{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:13:14Z","timestamp":1770271994968,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"the National Key R&D Program of China","award":["2024YFB4105200"],"award-info":[{"award-number":["2024YFB4105200"]}]},{"name":"the National Natural Science Foundation of China","award":["62473384, 62473385, U24A20256, 62202499"],"award-info":[{"award-number":["62473384, 62473385, U24A20256, 62202499"]}]},{"name":"the Beijing Municipal Natural Science Foundation","award":["L231012"],"award-info":[{"award-number":["L231012"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754917","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"7500-7509","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4223-7717","authenticated-orcid":false,"given":"Haojie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0407-5838","authenticated-orcid":false,"given":"Yixiong","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7341-9871","authenticated-orcid":false,"given":"Hulin","family":"Kuang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-4818","authenticated-orcid":false,"given":"Lihui","family":"Cen","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-2137","authenticated-orcid":false,"given":"Zhe","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-9422","authenticated-orcid":false,"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1726-0955","authenticated-orcid":false,"given":"Min","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-6196","authenticated-orcid":false,"given":"Shichao","family":"Kan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00201"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"e_1_3_2_1_8_1","volume-title":"PathVQA: 30000 Questions for Medical Visual Question Answering. arXiv preprint arXiv:2003.10286","author":"He Xuehai","year":"2020","unstructured":"Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, and Pengtao Xie. 2020. PathVQA: 30000 Questions for Medical Visual Question Answering. arXiv preprint arXiv:2003.10286 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790-2799."},{"key":"e_1_3_2_1_10_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, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01141"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00281"},{"key":"e_1_3_2_1_13_1","volume-title":"HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models. In The Thirteenth International Conference on Learning Representations.","author":"Huang Qiushi","year":"2025","unstructured":"Qiushi Huang, Tom Ko, Zhan Zhuang, Lilian Tang, and Yu Zhang. 2025. HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_16_1","volume-title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning. arXiv preprint arXiv:2502.11019","author":"Jiang Gangwei","year":"2025","unstructured":"Gangwei Jiang, Caigao Jiang, Zhaoyi Li, Siqiao Xue, Jun Zhou, Linqi Song, Defu Lian, and Yin Wei. 2025. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning. arXiv preprint arXiv:2502.11019 (2025)."},{"key":"e_1_3_2_1_17_1","volume-title":"Huiying Liang, Sally L Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, et al.","author":"Kermany Daniel S","year":"2018","unstructured":"Daniel S Kermany, Michael Goldbaum, Wenjia Cai, Carolina CS Valentim, Huiying Liang, Sally L Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, et al., 2018. Identifying medical diagnoses and treatable diseases by image-based deep learning. cell, Vol. 172, 5 (2018), 1122-1131."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106414"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_20_1","volume-title":"Asma Ben Abacha, and Dina Demner-Fushman","author":"Lau Jason J","year":"2018","unstructured":"Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data, Vol. 5, 1 (2018), 1-10."},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Li Chunyuan","year":"2024","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2024. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR","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. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Youwei Liang Han Guo and Pengtao Xie. 2023. XrayChat: Towards Enabling ChatGPT-Like Capabilities on Chest X-ray Images. (2023).","DOI":"10.36227\/techrxiv.22945922"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02231"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"e_1_3_2_1_27_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Class incremental learning with pre-trained vision-language models. arXiv preprint arXiv:2310.20348","author":"Liu Xialei","year":"2023","unstructured":"Xialei Liu, Xusheng Cao, Haori Lu, Jia-wen Xiao, Andrew D Bagdanov, and Ming-Ming Cheng. 2023. Class incremental learning with pre-trained vision-language models. arXiv preprint arXiv:2310.20348 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Gradient episodic memory for continual learning. Advances in neural information processing systems","author":"Lopez-Paz David","year":"2017","unstructured":"David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_30_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00250"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_34_1","volume-title":"Christopher Kanan, and Stefan Wermter.","author":"Parisi German I","year":"2019","unstructured":"German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. 2019. Continual lifelong learning with neural networks: A review. Neural networks, Vol. 113 (2019), 54-71."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1803"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 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_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_2_1_38_1","volume-title":"Gradient Projection Memory for Continual Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=3AOj0RCNC2","author":"Saha Gobinda","year":"2021","unstructured":"Gobinda Saha, Isha Garg, and Kaushik Roy. 2021. Gradient Projection Memory for Continual Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=3AOj0RCNC2"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"e_1_3_2_1_40_1","volume-title":"Joost Van de Weijer, and Bartl\u00f8miej Twardowski","author":"Soutif-Cormerais Albin","year":"2021","unstructured":"Albin Soutif-Cormerais, Marc Masana, Joost Van de Weijer, and Bartl\u00f8miej Twardowski. 2021. On the importance of cross-task features for class-incremental learning. arXiv preprint arXiv:2106.11930, Vol. 1 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Pathasst: Redefining pathology through generative foundation ai assistant for pathology. arXiv preprint arXiv:2305.15072","author":"Sun Yuxuan","year":"2023","unstructured":"Yuxuan Sun, Chenglu Zhu, Sunyi Zheng, Kai Zhang, Zhongyi Shui, Xiaoxuan Yu, Yizhi Zhao, Honglin Li, Yunlong Zhang, Ruojia Zhao, et al., 2023. Pathasst: Redefining pathology through generative foundation ai assistant for pathology. arXiv preprint arXiv:2305.15072 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_43_1","volume-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data. 2018","author":"Tschandl Philipp","year":"1801","unstructured":"Philipp Tschandl, Cliff Rosendahl, and Harald Kittler. 2018. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data. 2018; 5: 180161. Search in, Vol. 2 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2300138"},{"key":"e_1_3_2_1_45_1","first-page":"210","volume-title":"Granada","author":"Veeling Bastiaan S","year":"2018","unstructured":"Bastiaan S Veeling, Jasper Linmans, Jim Winkens, Taco Cohen, and Max Welling. 2018. Rotation equivariant CNNs for digital pathology. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11. Springer, 210-218."},{"key":"e_1_3_2_1_46_1","volume-title":"A comprehensive survey of continual learning: theory, method and application","author":"Wang Liyuan","year":"2024","unstructured":"Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. 2024. A comprehensive survey of continual learning: theory, method and application. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning. In The Thirteenth International Conference on Learning Representations.","author":"Wu Yichen","unstructured":"Yichen Wu, Hongming Piao, Long-Kai Huang, Renzhen Wang, Wanhua Li, Hanspeter Pfister, Deyu Meng, Kede Ma, and Ying Wei. [n.d.]. SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"e_1_3_2_1_49_1","volume-title":"International conference on machine learning. PMLR, 3987-3995","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In International conference on machine learning. PMLR, 3987-3995."},{"key":"e_1_3_2_1_50_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. 2024. A generalist vision-language foundation model for diverse biomedical tasks. Nature Medicine (2024) 1-13."},{"key":"e_1_3_2_1_51_1","volume-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Nikos Karampatziakis, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023. AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0052-1"},{"key":"e_1_3_2_1_54_1","unstructured":"Juexiao Zhou Xiaonan He Liyuan Sun Jiannan Xu Xiuying Chen Yuetan Chu Longxi Zhou Xingyu Liao Bin Zhang and Xin Gao. 2023. SkinGPT-4: an interactive dermatology diagnostic system with visual large language model. (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_57_1","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou Yanqi","year":"2022","unstructured":"Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du, Yanping Huang, Vincent Zhao, Andrew M Dai, Quoc V Le, James Laudon, et al., 2022a. Mixture-of-experts with expert choice routing. Advances in Neural Information Processing Systems, Vol. 35 (2022), 7103-7114.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_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 '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T05:45:09Z","timestamp":1769406309000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3754917","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754917","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"}}]}}