# VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery Source: [VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery]() Collection index: [llms.txt]() Data updated: 2026-07-16T06:00:01.361Z Authors: Jiazi Wang, Nonghai Zhang, Qiushi Xie, Zeyu Zhang, Yufeng Chen, Yang Zhao, Ling Shao, Hao Tang Published: 2026-07-07T15:11:56.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Ambiguous Question Answering on Museum Artifact Dataset Amb. 1.0 (test)](): Ambiguous Question Answering; Museum Artifact Dataset Amb. 1.0 (test); Answer Accuracy: 55. - [Visual Question Answering on Museum Artifact Dataset V-Only 1.0 (test)](): Visual Question Answering; Museum Artifact Dataset V-Only 1.0 (test); Accuracy (A): 24. - [Knowledge-Intensive Visual Question Answering on Museum Artifact Dataset V+K 1.0 (test)](): Knowledge-Intensive Visual Question Answering; Museum Artifact Dataset V+K 1.0 (test); Answer Accuracy: 54. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()