{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:08:44Z","timestamp":1780330124146,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":7,"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\/3812835.3814828","type":"proceedings-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:54:37Z","timestamp":1780329277000},"page":"126-127","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Building Efficient Inference Systems for Resource-Constrained Edge AI Deployment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5341-2303","authenticated-orcid":false,"given":"Xiangyu","family":"Li","sequence":"first","affiliation":[{"name":"Institue for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Laura Smith, Jost Tobias Springenberg, Kyle Stachowicz, James Tanner, Quan Vuong, Homer Walke, Anna Walling, Haohuan Wang, Lili Yu, and Ury Zhilinsky.","author":"Intelligence Physical","year":"2025","unstructured":"Physical Intelligence, Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Manuel Y. Galliker, Dibya Ghosh, Lachy Groom, Karol Hausman, Brian Ichter, Szymon Jakubczak, Tim Jones, Liyiming Ke, Devin LeBlanc, Sergey Levine, Adrian Li-Bell, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Allen Z. Ren, Lucy Xiaoyang Shi, Laura Smith, Jost Tobias Springenberg, Kyle Stachowicz, James Tanner, Quan Vuong, Homer Walke, Anna Walling, Haohuan Wang, Lili Yu, and Ury Zhilinsky. 2025. \u03c00.5: a Vision-Language-Action Model with Open-World Generalization. arXiv preprint arXiv:2504.16054 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649391"},{"key":"e_1_3_2_1_3_1","volume-title":"OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism. arXiv preprint arXiv:2603.14371","author":"Li Xiangyu","year":"2026","unstructured":"Xiangyu Li, Huaizhi Tang, Xin Ding, Weijun Wang, Ting Cao, and Yunxin Liu. 2026. OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism. arXiv preprint arXiv:2603.14371 (2026)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3745756.3809200"},{"key":"e_1_3_2_1_5_1","volume-title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. arXiv preprint arXiv:2411.04996","author":"Liang Weixin","year":"2024","unstructured":"Weixin Liang, Lili Yu, Liang Luo, Srinivasan Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, and Xi Victoria Lin. 2024. Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. arXiv preprint arXiv:2411.04996 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations.","author":"Park Gunho","year":"2024","unstructured":"Gunho Park, Baeseong Park, Minsub Kim, Sungjae Lee, Jeonghoon Kim, Beomseok Kwon, Se Jung Kwon, Byeongwook Kim, Youngjoo Lee, and Dongsoo Lee. 2024. LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696099"}],"event":{"name":"MobiSys Companion '26: 24th Annual International Conference on Mobile Systems, Applications and Services Companion","location":"University of Cambridge Cambridge United Kingdom","acronym":"MobiSys Companion '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 Companion"],"original-title":[],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:55:18Z","timestamp":1780329318000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3812835.3814828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":7,"alternative-id":["10.1145\/3812835.3814828","10.1145\/3812835"],"URL":"https:\/\/doi.org\/10.1145\/3812835.3814828","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"}}]}}