VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

Hugging Face Daily Papers Papers
vision-language-models cultural-heritage digital-museum multimodal-agent hallucination-mitigation knowledge-retrieval ancient-greek-pottery

Summary

This paper proposes VaseMuseum, a lightweight multimodal agent framework that combines 3D digitization with vision-language models to create an interactive digital museum for ancient Greek pottery, addressing challenges of evidence grounding and hallucination through source-level and response-level reliability control.

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 source-level 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.
Original Article
View Cached Full Text

Cached at: 07/13/26, 07:49 AM

Paper page - VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

Source: https://huggingface.co/papers/2607.06374

Abstract

Vision-languagemodels(VLMs)havemadeinteractivedigitalmuseumsincreasinglyfeasiblebyconnecting3Ddigitizationwithnatural-languageartifactexploration.However,inculturalheritagedomainssuchasancientGreekpottery,reliableVLMassistanceislimitedbytwochallenges.First,open-endedinterpretationrequiresgroundingfine-grained2D/3Dvisualevidenceinspecializedcuratorialknowledge,yettheretrievalprocessmayintroduceweaksourcesandunverifiablereferences.Second,whentheavailableevidenceisincomplete,noisy,orambiguous,VLMsoftenproduceconfidentbutunsupportedanswersinsteadofcalibrateduncertainty.Toaddressthesechallenges,weproposeVaseMuseum,alightweightandmodularmultimodalagentframeworkforintelligentdigitalmuseumsofancientGreekpottery.VaseMuseumcombinesaninteractivevirtualmuseumwithVaseAgent,whichsupportsboth2Dimagesand3Dartifactsthroughmultimodalperception,3D-awarereasoning,externalknowledgeretrieval,andinference-timereliabilitycontrol.Specifically,VaseAgentretrievesevidencefromauthoritativewebandmuseumknowledgesources,andsource-levelcontrolselectsdiverseandverifiableevidencebeforegeneration.Meanwhile,response-levelcontrolchecksgeneratedclaimsagainsttheevidencepoolandencouragesneutral,evidence-boundedanswerswhensupportisinsufficientorconflicting.Moreover,atraining-freeGRPO-styleselectionmechanismfavorsresponseswithvalidreferencesandcalibratedconfidencewithoutupdatingtheVLMbackbone.ExperimentsinarealisticdigitalmuseumsimulationshowthatVaseMuseumimprovescitationvalidity,reduceshallucinationsonknowledge-intensivequeries,andproducesmoreneutralanswersunderambiguitycomparedwithsearch-enabledVLMbaselines.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2607\.06374

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.06374 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.06374 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.06374 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Virtual Art Museum built with Three js

Lobsters Hottest

A developer built a virtual art museum website using Three.js to showcase his wife's award-winning artworks, featuring interactive halls, customizable weather/time settings, and 3D-scanned sculptures.

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

Hugging Face Daily Papers

MemEye is a visual-centric evaluation framework that assesses multimodal agent memory by measuring visual evidence granularity and retrieval complexity across 8 life-scenario tasks, revealing that current architectures struggle to preserve fine-grained visual details and reason about state changes over time.

Collaborative Memory for Multi-Agent VLM Systems

arXiv cs.AI

This paper proposes a collaborative memory framework for multi-agent vision-language model systems to address distributed perception and improve shared visual context and reasoning consistency.

Designing a 4D Digital Archive for Ikebana

Hacker News Top

This paper proposes a 4D digital viewing system for archiving the creation process of Ikebana using synchronized cameras, eye tracking, and 3D Gaussian Splatting, enabling interactive viewing from arbitrary angles.