2026
DaVinci: Reinforcing Visual-Structural Syntax in MLLMs for Generalized Scientific Diagram Parsing
ICLR 2026poster
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,…