opendatalab/MinerU-Diffusion

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

Computer visionPython MIT 42created 2026-03-13

Website GitHub

Stars

624

1-day growth

—

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

The chart appears after at least 2 days of data.

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

Top contributors

Not collected yet (contributors job).