MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale Paper • 2604.04771 • Published Apr 6 • 122
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding Paper • 2603.22458 • Published Mar 23 • 135
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing Paper • 2509.22186 • Published Sep 26, 2025 • 161
Running on L40S Agents 595 MinerU Document Extraction Tools 📚 595 Easy converting PDF and Office docs into Markdown and JSON