opendatalab/MinerU-Diffusion

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

↗ Open on GitHub

Stars

617

Forks

42

Language

Python

License

MIT

Last push

3 months ago

Python python pdf parser ocr diffusion document-analysis ai4science pdf-converter dlm extract-data layout-analysis llada pdf-extractor-llm pdf-extractor-pretrain pdf-extractor-rag pdf-parser

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.