EUVIMEDEUVIMED entdecken
Crossref

MoGraphGPT : Creating Interactive Scenes Using Modular LLM and Graphical Control

Hui Ye, Chufeng Xiao, Jiaye Leng, Pengfei Xu, Hongbo Fu

IEEE Transactions on Visualization and Computer Graphics · 2026-07 · 32 (7) · 5317-5332

DOI: 10.1109/tvcg.2026.3667904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Visualization and Computer Graphics, 2026-07. Verfasst von Hui Ye und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Research Grants Council of the Hong Kong Special Administrative Region, China, National Natural Science Foundation of China, Natural Science Foundation of Shenzhen Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Creating interactive scenes often involves complex programming tasks. Although large language models (LLMs) like ChatGPT can generate code from natural language, their output is often error-prone, particularly when scripting interactions among multiple elements. The linear conversational structure limits the editing of individual elements, and the lack of graphical and precise control complicates visual integration. To address these issues, we integrate a context-aware modularization technique that processes textual descriptions for individual elements through separate LLM modules, with a central module managing interactions among elements. It defines a top-down structure to manage interactions, ensuring clear update logic and facilitating efficient collaboration while allowing for independent updates for each element. We design a graphical user interface, MoGraphGPT, which combines modular LLMs with enhanced graphical control to generate codes for 2D interactive scenes. It enables direct integration of graphical information and offers quick, precise control through automatically generated sliders. A comparative study with Cursor Composer shows MoGraphGPT significantly improves easiness, controllability, and performance in creating 2D interactive scenes with multiple visual elements in a coding-free manner. An ablation study validates the effectiveness of modularization, and an open-ended study demonstrates the usability and expressiveness of MoGraphGPT.

Förderung

  • Research Grants Council of the Hong Kong Special Administrative Region, China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Shenzhen Municipality

Zitieren

APA

Ye, H., Xiao, C., Leng, J., Xu, P., & Fu, H. (2026). MoGraphGPT : Creating Interactive Scenes Using Modular LLM and Graphical Control. IEEE Transactions on Visualization and Computer Graphics, 32(7), 5317-5332. https://doi.org/10.1109/tvcg.2026.3667904

Vancouver

Ye H, Xiao C, Leng J, Xu P, Fu H. MoGraphGPT : Creating Interactive Scenes Using Modular LLM and Graphical Control. IEEE Transactions on Visualization and Computer Graphics. 2026;32(7):5317-5332. doi:10.1109/tvcg.2026.3667904

BibTeX
@article{Ye2026,
  author = {Ye, Hui and Xiao, Chufeng and Leng, Jiaye and Xu, Pengfei and Fu, Hongbo},
  title = {MoGraphGPT : Creating Interactive Scenes Using Modular LLM and Graphical Control},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  year = {2026},
  volume = {32},
  number = {7},
  pages = {5317--5332},
  doi = {10.1109/tvcg.2026.3667904}
}
Kostenlos starten →