{"total":19,"rows":[{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267,"area":null},{"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":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79,"area":null},{"id":"2409.03643","title":"Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching","created":"2024-09-05","cited_by_count":41,"area":null},{"id":"2604.04771","title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","created":"2026-04-06","cited_by_count":27,"area":null},{"id":"2407.07764","title":"PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer","created":"2024-07-10","cited_by_count":18,"area":null},{"id":"2512.21095","title":"UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters","created":"2025-12-24","cited_by_count":13,"area":null},{"id":"2503.18382","title":"PP-FormulaNet: Bridging Accuracy and Efficiency in Advanced Formula Recognition","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2512.10619","title":"DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2508.00311","title":"DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.01348","title":"ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2409.11677","title":"Enhancing Complex Formula Recognition with Hierarchical Detail-Focused Network","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2508.09220","title":"Towards Scalable Training for Handwritten Mathematical Expression Recognition","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2602.17189","title":"Texo: Formula Recognition within 20M Parameters","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2609.12917","title":"PA-CDM: Position-Aware Character Detection Matching for Evaluating Handwritten Mathematical Expression Recognition","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}