EUVIMEDEUVIMED entdecken
Crossref

DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models

Yongyuan Chen, Minjie Hong, Boxi Wu, Xicheng Han

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30341-30349

DOI: 10.1609/aaai.v40i36.40286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yongyuan Chen und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The automation of diagram generation has gained significant attention in recent years. Previous studies mainly focused on generating diagrams from natural language, but often lacked support for user-friendly editing like drag-and-drop. This paper proposes a novel task: generating editable, high-fidelity diagrams from either text or raster images. It is also among the first to introduce diagram restoration and style transfer in this setting.To tackle these tasks, we constructed the Diagram-mxGraph dataset, covering restoration, text-to-diagram generation, and style transfer. We propose two core innovations: Fine-grained Adaptive Background Suppression (FABS) and Component-Aware Adaptive Loss (CAAL). Leveraging pre-trained Vision Transformers (ViTs) and the Diagram Adapter module, our method aligns diagram features with a Large Language Model (LLM) to output diagrams in editable mxGraph format.

Zitieren

APA

Chen, Y., Hong, M., Wu, B., & Han, X. (2026). DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30341-30349. https://doi.org/10.1609/aaai.v40i36.40286

Vancouver

Chen Y, Hong M, Wu B, Han X. DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30341-30349. doi:10.1609/aaai.v40i36.40286

BibTeX
@article{Chen2026,
  author = {Chen, Yongyuan and Hong, Minjie and Wu, Boxi and Han, Xicheng},
  title = {DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {36},
  pages = {30341--30349},
  doi = {10.1609/aaai.v40i36.40286}
}
Kostenlos starten →