{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:59:27Z","timestamp":1780851567124,"version":"3.54.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032281098","type":"print"},{"value":"9783032281104","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-28110-4_19","type":"book-chapter","created":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:29:19Z","timestamp":1780849759000},"page":"341-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SlimAI4Edge: A Cloud-Edge Framework for\u00a0Downsizing AI Models as-a-Service"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6307-7194","authenticated-orcid":false,"given":"Adriano","family":"Puglisi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3349-7861","authenticated-orcid":false,"given":"Flavia","family":"Monti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9216-8502","authenticated-orcid":false,"given":"Francesco","family":"Leotta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3336-5853","authenticated-orcid":false,"given":"Christian","family":"Napoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9730-8882","authenticated-orcid":false,"given":"Massimo","family":"Mecella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"19_CR1","unstructured":"Ashton, K., et al.: That \u2018internet of things\u2019 thing. RFID J. 22(7), 97\u2013114 (2009)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Athanasopoulos, D., Liu, D.: AI back-end as a service for learning switching of mobile apps between the fog and the cloud. IEEE TSC 15 (2021)","DOI":"10.1109\/TSC.2021.3117927"},{"issue":"03","key":"19_CR3","first-page":"1750012","volume":"2","author":"H Chen","year":"2017","unstructured":"Chen, H.: Applications of cyber-physical system: a literature review. J. Ind. Integr. Manag. 2(03), 1750012 (2017)","journal-title":"J. Ind. Integr. Manag."},{"key":"19_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.101919","volume":"56","author":"Q Chen","year":"2023","unstructured":"Chen, Q., Li, M., Xu, G., Huang, G.Q.: Cyber-physical spare parts intralogistics system for aviation MRO. Adv. Eng. Inform. 56, 101919 (2023)","journal-title":"Adv. Eng. Inform."},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Ding, Y., Niu, C., Wu, F., Tang, S., Lyu, C., Chen, G.: Enhancing on-device LLM inference with historical cloud-based LLM interactions. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, pp. 597\u2013608. ACM, New York, NY, USA (2024)","DOI":"10.1145\/3637528.3671679"},{"key":"19_CR6","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Hao, Z., Jiang, H., Jiang, S., Ren, J., Cao, T.: Hybrid SLM and LLM for edge-cloud collaborative inference. In: Proceedings of the Workshop on Edge and Mobile Foundation Models, EdgeFM 2024, pp. 36\u201341. ACM, New York, NY, USA (2024)","DOI":"10.1145\/3662006.3662067"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Jin, H., Wu, Y.: CE-CoLLM: efficient and adaptive large language models through cloud-edge collaboration. In: 2025 IEEE International Conference on Web Services (ICWS), pp. 316\u2013323. IEEE Computer Society, Los Alamitos, CA, USA (2025)","DOI":"10.1109\/ICWS67624.2025.00046"},{"key":"19_CR9","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Toronto, ON, Canada (2009)"},{"key":"19_CR10","unstructured":"Li, M., et al.: Nearest neighbor speculative decoding for LLM generation and attribution. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2024)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: Truthfulqa: measuring how models mimic human falsehoods. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 3214\u20133252 (2022)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"19_CR12","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)"},{"issue":"1","key":"19_CR13","doi-asserted-by":"publisher","first-page":"4","DOI":"10.64552\/wipiec.v11i1.89","volume":"11","author":"A Puglisi","year":"2025","unstructured":"Puglisi, A., Monti, F., Napoli, C., Mecella, M.: Efficient neural network reduction for AI-on-the-edge applications through structural compression. WiPiEC J.-Works Progress Embed. Comput. J. 11(1), 4 (2025)","journal-title":"WiPiEC J.-Works Progress Embed. Comput. J."},{"key":"19_CR14","unstructured":"Romero, F., Li, Q., Yadwadkar, N.J., Kozyrakis, C.: INFaaS: automated model-less inference serving. In: USENIX ATC 2021, pp. 397\u2013411 (2021)"},{"key":"19_CR15","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Tan, J., Dou, Z., Zhu, Y., Guo, P., Fang, K., Wen, J.R.: Small models, big insights: leveraging slim proxy models to decide when and what to retrieve for LLMs. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pp. 4420\u20134436. ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.242"},{"key":"19_CR17","unstructured":"Team, Q., et\u00a0al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"issue":"5","key":"19_CR18","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1080\/02564602.2021.1950578","volume":"39","author":"S Tiwari","year":"2022","unstructured":"Tiwari, S., Agarwal, S.: Data stream management for cps-based healthcare: a contemporary review. IETE Tech. Rev. 39(5), 987\u20131010 (2022)","journal-title":"IETE Tech. Rev."},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Yao, Y., Li, Z., Zhao, H.: GKT: a novel guidance-based knowledge transfer framework for efficient cloud-edge collaboration LLM deployment. In: ACL (Findings), pp. 3433\u20133446 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.204"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wang, J., Hua, E., Qi, B., Ding, N., Zhou, B.: CoGenesis: a framework collaborating large and small language models for secure context-aware instruction following. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pp. 4295\u20134312. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.acl-long.235"},{"issue":"2","key":"19_CR21","first-page":"1954","volume":"11","author":"W Zhang","year":"2022","unstructured":"Zhang, W., Zeadally, S., Li, W., Zhang, H., Hou, J., Leung, V.C.: Edge AI as a service: configurable model deployment and delay-energy optimization with result quality constraints. IEEE TCC 11(2), 1954\u20131969 (2022)","journal-title":"IEEE TCC"},{"key":"19_CR22","unstructured":"Zhao, Y., et al.: Accelerating greedy coordinate gradient and general prompt optimization via probe sampling. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-28110-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:29:26Z","timestamp":1780849766000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-28110-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032281098","9783032281104"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-28110-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAiSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Verona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caise2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caise26.polimi.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}