AI RESEARCH
DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation
arXiv CS.AI
•
ArXi:2604.20857v1 Announce Type: cross Recent advances in autonomous ``AI scientist'' systems have nstrated the ability to automatically write scientific manuscripts and codes with execution. However, producing a publication-grade scientific diagram (e.g., teaser figure) is still a major bottleneck in the ``end-to-end'' paper generation process. For example, a teaser figure acts as a strategic visual interface and serves a different purpose than derivative data plots.