Synergistic Cloud-Edge Intelligence for Real-time Multimodal Entity Linking and Knowledge Retrieval

Synergistic Cloud-Edge Intelligence for Real-time Multimodal Entity Linking and Knowledge Retrieval | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Synergistic Cloud-Edge Intelligence for Real-time Multimodal Entity Linking and Knowledge Retrieval Ming Chen, Ping Qi, Xiaoya Pi, Mengxin Cui This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7670864/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Dec, 2025 Read the published version in Journal of Cloud Computing → Version 1 posted 12 You are reading this latest preprint version Abstract The synergy between powerful, cloud-hosted large models and efficient, on-device small models presents a new frontier for mobile artificial intelligence. However, enabling real-time, knowledge-intensive interactions, such as querying physical objects in the user's environment, is severely hampered by the high latency of cloud-centric approaches and the limited reasoning capabilities of edge-only models. This paper introduces a novel synergistic cloud-edge intelligence framework designed to bridge this critical gap. Our framework implements a semantic partitioning of labor: a lightweight edge client performs real-time perception to generate compact multimodal features, while an intelligent trigger decides when to offload a structured, minimal-data payload to a powerful cloud-based reasoning engine for definitive entity linking and knowledge-grounded question answering. We validate our approach on SynergyQA, a new benchmark for this task. Experimental results show that our framework reduces end-to-end latency by over 80% and data transmission by over 98% compared to naive offloading strategies, while achieving question-answering performance that is competitive with state-of-the-art cloud-only models. Our work provides an efficient and robust blueprint for deploying the next generation of interactive, context-aware AI on mobile and edge devices. Cloud-Edge Collaboration Multimodal Large Models Edge Intelligence Multimodal Entity Linking Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Dec, 2025 Read the published version in Journal of Cloud Computing → Version 1 posted Editorial decision: Revision requested 08 Oct, 2025 Reviews received at journal 07 Oct, 2025 Reviews received at journal 05 Oct, 2025 Reviews received at journal 02 Oct, 2025 Reviewers agreed at journal 29 Sep, 2025 Reviewers agreed at journal 28 Sep, 2025 Reviewers agreed at journal 27 Sep, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers invited by journal 26 Sep, 2025 Editor assigned by journal 24 Sep, 2025 Submission checks completed at journal 24 Sep, 2025 First submitted to journal 22 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7670864","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":525730700,"identity":"d915eb7c-ce19-42f7-b149-fb2af35620bd","order_by":0,"name":"Ming Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIie3OMQrCQBCF4QkLSTOSdm3iFSZYGvAqGwRTCalSC0LS5AALnkI8gNEFq2BtYWFlvXaCCho7C+PaWezfPZgPBsBm+8N8xioSFAXgNdM1IN0iF6lOx31kpoTqms5Sb+LSmMBehEukKlkxJNCZAn8+bReOFKM+0mFSPokjdwr4oWonjIvtk5xehHVyBcRFO3F5XFyRVIINuZsQRAWhJCVexDEh3MuBNI3DUrnputwlyPdfyFD5msQt6nnFbHG8ZIPAl1/IW1Xz6Q/3NpvNZvvUA15mP7Nha+kAAAAAAElFTkSuQmCC","orcid":"","institution":"Tongling University","correspondingAuthor":true,"prefix":"","firstName":"Ming","middleName":"","lastName":"Chen","suffix":""},{"id":525730702,"identity":"ab84f57c-8226-432f-9e3d-bddd35259d32","order_by":1,"name":"Ping Qi","email":"","orcid":"","institution":"Tongling University","correspondingAuthor":false,"prefix":"","firstName":"Ping","middleName":"","lastName":"Qi","suffix":""},{"id":525730703,"identity":"dac64ff8-d5fc-4c89-bd64-ec3aa102730f","order_by":2,"name":"Xiaoya Pi","email":"","orcid":"","institution":"Tongling University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoya","middleName":"","lastName":"Pi","suffix":""},{"id":525730704,"identity":"507fad43-7ebe-4fb4-915c-40e497768874","order_by":3,"name":"Mengxin Cui","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mengxin","middleName":"","lastName":"Cui","suffix":""}],"badges":[],"createdAt":"2025-09-22 09:24:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7670864/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7670864/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13677-025-00801-5","type":"published","date":"2025-12-24T15:57:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93073125,"identity":"e700b350-511b-40a4-88db-8f048fe5f1b0","added_by":"auto","created_at":"2025-10-08 18:17:02","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5504,"visible":true,"origin":"","legend":"","description":"","filename":"8c4df9bebb7c43bd9b1ad6ee3e7c7f1d.json","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/578155e35131e1b86d65e492.json"},{"id":93073060,"identity":"74726dc7-e7e9-4c4c-ab28-ef0f7fceb0cd","added_by":"auto","created_at":"2025-10-08 18:16:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":917654,"visible":true,"origin":"","legend":"","description":"","filename":"Springerforchenming.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/05ee7d19444229d7c09b6b01.pdf"},{"id":93073063,"identity":"f23f0b3a-294f-47d6-a15f-d25fa69270be","added_by":"auto","created_at":"2025-10-08 18:16:58","extension":"eps","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":357553,"visible":true,"origin":"","legend":"","description":"","filename":"fig1.eps","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/15b80f66523ed5026039eec7.eps"},{"id":93073239,"identity":"e33d7db0-cc35-4296-915c-1580b5bd363a","added_by":"auto","created_at":"2025-10-08 18:37:37","extension":"jpg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":269810,"visible":true,"origin":"","legend":"","description":"","filename":"fig1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/9c6369adeb12f5677cabf0ac.jpg"},{"id":93073089,"identity":"53777737-a4b3-4624-823a-0db2a97cfe71","added_by":"auto","created_at":"2025-10-08 18:17:00","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54231,"visible":true,"origin":"","legend":"","description":"","filename":"fig2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/bf54bdd184a51c1b2cc4ab39.jpg"},{"id":93073071,"identity":"bbc04b8f-da6d-46c8-96e6-fa10ba4971c3","added_by":"auto","created_at":"2025-10-08 18:16:59","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52135,"visible":true,"origin":"","legend":"","description":"","filename":"fig3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/6fb7456b7ac95e80259ab1ec.jpg"},{"id":93073103,"identity":"aacbe0fc-2773-4cca-863a-c29fd8080874","added_by":"auto","created_at":"2025-10-08 18:17:01","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109354,"visible":true,"origin":"","legend":"","description":"","filename":"fig4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/41ac8df60137362af9e5d751.jpg"},{"id":93073065,"identity":"f8559815-2a68-4fa1-9447-83c6a9052e1c","added_by":"auto","created_at":"2025-10-08 18:16:58","extension":"txt","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8394,"visible":true,"origin":"","legend":"","description":"","filename":"history.txt","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/f3830cf95e1754857ce6e636.txt"},{"id":93073122,"identity":"4e62c1fa-fbb8-4a8e-84f0-b471e953e82c","added_by":"auto","created_at":"2025-10-08 18:17:02","extension":"cls","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43402,"visible":true,"origin":"","legend":"","description":"","filename":"llncs.cls","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/6a7e3e5c8e62d7d355d343df.cls"},{"id":93073105,"identity":"0a0ac97c-df9d-464f-83c1-8c6b2bea6e80","added_by":"auto","created_at":"2025-10-08 18:17:01","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":232527,"visible":true,"origin":"","legend":"","description":"","filename":"llncsdoc.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/fa4e7732ce950af7a23275f1.pdf"},{"id":93073106,"identity":"cb6825ba-c7fd-493c-9b63-d4a97452ae5d","added_by":"auto","created_at":"2025-10-08 18:17:01","extension":"txt","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":573,"visible":true,"origin":"","legend":"","description":"","filename":"readme.txt","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/7e771044ae43ebc04d7b9d83.txt"},{"id":93073066,"identity":"031bbad1-3450-47c2-9d20-fcd87340be1b","added_by":"auto","created_at":"2025-10-08 18:16:58","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32146,"visible":true,"origin":"","legend":"","description":"","filename":"splncs04.bst","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/82e7f4f2dc52e566b5c4394e.bst"},{"id":93073124,"identity":"0b7b50eb-437a-4c80-a8ed-f9c699162ec6","added_by":"auto","created_at":"2025-10-08 18:17:02","extension":"xml","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68726,"visible":true,"origin":"","legend":"","description":"","filename":"8c4df9bebb7c43bd9b1ad6ee3e7c7f1d1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1/f1459e8febca64c4a65d032a.xml"},{"id":99172445,"identity":"16a3e59a-ab6e-48be-869a-d30b215c12da","added_by":"auto","created_at":"2025-12-29 16:09:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":763766,"visible":true,"origin":"","legend":"","description":"","filename":"Springerforchenming.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7670864/v1_covered_844c7ee4-9f01-49a5-a13d-b5a0784598dc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Synergistic Cloud-Edge Intelligence for Real-time Multimodal Entity Linking and Knowledge Retrieval","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-cloud-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clco","sideBox":"Learn more about [Journal of Cloud Computing](http://journalofcloudcomputing.springeropen.com)","snPcode":"13677","submissionUrl":"https://submission.nature.com/new-submission/13677/3","title":"Journal of Cloud Computing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Cloud-Edge Collaboration, Multimodal Large Models, Edge Intelligence, Multimodal Entity Linking","lastPublishedDoi":"10.21203/rs.3.rs-7670864/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7670864/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The synergy between powerful, cloud-hosted large models and efficient, on-device small models presents a new frontier for mobile artificial intelligence. \nHowever, enabling real-time, knowledge-intensive interactions, such as querying physical objects in the user's environment, is severely hampered by the high latency of cloud-centric approaches and the limited reasoning capabilities of edge-only models. \nThis paper introduces a novel synergistic cloud-edge intelligence framework designed to bridge this critical gap.\nOur framework implements a semantic partitioning of labor: a lightweight edge client performs real-time perception to generate compact multimodal features, while an intelligent trigger decides when to offload a structured, minimal-data payload to a powerful cloud-based reasoning engine for definitive entity linking and knowledge-grounded question answering. \nWe validate our approach on SynergyQA, a new benchmark for this task. Experimental results show that our framework reduces end-to-end latency by over 80\\% and data transmission by over 98\\% compared to naive offloading strategies, while achieving question-answering performance that is competitive with state-of-the-art cloud-only models. \nOur work provides an efficient and robust blueprint for deploying the next generation of interactive, context-aware AI on mobile and edge devices.","manuscriptTitle":"Synergistic Cloud-Edge Intelligence for Real-time Multimodal Entity Linking and Knowledge Retrieval","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-08 18:16:19","doi":"10.21203/rs.3.rs-7670864/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-09T01:37:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-07T04:56:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T02:51:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-03T02:28:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"332203322059408422976577104259176466456","date":"2025-09-30T02:48:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24786160307478770199450012125065678940","date":"2025-09-28T23:35:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"149085228335097890636558880899071763130","date":"2025-09-28T02:36:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99591532788503419806600805558062067257","date":"2025-09-27T01:38:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-26T11:15:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-25T02:07:06+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-24T18:52:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cloud Computing","date":"2025-09-22T09:12:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cloud-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clco","sideBox":"Learn more about [Journal of Cloud Computing](http://journalofcloudcomputing.springeropen.com)","snPcode":"13677","submissionUrl":"https://submission.nature.com/new-submission/13677/3","title":"Journal of Cloud Computing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"570eee88-607c-4346-a47b-8eb0285bd756","owner":[],"postedDate":"October 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T16:05:09+00:00","versionOfRecord":{"articleIdentity":"rs-7670864","link":"https://doi.org/10.1186/s13677-025-00801-5","journal":{"identity":"journal-of-cloud-computing","isVorOnly":false,"title":"Journal of Cloud Computing"},"publishedOn":"2025-12-24 15:57:12","publishedOnDateReadable":"December 24th, 2025"},"versionCreatedAt":"2025-10-08 18:16:19","video":"","vorDoi":"10.1186/s13677-025-00801-5","vorDoiUrl":"https://doi.org/10.1186/s13677-025-00801-5","workflowStages":[]},"version":"v1","identity":"rs-7670864","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7670864","identity":"rs-7670864","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}