{"total":42,"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":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"area":null},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15,"area":null},{"id":"2510.03853","title":"UGround: Towards Unified Visual Grounding with Unrolled Transformers","created":"2025-10-04","cited_by_count":14,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2502.04223","title":"\\'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents","created":"2025-02-06","cited_by_count":9,"area":null},{"id":"2410.12844","title":"TextLap: Customizing Language Models for Text-to-Layout Planning","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2507.09861","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","created":"2025-07-14","cited_by_count":8,"area":null},{"id":"2408.15646","title":"{\\mu}gat: Improving Single-Page Document Parsing by Providing Multi-Page Context","created":"2024-08-28","cited_by_count":7,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2408.00441","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2405.03099","title":"SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2512.20174","title":"Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2408.14764","title":"SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2603.06700","title":"SIQA: Toward Reliable Scientific Image Quality Assessment","created":"2026-03-05","cited_by_count":4,"area":null},{"id":"2502.09843","title":"MuDoC: An Interactive Multimodal Document-grounded Conversational AI System","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2504.13884","title":"Towards a Multimodal Document-grounded Conversational AI System for Education","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2506.12116","title":"Unsupervised Document and Template Clustering using Multimodal Embeddings","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2401.15118","title":"GeoDecoder: Empowering Multimodal Map Understanding","created":"2024-01-26","cited_by_count":2,"area":null},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2607.02956","title":"MORE: A Multilingual Document Parsing Benchmark and Evaluation","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2404.00439","title":"DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering","created":"2024-03-30","cited_by_count":1,"area":null},{"id":"2511.20478","title":"NVIDIA Nemotron Parse 1.1","created":"2025-11-25","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":"2606.03401","title":"Towards Characterizing Scientific Image Utility and Upgradability","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.00596","title":"Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2510.09822","title":"Task-Aware Resolution Optimization for Visual Large Language Models","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2512.18115","title":"Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2606.29378","title":"Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.31811","title":"MuSViT: A Foundation Vision Model for Sheet Music Representation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.14682","title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.00536","title":"DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2610.20335","title":"Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}