Skip to content

Source paper

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Cheng Cui, Ting Sun, Suyin Liang and 15 more

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

arXiv 2510.14528 · 2025107 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper presents PaddleOCR-VL, a resource-efficient document parsing system built around a 0.9B parameter Vision-Language Model (VLM). By decoupling layout analysis (using PP-DocLayoutV2) from element recognition (using the VLM with a NaViT-style encoder and ERNIE-4.5-0.3B backbone), the authors achieve SOTA performance on multilingual document benchmarks while maintaining low latency suitable for deployment.

How it works (AI summary)

The system employs a two-stage pipeline: first, PP-DocLayoutV2 (based on RT-DETR and a pointer network) detects layout elements and reading order; second, PaddleOCR-VL-0.9B (combining a dynamic resolution visual encoder and a 0.3B LLM) performs fine-grained recognition of text, tables, formulas, and charts using instruction tuning on a massive dataset of synthetic and real-world samples.