{"total":106,"rows":[{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050,"area":"mllm"},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217,"area":"mllm"},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170,"area":"diffusion"},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143,"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":"2411.15245","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","created":"2024-11-22","cited_by_count":53,"area":null},{"id":"2505.03329","title":"FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing","created":"2025-05-06","cited_by_count":46,"area":"diffusion"},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2406.07594","title":"MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models","created":"2024-06-11","cited_by_count":34,"area":"mllm"},{"id":"2411.18824","title":"FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution","created":"2024-11-27","cited_by_count":32,"area":"diffusion"},{"id":"2407.02252","title":"GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models","created":"2024-07-02","cited_by_count":29,"area":"diffusion"},{"id":"2502.14914","title":"CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","created":"2025-02-19","cited_by_count":25,"area":"mllm"},{"id":"2505.17163","title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning","created":"2025-05-22","cited_by_count":25,"area":"lr"},{"id":"2411.15858","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","created":"2024-11-24","cited_by_count":24,"area":null},{"id":"2310.11016","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","created":"2023-10-17","cited_by_count":23,"area":null},{"id":"2311.11268","title":"Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters","created":"2023-11-19","cited_by_count":22,"area":null},{"id":"2510.03663","title":"UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG","created":"2025-10-04","cited_by_count":21,"area":"rag"},{"id":"2303.13095","title":"Modeling Entities as Semantic Points for Visual Information Extraction in the Wild","created":"2023-03-23","cited_by_count":20,"area":null},{"id":"2503.14140","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","created":"2025-03-18","cited_by_count":20,"area":"mllm"},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"id":"2410.10168","title":"First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending","created":"2024-10-14","cited_by_count":16,"area":"diffusion"},{"id":"2503.21749","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis","created":"2025-03-27","cited_by_count":15,"area":null},{"id":"2507.21585","title":"SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation","created":"2025-07-29","cited_by_count":15,"area":"mllm"},{"id":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2412.17225","title":"CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encoder","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14,"area":"mllm"},{"id":"2606.13108","title":"PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks","created":"2026-06-11","cited_by_count":14,"area":"mllm"},{"id":"2403.16422","title":"Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation","created":"2024-03-25","cited_by_count":13,"area":"diffusion"},{"id":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"id":"2407.10810","title":"FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries","created":"2024-07-15","cited_by_count":12,"area":null},{"id":"2407.12317","title":"Out of Length Text Recognition with Sub-String Matching","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2403.00303","title":"ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting","created":"2024-03-01","cited_by_count":10,"area":null},{"id":"2508.13238","title":"DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2404.04624","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","created":"2024-04-06","cited_by_count":9,"area":null},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9,"area":"mllm"},{"id":"2308.08806","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","created":"2023-08-17","cited_by_count":8,"area":"distill"},{"id":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2409.10064","title":"MindGuard: Towards Accessible and Sitgma-free Mental Health First Aid via Edge LLM","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2504.19724","title":"RepText: Rendering Visual Text via Replicating","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2505.19571","title":"VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2603.22228","title":"SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation","created":"2026-03-23","cited_by_count":6,"area":"alignment"},{"id":"2402.14314","title":"Typographic Text Generation with Off-the-Shelf Diffusion Model","created":"2024-02-22","cited_by_count":5,"area":"diffusion"},{"id":"2410.09879","title":"TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control","created":"2024-10-13","cited_by_count":5,"area":null},{"id":"2503.13730","title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark","created":"2025-03-17","cited_by_count":5,"area":"diffusion"},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"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":"2605.14708","title":"StyleTextGen: Style-Conditioned Multilingual Scene Text Generation","created":"2026-05-14","cited_by_count":5,"area":null},{"id":"2405.00145","title":"GUing: A Mobile GUI Search Engine using a Vision-Language Model","created":"2024-04-30","cited_by_count":4,"area":null},{"id":"2406.17777","title":"Text-Animator: Controllable Visual Text Video Generation","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2502.21314","title":"Raccoon: Multi-stage Diffusion Training with Coarse-to-Fine Curating Videos","created":"2025-02-28","cited_by_count":4,"area":"diffusion"},{"id":"2510.11496","title":"AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model","created":"2025-10-13","cited_by_count":4,"area":"mllm"},{"id":"2512.01422","title":"MDiff4STR: Mask Diffusion Model for Scene Text Recognition","created":"2025-12-01","cited_by_count":4,"area":"diffusion"},{"id":"2409.19573","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2501.07334","title":"Anonymization of Documents for Law Enforcement with Machine Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2506.03197","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2510.04003","title":"Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2510.21590","title":"Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2511.11313","title":"DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","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":"2604.16943","title":"MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation","created":"2026-04-18","cited_by_count":2,"area":"mllm"},{"id":"2310.06440","title":"Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2403.07553","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2404.13579","title":"LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2407.18626","title":"Every Part Matters: Integrity Verification of Scientific Figures Based on Multimodal Large Language Models","created":"2024-07-26","cited_by_count":1,"area":"mllm"},{"id":"2410.18823","title":"Towards Visual Text Design Transfer Across Languages","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2412.04137","title":"Text Change Detection in Multilingual Documents Using Image Comparison","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2501.02962","title":"SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2504.14108","title":"DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2504.15182","title":"Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2506.05843","title":"FontAdapter: Instant Font Adaptation in Visual Text Generation","created":"2025-06-06","cited_by_count":1,"area":"diffusion"},{"id":"2507.16362","title":"LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2508.21693","title":"Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2510.02543","title":"Exploring OCR-augmented Generation for Bilingual VQA","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2510.18483","title":"StarBench: A Turn-Based RPG Benchmark for Agentic Multimodal Decision-Making and Information Seeking","created":"2025-10-21","cited_by_count":1,"area":"agents"},{"id":"2601.11981","title":"Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2603.22027","title":"Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models","created":"2026-03-23","cited_by_count":1,"area":"diffusion"},{"id":"2605.23264","title":"Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.12666","title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2404.00852","title":"Ensemble Learning for Vietnamese Scene Text Spotting in Urban Environments","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2406.09779","title":"OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2502.09026","title":"Billet Number Recognition Based on Test-Time Adaptation","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2502.18101","title":"Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Models","created":"2025-02-25","cited_by_count":0,"area":"mllm"},{"id":"2507.17335","title":"TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2509.26235","title":"Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2511.02563","title":"The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.16712","title":"PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.18004","title":"Seeing Justice Clearly: Handwritten Legal Document Translation with OCR and Vision-Language Models","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.06402","title":"MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing","created":"2026-02-06","cited_by_count":0,"area":"mllm"},{"id":"2602.19188","title":"PositionOCR: Augmenting Positional Awareness in Multi-Modal Models via Hybrid Specialist Integration","created":"2026-02-22","cited_by_count":0,"area":"mllm"},{"id":"2602.19641","title":"Evaluating the Impact of Data Anonymization on Image Retrieval","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.06038","title":"FontUse: A Data-Centric Approach to Style- and Use-Case-Conditioned In-Image Typography","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.13059","title":"A Proactive EMR Assistant for Doctor-Patient Dialogue: Streaming ASR, Belief Stabilization, and Preliminary Controlled Evaluation","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.24419","title":"BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.24675","title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.28077","title":"TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":"100"}