Davie Chen

Research Focus

My work sits at the intersection of generative AI and academic visual communication. Across biomedical illustration, patent drawings, and scholarly writing, researchers spend a disproportionate share of their time on artifacts that are essential but ancillary to their core findings. I study where current AI systems succeed and fail at these tasks, and develop domain-specific tools that translate those findings into something usable.

Each of the projects below began as a research question and matured into a product with real users. The papers and the tools are two sides of the same investigation: the papers describe what works, and the tools demonstrate it at scale.

Projects

SciDraw AI →

AI scientific figure generation for researchers.

A platform that helps biomedical and life-science researchers generate publication-ready figures, graphical abstracts, and conceptual diagrams from natural-language descriptions. Built on a taxonomy of 2,792 real-world use cases.

PatentFig AI →

AI patent illustrations aligned with USPTO, EPO, and CNIPA standards.

Patent drawings have stricter formal requirements than any other figure category in technical communication. PatentFig AI generates compliant line-drawing illustrations and supports DXF/SVG export for downstream patent prosecution workflows.

Data2Paper →

From structured data to publication-ready manuscripts.

An automated drafting assistant for researchers who need to turn datasets, case records, or experimental results into well-structured academic prose. Currently focused on case reports and short-form scientific communications.

Selected Preprints