MinerU-Diffusion (OpenDataLab, ECCV 2026)

github.com/opendatalab/mineru-diffusion
Active613updated 3 weeks ago
Python
MIT

Diffusion-based document OCR framework replacing autoregressive decoding with block-level parallel diffusion decoding, enabling high-accuracy text recognition in scientific PDFs (613+ stars, MIT License)

Sourced from

  • Awesome AI for Sciencegithub.com/opendatalab/mineru-diffusion
  • GitHubgithub.com/opendatalab/mineru-diffusion

Related resources

SOTA multimodal document parsing with 1.2B parameters outperforming GPT-4o, converts PDFs to LLM-ready Markdown/JSON

Active65.9K1 month ago
Python
NOASSERTION

Advanced OCR with PP-StructureV3 document parsing, 13% accuracy improvement, supports 80+ languages

Active81.3K1 month ago
Python
Apache-2.0

Open-source PDF parser for AI-ready data, converting PDFs into Markdown/JSON/HTML/Tagged PDF with layout analysis and reading-order detection; ranks #1 overall on extraction benchmarks with deterministic bounding boxes and hybrid AI mode (26K+ stars, Apache 2.0)

Active26.3K1 week ago
Java
Apache-2.0

Machine learning software for extracting structured metadata from scholarly documents

Active5K1 week ago
Java
Apache-2.0

High-accuracy PDF→Markdown/JSON/HTML conversion, specialized for tables/formulas/code blocks with benchmark scripts

Active36.4K2 weeks ago
Python
GPL-3.0

Toolkit for linearizing academic PDFs into LLM-ready text with high accuracy and structure preservation, optimized for scientific literature extraction

Active17.4K3 months ago
Python
Apache-2.0