_1_22_1","volume-title":"Jinho Chang, and Jong Chul Ye.","author":"Lee Suhyeon","year":"2023","unstructured":"Suhyeon Lee, Won Jun Kim, Jinho Chang, and Jong Chul Ye. 2023. LLM-CXR: instruction-finetuned LLM for CXR image understanding and generation. arXiv preprint arXiv:2305.11490 (2023)."},{"key":"e_1_3_2_1_23_1","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems, Vol. 36 (2023), 28541-28564.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57426-0"},{"key":"e_1_3_2_1_25_1","volume-title":"M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI. arXiv preprint arXiv:2411.14522","author":"Li Tianbin","year":"2024","unstructured":"Tianbin Li, Yanzhou Su, Wei Li, Bin Fu, Zhe Chen, Ziyan Huang, Guoan Wang, Chenglong Ma, Ying Chen, Ming Hu, et al., 2024a. GMAI-VL & GMAI-VL-5.5 M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI. arXiv preprint arXiv:2411.14522 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"That Is the Question: A Survey on Large Multi-Modal Models from the Perspective of Input-Output Space Extension.","author":"Li Zejun","year":"2024","unstructured":"Zejun Li, Jiwen Zhang, Dianyi Wang, Ye Wang, Xuanjing Huang, and Zhongyu Wei. 2024b. Continuous or Discrete, That Is the Question: A Survey on Large Multi-Modal Models from the Perspective of Input-Output Space Extension. (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"e_1_3_2_1_28_1","volume-title":"Has multimodal learning delivered universal intelligence in healthcare? A comprehensive survey. Information Fusion","author":"Lin Qika","year":"2024","unstructured":"Qika Lin, Yifan Zhu, Xin Mei, Ling Huang, Jingying Ma, Kai He, Zhen Peng, Erik Cambria, and Mengling Feng. 2024. Has multimodal learning delivered universal intelligence in healthcare? A comprehensive survey. Information Fusion (2024), 102795."},{"key":"e_1_3_2_1_29_1","unstructured":"Tianwei Lin Wenqiao Zhang Sijing Li Yuqian Yuan Binhe Yu Haoyuan Li Wanggui He Hao Jiang Mengze Li Xiaohui Song et al. 2025. HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation. arXiv preprint arXiv:2502.09838 (2025)."},{"key":"e_1_3_2_1_30_1","volume-title":"A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis. arXiv preprint arXiv:2411.16778","author":"Liu Bo","year":"2024","unstructured":"Bo Liu, Ke Zou, Liming Zhan, Zexin Lu, Xiaoyu Dong, Yidi Chen, Chengqiang Xie, Jiannong Cao, Xiao-Ming Wu, and Huazhu Fu. 2024. GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis. arXiv preprint arXiv:2411.16778 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/ab5d4d"},{"key":"e_1_3_2_1_33_1","volume-title":"Richard J Chen, Kenji Ikamura, Georg Gerber, Ivy Liang, Long Phi Le, Tong Ding, Anil V Parwani, et al.","author":"Lu Ming Y","year":"2023","unstructured":"Ming Y Lu, Bowen Chen, Drew FK Williamson, Richard J Chen, Kenji Ikamura, Georg Gerber, Ivy Liang, Long Phi Le, Tong Ding, Anil V Parwani, et al., 2023. A foundational multimodal vision language AI assistant for human pathology. arXiv preprint arXiv:2312.07814 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2017.05.006"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"New insights and perspectives on the natural gradient method","volume":"21","author":"Martens James","year":"2020","unstructured":"James Martens. 2020. New insights and perspectives on the natural gradient method. Journal of Machine Learning Research, Vol. 21, 146 (2020), 1-76.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_36_1","first-page":"259","volume-title":"Nature","volume":"616","author":"Moor Michael","year":"2023","unstructured":"Michael Moor, Oishi Banerjee, Zahra Shakeri Hossein Abad, Harlan M Krumholz, Jure Leskovec, Eric J Topol, and Pranav Rajpurkar. 2023a. Foundation models for generalist medical artificial intelligence. Nature, Vol. 616, 7956 (2023), 259-265."},{"key":"e_1_3_2_1_37_1","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner. In Machine Learning for Health (ML4H)","author":"Moor Michael","year":"2023","unstructured":"Michael Moor, Qian Huang, Shirley Wu, Michihiro Yasunaga, Yash Dalmia, Jure Leskovec, Cyril Zakka, Eduardo Pontes Reis, and Pranav Rajpurkar. 2023b. Med-flamingo: a multimodal medical few-shot learner. In Machine Learning for Health (ML4H). PMLR, 353-367.","journal-title":"PMLR"},{"key":"e_1_3_2_1_38_1","volume-title":"Radialog: A large vision-language model for radiology report generation and conversational assistance. arXiv preprint arXiv:2311.18681","author":"Pellegrini Chantal","year":"2023","unstructured":"Chantal Pellegrini, Ege \u00d6zsoy, Benjamin Busam, Nassir Navab, and Matthias Keicher. 2023. Radialog: A large vision-language model for radiology report generation and conversational assistance. arXiv preprint arXiv:2311.18681 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225","author":"Rajpurkar Pranav","year":"2017","unstructured":"Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, et al., 2017. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"MedM-VL: What Makes a Good Medical LVLM? arXiv preprint arXiv:2504.04323","author":"Shi Yiming","year":"2025","unstructured":"Yiming Shi, Shaoshuai Yang, Xun Zhu, Haoyu Wang, Miao Li, and Ji Wu. 2025. MedM-VL: What Makes a Good Medical LVLM? arXiv preprint arXiv:2504.04323 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28308"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"e_1_3_2_1_43_1","volume-title":"High-performance medicine: the convergence of human and artificial intelligence. Nature medicine","author":"Topol Eric J","year":"2019","unstructured":"Eric J Topol. 2019. High-performance medicine: the convergence of human and artificial intelligence. Nature medicine, Vol. 25, 1 (2019), 44-56."},{"key":"e_1_3_2_1_44_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300138"},{"key":"e_1_3_2_1_46_1","volume-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. arXiv preprint arXiv:2308.02463","author":"Wu Chaoyi","year":"2023","unstructured":"Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. arXiv preprint arXiv:2308.02463 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"Yunfei Xie Ce Zhou Lang Gao Juncheng Wu Xianhang Li Hong-Yu Zhou Sheng Liu Lei Xing James Zou Cihang Xie et al. 2024. Medtrinity-25m: A large-scale multimodal dataset with multigranular annotations for medicine. arXiv preprint arXiv:2408.02900 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"e_1_3_2_1_49_1","unstructured":"Kai Zhang Rong Zhou Eashan Adhikarla Zhiling Yan Yixin Liu Jun Yu Zhengliang Liu Xun Chen Brian D Davison Hui Ren et al. 2024b. A generalist vision-language foundation model for diverse biomedical tasks. Nature Medicine (2024) 1-13."},{"key":"e_1_3_2_1_50_1","volume-title":"Radgenome-chest ct: A grounded vision-language dataset for chest ct analysis. arXiv preprint arXiv:2404.16754","author":"Zhang Xiaoman","year":"2024","unstructured":"Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Jiayu Lei, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2024a. Radgenome-chest ct: A grounded vision-language dataset for chest ct analysis. arXiv preprint arXiv:2404.16754 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50043-3"},{"key":"e_1_3_2_1_52_1","volume-title":"Uni-med: a unified medical generalist foundation model for multi-task learning via connector-MoE. arXiv preprint arXiv:2409.17508","author":"Zhu Xun","year":"2024","unstructured":"Xun Zhu, Ying Hu, Fanbin Mo, Miao Li, and Ji Wu. 2024. Uni-med: a unified medical generalist foundation model for multi-task learning via connector-MoE. arXiv preprint arXiv:2409.17508 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:32Z","timestamp":1765343072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3754716","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754716","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}