WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI

2026-05-16

AI Summary

This study addresses the limitations of both physical exhibitions, which often lack personalization, and purely digital exhibitions, which diminish the physical and social context essential for immersive and interpretive engagement. To bridge this gap, the authors propose a high-resolution extended reality (XR) system that integrates Subtractive Reality with large language models. By preserving the authentic exhibition environment and leveraging artwork recognition to enable spatially aware, context-sensitive conversational interactions, the system dynamically adapts to individual visitor contexts and fosters reflective participation. This work presents the first integration of Subtractive Reality with generative AI in a cultural setting. User studies demonstrate a significant increase in average viewing duration—from 35.3 to 98.3 seconds (p<0.001)—with 60% of AI interactions involving analytical, emotional, or comparative inquiries, thereby enhancing depth of cultural experience.

Abstract

Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive aids that lack adaptability to individual backgrounds or curiosity, and their effectiveness depends heavily on a visitor's Personal Context, prior knowledge, and cultural literacy. Meanwhile, digital exhibitions prioritize convenience and accessibility but risk weakening the Physical and Social Contexts that define embodied cultural experience. WhiteTesseract addresses this gap by enabling in-situ interpretation through high-resolution XR and conversational AI. The system integrates spatial intelligence via artwork recognition to allow visitors to selectively reduce environmental distractions (via diminished reality) and engage in context-aware dialogue (via large language models). The goal is to preserve the richness of the physical and social environment while providing a flexible space for personal reflection, enhancing Personal Context without compromising physical authenticity. We deployed the system in a Claude Monet exhibition and conducted a controlled user study with 26 participants. Quantitative results showed that WhiteTesseract modulation significantly increased average viewing duration from 35.3 to 98.3 seconds (p < 0.001). Analysis of 529 visitor-AI interactions revealed that 60% extended beyond factual queries to include analytical, emotional, and comparative inquiries. These findings demonstrate how XR and AI can enrich the physical exhibition experience by supporting deeper, more personalized engagement without displacing the embodied value of cultural heritage. We discuss technical and social constraints for real-world deployment and limitations of our controlled setting.

Problem

• cultural heritage
• visitor engagement
• exhibition design
• personal context
• embodied experience

Innovation

• Extended Reality (XR)
• Conversational AI
• Diminished Reality
• Context-Aware Interaction
• Cultural Heritage Interpretation