# OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning

arXiv: https://arxiv.org/abs/2510.26213 · HTML: https://mlsanity.com/paper/2510.26213/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 50 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Builds on (most cited first, 30 of 38)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More](https://mlsanity.com/paper/2502.11494/) (2025)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://mlsanity.com/paper/2006.14615/) (2020)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?](https://mlsanity.com/paper/2502.11501/) (2025)
- [BLT: Bidirectional Layout Transformer for Controllable Layout Generation](https://mlsanity.com/paper/2112.05112/) (2021)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [LEGION: Learning to Ground and Explain for Synthetic Image Detection](https://mlsanity.com/paper/2503.15264/) (2025)
- [PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout](https://mlsanity.com/paper/2303.15937/) (2023)
- [Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs](https://mlsanity.com/paper/2205.00303/) (2022)
- [LayoutPrompter: Awaken the Design Ability of Large Language Models](https://mlsanity.com/paper/2311.06495/) (2023)
- [Vision Grid Transformer for Document Layout Analysis](https://mlsanity.com/paper/2308.14978/) (2023)
- [M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis](https://mlsanity.com/paper/2305.08719/) (2023)
- [LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction](https://mlsanity.com/paper/2208.08037/) (2022)
- [Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models](https://mlsanity.com/paper/2501.05179/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints](https://mlsanity.com/paper/2402.04754/) (2024)
- [OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.02592/) (2024)
- [Efficient Multi-modal Large Language Models via Progressive Consistency Distillation](https://mlsanity.com/paper/2510.00515/) (2025)
- [LayoutFlow: Flow Matching for Layout Generation](https://mlsanity.com/paper/2403.18187/) (2024)

## Built on by (most cited first, 2 of 2)

- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs](https://mlsanity.com/paper/2608.02218/) (2026)

## Abstract (arXiv)

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 M6Doc dataset, substantially surpassing both existing layout generation experts and several latest general-purpose LLMs. Our code, dataset, and models will be publicly released.