OmniDocLayout：面向多样化文档版面生成的由粗到细大语言模型学习
OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
把版面元素序列当作语言建模对象，用两阶段粗到细的 LLM 学习从通用版面先验迁移到特定文档域，这种「大规模合成数据预训练 + 少量细粒度样本域迁移」的范式可直接迁移到视觉生成中的结构化布局控制（如海报、图文混排、UI 生成）。
原文依据 a 0.5B model with designed two-stage Coarse-to-Fine learning paradigm
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文档人工智能发展迅速，正受到越来越多的关注。然而，现有研究大多集中于文档版面分析（DLA），其生成式对应任务——版面生成——仍鲜有探索。与传统的图形版面设计和房间布局规划不同，文档版面生成通常每页涉及更多元素，并表现出更强的结构多样性与复杂性。目前，一个主要障碍在于多样化文档版面的稀缺：具有曼哈顿式结构的学术论文在现有研究中占据主导，而报纸、杂志等开放世界体裁则严重缺乏代表性。为弥补这一空白，我们构建了 OmniDocLayout-1M，这是首个百万规模的多样的文档版面数据集，涵盖六种常见文档类型，并包含从多个来源收集的当代版面。此外，由于现有方法在复杂领域表现不佳，且往往无法连贯地排布长序列，我们提出了 OmniDocLayout-LLM，一个 0.5B 模型，采用所设计的两阶段由粗到细学习范式：1）以粗粒度类别定义从我们的数据集中学习通用版面原则；2）借助少量细粒度标注样本将知识迁移到特定领域。大量实验表明，我们的方法在 M^6Doc 数据集的多个领域上取得了强劲性能，显著超越了现有的版面生成专家模型以及若干最新的通用大语言模型。更多信息见 https://github.com/opendatalab/OmniDocLayout。
英文原文摘要 1595 字符
Document AI has advanced rapidly and is attracting increasing attention. Yet, while most efforts have focused on document layout analysis (DLA), its generative counterpart, layout generation, remains underexplored. Distinct from traditional graphic layout design and room layout planning, document layout generation typically involves a larger number of elements per page and exhibits greater structural diversity and complexity. Currently, a major obstacle lies in the scarcity of diverse document layouts: academic papers with Manhattan-style structures dominate existing studies, while open-world genres such as newspapers and magazines remain severely underrepresented. To address this gap, we curate OmniDocLayout-1M, the first million-scale dataset of diverse document layouts, covering six common document types and comprising contemporary layouts collected from multiple sources. Moreover, since existing methods struggle in complex domains and often fail to arrange long sequences coherently, we introduce OmniDocLayout-LLM, a 0.5B model with designed two-stage Coarse-to-Fine learning paradigm: 1) learning universal layout principles from our dataset with coarse category definitions, and 2) transferring the knowledge to a specific domain with few fine-grained annotated samples. Extensive experiments demonstrate that our approach achieves strong performance on multiple domains in M^6Doc dataset, substantially surpassing both existing layout generation experts and several latest general-purpose LLMs. More information can be found at https://github.com/opendatalab/OmniDocLayout.