{"total":32,"rows":[{"id":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2506.07015","title":"TABLET: Table Structure Recognition using Encoder-only Transformers","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2409.11656","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2505.13887","title":"Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2510.00039","title":"AutoPK: Leveraging LLMs and a Hybrid Similarity Metric for Advanced Retrieval of Pharmacokinetic Data from Complex Tables and Documents","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2511.05818","title":"LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2512.10004","title":"Exploring LLMs for Scientific Information Extraction Using The SciEx Framework","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2409.19573","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2502.17110","title":"Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2504.16419","title":"PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2503.18641","title":"From Fragment to One Piece: A Survey on AI-Driven Graphic Design","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2505.03214","title":"DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2506.21055","title":"Class-Agnostic Region-of-Interest Matching in Document Images","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2502.12614","title":"Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.20978","title":"ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2504.00385","title":"Leveraging Contrast Information for Efficient Document Shadow Removal","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.20047","title":"HCT-QA: A Benchmark for Question Answering on Human-Centric Tables","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2603.22819","title":"TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.02880","title":"InstructTable: Improving Table Structure Recognition Through Instructions","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2409.10811","title":"Grounded GUI Understanding for Vision-Based Spatial Intelligent Agent: Exemplified by Extended Reality Apps","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2508.10311","title":"From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2602.16430","title":"Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.16070","title":"TableSeq: Unified Generation of Structure, Content, and Layout","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.16665","title":"CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.22422","title":"FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.17874","title":"Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations","created":"2026-06-16","cited_by_count":0,"area":null}],"next_cursor":null}