{"total":66,"rows":[{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"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":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"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":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2404.09987","title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","created":"2024-04-15","cited_by_count":39,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"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":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","cited_by_count":24,"area":null},{"id":"2502.13759","title":"Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework","created":"2025-02-19","cited_by_count":24,"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":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2408.04203","title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2412.02621","title":"Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions","created":"2024-12-03","cited_by_count":18,"area":null},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"area":null},{"id":"2412.19712","title":"From Elements to Design: A Layered Approach for Automatic Graphic Design Composition","created":"2024-12-27","cited_by_count":13,"area":null},{"id":"2510.18915","title":"UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models","created":"2025-10-21","cited_by_count":13,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2409.04095","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","created":"2024-09-06","cited_by_count":12,"area":null},{"id":"2402.03848","title":"ANLS* -- A Universal Document Processing Metric for Generative Large Language Models","created":"2024-02-06","cited_by_count":10,"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":"2407.12594","title":"VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding","created":"2024-07-17","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":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2412.14596","title":"LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining","created":"2024-12-19","cited_by_count":5,"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":"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":"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":"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":"2406.05496","title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities","created":"2024-06-08","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":"2408.14805","title":"Platypus: A Generalized Specialist Model for Reading Text in Various Forms","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2505.18115","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2603.11044","title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","created":"2026-03-11","cited_by_count":2,"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":"2511.17607","title":"Robustness of Structured Data Extraction from Perspectively Distorted Documents","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2602.10138","title":"Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement","created":"2026-02-08","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":"2505.00275","title":"AdCare-VLM: Towards a Unified and Pre-aligned Latent Representation for Healthcare Video Understanding","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2602.21225","title":"Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.01528","title":"Boosting AI Reliability with an FSM-Driven Streaming Inference Pipeline: An Industrial Case","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.04380","title":"CPT: Controllable and Editable Design Variations with Language Models","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.11042","title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2608.00036","title":"XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.07527","title":"DocAtlas: Long-Document Understanding as Mutable-State Interaction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.17538","title":"From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.20574","title":"DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering","created":"2026-09-17","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}