{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:01:39Z","timestamp":1780063299077,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,21]]},"DOI":"10.1145\/3745756.3809211","type":"proceedings-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:52:21Z","timestamp":1780059141000},"page":"392-404","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AdaSprite: Resource-efficient Online Co-Adaptation for V2I Systems Under Large-scale Data Drifts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1548-080X","authenticated-orcid":false,"given":"Lehao","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9905-3238","authenticated-orcid":false,"given":"Zhiwen","family":"Yu","sequence":"additional","affiliation":[{"name":"1. Northwestern Polytechnical University 2. Harbin Engineering University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4402-1260","authenticated-orcid":false,"given":"Sicong","family":"Liu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5061-8822","authenticated-orcid":false,"given":"Kefan","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6965-623X","authenticated-orcid":false,"given":"Fengmin","family":"Wu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-2467","authenticated-orcid":false,"given":"Bin","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","first-page":"11024","DOI":"10.1609\/aaai.v38i10.28978","article-title":"Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning","volume":"38","author":"Basu Samyadeep","year":"2024","unstructured":"Samyadeep Basu, Shell Hu, Daniela Massiceti, and Soheil Feizi. 2024. Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning. In Proceedings of AAAI, Vol. 38. 11024\u201311031.","journal-title":"Proceedings of AAAI"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of NSDI. 119\u2013135","author":"Bhardwaj Romil","year":"2022","unstructured":"Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Nikolaos Karianakis, Kevin Hsieh, Paramvir Bahl, and Ion Stoica. 2022. Ekya: Continuous learning of video analytics models on edge compute servers. In Proceedings of NSDI. 119\u2013135."},{"key":"e_1_3_2_1_4_1","unstructured":"BigScience. 2023. BLOOM. https:\/\/huggingface.co\/bigscience\/bloom. (Accessed on 01\/09\/2025)."},{"key":"e_1_3_2_1_5_1","unstructured":"Broadcom. 2025. RabbitMQ. https:\/\/www.rabbitmq.com\/. (Accessed on 04\/12\/2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of ICCV. 17346\u201317357","author":"Chen Tianlong","year":"2023","unstructured":"Tianlong Chen, Xuxi Chen, Xianzhi Du, Abdullah Rashwan, Fan Yang, Huizhong Chen, Zhangyang Wang, and Yeqing Li. 2023. Adamv-moe: Adaptive multi-task vision mixture-of-experts. In Proceedings of ICCV. 17346\u201317357."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of ICML. PMLR, 794\u2013803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In Proceedings of ICML. PMLR, 794\u2013803."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of CVPR. 11828\u201311837","author":"Chen Zitian","year":"2023","unstructured":"Zitian Chen, Yikang Shen, Mingyu Ding, Zhenfang Chen, Hengshuang Zhao, Erik G Learned-Miller, and Chuang Gan. 2023. Mod-squad: Designing mixtures of experts as modular multi-task learners. In Proceedings of CVPR. 11828\u201311837."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 18205\u201318214","author":"Chen Ziming","year":"2023","unstructured":"Ziming Chen, Yifeng Shi, and Jinrang Jia. 2023. Transiff: An instance-level feature fusion framework for vehicle-infrastructure cooperative 3d detection with transformers. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 18205\u201318214."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01674"},{"key":"e_1_3_2_1_11_1","unstructured":"Ning Ding Yujia Qin Guang Yang Fuchao Wei Zonghan Yang Yusheng Su Shengding Hu Yulin Chen Chi-Min Chan Weize Chen et al. 2022. Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904 (2022)."},{"key":"e_1_3_2_1_12_1","first-page":"167","article-title":"Ios: Inter-operator scheduler for cnn acceleration","volume":"3","author":"Ding Yaoyao","year":"2021","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. 2021. Ios: Inter-operator scheduler for cnn acceleration. Proceedings of MLSys 3 (2021), 167\u2013180.","journal-title":"Proceedings of MLSys"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of CORL. PMLR, 1\u201316","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Proceedings of CORL. PMLR, 1\u201316."},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"A novel hybrid of Shortest job first and round Robin with dynamic variable quantum time task scheduling technique","volume":"6","author":"Elmougy Samir","year":"2017","unstructured":"Samir Elmougy, Shahenda Sarhan, and Manar Joundy. 2017. A novel hybrid of Shortest job first and round Robin with dynamic variable quantum time task scheduling technique. Journal of Cloud computing 6 (2017), 1\u201312.","journal-title":"Journal of Cloud computing"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 295\u2013308","author":"Fang Cheng","year":"2024","unstructured":"Cheng Fang, Sicong Liu, Zimu Zhou, Bin Guo, Jiaqi Tang, Ke Ma, and Zhiwen Yu. 2024. AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments. In Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 295\u2013308."},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 120 (2022), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_17_1","volume-title":"AttentionStore: Cost-effective Attention Reuse across Multi-turn Conversations in Large Language Model Serving. arXiv preprint arXiv:2403.19708","author":"Gao Bin","year":"2024","unstructured":"Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, and Pengfei Zuo. 2024. AttentionStore: Cost-effective Attention Reuse across Multi-turn Conversations in Large Language Model Serving. arXiv preprint arXiv:2403.19708 (2024)."},{"key":"e_1_3_2_1_18_1","unstructured":"gRPC Authors. 2025. gRPC. https:\/\/grpc.io\/. (Accessed on 04\/12\/2025)."},{"key":"e_1_3_2_1_19_1","first-page":"2808","article-title":"Liquid: Intelligent resource estimation and network-efficient scheduling for deep learning jobs on distributed GPU clusters","volume":"33","author":"Gu Rong","year":"2021","unstructured":"Rong Gu, Yuquan Chen, Shuai Liu, Haipeng Dai, Guihai Chen, Kai Zhang, Yang Che, and Yihua Huang. 2021. Liquid: Intelligent resource estimation and network-efficient scheduling for deep learning jobs on distributed GPU clusters. IEEE Transactions on Parallel and Distributed Systems 33, 11 (2021), 2808\u20132820.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"Sugarmate: Non-intrusive blood glucose monitoring with smartphones","volume":"1","author":"Gu Weixi","year":"2017","unstructured":"Weixi Gu, Yuxun Zhou, Zimu Zhou, Xi Liu, Han Zou, Pei Zhang, Costas J Spanos, and Lin Zhang. 2017. Sugarmate: Non-intrusive blood glucose monitoring with smartphones. Proceedings of IMWUT 1, 3 (2017), 1\u201327.","journal-title":"Proceedings of IMWUT"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of MobiCom. 19\u201334","author":"Guo Peizhen","year":"2018","unstructured":"Peizhen Guo, Bo Hu, Rui Li, and Wenjun Hu. 2018. Foggycache: Cross-device approximate computation reuse. In Proceedings of MobiCom. 19\u201334."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of ASPLOS. 271\u2013284","author":"Guo Peizhen","year":"2018","unstructured":"Peizhen Guo and Wenjun Hu. 2018. Potluck: Cross-application approximate deduplication for computation-intensive mobile applications. In Proceedings of ASPLOS. 271\u2013284."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of MobiSys. 465\u2013478","author":"Han Lixiang","year":"2024","unstructured":"Lixiang Han, Zimu Zhou, and Zhenjiang Li. 2024. Pantheon: Preemptible Multi-DNN Inference on Mobile Edge GPUs. In Proceedings of MobiSys. 465\u2013478."},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3648160.3648184"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596852"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of CVPR. 10878\u201310887","author":"Huang Qidong","year":"2023","unstructured":"Qidong Huang, Xiaoyi Dong, Dongdong Chen, Weiming Zhang, Feifei Wang, Gang Hua, and Nenghai Yu. 2023. Diversity-aware meta visual prompting. In Proceedings of CVPR. 10878\u201310887."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of JGI. 48\u201357","author":"Hudson Richard L","year":"2001","unstructured":"Richard L Hudson and J Eliot B Moss. 2001. Sapphire: Copying GC without stopping the world. In Proceedings of JGI. 48\u201357."},{"key":"e_1_3_2_1_29_1","volume-title":"Ground then navigate: Language-guided navigation in dynamic scenes. arXiv preprint arXiv:2209.11972","author":"Jain Kanishk","year":"2022","unstructured":"Kanishk Jain, Varun Chhangani, Amogh Tiwari, K Madhava Krishna, and Vineet Gandhi. 2022. Ground then navigate: Language-guided navigation in dynamic scenes. arXiv preprint arXiv:2209.11972 (2022)."},{"key":"e_1_3_2_1_30_1","first-page":"209","article-title":"CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices","volume":"22","author":"Jia Fucheng","year":"2022","unstructured":"Fucheng Jia, Deyu Zhang, Ting Cao, Shiqi Jiang, Yunxin Liu, Ju Ren, and Yaoxue Zhang. 2022. CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices.. In MobiSys, Vol. 22. 209\u2013221.","journal-title":"MobiSys"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3018159"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of CVPR. 7482\u20137491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of CVPR. 7482\u20137491."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of NSDI. 917\u2013932","author":"Khani Mehrdad","year":"2023","unstructured":"Mehrdad Khani, Ganesh Ananthanarayanan, Kevin Hsieh, Junchen Jiang, Ravi Netravali, Yuanchao Shu, Mohammad Alizadeh, and Victor Bahl. 2023. {RECL}: Responsive {Resource-Efficient} continuous learning for video analytics. In Proceedings of NSDI. 917\u2013932."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of ICCV. 4572\u20134582","author":"Khani Mehrdad","year":"2021","unstructured":"Mehrdad Khani, Pouya Hamadanian, Arash Nasr-Esfahany, and Mohammad Alizadeh. 2021. Real-time video inference on edge devices via adaptive model streaming. In Proceedings of ICCV. 4572\u20134582."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of ACM MM. 9051\u20139060","author":"Kong Yuxin","year":"2023","unstructured":"Yuxin Kong, Peng Yang, and Yan Cheng. 2023. Edge-assisted on-device model update for video analytics in adverse environments. In Proceedings of ACM MM. 9051\u20139060."},{"key":"e_1_3_2_1_37_1","first-page":"8343","article-title":"Nimble: Lightweight and parallel gpu task scheduling for deep learning","volume":"33","author":"Kwon Woosuk","year":"2020","unstructured":"Woosuk Kwon, Gyeong-In Yu, Eunji Jeong, and Byung-Gon Chun. 2020. Nimble: Lightweight and parallel gpu task scheduling for deep learning. Proceedings of NeurIPS 33 (2020), 8343\u20138354.","journal-title":"Proceedings of NeurIPS"},{"key":"e_1_3_2_1_38_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_39_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_40_1","first-page":"1","article-title":"Joint modeling of heterogeneous sensing data for depression assessment via multi-task learning","volume":"2","author":"Lu Jin","year":"2018","unstructured":"Jin Lu, Chao Shang, Chaoqun Yue, Reynaldo Morillo, Shweta Ware, Jayesh Kamath, Athanasios Bamis, Alexander Russell, Bing Wang, and Jinbo Bi. 2018. Joint modeling of heterogeneous sensing data for depression assessment via multi-task learning. Proceedings of IMWUT 2, 1 (2018), 1\u201321.","journal-title":"Proceedings of IMWUT"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of SenSys. 263\u2013276","author":"Lu Yan","year":"2022","unstructured":"Yan Lu, Shiqi Jiang, Ting Cao, and Yuanchao Shu. 2022. Turbo: Opportunistic enhancement for edge video analytics. In Proceedings of SenSys. 263\u2013276."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of OSDI. 881\u2013897","author":"Ma Lingxiao","year":"2020","unstructured":"Lingxiao Ma, Zhiqiang Xie, Zhi Yang, Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, and Lidong Zhou. 2020. Rammer: Enabling holistic deep learning compiler optimizations with {rTasks}. In Proceedings of OSDI. 881\u2013897."},{"key":"e_1_3_2_1_43_1","volume-title":"Characterizing Physical Memory Fragmentation. arXiv preprint arXiv:2401.03523","author":"Mansi Mark","year":"2024","unstructured":"Mark Mansi and Michael M Swift. 2024. Characterizing Physical Memory Fragmentation. arXiv preprint arXiv:2401.03523 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Gpt-driver: Learning to drive with gpt. arXiv preprint arXiv:2310.01415","author":"Mao Jiageng","year":"2023","unstructured":"Jiageng Mao, Yuxi Qian, Junjie Ye, Hang Zhao, and Yue Wang. 2023. Gpt-driver: Learning to drive with gpt. arXiv preprint arXiv:2310.01415 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of AISTATS. PMLR, 1273\u20131282","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of AISTATS. PMLR, 1273\u20131282."},{"key":"e_1_3_2_1_46_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Meng Zili","year":"2024","unstructured":"Zili Meng, Xiao Kong, Jing Chen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, and Xue Wei. 2024. Hairpin: Rethinking packet loss recovery in edge-based interactive video streaming. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 907\u2013926."},{"key":"e_1_3_2_1_47_1","unstructured":"Microsoft. 2022. Edge Video Services. https:\/\/github.com\/microsoft\/edge-video-services. Accessed on 01\/09\/2025."},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of CVPR. 3994\u20134003","author":"Misra Ishan","year":"2016","unstructured":"Ishan Misra, Abhinav Shrivastava, Abhinav Gupta, and Martial Hebert. 2016. Cross-stitch networks for multi-task learning. In Proceedings of CVPR. 3994\u20134003."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of ICCV. 3573\u20133582","author":"Mullapudi Ravi Teja","year":"2019","unstructured":"Ravi Teja Mullapudi, Steven Chen, Keyi Zhang, Deva Ramanan, and Kayvon Fatahalian. 2019. Online model distillation for efficient video inference. In Proceedings of ICCV. 3573\u20133582."},{"key":"e_1_3_2_1_50_1","first-page":"1","article-title":"Flexmoe: Scaling large-scale sparse pre-trained model training via dynamic device placement","volume":"1","author":"Nie Xiaonan","year":"2023","unstructured":"Xiaonan Nie, Xupeng Miao, Zilong Wang, Zichao Yang, Jilong Xue, Lingxiao Ma, Gang Cao, and Bin Cui. 2023. Flexmoe: Scaling large-scale sparse pre-trained model training via dynamic device placement. Proceedings of SIGMOD 1, 1 (2023), 1\u201319.","journal-title":"Proceedings of SIGMOD"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of ICDE. IEEE, 2615\u20132628","author":"Nie Xiaonan","year":"2022","unstructured":"Xiaonan Nie, Xupeng Miao, Zhi Yang, and Bin Cui. 2022. Tsplit: Fine-grained gpu memory management for efficient dnn training via tensor splitting. In Proceedings of ICDE. IEEE, 2615\u20132628."},{"key":"e_1_3_2_1_52_1","volume-title":"Test-time model adaptation with only forward passes. arXiv preprint arXiv:2404.01650","author":"Niu Shuaicheng","year":"2024","unstructured":"Shuaicheng Niu, Chunyan Miao, Guohao Chen, Pengcheng Wu, and Peilin Zhao. 2024. Test-time model adaptation with only forward passes. arXiv preprint arXiv:2404.01650 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of ICML. PMLR, 16888\u201316905","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient test-time model adaptation without forgetting. In Proceedings of ICML. PMLR, 16888\u201316905."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/1594371.1594375"},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of NSDI. 973\u2013994","author":"Padmanabhan Arthi","year":"2023","unstructured":"Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, and Ravi Netravali. 2023. Gemel: Model Merging for {Memory-Efficient},{Real-Time} Video Analytics at the Edge. In Proceedings of NSDI. 973\u2013994."},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of ASPLOS. 891\u2013905","author":"Peng Xuan","year":"2020","unstructured":"Xuan Peng, Xuanhua Shi, Hulin Dai, Hai Jin, Weiliang Ma, Qian Xiong, Fan Yang, and Xuehai Qian. 2020. Capuchin: Tensor-based gpu memory management for deep learning. In Proceedings of ASPLOS. 891\u2013905."},{"key":"e_1_3_2_1_57_1","volume-title":"Mir Sazzat Hossain, AKM Rahman, Sajib Mistry, M Ashraful Amin, and Amin Ahsan Ali.","author":"Rajib Rakibul Hasan","year":"2025","unstructured":"Rakibul Hasan Rajib, Md Akil Raihan Iftee, Mir Sazzat Hossain, AKM Rahman, Sajib Mistry, M Ashraful Amin, and Amin Ahsan Ali. 2025. FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning. arXiv preprint arXiv:2505.13643 (2025)."},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of ATC. 551\u2013564","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. {Zero-offload}: Democratizing {billion-scale} model training. In Proceedings of ATC. 551\u2013564."},{"key":"e_1_3_2_1_59_1","volume-title":"Daniel Keysers, and Neil Houlsby.","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling Vision with Sparse Mixture of Experts. arXiv:2106.05974 [cs.CV] https:\/\/arxiv.org\/abs\/2106.05974"},{"key":"e_1_3_2_1_60_1","unstructured":"SciPy. 2008. NNLS. https:\/\/docs.scipy.org\/doc\/scipy\/reference\/generated\/scipy.optimize.nnls.html. (Accessed on 01\/09\/2025)."},{"key":"e_1_3_2_1_61_1","volume-title":"Lossless adaptation of pretrained vision models for robotic manipulation. arXiv preprint arXiv:2304.06600","author":"Sharma Mohit","year":"2023","unstructured":"Mohit Sharma, Claudio Fantacci, Yuxiang Zhou, Skanda Koppula, Nicolas Heess, Jon Scholz, and Yusuf Aytar. 2023. Lossless adaptation of pretrained vision models for robotic manipulation. arXiv preprint arXiv:2304.06600 (2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530455"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of CASES. 9\u201317","author":"Siebert Fridtjof","year":"2000","unstructured":"Fridtjof Siebert. 2000. Eliminating external fragmentation in a non-moving garbage collector for Java. In Proceedings of CASES. 9\u201317."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133956.1133964"},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of ICML. PMLR, 9120\u20139132","author":"Standley Trevor","year":"2020","unstructured":"Trevor Standley, Amir Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, and Silvio Savarese. 2020. Which tasks should be learned together in multi-task learning?. In Proceedings of ICML. PMLR, 9120\u20139132."},{"key":"e_1_3_2_1_66_1","first-page":"8728","article-title":"Adashare: Learning what to share for efficient deep multi-task learning","volume":"33","author":"Sun Ximeng","year":"2020","unstructured":"Ximeng Sun, Rameswar Panda, Rogerio Feris, and Kate Saenko. 2020. Adashare: Learning what to share for efficient deep multi-task learning. Proceedings of NeurIPS 33 (2020), 8728\u20138740.","journal-title":"Proceedings of NeurIPS"},{"key":"e_1_3_2_1_67_1","first-page":"27897","article-title":"Convolutional visual prompt for robust visual perception","volume":"36","author":"Tsai Yun-Yun","year":"2023","unstructured":"Yun-Yun Tsai, Chengzhi Mao, and Junfeng Yang. 2023. Convolutional visual prompt for robust visual perception. Proceedings of NeurIPS 36 (2023), 27897\u201327921.","journal-title":"Proceedings of NeurIPS"},{"key":"e_1_3_2_1_68_1","volume-title":"Proceedings of MSPC. 38\u201347","author":"Veldema Ronald","year":"2012","unstructured":"Ronald Veldema and Michael Philippsen. 2012. Parallel memory defragmentation on a GPU. In Proceedings of MSPC. 38\u201347."},{"key":"e_1_3_2_1_69_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","first-page":"5372","DOI":"10.1609\/aaai.v38i6.28345","article-title":"Lion: Implicit vision prompt tuning","volume":"38","author":"Wang Haixin","year":"2024","unstructured":"Haixin Wang, Jianlong Chang, Yihang Zhai, Xiao Luo, Jinan Sun, Zhouchen Lin, and Qi Tian. 2024. Lion: Implicit vision prompt tuning. In Proceedings of AAAI, Vol. 38. 5372\u20135380.","journal-title":"Proceedings of AAAI"},{"key":"e_1_3_2_1_71_1","volume-title":"AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices","author":"Wang Lehao","year":"2023","unstructured":"Lehao Wang, Zhiwen Yu, Haoyi Yu, Sicong Liu, Yaxiong Xie, Bin Guo, and Yunxin Liu. 2023. AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices. IEEE Transactions on Mobile Computing (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"Proceedings of MobiSys. 450\u2013463","author":"Wang Qipeng","year":"2022","unstructured":"Qipeng Wang, Mengwei Xu, Chao Jin, Xinran Dong, Jinliang Yuan, Xin Jin, Gang Huang, Yunxin Liu, and Xuanzhe Liu. 2022. Melon: Breaking the memory wall for resource-efficient on-device machine learning. In Proceedings of MobiSys. 450\u2013463."},{"key":"e_1_3_2_1_73_1","volume-title":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 606\u2013618","author":"Wu Fengmin","year":"2024","unstructured":"Fengmin Wu, Sicong Liu, Kehao Zhu, Xiaochen Li, Bin Guo, Zhiwen Yu, Hongkai Wen, Xiangrui Xu, Lehao Wang, and Xiangyu Liu. 2024. AdaFlow: Opportunistic Inference on Asynchronous Mobile Data with Generalized Affinity Control. In Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 606\u2013618."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"e_1_3_2_1_75_1","volume-title":"Proceedings of SenSys. 111\u2013124","author":"Yang Bufang","year":"2023","unstructured":"Bufang Yang, Lixing He, Neiwen Ling, Zhenyu Yan, Guoliang Xing, Xian Shuai, Xiaozhe Ren, and Xin Jiang. 2023. Edgefm: Leveraging foundation model for open-set learning on the edge. In Proceedings of SenSys. 111\u2013124."},{"key":"e_1_3_2_1_76_1","volume-title":"Aim: Adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024","author":"Yang Taojiannan","year":"2023","unstructured":"Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, and Mu Li. 2023. Aim: Adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024 (2023)."},{"key":"e_1_3_2_1_77_1","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient surgery for multi-task learning. Proceedings of NeurIPS 33 (2020), 5824\u20135836.","journal-title":"Proceedings of NeurIPS"},{"key":"e_1_3_2_1_78_1","volume-title":"Proceedings of OSDI. 681\u2013699","author":"Zhang Chen","year":"2023","unstructured":"Chen Zhang, Lingxiao Ma, Jilong Xue, Yining Shi, Ziming Miao, Fan Yang, Jidong Zhai, Zhi Yang, and Mao Yang. 2023. Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In Proceedings of OSDI. 681\u2013699."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1109\/TIV.2023.3308098","article-title":"Occlusion-aware planning for autonomous driving with vehicle-to-everything communication","volume":"9","author":"Zhang Chi","year":"2023","unstructured":"Chi Zhang, Florian Steinhauser, Gereon Hinz, and Alois Knoll. 2023. Occlusion-aware planning for autonomous driving with vehicle-to-everything communication. IEEE Transactions on Intelligent Vehicles 9, 1 (2023), 1229\u20131242.","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"e_1_3_2_1_80_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv:2205.01068 [cs.CL] https:\/\/arxiv.org\/abs\/2205.01068"},{"key":"e_1_3_2_1_81_1","volume-title":"Proceedings of CVPR. 4106\u20134115","author":"Zhang Zhenyu","year":"2019","unstructured":"Zhenyu Zhang, Zhen Cui, Chunyan Xu, Yan Yan, Nicu Sebe, and Jian Yang. 2019. Pattern-affinitive propagation across depth, surface normal and semantic segmentation. In Proceedings of CVPR. 4106\u20134115."}],"event":{"name":"MobiSys '26: 24th Annual International Conference on Mobile Systems, Applications and Services","location":"University of Cambridge Cambridge United Kingdom","acronym":"MobiSys '26","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services"],"original-title":[],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T13:01:40Z","timestamp":1780059700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3745756.3809211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":81,"alternative-id":["10.1145\/3745756.3809211","10.1145\/3745756"],"URL":"https:\/\/doi.org\/10.1145\/3745756.3809211","relation":{},"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2026-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}