https://ym-xu.github.io/living-survey/fields/document-understanding/#tag=tablesTable detection, structure recognition and table question answering.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2610.29188https://arxiv.org/abs/2610.29188Wed, 21 Oct 2026 00:00:00 +0000Eunbin Kim, Hyeonseok Kang, Sangkeun Jung · EMNLP 2026 Tables in real-world documents, including scientific papers, financial reports, and statistical summaries, frequently use merged cells, multi-level headers, and sectioned layouts. Yet the lightweight formats LLMs handle best (Markdown, CSV) cannot express these structures, while expressive formats (HTML, LaTeX) impose …https://arxiv.org/abs/2610.17937https://arxiv.org/abs/2610.17937Tue, 13 Oct 2026 00:00:00 +0000Haoyang Jiang, Zhuotong Fan, Mingyang Yi, Ju Fan, et al. Table reasoning with language models typically assumes access to clean textual tables. In practice, tables are often serialized into text, which can corrupt cell contents, distort structural relationships, and discard visual cues, leaving the model to reason over incomplete evidence. In contrast, table images retain th…https://arxiv.org/abs/2610.17448https://arxiv.org/abs/2610.17448Mon, 12 Oct 2026 00:00:00 +0000Todd Y. Zhou, James M. Snyder Gaps, skips, and mistakes are the normal state of a historical register: rows go missing, tables cross page breaks, columns slip under wrong names, and column sums disagree with the corresponding row entries. Readers read digits correctly but lose the table structure. On seven clean panels of election returns, the best…https://arxiv.org/abs/2609.32660https://arxiv.org/abs/2609.32660Sat, 26 Sep 2026 00:00:00 +0000Hanqian Li, Sirui Huang, Chen Ling, Jungang Li, et al. Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns, and cells step by step. Current multimodal large language models (MLLMs) encode the whole image once before reasoning, so they cannot pick up row-, column-, and cell-…https://arxiv.org/abs/2609.26381https://arxiv.org/abs/2609.26381Tue, 22 Sep 2026 00:00:00 +0000Luca Foppiano, Sana Khamassi, Vipul Gupta Transforming scholarly PDFs into machine-readable fulltext remains a bottleneck for large-scale information systems. Recent vision-based parsers improve accuracy, but need GPUs and may introduce noise into the extracted text. GROBID, a modular font-stream parser running on CPU, is the de-facto standard for structuring …https://arxiv.org/abs/2609.17458https://arxiv.org/abs/2609.17458Tue, 15 Sep 2026 00:00:00 +0000Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi, Utkarsh Verma, et al. · WACV 2026 Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative base…https://arxiv.org/abs/2609.08705https://arxiv.org/abs/2609.08705Tue, 08 Sep 2026 00:00:00 +0000Lei Hu, Shuangping Huang · ICPR 2024 Table Structure Recognition (TSR) aims to extract the bounding boxes of cells and table structure (e.g., HTML) from table images. Although current approaches have made significant progress, the latest image-to-sequence methods overlook the explicit utilization of the bounding box information when predicting HTML sequen…https://arxiv.org/abs/2609.08330https://arxiv.org/abs/2609.08330Tue, 08 Sep 2026 00:00:00 +0000Dhruv Kudale, Udhay Brahmi, Ganesh Ramakrishnan · ICDAR 2026 Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visual question answering. While existing deep learning models perform well on English and Chinese documents, they struggle with multilingual, multi-script documents due to…https://arxiv.org/abs/2608.08459https://arxiv.org/abs/2608.08459Sun, 09 Aug 2026 00:00:00 +0000Zhuowen Liang, Zhengxuan Zhang, Jiayang Wang, Jiazhuo Chen, et al. Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare, education, transportation, and enterprise operations, downstream workflows rely on normalized schemas, entity identities, keys, cross-table…https://arxiv.org/abs/2607.13347https://arxiv.org/abs/2607.13347Wed, 15 Jul 2026 00:00:00 +0000Donghwan Kim LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We study it in table recognition, where deterministic TEDS evaluation provides a controlled testbed, using FinTabNet and OmniDocBench. Three findings emerge. First, judge si…https://arxiv.org/abs/2607.00747https://arxiv.org/abs/2607.00747Wed, 01 Jul 2026 00:00:00 +0000Eliott Thomas, Mickael Coustaty, Aurelie Joseph, Gaspar Deloin, et al. · ICDAR 2026 Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their internal layout. Building task-specific training sets for this pipeline is costly, particularly for TSR which requires fine-grained structura…https://arxiv.org/abs/2607.00734https://arxiv.org/abs/2607.00734Wed, 01 Jul 2026 00:00:00 +0000Eliott Thomas, Tri-Cong Pham, Mickael Coustaty, Aurelie Joseph, et al. · ICDAR 2026 Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images, a key step in document understanding pipelines. Accurate TSR depends on precise boundary localization: small errors in row or column boundaries can propagate into incorrect cell assignments and structural inconsi…https://arxiv.org/abs/2606.29905https://arxiv.org/abs/2606.29905Mon, 29 Jun 2026 00:00:00 +0000Gengluo Li, Shangpin Peng, Chengquan Zhang, Binghong Wu, et al. · ECCV 2026 Table parsing aims to convert table images into structured, machine-readable representations, a task requiring the joint perception of complex spatial layouts and textual content. While recent vision-language models (VLMs) enable end-to-end parsing, they typically rely on direct supervision of the final output, thereby…https://arxiv.org/abs/2606.18721https://arxiv.org/abs/2606.18721Wed, 17 Jun 2026 00:00:00 +0000Hong-Jun Choi, Jongho Lee, Jaeyoung Kim · ICPR 2026 Table Structure Recognition (TSR) using a pointer network achieves impressive results by predicting HTML sequences while aligning tags to detected text (or cell) regions. However, our analysis reveals that when pointer networks fail, 79.6% of errors occur between spatially adjacent cells (Manhattan distance <= 2). Desp…https://arxiv.org/abs/2606.17874https://arxiv.org/abs/2606.17874Tue, 16 Jun 2026 00:00:00 +0000Takaya Kawakatsu · ICDAR 2026 Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition within a unified framework. Existing approaches often rely on autoregressive decoders to generate table structures and reuse their hidden states for cell localization and content recognition. This …https://arxiv.org/abs/2606.09788https://arxiv.org/abs/2606.09788Mon, 08 Jun 2026 00:00:00 +0000Brandon Smock, Libin Liang, Maxim Sokolov, Amrit Ramesh, et al. · DAS 2026 Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweig…https://arxiv.org/abs/2606.01132https://arxiv.org/abs/2606.01132Sun, 31 May 2026 00:00:00 +0000Issa Sugiura, Shuhei Kurita, Yusuke Oda, Naoaki Okazaki Understanding chart and table images is essential for applying vision-language models (VLMs) to real-world document understanding. While English benchmarks have advanced rapidly, non-English counterparts remain scarce, leaving it unclear whether this progress generalizes across languages. A key obstacle is the difficul…