GatheringSense: AI-Generated Imagery and Embodied Experiences for Understanding Literati Gatherings

TL;DR

An AI-driven dual-path framework for cultural understanding is proposed, which is instantiate through GatheringSense, a literati-gathering experience that significantly deepens participants' understanding of ritual rules and social roles, and increases their psychological closeness and presence.

Abstract

Chinese literati gatherings (Wenren Yaji), as a situated form of Chinese traditional culture, remain underexplored in depth. Although generative AI supports powerful multimodal generation, current cultural applications largely emphasize aesthetic reproduction and struggle to convey the deeper meanings of cultural rituals and social frameworks. Based on embodied cognition, we propose an AI-driven dual-path framework for cultural understanding, which we instantiate through GatheringSense, a literati-gathering experience. We conduct a mixed-methods study (N=48) to compare how AI-generated multimodal content and embodied participation complement each other in supporting the understanding of literati gatherings and fostering cultural resonance. Our results show that AI-generated content effectively improves the readability of cultural symbols and initial emotional attraction, yet limitations in physical coherence and micro-level credibility may affect users' satisfaction. In contrast, embodied experience significantly deepens participants' understanding of ritual rules and social roles, and increases their psychological closeness and presence. Based on these findings, we offer empirical evidence and five transferable design implications for generative experience in cultural heritage.

Figures (13)

• Figure 1: AI-driven dual-path framework for cultural understanding. (A) Immersive setup spans human–object–field. (B1-C1) AI symbolic visual path: AI multimodal content $\rightarrow$ cultural semiotics $\rightarrow$ semiotic readability $\rightarrow$ empathy, priming interpretation and participation. (B2-C2) Embodied experience physical path: embodied cognition + social experience + multisensory/interactive cues, deepening engagement. (B3) Shared cognitive relay mechanism: seeing $\rightarrow$ perceiving $\rightarrow$ resonating (collaboration enhances the handoff). (D) Outcomes: cultural-symbol interpretation, symbolic understanding, emotional/aesthetic resonance, and cultural identity. The two paths are complementary rather than substitutive, jointly driving the understanding and resonance of literati gatherings.
• Figure 2: Workflow of our methodology. Our workflow includes three main layers, namely the Data Layer, the Content Layer, and the Interactive Layer. In the Data Layer, we collect, analyze, and process data. In the Content Layer, we utilize multiple generative AIs to create visual content. Finally, we carefully designed visual and embodied experiences, as shown in the Interactive Layer.
• Figure 3: Visual demonstration of four core activities. Pitch-pot, Go, calligraphy, and poetry singing are commonly perceived as the core activities of literati gatherings in historical, literary, and aesthetic contexts.
• Figure 4: Comparison of different models on Go in four styles. We tested four different AI models by using the same prompt to generate a key frame of Go in four different styles. Dou Bao AI performed best in Ink wash and Fine-brush styles, while gpt-image-1 outperformed in Oil and Cartoon styles. The best results were bounded with red boxes in the figure.
• Figure 5: Embodied literati gathering in a structured social frame. Four representative activities were staged within an immersive space, with participants experiencing each one within the social framework of triads.