dlgjr/FINAR-VL
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.
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
$ git clone https://github.com/X-PLUG/mPLUG-DocOwl.gitOpen-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.
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.
Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO
▲ +5 ★ this week
A Repo For Document AI
▲ +25 ★ this week
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
▲ +1 ★ this week
Get clean data from tricky documents, powered by vision-language models ⚡
Data from GitHub · snapshot Nov 16, 2026