Knossos 与 Ariadne：用视觉语言模型提取图表完整拓扑结构
Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
研究员做了 Knossos 基准加 Ariadne 框架，让 VLM 能把流程图、架构图完整转成节点和边组成的图，代码开源可试。
研究团队提出图表转图谱任务：抽取图中全部实体及实体间的完整关系。配套基准 Knossos 包含 19,200 张覆盖六个领域的图表，标注了 245,179 个节点和 439,740 条边。框架 Ariadne 将任务拆分为节点清单提取和基于源节点的边预测两步。实验显示，在 Knossos 上训练能明显提升较小开源 VLM 的完整拓扑提取能力，Ariadne 在该基准上取得最高的平均 Edge F1，并在真实世界外部基准上也有提升。
Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
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 https://github.com/bangwayne/knossos_Ariadne_Public.