Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and significantly raises computational costs. We attribute this inefficiency to substantial visual regions redundancy in document images, like background. To tackle this, we propose PaddleOCR-VL, a novel coarse-to-fine architecture that focuses on semantically relevant regions while suppressing redundant ones, thereby improving both efficiency and performance. Specifically, we introduce a lightweight Valid Region Focus Module (VRFM) which leverages localization and contextual relationship prediction capabilities to identify valid vision tokens. Subsequently, we design and train a compact yet powerful 0.9B vision-language model (PaddleOCR-VL-0.9B) to perform detailed recognition, guided by VRFM outputs to avoid direct processing of the entire large image. Extensive experiments demonstrate that PaddleOCR-VL achieves state-of-the-art performance in both page-level parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference while utilizing substantially fewer vision tokens and parameters, highlighting the effectiveness of targeted coarse-to-fine parsing for accurate and efficient document understanding. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.

翻译：文档解析是一项细粒度任务，图像分辨率对性能具有显著影响。尽管利用视觉-语言模型的先进研究通过高分辨率输入提升模型性能，但这通常会导致视觉令牌数量呈二次方增长，并显著增加计算成本。我们将这种低效归因于文档图像中存在大量视觉区域冗余（如背景）。为解决这一问题，我们提出PaddleOCR-VL，一种新颖的粗到细架构，该架构聚焦语义相关区域的同时抑制冗余区域，从而提升效率与性能。具体而言，我们引入轻量级有效区域聚焦模块（VRFM），利用定位与上下文关系预测能力识别有效视觉令牌。随后，我们设计并训练了一个紧凑而强大的0.9B视觉-语言模型（PaddleOCR-VL-0.9B），根据VRFM输出引导详细识别，避免直接处理整个大图。大量实验表明，PaddleOCR-VL在页面级解析与元素级识别任务中均达到最优性能。该模型显著优于现有解决方案，与顶级视觉语言模型相比展现出强劲竞争力，在显著减少视觉令牌与参数的同时实现快速推理，突显了定向粗到细解析方法在准确高效文档理解中的有效性。源代码与模型已开源至https://github.com/PaddlePaddle/PaddleOCR。