Metraipolis › archive › dc_8b07ce9bdcbc

Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models — arXiv:2610.04721

Source
arXiv
Original
https://arxiv.org/abs/2610.04721
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:24.207Z
SHA-256 of the archived text
10ddf819779dfe46952075a1e7d6ec9bd28389c90ee84b8778db6a5d84aaafef
Stable URL of this page
https://metraipolis.com/documento/dc_8b07ce9bdcbc

How to cite

Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models — arXiv:2610.04721 — arXiv, https://arxiv.org/abs/2610.04721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b07ce9bdcbc (Metraipolis archive dc_8b07ce9bdcbc, sha256 10ddf819779dfe46952075a1e7d6ec9bd28389c90ee84b8778db6a5d84aaafef)
BibTeX
@misc{dc8b07ce9bdcbc,
  title = {Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models — arXiv:2610.04721},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04721},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b07ce9bdcbc; sha256 10ddf819779dfe46952075a1e7d6ec9bd28389c90ee84b8778db6a5d84aaafef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains. Recent vision-language models (VLMs) have become increasingly capable of recognizing diagram elements and reasoning about their content, while complete diagram topology extraction remains comparatively underexplored. In this paper, we study diagram-to-graph topology extraction: extracting all diagram entities and the complete relations among them. To enable large-scale supervised training and systematic evaluation of this task, we introduce Knossos, a benchmark of 19,200 diagrams across six diverse domains, with 245,179 nodes and 439,740 edges. Its symbolic generation process provides exact alignment between rendered diagrams and annotations of complete topology, relation types, and connector geometry. To address the modeling challenge of complete topology extraction, we also present Ariadne, a structured framework that decomposes the task into node inventory extraction and source-conditioned edge prediction. Extensive experiments show that training on Knossos substantially improves complete topology extraction in smaller open-source VLMs. Ariadne further improves over one-step extraction under matched supervision, demonstrating the additional benefit of structured decomposition. It achieves the highest average Edge F1 among the evaluated methods on Knossos, while both backbone variants also improve over their unadapted counterparts on the real-world external benchmark. Code and benchmark are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04721 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.907Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).