{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:06:58Z","timestamp":1765339618777,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62441231, 62293542"],"award-info":[{"award-number":["62441231, 62293542"]}]},{"name":"Liaoning Province Science and Technology Plan","award":["2023JH26\/10200016"],"award-info":[{"award-number":["2023JH26\/10200016"]}]},{"name":"Dalian City Science and Technology Innovation Fund","award":["2023JJ11CG001"],"award-info":[{"award-number":["2023JJ11CG001"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LD25F020001"],"award-info":[{"award-number":["LD25F020001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Key R&D Project","award":["2025Z039"],"award-info":[{"award-number":["2025Z039"]}]},{"name":"Research Grant","award":["2024-0011(ZX20240867)"],"award-info":[{"award-number":["2024-0011(ZX20240867)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755359","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"1666-1675","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Regularizing Subspace Redundancy of Low-Rank Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8695-1256","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4156-5417","authenticated-orcid":false,"given":"Haiwen","family":"Diao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8785-7311","authenticated-orcid":false,"given":"Shang","family":"Gao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6758-7407","authenticated-orcid":false,"given":"Jiazuo","family":"Yu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-1654","authenticated-orcid":false,"given":"Jiawen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7856-0495","authenticated-orcid":false,"given":"Shuai","family":"Hao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-3505","authenticated-orcid":false,"given":"Xu","family":"Jia","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-4437","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6005-4989","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeChat Vision, Tencent Inc, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Charles Beattie Joel Z Leibo Denis Teplyashin Tom Ward Marcus Wainwright Heinrich K\u00fcttler Andrew Lefrancq Simon Green V\u00edctor Vald\u00e9s Amir Sadik et al. 2016. Deepmind lab. arXiv:1612.03801 (2016)."},{"volume-title":"Food-101-mining discriminative components with random forests","author":"Bossard Lukas","key":"e_1_3_2_1_2_1","unstructured":"Lukas Bossard, Matthieu Guillaumin, and Luc Van Gool. 2014. Food-101-mining discriminative components with random forests. In ECCV. Springer, 446-461."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell 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_4_1","first-page":"15789","article-title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","author":"Chen Jiacheng","year":"2021","unstructured":"Jiacheng Chen, Hexiang Hu, Hao Wu, Yuning Jiang, and Changhu Wang. 2021. Learning the Best Pooling Strategy for Visual Semantic Embedding. In CVPR. 15789-15798.","journal-title":"CVPR."},{"key":"e_1_3_2_1_5_1","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen Shoufa","year":"2022","unstructured":"Shoufa Chen, Chongjian Ge, Zhan Tong, Jiangliu Wang, Yibing Song, Jue Wang, and Ping Luo. 2022. Adaptformer: Adapting vision transformers for scalable visual recognition. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16664-16678.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Chen Jing Liu Ye Wang Matthew Brand Guanghui Wang Toshiaki Koike-Akino et al. 2024. SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules. arXiv:2403.11887 (2024).","DOI":"10.1109\/CVPRW63382.2024.00804"},{"key":"e_1_3_2_1_7_1","unstructured":"Zhe Chen Yuchen Duan Wenhai Wang Junjun He Tong Lu Jifeng Dai and Yu Qiao. 2023. Vision Transformer Adapter for Dense Predictions. In ICLR."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"e_1_3_2_1_9_1","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi Mircea","year":"2014","unstructured":"Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Sammy Mohamed, and Andrea Vedaldi. 2014. Describing textures in the wild. In CVPR. 3606-3613.","journal-title":"CVPR."},{"key":"e_1_3_2_1_10_1","first-page":"4171","article-title":"BERT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171-4186.","journal-title":"Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_1_11_1","unstructured":"Haiwen Diao Yufeng Cui Xiaotong Li Yueze Wang Huchuan Lu and Xinlong Wang. 2024a. Unveiling Encoder-Free Vision-Language Models. In NeurIPS."},{"key":"e_1_3_2_1_12_1","volume-title":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models. arXiv:2502.06788","author":"Diao Haiwen","year":"2025","unstructured":"Haiwen Diao, Xiaotong Li, Yufeng Cui, Yueze Wang, Haoge Deng, Ting Pan, Wenxuan Wang, Huchuan Lu, and Xinlong Wang. 2025a. EVEv2: Improved Baselines for Encoder-Free Vision-Language Models. arXiv:2502.06788 (2025)."},{"key":"e_1_3_2_1_13_1","first-page":"75","article-title":"SHERL","author":"Diao Haiwen","year":"2025","unstructured":"Haiwen Diao, Bo Wan, Xu Jia, Yunzhi Zhuge, Ying Zhang, Huchuan Lu, and Long Chen. 2025b. SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning. In ECCV. 75-95.","journal-title":"In ECCV."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Haiwen Diao Bo Wan Ying Zhang Xu Jia Huchuan Lu and Long Chen. 2024b. UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory. In CVPR.","DOI":"10.1109\/CVPR52733.2024.02714"},{"key":"e_1_3_2_1_15_1","first-page":"6241","article-title":"GSSF","volume":"33","author":"Diao Haiwen","year":"2024","unstructured":"Haiwen Diao, Ying Zhang, Shang Gao, Jiawen Zhu, Long Chen, and Huchuan Lu. 2024c. GSSF: Generalized Structural Sparse Function for Deep Cross-Modal Metric Learning. TIP, Vol. 33 (2024), 6241-6252.","journal-title":"TIP"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Ning Ding Xingtai Lv Qiaosen Wang Yulin Chen Bowen Zhou Zhiyuan Liu and Maosong Sun. 2023. Sparse Low-rank Adaptation of Pre-trained Language Models. In EMNLP.","DOI":"10.18653\/v1\/2023.emnlp-main.252"},{"key":"e_1_3_2_1_17_1","volume-title":"Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation. arXiv: 2410.22952","author":"Dong Wei","year":"2024","unstructured":"Wei Dong, Yuan Sun, Yiting Yang, Xing Zhang, Zhijun Lin, Qingsen Yan, Haokui Zhang, Peng Wang, Yang Yang, and Hengtao Shen. 2024a. Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation. arXiv: 2410.22952 (2024)."},{"key":"e_1_3_2_1_18_1","first-page":"52548","article-title":"Efficient adaptation of large vision transformer via adapter re-composing","volume":"36","author":"Dong Wei","year":"2023","unstructured":"Wei Dong, Dawei Yan, Zhijun Lin, and Peng Wang. 2023. Efficient adaptation of large vision transformer via adapter re-composing. Advances in Neural Information Processing Systems, Vol. 36 (2023), 52548-52567.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01524"},{"key":"e_1_3_2_1_20_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29096"},{"key":"e_1_3_2_1_23_1","volume-title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters. arXiv: 2110.04544","author":"Gao Peng","year":"2021","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, and Yu Qiao. 2021. CLIP-Adapter: Better Vision-Language Models with Feature Adapters. arXiv: 2110.04544 (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research","author":"Geiger A","year":"2013","unstructured":"A Geiger, P Lenz, C Stiller, and R Urtasun. 2013. Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research (2013), 1-6."},{"key":"e_1_3_2_1_25_1","first-page":"4884","article-title":"Parameter-Efficient Transfer Learning with Diff Pruning","author":"Guo Demi","year":"2021","unstructured":"Demi Guo, Alexander M. Rush, and Yoon Kim. 2021. Parameter-Efficient Transfer Learning with Diff Pruning. In ACL. 4884-4896.","journal-title":"ACL."},{"key":"e_1_3_2_1_26_1","first-page":"11825","article-title":"Sensitivity-aware visual parameter-efficient fine-tuning","author":"He Haoyu","year":"2023","unstructured":"Haoyu He, Jianfei Cai, Jing Zhang, Dacheng Tao, and Bohan Zhuang. 2023. Sensitivity-aware visual parameter-efficient fine-tuning. In ICCV. 11825-11835.","journal-title":"ICCV."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_1_28_1","volume-title":"ICML (Proceedings of Machine Learning Research","volume":"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 ICML (Proceedings of Machine Learning Research, Vol. 97). 2790-2799."},{"key":"e_1_3_2_1_29_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Shibo Jie and Zhi-Hong Deng. 2023. FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer. In AAAI.","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"e_1_3_2_1_32_1","first-page":"2901","article-title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning","author":"Johnson Justin","year":"2017","unstructured":"Justin Johnson, Bharath Hariharan, Laurens Van Der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick. 2017. Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR. 2901-2910.","journal-title":"CVPR."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"e_1_3_2_1_34_1","volume-title":"Kaggle Diabetic Retinopathy Detection. https:\/\/www.kaggle.com\/c\/diabetic-retinopathy-detection Accessed","author":"Kaggle EyePacs","year":"2024","unstructured":"EyePacs Kaggle. 2015. Kaggle Diabetic Retinopathy Detection. https:\/\/www.kaggle.com\/c\/diabetic-retinopathy-detection Accessed: Sep. 12, 2024."},{"key":"e_1_3_2_1_35_1","volume-title":"How to Adapt Your Large-Scale Vision-and-Language Model. openreview","author":"Kim Konwoo","year":"2021","unstructured":"Konwoo Kim, Michael Laskin, Igor Mordatch, and Deepak Pathak. 2021. How to Adapt Your Large-Scale Vision-and-Language Model. openreview (2021)."},{"key":"e_1_3_2_1_36_1","first-page":"554","article-title":"3d object representations for fine-grained categorization","author":"Krause Jonathan","year":"2013","unstructured":"Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3d object representations for fine-grained categorization. In ICCVW. 554-561.","journal-title":"ICCVW."},{"key":"e_1_3_2_1_37_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"e_1_3_2_1_39_1","first-page":"4582","article-title":"Prefix-Tuning","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-Tuning: Optimizing Continuous Prompts for Generation. In ACL. 4582-4597.","journal-title":"Optimizing Continuous Prompts for Generation. In ACL."},{"key":"e_1_3_2_1_40_1","unstructured":"Dongze Lian Daquan Zhou Jiashi Feng and Xinchao Wang. 2022. Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning. In NeurIPS."},{"key":"e_1_3_2_1_41_1","first-page":"9992","article-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In ICCV. IEEE, 9992-10002.","journal-title":"ICCV. IEEE"},{"key":"e_1_3_2_1_42_1","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu Zhuang","year":"2022","unstructured":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. 2022. A convnet for the 2020s. In CVPR. 11976-11986.","journal-title":"CVPR."},{"key":"e_1_3_2_1_43_1","unstructured":"Ilya Loshchilov Frank Hutter et al. 2017. Fixing weight decay regularization in adam. arXiv:1711.05101 Vol. 5 (2017)."},{"key":"e_1_3_2_1_44_1","volume-title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. arXiv: 2104.08860","author":"Luo Huaishao","year":"2021","unstructured":"Huaishao Luo, Lei Ji, Ming Zhong, Yang Chen, Wen Lei, Nan Duan, and Tianrui Li. 2021. CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. arXiv: 2104.08860 (2021)."},{"key":"e_1_3_2_1_45_1","first-page":"1022","article-title":"Compacter","author":"Mahabadi Rabeeh Karimi","year":"2021","unstructured":"Rabeeh Karimi Mahabadi, James Henderson, and Sebastian Ruder. 2021. Compacter: Efficient Low-Rank Hypercomplex Adapter Layers. In NeurIPS. 1022-1035.","journal-title":"Efficient Low-Rank Hypercomplex Adapter Layers. In NeurIPS."},{"key":"e_1_3_2_1_46_1","volume-title":"Fine-grained visual classification of aircraft. arXiv:1306.5151","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_1_47_1","unstructured":"Loic Matthey Irina Higgins Demis Hassabis and Alexander Lerchner. 2017. dsprites: Disentanglement testing sprites dataset."},{"key":"e_1_3_2_1_48_1","volume-title":"NIPS workshop on deep learning and unsupervised feature learning","volume":"2011","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, Andrew Y Ng, et al., 2011. Reading digits in natural images with unsupervised feature learning. In NIPS workshop on deep learning and unsupervised feature learning, Vol. 2011. Granada, 4."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_51_1","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi Omkar M","year":"2012","unstructured":"Omkar M Parkhi, Andrea Vedaldi, Andrew Zisserman, and CV Jawahar. 2012. Cats and dogs. In CVPR. IEEE, 3498-3505.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_52_1","first-page":"8748","volume-title":"ICML","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML, Vol. 139. 8748-8763."},{"key":"e_1_3_2_1_53_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_54_1","first-page":"91","article-title":"Faster R-CNN","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NIPS. 91-99.","journal-title":"Towards Real-Time Object Detection with Region Proposal Networks. In NIPS."},{"key":"e_1_3_2_1_55_1","volume-title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning. In NeurIPS.","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022a. LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning. In NeurIPS."},{"key":"e_1_3_2_1_56_1","first-page":"5217","article-title":"VL-ADAPTER","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022b. VL-ADAPTER: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks. In CVPR. 5217-5227.","journal-title":"Parameter-Efficient Transfer Learning for Vision-and-Language Tasks. In CVPR."},{"volume-title":"Rotation equivariant CNNs for digital pathology","author":"Veeling Bastiaan S","key":"e_1_3_2_1_57_1","unstructured":"Bastiaan S Veeling, Jasper Linmans, Jim Winkens, Taco Cohen, and Max Welling. 2018. Rotation equivariant CNNs for digital pathology. In MICCAI. Springer, 210-218."},{"key":"e_1_3_2_1_58_1","volume-title":"MLAE: Masked LoRA Experts for Parameter-Efficient Fine-Tuning. arXiv:2405.18897","author":"Wang Junjie","year":"2024","unstructured":"Junjie Wang, Guangjing Yang, Wentao Chen, Huahui Yi, Xiaohu Wu, and Qicheng Lao. 2024. MLAE: Masked LoRA Experts for Parameter-Efficient Fine-Tuning. arXiv:2405.18897 (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"Mixture-of-Subspaces in Low-Rank Adaptation. arXiv:2406.11909","author":"Wu Taiqiang","year":"2024","unstructured":"Taiqiang Wu, Jiahao Wang, Zhe Zhao, and Ngai Wong. 2024. Mixture-of-Subspaces in Low-Rank Adaptation. arXiv:2406.11909 (2024)."},{"key":"e_1_3_2_1_60_1","first-page":"3485","article-title":"Sun database: Large-scale scene recognition from abbey to zoo","author":"Xiao Jianxiong","year":"2010","unstructured":"Jianxiong Xiao, James Hays, Krista A Ehinger, Aude Oliva, and Antonio Torralba. 2010. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR. IEEE, 3485-3492.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_61_1","first-page":"5288","article-title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language","author":"Xu Jun","year":"2016","unstructured":"Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In CVPR. 5288-5296.","journal-title":"CVPR."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_63_1","unstructured":"Jiazuo Yu Haomiao Xiong Lu Zhang Haiwen Diao Yunzhi Zhuge Lanqing Hong Dong Wang Huchuan Lu You He and Long Chen. 2024. LLMs Can Evolve Continually on Modality for X-Modal Reasoning. In NeurIPS."},{"key":"e_1_3_2_1_64_1","first-page":"1","article-title":"BitFit","author":"Zaken Elad Ben","year":"2022","unstructured":"Elad Ben Zaken, Yoav Goldberg, and Shauli Ravfogel. 2022. BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models. In ACL. 1-9.","journal-title":"Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models. In ACL."},{"key":"e_1_3_2_1_65_1","volume-title":"Maxim Neumann, Alexey Dosovitskiy, et al.","author":"Zhai Xiaohua","year":"2019","unstructured":"Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, et al., 2019. A large-scale study of representation learning with the visual task adaptation benchmark. arXiv:1910.04867 (2019)."},{"key":"e_1_3_2_1_66_1","volume-title":"Increlora: Incremental parameter allocation method for parameter-efficient fine-tuning. arXiv:2308.12043","author":"Zhang Feiyu","year":"2023","unstructured":"Feiyu Zhang, Liangzhi Li, Junhao Chen, Zhouqiang Jiang, Bowen Wang, and Yiming Qian. 2023b. Increlora: Incremental parameter allocation method for parameter-efficient fine-tuning. arXiv:2308.12043 (2023)."},{"key":"e_1_3_2_1_67_1","unstructured":"Qingru Zhang Minshuo Chen Alexander Bukharin Pengcheng He Yu Cheng Weizhu Chen and Tuo Zhao. 2023a. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. In ICLR."},{"key":"e_1_3_2_1_68_1","volume-title":"Sai Ashish Somayajula, and Pengtao Xie","author":"Zhang Ruiyi","year":"2024","unstructured":"Ruiyi Zhang, Rushi Qiang, Sai Ashish Somayajula, and Pengtao Xie. 2024. AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning. arXiv:2403.09113 (2024)."},{"key":"e_1_3_2_1_69_1","volume-title":"Neural Prompt Search. arXiv: 2206.04673","author":"Zhang Yuanhan","year":"2022","unstructured":"Yuanhan Zhang, Kaiyang Zhou, and Ziwei Liu. 2022. Neural Prompt Search. arXiv: 2206.04673 (2022)."},{"key":"e_1_3_2_1_70_1","first-page":"1","article-title":"KARST","author":"Zhu Yue","year":"2025","unstructured":"Yue Zhu, Haiwen Diao, Shang Gao, Long Chen, and Huchuan Lu. 2025. KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification. In ICASSP. 1-5.","journal-title":"In ICASSP."},{"key":"e_1_3_2_1_71_1","volume-title":"Sira: Sparse mixture of low rank adaptation. arXiv:2311.09179","author":"Zhu Yun","year":"2023","unstructured":"Yun Zhu, Nevan Wichers, Chu-Cheng Lin, Xinyi Wang, Tianlong Chen, Lei Shu, Han Lu, Canoee Liu, Liangchen Luo, Jindong Chen, et al., 2023. Sira: Sparse mixture of low rank adaptation. arXiv:2311.09179 (2023)."}],"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\/3746027.3755359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:03:15Z","timestamp":1765339395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":71,"alternative-id":["10.1145\/3746027.3755359","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755359","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"}}]}}