Condor: A Neural Connection Network for Enhanced Attention

Condor: A Neural Connection Network for Enhanced Attention | 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Research Article Condor: A Neural Connection Network for Enhanced Attention Youngseong Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7442318/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The attention mechanism in traditional neural networks relies on pairwise interactions between tokens, limiting its ability to capture complex, multi-token relationships. This study introduces Condor, a novel architecture that extends the attention mechanism through a neural connection network based on the KY Transform theory. Our approach replaces static attention patterns with learnable connection functions that dynamically model relationships within a local window. The Condor architecture achieves linear computational complexity of O(LWH) while maintaining the expressive power to capture sophisticated sequence patterns. Experimental results on wikitext-2 demonstrate improved perplexity and faster convergence compared to the standard Transformer, confirming that each attention head learns unique connection patterns specializing in different aspects of sequence modeling. Code is available at: https://github.com/Kim-Ai-gpu/Condor Artificial Intelligence and Machine Learning attention mechanism neural networks transformer sequence modeling computational complexity natural language processing deep learning KY-attention machine learning neural architecture Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-7442318","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":504625507,"identity":"00c2b0a3-f2e0-43bb-8064-98ee5b44f39e","order_by":0,"name":"Youngseong Kim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIie3PMUvDQBTA8Xc8uC5put4RsV/hQiex6ld5cpCpxQ8gaKAQl+isk9+icySQLELXyg0GsjqkWywZbNwcmtRN8P7DGx7vNzwAm+0vlrACYAojwDwtqt2CD3oJKoAAZMhngf/YEjyckPKcdtNH3DxlVU3nYhQBTabb5dhFYNVmtp/IV40yJi1ExpJy/mD8CAHl03I/UclVIoY13sB7SJN5bNiOcBx2kVWJnw3dinEGyjuJzUU/WWvuOZQK1RKozWUvkeuSnx5RLvzMCfz70OgI2aLzF3el8e2DrsVxNkiLujFnz3eLl2rTQX7Gou8ZHnrf1vzm2Gaz2f5LX3gLUsUDnNgqAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0009-5077-0920","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Youngseong","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-08-23 15:57:42","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7442318/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7442318/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89967187,"identity":"1fb666ce-82ab-4f6e-9a0c-6e7ed03d290b","added_by":"auto","created_at":"2025-08-27 03:55:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":374056,"visible":true,"origin":"","legend":"","description":"","filename":"CondorEng61.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7442318/v1_covered_7dc6c469-b8f3-43d4-9097-f93bf745eae5.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eCondor: A Neural Connection Network for Enhanced Attention\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Independent","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"attention mechanism, neural networks, transformer, sequence modeling, computational complexity, natural language processing, deep learning, KY-attention, machine learning, neural architecture","lastPublishedDoi":"10.21203/rs.3.rs-7442318/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7442318/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe attention mechanism in traditional neural networks relies on pairwise interactions between tokens, limiting its ability to capture complex, multi-token relationships. This study introduces Condor, a novel architecture that extends the attention mechanism through a neural connection network based on the KY Transform theory. Our approach replaces static attention patterns with learnable connection functions that dynamically model relationships within a local window. The Condor architecture achieves linear computational complexity of O(LWH) while maintaining the expressive power to capture sophisticated sequence patterns. Experimental results on wikitext-2 demonstrate improved perplexity and faster convergence compared to the standard Transformer, confirming that each attention head learns unique connection patterns specializing in different aspects of sequence modeling. Code is available at: https://github.com/Kim-Ai-gpu/Condor\u003c/p\u003e","manuscriptTitle":"Condor: A Neural Connection Network for Enhanced Attention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-27 03:47:50","doi":"10.21203/rs.3.rs-7442318/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"44257b60-6f9e-4ddb-a57c-8cb4db7b665d","owner":[],"postedDate":"August 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53610681,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-08-27T03:47:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-27 03:47:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7442318","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7442318","identity":"rs-7442318","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}