Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 1

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Hejun Dong ⋅ Junbo Niu ⋅ Bin Wang ⋅ Weijun Zeng ⋅ Wentao Zhang ⋅ Conghui He

Keywords: Video Understanding, Generation and Multimodal Learning

Project Page