{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T16:11:40Z","timestamp":1772899900668,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cloud Comp"],"DOI":"10.1186\/s13677-025-00801-5","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T10:49:15Z","timestamp":1766573355000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Synergistic cloud-edge intelligence for real-time multimodal entity linking and knowledge retrieval"],"prefix":"10.1186","volume":"14","author":[{"given":"Ming","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoya","family":"Pi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"801_CR1","unstructured":"Alayrac JB, Donahue J, Luc P, Miech A, Barr I, Hasson Y, Lenc K, Mensch A, Millican K, Reynolds M et al (2022) Flamingo: a visual language model for few-shot learning. Adv Neural Inf Process Syst 35 23716\u201323736"},{"issue":"1","key":"801_CR2","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s13677-022-00367-6","volume":"12","author":"J Alonso","year":"2023","unstructured":"Alonso J, Orue-Echevarria L, Casola V, Torre AI, Huarte M, Osaba E, Lobo JL (2023) Understanding the challenges and novel architectural models of multi-cloud native applications\u2013a systematic literature review. J Cloud Comput (heidelb) 12(1):6","journal-title":"J Cloud Comput (heidelb)"},{"key":"801_CR3","unstructured":"Bistritz I, Mann A, Bambos N (2020) Distributed distillation for on-device learning. Adv Neural Inf Process Syst 33 22593\u201322604"},{"key":"801_CR4","unstructured":"Chu X, Qiao L, Lin X, Xu S, Yang Y, Hu Y, Wei F, Zhang X, Zhang B, Wei X, et al (2023). Mobilevlm: a fast, strong and open vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886"},{"key":"801_CR5","unstructured":"Dai W, Li J, Li D, Tiong A, Zhao J, Wang W, Li B, Fung PN, Hoi S (2023) Instructblip: towards general-purpose vision-language models with instruction tuning. Advances in neural information processing systems 36:49250\u201349267"},{"key":"801_CR6","doi-asserted-by":"crossref","unstructured":"Dong T, Li B, Liu J, Zhu S, Xiong D (2025) Mlas-lora: language-aware parameters detection and lora-based knowledge transfer for multilingual machine translation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 15645\u201315660","DOI":"10.18653\/v1\/2025.acl-long.762"},{"key":"801_CR7","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017). Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"801_CR8","unstructured":"Hurst A, Lerer A, Goucher AP, Perelman A, Ramesh A, Clark A, Ostrow A, Welihinda A, Hayes A, Radford A, et al (2024). Gpt-4o system card. arXiv preprint arXiv:2410.21276"},{"key":"801_CR9","doi-asserted-by":"crossref","unstructured":"Iannacci J (2022) A perspective vision of micro\/nano systems and technologies as enablers of 6g, super-iot, and tactile internet [point of view]. In Proceedings of the IEEE, vol 111(1), 5\u201318","DOI":"10.1109\/JPROC.2022.3223791"},{"issue":"1","key":"801_CR10","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/s41524-025-01554-0","volume":"11","author":"X Jiang","year":"2025","unstructured":"Jiang X, Wang W, Tian S, Wang H, Lookman T, Su Y (2025) Applications of natural language processing and large language models in materials discovery. NPJ Comput Mater 11(1):79","journal-title":"NPJ Comput Mater"},{"issue":"1","key":"801_CR11","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1145\/3093337.3037698","volume":"45","author":"Y Kang","year":"2017","unstructured":"Kang Y, Hauswald J, Gao C, Rovinski A, Mudge T, Mars J, Tang L (2017) Neurosurgeon: collaborative intelligence between the cloud and mobile edge. ACM SIGARCH Comput Archit News 45(1):615\u2013629","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"801_CR12","doi-asserted-by":"crossref","unstructured":"Lei Y, Xue Z, Zhao X, Sun H, Zhu S, Lin X, Xiong D (2023) Ckdst: comprehensively and effectively distill knowledge from machine translation to end-to-end speech translation. Findings Assoc Comput Linguistics: ACL 2023. 3123\u20133137","DOI":"10.18653\/v1\/2023.findings-acl.195"},{"key":"801_CR13","doi-asserted-by":"crossref","unstructured":"Li B, Zhang Y, Chen L, Wang J, Pu F, Cahyono JA, Yang J, Li C, Liu Z (2025) Otter: a multi-modal model with in-context instruction tuning. In IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"801_CR14","doi-asserted-by":"crossref","unstructured":"Li J, Yang Q, Jiang B, Zhu S, Sun Q (2025) Lrm-llava: overcoming the modality gap of multilingual large language-vision model for low-resource languages. In Proceedings of the AAAI Conference on Artificial Intelligence, vol 39. pp 24449\u201324457","DOI":"10.1609\/aaai.v39i23.34623"},{"key":"801_CR15","unstructured":"Li J, Li D, Savarese S, Hoi S (2023) Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, PMLR. pp. 19730\u201319742"},{"key":"801_CR16","unstructured":"Li J, Li D, Xiong C, Hoi S (2022) Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning, PMLR. pp. 12888\u201312900"},{"key":"801_CR17","doi-asserted-by":"crossref","unstructured":"Liu H, Li C, Li Y, Lee YJ (2024) Improved baselines with visual instruction tuning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 26296\u201326306","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"801_CR18","unstructured":"Liu H, Li C, Li Y, Li B, Zhang Y, Shen S, Lee YJ (2024) Llavanext: improved reasoning, ocr, and world knowledge"},{"key":"801_CR19","unstructured":"Mehta S, Rastegari M (2021). Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178"},{"issue":"8","key":"801_CR20","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MCOM.001.2001239","volume":"59","author":"G Shi","year":"2021","unstructured":"Shi G, Xiao Y, Li Y, Xie X (2021) From semantic communication to semantic-aware networking: model, architecture, and open problems. IEEE Commun Mag 59(8):44\u201350","journal-title":"IEEE Commun Mag"},{"key":"801_CR21","doi-asserted-by":"crossref","unstructured":"Tao Y, Wang Z, Zhang H, Wang L, Gu J (2025) Nevlp: noise-robust framework for efficient vision-language pre-training. In International Conference on Intelligent Computing, Springer. pp. 74\u201385","DOI":"10.1007\/978-981-95-0011-6_7"},{"key":"801_CR22","unstructured":"Team G, Anil R, Borgeaud S, Alayrac JB, Yu J, Soricut R, Schalkwyk J, Dai AM, Hauth A, Millican K, et al. (2023). Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805"},{"key":"801_CR23","unstructured":"Thawakar O, Vayani A, Khan S, Cholakal H, Anwer RM, Felsberg M, Baldwin T, Xing EP, Khan FS (2024). Mobillama: towards accurate and lightweight fully transparent gpt. arXiv preprint arXiv:2402.16840"},{"key":"801_CR24","doi-asserted-by":"crossref","unstructured":"Wang H, Gao Z, Zhang C, Sha Z, Sun M, Zhou Y, Zhu W, Sun W, Qiu H, Xiao X (2024) Clap: learning transferable binary code representations with natural language supervision. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, pp 503\u2013515","DOI":"10.1145\/3650212.3652145"},{"key":"801_CR25","doi-asserted-by":"crossref","unstructured":"Wang P, Wu J, Chen X (2022) Multimodal entity linking with gated hierarchical fusion and contrastive training. Proc 45th Int ACM SIGIR Conf Res Dev Inf Retr, pp 938\u2013948","DOI":"10.1145\/3477495.3531867"},{"issue":"2","key":"801_CR26","doi-asserted-by":"publisher","first-page":"4858","DOI":"10.1109\/TCE.2024.3378509","volume":"70","author":"G Yan","year":"2024","unstructured":"Yan G, Liu K, Liu C, Zhang J (2024) Edge intelligence for internet of vehicles: a survey. IEEE Trans Consum Electron 70(2):4858\u20134877","journal-title":"IEEE Trans Consum Electron"},{"key":"801_CR27","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"801_CR28","doi-asserted-by":"crossref","unstructured":"Zhang X, Nie J, Huang Y, Xie G, Xiong Z, Liu J, Niyato D, Shen XS (2024) Beyond the cloud: edge inference for generative large language models in wireless networks. In IEEE Transactions on Wireless Communications","DOI":"10.1109\/TWC.2024.3497923"},{"key":"801_CR29","unstructured":"Zhou B, Hu Y, Weng X, Jia J, Luo J, Liu X, Wu J, Huang L (2024). Tinyllava: a framework of small-scale large multimodal models. arXiv preprint arXiv:2402.14289"},{"key":"801_CR30","doi-asserted-by":"crossref","unstructured":"Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: paving the last mile of artificial intelligence with edge computing. In Proceedings of the IEEE, vol 107(8), 1738\u20131762","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"801_CR31","unstructured":"Zhu D, Chen J, Shen X, Li X, Elhoseiny M (2024) Minigpt-4: enhancing vision-language understanding with advanced large language models. In 12th International Conference on Learning Representations, ICLR 2024"},{"key":"801_CR32","doi-asserted-by":"crossref","unstructured":"Zhu S, Li S, Lei Y, Xiong D (2023) Peit: bridging the modality gap with pre-trained models for end-to-end image translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 13433\u201313447","DOI":"10.18653\/v1\/2023.acl-long.751"},{"key":"801_CR33","doi-asserted-by":"crossref","unstructured":"Zhu S, Li S, Xiong D (2024) Vistfc: vision-guided target-side future context learning for neural machine translation. Expert Syst With Appl 249, 123411","DOI":"10.1016\/j.eswa.2024.123411"},{"key":"801_CR34","unstructured":"Zhu S, Xu S, Sun H, Pan L, Cui M, Du J, Jin R, Branco A, Xiong D, et al (2024). Multilingual large language models: a systematic survey. arXiv preprint arXiv:2411.11072"}],"container-title":["Journal of Cloud Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-025-00801-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13677-025-00801-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-025-00801-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T10:49:21Z","timestamp":1766573361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13677-025-00801-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["801"],"URL":"https:\/\/doi.org\/10.1186\/s13677-025-00801-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7670864\/v1","asserted-by":"object"}]},"ISSN":["2192-113X"],"issn-type":[{"value":"2192-113X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"assertion":[{"value":"22 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"76"}}