Spatial Intelligence in Vision-Language Models: A Comprehensive Survey

Spatial Intelligence in Vision-Language Models: A Comprehensive Survey | 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 Spatial Intelligence in Vision-Language Models: A Comprehensive Survey Disheng Liu, Tuo Liang, Zhe Hu, Jierui Peng, Yiren Lu, Yi Xu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8919250/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 12 You are reading this latest preprint version Abstract Vision-language models have achieved impressive progress, yet they still struggle with spatial intelligence—understanding where objects are, how they relate, and how space changes across viewpoints. This limitation matters for embodiedAI, autonomous driving, and spatially consistent generation. Meanwhile, rapid advances in spatially enhanced VLMs have produced a scattered literature with inconsistent terminology, methods, and evaluation practices. In this survey, we provide the first unified overview of the field. We summarize core concepts behind spatial reasoning in VLMs, analyze why spatial failures occur, and organize existing solutions into a clear framework spanning prompting-based techniques, model improvements, explicit 2D cues, 3D enrichment, and data-driven strategies. We also examine how spatial ability is currently measured and report an empirical study across 37 models and 9 representative benchmarks. Our analysis highlights current best-performing approaches, clarifies when different strategies help or fail, and shows that many widely used benchmarks do not reliably capture true spatial understanding. By consolidating evidence and outlining open challenges, this survey offers a practical roadmap for building more spatially capable VLMs. We release our evaluation code and maintain a curated paper repository to support the rapidly growing research on spatial intelligence in vision-language models. Vision-Language Models Spatial Intelligence Foundation Models Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 13 May, 2026 Reviews received at journal 05 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 25 Apr, 2026 Reviewers agreed at journal 25 Apr, 2026 Reviews received at journal 07 Mar, 2026 Reviewers agreed at journal 28 Feb, 2026 Reviewers agreed at journal 27 Feb, 2026 Reviewers invited by journal 26 Feb, 2026 Editor assigned by journal 25 Feb, 2026 Submission checks completed at journal 21 Feb, 2026 First submitted to journal 19 Feb, 2026 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-8919250","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":598622580,"identity":"781cc188-18f5-40ad-9a7d-30a1b8f289ce","order_by":0,"name":"Disheng Liu","email":"","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":false,"prefix":"","firstName":"Disheng","middleName":"","lastName":"Liu","suffix":""},{"id":598622581,"identity":"ea29d2d4-e2b6-45ec-978a-b6730c4b1a13","order_by":1,"name":"Tuo Liang","email":"","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":false,"prefix":"","firstName":"Tuo","middleName":"","lastName":"Liang","suffix":""},{"id":598622582,"identity":"fcf25950-d6fa-47e9-b6fe-c1b0ce7d29b0","order_by":2,"name":"Zhe Hu","email":"","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":false,"prefix":"","firstName":"Zhe","middleName":"","lastName":"Hu","suffix":""},{"id":598622586,"identity":"5a646a23-66f7-4d32-a774-d6a045b5daa2","order_by":3,"name":"Jierui Peng","email":"","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":false,"prefix":"","firstName":"Jierui","middleName":"","lastName":"Peng","suffix":""},{"id":598622587,"identity":"b764e198-d223-48df-a979-d50921eae19e","order_by":4,"name":"Yiren Lu","email":"","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":false,"prefix":"","firstName":"Yiren","middleName":"","lastName":"Lu","suffix":""},{"id":598622588,"identity":"ce1bdbc0-d881-415b-aaeb-a11066e75553","order_by":5,"name":"Yi Xu","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Xu","suffix":""},{"id":598622589,"identity":"4c9c21d8-3a60-4771-a1e4-50e74d4eec66","order_by":6,"name":"Yun Fu","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Yun","middleName":"","lastName":"Fu","suffix":""},{"id":598622591,"identity":"e60feb17-ccce-4719-8bd1-6ab99f36ea0a","order_by":7,"name":"Yu Yin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqUlEQVRIiWNgGAWjYLCCBAYbKIuNeC1ppGphYDhMghaDGwlsEg93nJfn7z98gOFD2WEitSSeuW0440ZaAuOMc0RrabudwHCDx4CZt414LecS5M+f/8D8lwQtBxIMDuQwMDMSo0XyzMNmi8S2ZMONN9IMDvacSyeshe948sGbP9vs5OXOH3744EeZNWEtCgcYWyRgnAOE1QOBfAMD8weiVI6CUTAKRsHIBQCx6j2+fnukXQAAAABJRU5ErkJggg==","orcid":"","institution":"Case Western Reserve University","correspondingAuthor":true,"prefix":"","firstName":"Yu","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2026-02-19 16:08:58","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8919250/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8919250/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104401161,"identity":"487c247d-fb95-4ba3-a723-71f48cce9044","added_by":"auto","created_at":"2026-03-11 12:12:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5254192,"visible":true,"origin":"","legend":"","description":"","filename":"ArtificialIntelligenceReview.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8919250/v1_covered_eaf134b6-7cf6-49d2-bbf4-95d9296f892b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Spatial Intelligence in Vision-Language Models: A Comprehensive Survey","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Vision-Language Models, Spatial Intelligence, Foundation Models","lastPublishedDoi":"10.21203/rs.3.rs-8919250/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8919250/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Vision-language models have achieved impressive progress, yet they still struggle with spatial intelligence—understanding where objects are, how they relate, and how space changes across viewpoints. This limitation matters for embodiedAI, autonomous driving, and spatially consistent generation. Meanwhile, rapid advances in spatially enhanced VLMs have produced a scattered literature with inconsistent terminology, methods, and evaluation practices. In this survey, we provide the first unified overview of the field. We summarize core concepts behind spatial reasoning in VLMs, analyze why spatial failures occur, and organize existing solutions into a clear framework spanning prompting-based techniques, model improvements, explicit 2D cues, 3D enrichment, and data-driven strategies. We also examine how spatial ability is currently measured and report an empirical study across 37 models and 9 representative benchmarks. Our analysis highlights current best-performing approaches, clarifies when different strategies help or fail, and shows that many widely used benchmarks do not reliably capture true spatial understanding. By consolidating evidence and outlining open challenges, this survey offers a practical roadmap for building more spatially capable VLMs. We release our evaluation code and maintain a curated paper repository to support the rapidly growing research on spatial intelligence in vision-language models.","manuscriptTitle":"Spatial Intelligence in Vision-Language Models: A Comprehensive Survey","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-04 05:28:53","doi":"10.21203/rs.3.rs-8919250/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-13T05:58:36+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T08:57:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T22:44:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307457805727601556365796190534187347911","date":"2026-04-25T16:26:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"137973934730532377534161583743626349384","date":"2026-04-25T06:48:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T15:29:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109358461325790079758420100419071915611","date":"2026-02-28T08:37:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"47427137696665689159201717006583868740","date":"2026-02-27T06:51:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-27T02:48:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-26T01:57:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-21T06:29:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Artificial Intelligence Review","date":"2026-02-19T15:57:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8731ffee-b810-46eb-afbc-a9a0909a3b18","owner":[],"postedDate":"March 4th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-13T05:58:36+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T08:57:30+00:00","index":42,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T22:44:39+00:00","index":41,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T06:10:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-04 05:28:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8919250","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8919250","identity":"rs-8919250","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}