MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering

MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering | 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 Article MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering Caixiong Li, Xiongwei Zhao, Jinhang Zhang, Xing Zhang, Qihao Sun, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7716925/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract Open-vocabulary detection (OVD) is a challenging task to detect and classify objects from an unrestricted set of categories, including those unseen during training. Existing open-vocabulary detectors are limited by complex visual-textual misalignment and long-tailed category imbalances, leading to suboptimal performance in challenging scenarios. To address these limitations, we introduce MQADet, a universal paradigm for enhancing existing open-vocabulary detectors by leveraging the cross-modal reasoning capabilities of multimodal large language models (MLLMs). MQADet functions as a plug-and-play solution that integrates seamlessly with pre-trained object detectors without substantial additional training costs. Specifically, we design a novel three-stage Multimodal Question Answering (MQA) pipeline to guide the MLLMs to precisely localize complex textual and visual targets while effectively enhancing the focus of existing object detectors on relevant objects. To validate our approach, we present a new benchmark for evaluating our paradigm on four challenging open-vocabulary datasets, employing three state-of-the-art object detectors as baselines. Experimental results demonstrate that our proposed paradigm significantly improves the performance of existing detectors, particularly in unseen complex categories, across diverse and challenging scenarios. To facilitate future research, we will publicly release our code. Physical sciences/Engineering Physical sciences/Mathematics and computing Open-vocabulary Detection Multimodal Question Answering Multimodal Large Language Models Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 30 Oct, 2025 Reviews received at journal 29 Oct, 2025 Reviews received at journal 21 Oct, 2025 Reviewers agreed at journal 20 Oct, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviews received at journal 16 Oct, 2025 Reviewers agreed at journal 16 Oct, 2025 Reviewers agreed at journal 16 Oct, 2025 Reviewers invited by journal 16 Oct, 2025 Editor assigned by journal 16 Oct, 2025 Editor invited by journal 07 Oct, 2025 Submission checks completed at journal 06 Oct, 2025 First submitted to journal 06 Oct, 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-7716925","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":535064365,"identity":"317bea75-aee7-4a9a-93ad-e0c7bf48e7ae","order_by":0,"name":"Caixiong Li","email":"","orcid":"","institution":"Qinghai University","correspondingAuthor":false,"prefix":"","firstName":"Caixiong","middleName":"","lastName":"Li","suffix":""},{"id":535064366,"identity":"4e25ece7-3042-4c0f-a417-79a8217f5f3b","order_by":1,"name":"Xiongwei Zhao","email":"","orcid":"","institution":"Harbin Institute of Technology (Shen Zhen)","correspondingAuthor":false,"prefix":"","firstName":"Xiongwei","middleName":"","lastName":"Zhao","suffix":""},{"id":535064367,"identity":"e7bb8658-487c-4cdb-a772-d134805f63f3","order_by":2,"name":"Jinhang Zhang","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinhang","middleName":"","lastName":"Zhang","suffix":""},{"id":535064368,"identity":"93c080aa-39d0-4b68-98c8-d069768e3011","order_by":3,"name":"Xing Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABA0lEQVRIiWNgGAWjYFACNgYGxgYQA0RWAGlm5gZStJwBaWEkWgtIVxtMLx5gcLwt8ePPHXZ58hHJbQ+/zquN5m8HavlRsQ23ljPHDktInkkuNjxzsN1Ydtvx3BmHGRsYe87cxqnF7EZ6g4RhG3PixvbGNmnJbcdyG4BamBnb8Gi5/7z5R2JbfeLGZkagljnHcucT1HKD7ZjEwbbDifPZG9skPzbU5G4gpMX+TFqaZWPb8cQNPAfbpBmOHcjdCNRyEJ9fJNuPGd/82VadOH9G+jPJHzV1ufPOHz744EcFbi1wYHAAGIk8DIfBnAOE1QOBfAMwDn8w1BGleBSMglEwCkYWAABNo2Rn4PRnSQAAAABJRU5ErkJggg==","orcid":"","institution":"Qinghai University","correspondingAuthor":true,"prefix":"","firstName":"Xing","middleName":"","lastName":"Zhang","suffix":""},{"id":535064369,"identity":"fc377468-4de5-4711-aafa-4e33ce27d218","order_by":4,"name":"Qihao Sun","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qihao","middleName":"","lastName":"Sun","suffix":""},{"id":535064370,"identity":"8802f5de-9061-4a69-b76f-2a47e71e2791","order_by":5,"name":"Zhou Wu","email":"","orcid":"","institution":"Eryuan Digital Technology Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Zhou","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-09-26 02:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7716925/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7716925/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-36936-x","type":"published","date":"2026-01-27T15:57:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94716689,"identity":"7808e94f-6d42-4979-917e-c02e13acc924","added_by":"auto","created_at":"2025-10-30 03:50:53","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7365,"visible":true,"origin":"","legend":"","description":"","filename":"925305294179474ca254f60975c7e3a0.json","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/5191f85360fca681acfb0fb3.json"},{"id":94716690,"identity":"d63d1a6e-7468-4c44-8bb1-2221d3f4559f","added_by":"auto","created_at":"2025-10-30 03:50:53","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101160,"visible":true,"origin":"","legend":"","description":"","filename":"925305294179474ca254f60975c7e3a01enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/7bb563860126bb4ac0ae5ebe.xml"},{"id":94716691,"identity":"0cb29158-0991-43ee-93ca-f4579e898bf0","added_by":"auto","created_at":"2025-10-30 03:50:53","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105651,"visible":true,"origin":"","legend":"","description":"","filename":"AuthorsResponseFiles.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/457c00163e581cf63088ffec.pdf"},{"id":94716694,"identity":"89e9dee8-43fd-4185-b771-df8e17e2cac3","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2840129,"visible":true,"origin":"","legend":"","description":"","filename":"MQADetManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/24724817a7581b589baf6511.pdf"},{"id":94716696,"identity":"b72be0ac-dc2d-4a42-a098-0f6cc7910518","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":394066,"visible":true,"origin":"","legend":"","description":"","filename":"figa.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/84f21e7e1160f1fffd30e310.png"},{"id":94716692,"identity":"37e88856-4eed-4759-9db0-8355b87b5fdf","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":392353,"visible":true,"origin":"","legend":"","description":"","filename":"figb.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/6822633aba4fc1015b91fe42.png"},{"id":94730416,"identity":"6196ec3e-392d-4b83-8d89-e65095e333a4","added_by":"auto","created_at":"2025-10-30 07:05:54","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":392303,"visible":true,"origin":"","legend":"","description":"","filename":"figc.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/cfbe783576d0e964309a6e96.png"},{"id":94716698,"identity":"1fd38417-e454-4611-83c1-ddf132eb7825","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":393703,"visible":true,"origin":"","legend":"","description":"","filename":"figd.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/fc58062670a082f2aa2a7a70.png"},{"id":94716697,"identity":"e2ddc5ec-ec9d-4768-96c3-0ffe5b90e4c9","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100311,"visible":true,"origin":"","legend":"","description":"","filename":"plot1.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/569e33abb9670ded3b64733c.png"},{"id":94730179,"identity":"8dffcff3-6998-44be-b337-6874820c9a78","added_by":"auto","created_at":"2025-10-30 07:05:45","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107036,"visible":true,"origin":"","legend":"","description":"","filename":"plot2.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/2b953d48fb18bcaf76b503a7.png"},{"id":94716702,"identity":"91f09ee2-1e4a-410b-9ddb-c5ac238e05da","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/f11ececfaba92899ae38ec6f.bst"},{"id":94716709,"identity":"021da34d-a294-40bd-9e51-6f6f05cf596c","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/87f10aa92f6eee63a3d208b8.bst"},{"id":94729945,"identity":"de98245e-236d-425d-844b-fb4cb6368f81","added_by":"auto","created_at":"2025-10-30 07:05:31","extension":"pdf","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/dd82e281f04304559c0b9e2e.pdf"},{"id":94729149,"identity":"bb5d6fe4-e1e6-41b7-b631-bd75a43ba87b","added_by":"auto","created_at":"2025-10-30 07:04:39","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/dc9178f1a95d517e2b083c07.bst"},{"id":94716708,"identity":"5d2cced9-54fd-49b9-acba-8291af71420e","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/c9f1b7d221128b242565c7f9.bst"},{"id":94716706,"identity":"39646ddc-59a1-4a70-9a36-576549b68fca","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"cls","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/44a057da617625d34e5cc190.cls"},{"id":94716704,"identity":"d38d9b19-9fcb-45ec-8e80-9f6facb84d05","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/0df31d86ccbf0d82f7031850.bst"},{"id":94716711,"identity":"ddde10db-eb67-43f6-a41d-9536a637fc1e","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/f6abb08c078aaf4182eb1423.bst"},{"id":94729567,"identity":"573a48f7-873a-4a4a-888f-940c1d4a9763","added_by":"auto","created_at":"2025-10-30 07:05:09","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/39d48db69ba58070bcbe65ed.bst"},{"id":94716710,"identity":"1c11035a-a207-4a94-9212-7b84307179be","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/d6eba46f80378de5a286374e.bst"},{"id":94716700,"identity":"cc8ff7ce-d1a5-4fc8-837d-d2f224817878","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/1e8204ac4f79857f17efbdb4.bst"},{"id":94730047,"identity":"3d1b0389-1043-45f6-a428-20a847e3295d","added_by":"auto","created_at":"2025-10-30 07:05:37","extension":"pdf","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/4ecfa4afa2e5d9a69bdc76c2.pdf"},{"id":94716714,"identity":"6245d05d-222d-4a67-a409-b6f72a2340a9","added_by":"auto","created_at":"2025-10-30 03:50:55","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":746594,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefiga.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/6dee59ce6d84016d305e7256.png"},{"id":94716715,"identity":"ddc8dd16-a480-4982-9ce1-4be4cadf1187","added_by":"auto","created_at":"2025-10-30 03:50:55","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":734709,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigb.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/cc969063fdf522c9f093836a.png"},{"id":94729956,"identity":"65fb1f69-56ba-4055-806c-bb03c1a82f7b","added_by":"auto","created_at":"2025-10-30 07:05:31","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":730627,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigc.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/a32274d205009c723142a64b.png"},{"id":94716707,"identity":"9492bce6-189d-42ae-9df6-6eea0a4779e5","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":774184,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigd.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/72fe47dcd5c76369f2769395.png"},{"id":94716716,"identity":"ccaadfaf-0a84-430d-9382-40e7176545d0","added_by":"auto","created_at":"2025-10-30 03:50:55","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94475,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineplot2.png","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/5670c0ea756c8ea7a78e0d20.png"},{"id":94716705,"identity":"278dc5b4-ea75-431a-8b41-bf99869dc3a4","added_by":"auto","created_at":"2025-10-30 03:50:54","extension":"xml","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108692,"visible":true,"origin":"","legend":"","description":"","filename":"925305294179474ca254f60975c7e3a01structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/8d7a46ce3044cd1e5c00f38c.xml"},{"id":94729926,"identity":"532ce4b6-444e-47f8-b186-23b7757a9576","added_by":"auto","created_at":"2025-10-30 07:05:30","extension":"html","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115382,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1/26f97384d1beee784bc729ae.html"},{"id":101692234,"identity":"83900387-134f-421e-8578-c8034a35201a","added_by":"auto","created_at":"2026-02-02 16:17:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2822579,"visible":true,"origin":"","legend":"","description":"","filename":"MQADetManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7716925/v1_covered_4003a39e-e319-4756-b489-4d4b62925358.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Open-vocabulary Detection, Multimodal Question Answering, Multimodal Large Language Models","lastPublishedDoi":"10.21203/rs.3.rs-7716925/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7716925/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOpen-vocabulary detection (OVD) is a challenging task to detect and classify objects from an unrestricted set of categories, including those unseen during training. Existing open-vocabulary detectors are limited by complex visual-textual misalignment and long-tailed category imbalances, leading to suboptimal performance in challenging scenarios. To address these limitations, we introduce MQADet, a universal paradigm for enhancing existing open-vocabulary detectors by leveraging the cross-modal reasoning capabilities of multimodal large language models (MLLMs). MQADet functions as a plug-and-play solution that integrates seamlessly with pre-trained object detectors without substantial additional training costs. Specifically, we design a novel three-stage Multimodal Question Answering (MQA) pipeline to guide the MLLMs to precisely localize complex textual and visual targets while effectively enhancing the focus of existing object detectors on relevant objects. To validate our approach, we present a new benchmark for evaluating our paradigm on four challenging open-vocabulary datasets, employing three state-of-the-art object detectors as baselines. Experimental results demonstrate that our proposed paradigm significantly improves the performance of existing detectors, particularly in unseen complex categories, across diverse and challenging scenarios. To facilitate future research, we will publicly release our code.\u003c/p\u003e","manuscriptTitle":"MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-30 03:50:49","doi":"10.21203/rs.3.rs-7716925/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-30T11:24:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-30T02:37:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-21T16:38:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"321410161852824653943921553095434508201","date":"2025-10-20T08:16:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"158830464823785901428740527427394742329","date":"2025-10-17T08:36:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-16T14:02:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"305766987312724715183608778301964910435","date":"2025-10-16T13:24:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"108349836684400870756585683715655394626","date":"2025-10-16T10:37:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-16T09:41:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-16T09:18:37+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-08T03:06:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-06T12:29:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-06T12:26:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7d651a69-6e32-489a-833f-470d26fc9ef0","owner":[],"postedDate":"October 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":56886148,"name":"Physical sciences/Engineering"},{"id":56886149,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-02T16:15:41+00:00","versionOfRecord":{"articleIdentity":"rs-7716925","link":"https://doi.org/10.1038/s41598-026-36936-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-01-27 15:57:52","publishedOnDateReadable":"January 27th, 2026"},"versionCreatedAt":"2025-10-30 03:50:49","video":"","vorDoi":"10.1038/s41598-026-36936-x","vorDoiUrl":"https://doi.org/10.1038/s41598-026-36936-x","workflowStages":[]},"version":"v1","identity":"rs-7716925","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7716925","identity":"rs-7716925","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}