HunyuanOCR-1.5：让轻量级OCR视觉语言模型更快更好

摘要

我们提出HunyuanOCR-1.5，一种轻量级端到端OCR专用视觉语言模型。HunyuanOCR将文档解析、文本检测、信息提取、图文翻译以及多图像文档理解统一集成在单个端到端VLM中。基于HunyuanOCR-1.0的轻量级架构，HunyuanOCR-1.5未重新设计主干网络，而是系统性地提升了效率与能力。在效率方面，我们将DFlash适配到OCR解码中，显著降低了密集文档、表格和公式等长结构输出的延迟，同时保持了输出分布。借助DFlash，HunyuanOCR-1.5在Transformer推理上实现了6.37倍的加速，在vLLM下实现了2.14倍的加速，成为轻量级OCR VLM中推理速度最快的模型。在能力方面，我们提出了Agentic Data Flow，一种智能体驱动的数据构建系统，它将模型弱点转化为可执行的数据需求，并自主执行素材搜索、质量验证和流程开发。该系统大幅提升了古文OCR、细粒度图表与表格解析、多图像文本中心问答、低资源多语言解析以及文档幻觉评估等长尾能力。HunyuanOCR-1.5在OmniDocBench v1.6上跻身顶级端到端OCR方案之列，同时在这些长尾任务上取得了新的性能里程碑。结合升级的预训练与后训练方案，HunyuanOCR-1.5进一步扩展了在高分辨率、长上下文和多任务场景下的能力。实验证明了更快的推理速度、更广泛的OCR能力覆盖以及轻量级端到端模型的部署优势。我们将发布模型权重和训练代码，以支持未来的研究及实际OCR应用。

English

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.