Research-oriented, local-first document understanding system for PDFs and images. The pipeline combines document layout analysis, multilingual OCR, and targeted vision-language reasoning to produce ...
Abstract: An approach for layout-aware interconnect optimization is presented. It is based on the combination of three sub-problems into the same framework: gate duplication, buffer insertion and ...
Layout-based chunk alignment (Layout-CA) is a layout-aware alignment module designed for building parallel corpora directly from bilingual document images. Positioned between document-level and ...
Abstract: Ensuring compliance with IEEE formatting and structural guidelines remains a persistent challenge in academic publishing, as manual checks are time-consuming, subjective, and prone to ...