Morning Edition · Wednesday, July 15, 2026Published at 1:45 AM EDT · New York

MonkeyOCRv2 Pretrains a Document Vision Model on 113 Million Images Across 17 Languages

A dual objective that jointly learns image-to-text generation and pixel-level document reconstruction yields a reported 2.8-point absolute gain on the MDPBench multilingual parsing benchmark over the prior best open model.

Researchers from Huazhong University of Science and Technology and Kingsoft Office have released MonkeyOCRv2, a text-centric visual foundation model for document AI that unifies fine-grained text modeling and cross-lingual generalization in…