# 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.

- Published: 2026-07-15T05:45:50.502Z
- Canonical: https://polylog.news/ai/2026-07-15/monkeyocrv2-pretrains-a-document-vision-model-on-113-million
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2607.11562), [alphaXiv](https://www.alphaxiv.org/overview/2607.11562)

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…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-15/monkeyocrv2-pretrains-a-document-vision-model-on-113-million (subscription information: https://polylog.news/pricing).