CoChat

Stage Wizard: Enhancing Tangible Storytelling with Multimodal LLMs

Han, Kuntong, Tang, Keyang, Wang, Meng · 2025 · Proceedings of the Nineteenth International Conference on Tangible, Embedded, and Embodied Interaction

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

This paper introduces a pipeline that integrates multimodal large language models (LLMs) for tangible storytelling, featuring flexible materials generation, intuitive hands-on performance, and easy finalization. The design system enables teachers, parents, and children to create stage elements through natural language interactions and generate paper-cut style images. These elements can be easily fabricated using standard printing paper and assembled into a reconfigurable cardstock stage, allowing children to craft various plotlines through manipulation. The storytelling process can be directly recorded as a short film or transformed into an elaborate storybook using styled image filters and refining LLMs. By introducing the role of the stage in both the design and manipulation processes, this pipeline offers intuitive guidance and affordance for free but organized creation. The flexibility introduced by LLMs supports educators in diverse course design and children in self-expression. Without the requirement for specific hardware, the system also has the potential to be applied more broadly in less developed areas.

Overview

Integrity signals

Registry

Crossref · 10.1145/3689050.3704429

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Research works printed but not linked: 6

  1. Soenke Kirchhof. 2018. Storytelling for volumetric VR. In ACM SIGGRAPH 2018 Educator S Forum (SIGGRAPH '18). ACM, New York, NY, USA, Article 6, 1-2.
  2. Sophia C. Steinhaeusser and Birgit Lugrin. 2022. Effects of Colored LEDs in Robotic Storytelling on Storytelling Experience and Robot Perception. In Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction (HRI '22). IEEE Press, 1053-1058.
  3. Huang, C. C., et.al. (2015, January). Olegoru: a soundscape composition tool to enhance imaginative storytelling with tangible objects. In Proceedings of the ninth international conference on tangible, embedded, and embodied interaction (pp. 709-714).
  4. Zhang, L., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. arXivpreprint arXiv:2302.05543. · arXiv
  5. Ai, H., & Sheng, L. (2023). Stable Diffusion Reference Only: Image Prompt and Blueprint Jointly Guided Multi-Condition Diffusion Model for Secondary Painting. arXiv preprint arX-iv:2311.02343.
  6. Milord M. (2007). The effects of using storytelling on reading comprehension through drama and theater (Doctoral dissertation SUNY College at Brockport).

Cited by

See all 12

Metadata

Authors
Han, K., Tang, K., & Wang, M.
Affiliations
  • Tsinghua University (CN)
  • Beijing Institute for General Artificial Intelligence (CN)
Venue
Proceedings of the Nineteenth International Conference on Tangible, Embedded, and Embodied Interaction
Publisher
ACM
Published
2025-03-04
Pages
1-13
OpenAlex
W4407941976
Cited by
8
References
16
Citations by year
2026: 6 · 2025: 2
FWCI
63.88
Type
conference paper
Language
en
Open access
closed
Locations
International Conference on Tangible, Embedded, and Embodied Interaction (TEI) (publishedVersion)
Topics
  • Social Sciences › Education › Digital Storytelling and Education
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
  • Physical Sciences › Computer Science › Human-Computer Interaction › Interactive and Immersive Displays
Keywords
multimodal large language models, natural language interaction, children's creative expression, low-cost educational technology

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.