CREMA: Contextual Reconstruction and Extraction of Multimodal Assets from academic papers
Dec 3, 2025·
,,,·
0 min read
Woonghee Lee
Je-hyun Lee
Changsu Lee
Kwanyoung Park
Abstract
System that extracts visual elements (figures, tables, equations) from academic
papers, translates the body text, and reconstructs the document while preserving
the original layout and visual elements — aimed at improving the efficiency of
paper consumption for non-English-speaking researchers.
Type
Publication
Software Copyright Registration · Korea Copyright Commission
Authors
Senior Researcher · Principal Investigator
Woonghee Lee leads the DAIS Research Group at the Korea Institute of
Energy Research (KIER). His research applies deep learning to image, signal,
and text data — currently focused on AI methods for energy and materials
research, including time-series and document analysis, robust deep models,
and AI agents for research workflows.