Hengming Zhang

DaVinci: Reinforcing Visual-Structural Syntax in MLLMs for Generalized Scientific Diagram Parsing

Parsing raster-based scientific diagrams into structured representations is critical for editability and reusability. However, existing multimodal LLMs (MLLMs) struggle with the diverse visual primitives, complex structural layouts, and strict syntax involved. To address this, we introduce DaVinci,…