PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Cheng Cui; Ting Sun; Suyin Liang; Tingquan Gao; Zelun Zhang; Jiaxuan Liu; Xueqing Wang; Changda Zhou; Hongen Liu; Manhui Lin; Yue Zhang; Yubo Zhang; Yi Liu; Dianhai Yu; Yanjun Ma

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Computer Vision and Pattern Recognition 2026-04-06 v2

Authors: Cheng Cui , Ting Sun , Suyin Liang , Tingquan Gao , Zelun Zhang , Jiaxuan Liu , Xueqing Wang , Changda Zhou , Hongen Liu , Manhui Lin , Yue Zhang , Yubo Zhang , Yi Liu , Dianhai Yu , Yanjun Ma

View on arXiv ↗ PDF ↗

Abstract

We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions, including scanning, skew, warping, screen-photography, and illumination, we propose the Real5-OmniDocBench benchmark. Experimental results demonstrate that this enhanced model attains SOTA performance on the newly curated benchmark. Furthermore, we extend the model's capabilities by incorporating seal recognition and text spotting tasks, while remaining a 0.9B ultra-compact VLM with high efficiency. Code: https://github.com/PaddlePaddle/PaddleOCR

Keywords

linear systems rational surfaces Hirzebruch surfaces SHGH conjecture blow-up

Cite

@article{arxiv.2601.21957,
  title  = {PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing},
  author = {Cheng Cui and Ting Sun and Suyin Liang and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Xueqing Wang and Changda Zhou and Hongen Liu and Manhui Lin and Yue Zhang and Yubo Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
  journal= {arXiv preprint arXiv:2601.21957},
  year   = {2026}
}

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Abstract

Keywords

Cite

Related papers