SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Teaching AI to edit scientific diagrams the way researchers actually revise them
Researchers created a system that learns to automatically edit scientific figures by studying how researchers revise papers on arXiv. The system takes natural-language instructions and modifies vector-based diagrams—the editable source files behind figures—by learning patterns from real before-and-after figure pairs extracted from actual manuscript revisions.
Editing figures consumes hours of researcher time during manuscript revisions. If this system scales, it could accelerate the revision cycle for scientific papers and reduce manual labor that adds no intellectual value. The approach also demonstrates that real-world revision patterns are useful training data for teaching AI to handle complex, structured visual content.