LiteParse : Open-Source Tool Finally Fixing OCR’s Biggest Table & Layout Flaws

LiteParse pairs fast text parsing with a two-stage agent pattern, falling back to multimodal models when tables or charts ...
GitHub

// examples/basic_parse_demo.cpp

#include "database/nmea_data_fields.h" #include "database/handlers/db_gga_handler.h" #include "database/handlers/db_rmc_handler.h" #include "database/handlers/db_gsa ...
GitHub

README.md

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task ...