OCR & Documents
X-PLUG/mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
PythonApache-2.0updated May 30, 2025
Open-source financial multimodal LLM for document understanding, chart/table reasoning, numerical reasoning, and financial analysis, with SFT, dual-branch RL, MOPD distillation, and public benchmark evaluation.
$ git clone https://github.com/dlgjr/FINAR-VL.gitmPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
▲ +3 ★ this week
Parsing-free RAG supported by VLMs
A reproduction of the Deepseek-OCR model including training
▲ +5 ★ this week
A Repo For Document AI
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
Turn documents into AI-ready Markdown with visual understanding
Data from GitHub · snapshot Nov 16, 2026