{"total":21,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256,"area":null},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73,"area":null},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2106.10786","title":"ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction","created":"2021-06-21","cited_by_count":22,"area":null},{"id":"2208.11168","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","created":"2022-08-23","cited_by_count":17,"area":null},{"id":"2101.12741","title":"Post-OCR Paragraph Recognition by Graph Convolutional Networks","created":"2021-01-29","cited_by_count":16,"area":null},{"id":"2105.08194","title":"Visual FUDGE: Form Understanding via Dynamic Graph Editing","created":"2021-05-17","cited_by_count":15,"area":null},{"id":"2304.07957","title":"A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images","created":"2023-04-17","cited_by_count":9,"area":null},{"id":"2404.04003","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","created":"2024-04-05","cited_by_count":8,"area":null},{"id":"2403.04080","title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2405.14259","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2509.16506","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2402.05282","title":"TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2405.03104","title":"GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2305.04460","title":"Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2401.03742","title":"Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach","created":"2024-01-08","cited_by_count":1,"area":null},{"id":"2404.19259","title":"DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documents","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2404.00488","title":"Noise-Aware Training of Layout-Aware Language Models","created":"2024-03-30","cited_by_count":0,"area":null}],"next_cursor":null}