[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84113-en":3,"doc-seo-84113-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84113,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery","Vision-language models enable interactive digital museums by linking 3D digitization with natural-language artifact exploration, yet ancient Greek pottery presents two reliability barriers. VaseMuseum targets grounded interpretation from fine-grained 2D/3D evidence and expert-curatorial knowledge, where retrieval can yield weak or unverifiable sources. It also addresses incomplete or ambiguous evidence that otherwise leads VLMs to produce confident but unsupported answers. The framework adds evidence and reliability control for trustworthy museum guidance.","arXiv :2607 .06374v 1 [ cs .CV] 7 Jul 2026  \nVaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery  \nJiazi Wang∗ , Nonghai Zhang∗ , Qiushi Xie∗ , Zeyu Zhang∗†, Yufeng Chen, Yang Zhao,  \nLing Shao, Fellow, IEEE, Hao Tang‡  \nAbstract—Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact exploration. However, in cultural heritage domains such as ancient Greek pottery, reliable VLM assistance is limited by two challenges. First, open-ended interpretation requires grounding fine-grained 2D/3D visual evidence in specialized curatorial knowledge, yet the retrieval process may introduce weak sources and unverifiable references. Second, when the available evidence is incomplete, noisy, or ambiguous, VLMs often produce confident but unsupported answers instead of calibrated uncertainty. To address these challenges, we propose VaseMuseum, a lightweight and modular multimodal agent framework for intelligent digital museums of ancient Greek pottery. VaseMuseum combines an interactive virtual museum with VaseAgent, which supports both 2D images and 3D artifacts through multimodal perception, 3D-aware reasoning, external knowledge retrieval, and inference-time reliability control. Specifically, VaseAgent retrieves evidence from authoritative web and museum knowledge sources, and sourcelevel control selects diverse and verifiable evidence before generation. Meanwhile, response-level control checks generated claims against the evidence pool and encourages neutral, evidence-bounded answers when support is insufficient or conflicting. Moreover, a training-free GRPO-style selection mechanism favors responses with valid references and calibrated confidence without updating the VLM backbone. Experiments in a realistic digital museum simulation show that VaseMuseum improves citation validity, reduces hallucinations on knowledge-intensive queries, and produces more neutral answers under ambiguity compared with search-enabled VLM baselines. These results suggest a practical path toward trustworthy multimodal systems for cultural heritage applications. Code: [https://github.com/AIGeeksGroup/VaseMuseum. Website:](https://github.com/AIGeeksGroup/VaseMuseum. Website:) [https://aigeeksgroup.github.io/VaseMuseum](https://aigeeksgroup.github.io/VaseMuseum).  \nIndex Terms—Large language models, multimodal learning, vision-language models, visual question answering.  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nDIGITAL museums and virtual exhibitions are becoming  \nimportant infrastructures for cultural heritage preservation, access, and education. With 3D digitization and webbased visualization, artifacts can be explored as inspectable objects rather than static catalog entries. Meanwhile, vision– language models (VLMs) enable natural-language interaction with these visual assets. Together, these technologies point toward museum systems that can explain artifacts, not merely display them. Ancient Greek pottery is a representative testbed because its interpretation relies on vessel shape, painted scenes, production technique, chronology, and provenance.  \nHowever, turning such systems into reliable VLM-based guides remains difficult. First, many museum questions cannot be answered from appearance alone; they require  \n• ∗ Equal contribution.†Project lead.  \n• ‡Corresponding author, [E-mail: bjdxtanghao@gmail.com](E-mail: bjdxtanghao@gmail.com).  \n• Jiazi Wang and Yufeng Chen are with School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China.  \n• Nonghai Zhang, Zeyu Zhang, and Hao Tang are with School of Computer Science, Peking University, Beijing 100871, China.  \n• Qiushi Xie is with Huazhong University of Science and Technology, Wuhan 430074, China.  \n• Yang Zhao is with the Department of Computer Science and Information Technology, La Trobe University, Melbourne VIC 3000, Australia.  \n• Ling Shao is with the UCAS-Terminus AI L","cbCaijMX1gFvidT3","https://ap.wps.com/l/cbCaijMX1gFvidT3","pdf",24420797,1,10,"English","en",105,"# Introduction\n## Reliability challenges in VLM-guided cultural heritage\n## VaseMuseum framework overview\n# System architecture\n## Virtual museum and VaseAgent workflow","[{\"question\":\"What reliability challenges does VaseMuseum address for ancient Greek pottery museums?\",\"answer\":\"It addresses grounded interpretation that depends on specialized curatorial knowledge while retrieval may introduce weak or unverifiable sources, and it mitigates confident but unsupported answers when evidence is incomplete, noisy, or ambiguous.\"},{\"question\":\"How does VaseAgent improve evidence quality and citation validity?\",\"answer\":\"VaseAgent retrieves evidence from authoritative web and museum knowledge sources, then applies source-level control to select diverse and verifiable evidence before generation.\"},{\"question\":\"How does VaseMuseum ensure more neutral responses under ambiguity?\",\"answer\":\"Response-level control verifies generated claims against the retrieved evidence pool and encourages neutral, evidence-bounded answers when support is insufficient or conflicting, with a training-free GRPO-style selection mechanism for calibrated confidence.\"}]",1784192937,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"vasemuseum-digital-intelligent-museum-for-ancient-greek-pottery","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/vasemuseum-digital-intelligent-museum-for-ancient-greek-pottery/84113/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What reliability challenges does VaseMuseum address for ancient Greek pottery museums?","Question",{"text":75,"@type":76},"It addresses grounded interpretation that depends on specialized curatorial knowledge while retrieval may introduce weak or unverifiable sources, and it mitigates confident but unsupported answers when evidence is incomplete, noisy, or ambiguous.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does VaseAgent improve evidence quality and citation validity?",{"text":80,"@type":76},"VaseAgent retrieves evidence from authoritative web and museum knowledge sources, then applies source-level control to select diverse and verifiable evidence before generation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does VaseMuseum ensure more neutral responses under ambiguity?",{"text":84,"@type":76},"Response-level control verifies generated claims against the retrieved evidence pool and encourages neutral, evidence-bounded answers when support is insufficient or conflicting, with a training-free GRPO-style selection mechanism for calibrated confidence.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]