https://ym-xu.github.io/living-survey/fields/document-understanding/#tag=layoutPage structure: layout detection, reading order, logical structure.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.12957https://arxiv.org/abs/2611.12957Sat, 07 Nov 2026 00:00:00 +0000Bingdian Zhang, Zixuan Li, Long Bai, Xiaolong Jin, et al. VLM-based agents solve complex tasks by iteratively interacting with environments, and their effectiveness depends heavily on how the environment exposes information and provides tools for acting on it. However, constructing an effective environment for complex multimodal document question answering remains challenging…https://arxiv.org/abs/2610.34879https://arxiv.org/abs/2610.34879Mon, 26 Oct 2026 00:00:00 +0000Kehua Chen, Mingyi Chen Document layout analysis (DLA) faces a long-standing dilemma: existing methods either capture rich local details at prohibitive computational cost (e.g., Transformer-based approaches with quadratic complexity) or achieve efficient global modeling but sacrifice fine-grained structural awareness (e.g., state-space models…https://arxiv.org/abs/2610.28171https://arxiv.org/abs/2610.28171Tue, 20 Oct 2026 00:00:00 +0000Zhiyuan Zhao, Hengrui Kang, Guang Liang, Bin Wang, et al. Accurate and efficient document layout analysis is critical for modern document parsing systems. However, although the YOLO framework represents a leading paradigm for the real-time detector, its adaptation to heterogeneous documents remains underexplored. To address this gap, we propose DocLayout-YOLO, a document-spec…https://arxiv.org/abs/2610.20335https://arxiv.org/abs/2610.20335Wed, 14 Oct 2026 00:00:00 +0000Yuheng Chen, Yufan Chen, Zhuojun Cai, Ruiping Liu, et al. · NeurIPS 2026 Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scientific figures, captions, and visual semantics weakly connected, and fails to measure whether a model can produce a sing…https://arxiv.org/abs/2610.18238https://arxiv.org/abs/2610.18238Tue, 13 Oct 2026 00:00:00 +0000Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models ind…https://arxiv.org/abs/2609.24220https://arxiv.org/abs/2609.24220Mon, 21 Sep 2026 00:00:00 +0000Uday Allu, Abhivanth Sivaprakash, Pratik Singh, Aman Manocha Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presentations, and scans -- whose content is locked inside complex visual layouts, multi-column pages, and dense tables. Rule-based extraction and OCR destroy reading order, f…https://arxiv.org/abs/2609.03874https://arxiv.org/abs/2609.03874Thu, 03 Sep 2026 00:00:00 +0000Vineet Kumar, Meghanadh Pulivarthi, vishwajeet kumar, Jaydeep Sen, et al. Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at handling long context, but still suffer from "lost in the middle" problem. Thus, precise and accurate retrieval is important. Current retrievers chunk …https://arxiv.org/abs/2608.26921https://arxiv.org/abs/2608.26921Thu, 27 Aug 2026 00:00:00 +0000Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib, Sahraoui Dhelim We introduce AraMS-28k, the largest publicly released line-level dataset of genuine historical Arabic manuscripts, comprising 14 books, 3,043 pages, and 28,600 annotated text lines (27,971 main-text, 629 margin). Thirteen books are hand-copied manuscripts spanning three script traditions -- Naskh, Ruq'ah, and Maghrebi …https://arxiv.org/abs/2608.12898https://arxiv.org/abs/2608.12898Thu, 13 Aug 2026 00:00:00 +0000Peng Cai, Zhaofan Zou, Shifa Liu, Yikun Wang, et al. Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have significantly advanced document parsing. However, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on …https://arxiv.org/abs/2608.10396https://arxiv.org/abs/2608.10396Tue, 11 Aug 2026 00:00:00 +0000Lujie Ban, Jiangtao Zhu, Yuanheng Yu, Jiasheng Shi, et al. Transforming table-form documents into machine-processable records requires recovering not only their visible content but also the multilevel structure that organizes it. However, existing benchmarks evaluate either holistic document outputs or conventional table grids, and their aggregate scores provide little insight…https://arxiv.org/abs/2607.22200https://arxiv.org/abs/2607.22200Fri, 24 Jul 2026 00:00:00 +0000Xudong Liu, Bicheng Wan, Yulin Jin End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying gener…https://arxiv.org/abs/2607.18997https://arxiv.org/abs/2607.18997Tue, 21 Jul 2026 00:00:00 +0000Tianyang Huang, Alessio Lombardi, Ahmed Elnagar, Ahmed Zalouk, et al. Information Extraction (IE) from Architecture, Engineering, and Construction (AEC) drawings remains hindered by manual inefficiency, while Layout Detection, a vital 'middleware' organizing graphical and textual hierarchies, is underexplored. General document layout models, optimized for text-centric content, lack valid…https://arxiv.org/abs/2607.15082https://arxiv.org/abs/2607.15082Thu, 16 Jul 2026 00:00:00 +0000William Mocaër, Solène Tarride, Thomas Constum, Merveilles Agbeti-Messan, et al. · ICDAR 2026 Workshop Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines state-of-the-art ope…https://arxiv.org/abs/2607.22679https://arxiv.org/abs/2607.22679Sat, 11 Jul 2026 00:00:00 +0000Bohou Li, Benjamin Sowell, Mehul Shah, Mark Lindblad, et al. In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relatio…https://arxiv.org/abs/2607.07836https://arxiv.org/abs/2607.07836Wed, 08 Jul 2026 00:00:00 +0000Zuming Huang, Jun Huang, Kexuan Ren, Baode Wang, et al. We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthe…https://arxiv.org/abs/2607.01018https://arxiv.org/abs/2607.01018Wed, 01 Jul 2026 00:00:00 +0000Iddo Hakim, Sharva Gogawale, Omer Ventura, Gal Grudka, et al. · DAS 2026 Reading order inference remains a critical bottleneck in the digitization of complex historical manuscripts, where pages contain multiple spatially interleaved reading streams, the canonical example being the Glossa Ordinaria layout, in which a central text is surrounded by commentaries that wrap around it in non-recta…https://arxiv.org/abs/2607.00596https://arxiv.org/abs/2607.00596Wed, 01 Jul 2026 00:00:00 +0000Chahan Vidal-Gorène, Nadi Tomeh, Victoria Khurshudyan · ICPR 2026 This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dataset of 66 pages and compare geometric heuristics, YOLO-based layout parsing, an end-to-end document model ECLAIR, and a hybrid method combi…https://arxiv.org/abs/2606.28081https://arxiv.org/abs/2606.28081Fri, 26 Jun 2026 00:00:00 +0000Wei Liu, John Wenskovitch, Chris North, Rebecca Faust Spatialized document layouts are widely used for exploratory analysis of text corpora, but interpreting the spatial organization of documents and the relationships between regions remains challenging. Existing approaches primarily summarize document content or explain how layouts are generated, providing limited suppor…https://arxiv.org/abs/2606.23344https://arxiv.org/abs/2606.23344Mon, 22 Jun 2026 00:00:00 +0000Cheng Cui, Tingquan Gao, Xueqing Wang, Changda Zhou, et al. · ECCV 2026 Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document layout elements, geometric distortions (\eg, paper warping and bending, perspective variations), and reading order within diverse layout structures. Existing approache…https://arxiv.org/abs/2608.14587https://arxiv.org/abs/2608.14587Fri, 19 Jun 2026 00:00:00 +0000Nicolas Turenne, Youcef Sklab, Eric Chenin, Jean-Daniel Zucker Background: Recent advances in information retrieval (IR) leverage both dense and sparse representations, large language models (LLMs), and specialized retrieval models to improve ranking accuracy, relevance, and cross-lingual performance. Complementary techniques such as passage indexing, document layout analysis, and…https://arxiv.org/abs/2606.17644https://arxiv.org/abs/2606.17644Tue, 16 Jun 2026 00:00:00 +0000Nick Jochum, Tobias Alt-Veit, Christian Schön, Alexander Lück, et al. · ICDAR 2026 Datasets in practical document processing scenarios typically grow over time, and their class annotations undergo continuous refinement. This creates significant re-annotation efforts, which are time-consuming and costly. A promising remedy is to re-annotate only a small subset of available documents manually and apply…https://arxiv.org/abs/2606.07401https://arxiv.org/abs/2606.07401Fri, 05 Jun 2026 00:00:00 +0000Ameya Joshi, Joon Kim, Gus Eggert, Joseph Bajor, et al. Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level sim…https://arxiv.org/abs/2606.06242https://arxiv.org/abs/2606.06242Thu, 04 Jun 2026 00:00:00 +0000AJ Carl P. Dy, Aivin V. Solatorio Institutional documents contain substantial amounts of operational and analytical information embedded within figures and tables. Current approaches for extracting visual content from documents are largely built around generic document layout analysis, where figures and tables are treated as uniformly relevant document…https://arxiv.org/abs/2606.04231https://arxiv.org/abs/2606.04231Tue, 02 Jun 2026 00:00:00 +0000Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, et al. · ACL 2026 Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and for answer generation. While efficient, this trend often neglects explicit handling of the rich, structured information in complex enterprise doc…https://arxiv.org/abs/2606.04166https://arxiv.org/abs/2606.04166Tue, 02 Jun 2026 00:00:00 +0000Benjamin Kiessling Practical text-recognition pipelines for historical documents typically decompose layout analysis into line detection followed by a separate reading-order step, with the latter most often handled by a hand-coded geometric heuristic that struggles with marginalia, multiple columns, tables, and source-specific editorial …https://arxiv.org/abs/2605.22100https://arxiv.org/abs/2605.22100Thu, 21 May 2026 00:00:00 +0000Bangbang Zhou, Hangdi Xing, Yifan Chen, Jianjun Xu, et al. Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain inadequate for realistic scenarios. Existing benchmarks either focus on specific tasks o…