{"total":29,"rows":[{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2305.07498","title":"Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","cited_by_count":40,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2505.17330","title":"FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding","created":"2025-05-22","cited_by_count":10,"area":null},{"id":"2308.13982","title":"Universal Graph Continual Learning","created":"2023-08-27","cited_by_count":9,"area":null},{"id":"2406.11403","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2602.20569","title":"AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2402.02379","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2511.12658","title":"Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis","created":"2025-11-16","cited_by_count":3,"area":null},{"id":"2604.25213","title":"When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2310.03777","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2609.13617","title":"ChatGPT Images 2.5 on Forgery Tasks: Testing Advertised Improvements Against Known Answers","created":"2026-09-12","cited_by_count":2,"area":null},{"id":"2207.06695","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2311.05778","title":"DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2408.01038","title":"UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2607.22745","title":"AI-generated Images Challenge Visual Trust in High-risk Scenarios","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2309.09800","title":"AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2312.03367","title":"Lazy-k: Decoding for Constrained Token Classification","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2609.00756","title":"Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.14352","title":"Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}