Youtu-Parsing：通过高并行解码实现感知、结构化与识别
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
AI总结：
Youtu-Parsing是用于高性能内容提取的文档解析模型，采用含动态分辨率视觉编码器的ViT与Youtu-LLM-2B语言模型，引入令牌并行和查询并行的高并行解码策略，涵盖多种文档元素，在多基准测试中达最优性能，有重要实验和实用价值。
摘要：
本文介绍了Youtu-Parsing，一种用于高性能内容提取的高效通用文档解析模型。其架构采用具有动态分辨率视觉编码器的原生视觉Transformer（ViT）来提取共享文档特征，结合提示引导的Youtu-LLM-2B语言模型进行布局分析和区域提示解码。利用这种解耦且特征可重用的框架，引入了包含令牌并行和查询并行两个核心组件的高并行解码策略。令牌并行策略在每个推理步骤可同时生成多达64个候选令牌并通过验证机制验证，比传统自回归解码提速5至11倍，适用于表格识别等高度结构化场景。查询并行策略能同时对多个边界框进行内容预测，在保持输出质量的同时再提速2倍。Youtu-Parsing涵盖多种文档元素，对罕见字符、多语言文本和手写内容有强鲁棒性，在多个基准测试中达到了当前最优性能，对大规模文档智能应用具有重要实验价值和实用价值。
英文摘要：
This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Transformer (ViT) featuring a dynamic-resolution visual encoder to extract shared document features, coupled with a prompt-guided Youtu-LLM-2B language model for layout analysis and region-prompted decoding. Leveraging this decoupled and feature-reusable framework, we introduce a high-parallelism decoding strategy comprising two core components: token parallelism and query parallelism. The token parallelism strategy concurrently generates up to 64 candidate tokens per inference step, which are subsequently validated through a verification mechanism. This approach yields a 5--11x speedup over traditional autoregressive decoding and is particularly well-suited for highly structured scenarios, such as table recognition. To further exploit the advantages of region-prompted decoding, the query parallelism strategy enables simultaneous content prediction for multiple bounding boxes (up to five), providing an additional 2x acceleration while maintaining output quality equivalent to standard decoding. Youtu-Parsing encompasses a diverse range of document elements, including text, formulas, tables, charts, seals, and hierarchical structures. Furthermore, the model exhibits strong robustness when handling rare characters, multilingual text, and handwritten content. Extensive evaluations demonstrate that Youtu-Parsing achieves state-of-the-art (SOTA) performance on both the OmniDocBench and olmOCR-bench benchmarks. Overall, Youtu-Parsing demonstrates significant experimental value and practical utility for large-scale document intelligence applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
