{"total":279,"rows":[{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071,"area":"mllm"},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245,"area":null},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229,"area":"diffusion"},{"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":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"area":null},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140,"area":"diffusion"},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62,"area":null},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2312.02439","title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation","created":"2023-12-05","cited_by_count":56,"area":"lr"},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2305.10825","title":"DiffUTE: Universal Text Editing Diffusion Model","created":"2023-05-18","cited_by_count":45,"area":"diffusion"},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2309.09298","title":"OWL: A Large Language Model for IT Operations","created":"2023-09-17","cited_by_count":43,"area":null},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34,"area":null},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24,"area":null},{"id":"2409.08573","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2601.14251","title":"LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR","created":"2026-01-20","cited_by_count":23,"area":"mllm"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2401.10224","title":"The Manga Whisperer: Automatically Generating Transcriptions for Comics","created":"2024-01-18","cited_by_count":21,"area":null},{"id":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19,"area":null},{"id":"2110.05909","title":"Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes","created":"2021-10-12","cited_by_count":18,"area":null},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18,"area":"mllm"},{"id":"2402.10798","title":"VATr++: Choose Your Words Wisely for Handwritten Text Generation","created":"2024-02-16","cited_by_count":18,"area":"diffusion"},{"id":"2208.07682","title":"The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition","created":"2022-08-16","cited_by_count":17,"area":null},{"id":"2411.11098","title":"MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild","created":"2024-11-17","cited_by_count":17,"area":null},{"id":"2208.08109","title":"Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2302.12324","title":"Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization","created":"2023-02-23","cited_by_count":14,"area":null},{"id":"2406.01062","title":"Layout Agnostic Scene Text Image Synthesis with Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"id":"2305.02593","title":"How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2405.12105","title":"End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music","created":"2024-05-20","cited_by_count":13,"area":null},{"id":"2406.09630","title":"Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition","created":"2024-06-13","cited_by_count":13,"area":null},{"id":"2503.17074","title":"Zero-Shot Styled Text Image Generation, but Make It Autoregressive","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2502.08417","title":"Handwritten Text Recognition: A Survey","created":"2025-02-12","cited_by_count":12,"area":null},{"id":"2308.12477","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","created":"2023-08-24","cited_by_count":11,"area":null},{"id":"2503.15195","title":"Benchmarking Large Language Models for Handwritten Text Recognition","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2505.04915","title":"GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2203.11008","title":"Transformer-based HTR for Historical Documents","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2411.17332","title":"On the Generalization of Handwritten Text Recognition Models","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2306.15769","title":"What Makes ImageNet Look Unlike LAION","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2307.15045","title":"A Transformer-based Approach for Arabic Offline Handwritten Text Recognition","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2311.06176","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers","created":"2023-11-10","cited_by_count":9,"area":null},{"id":"2407.09103","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2410.02179","title":"HATFormer: Historic Handwritten Arabic Text Recognition with Transformers","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2305.19543","title":"Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model","created":"2023-05-31","cited_by_count":8,"area":"diffusion"},{"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":"2406.11432","title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","created":"2024-06-17","cited_by_count":8,"area":"diffusion"},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"id":"2511.04727","title":"IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs","created":"2025-11-06","cited_by_count":8,"area":"mllm"},{"id":"2307.10867","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","created":"2023-07-20","cited_by_count":7,"area":"alignment"},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2309.14389","title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering","created":"2023-09-25","cited_by_count":7,"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":"2407.13559","title":"Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2411.18159","title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2506.15010","title":"Hyper-Local Deformable Transformers for Text Spotting on Historical Maps","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2205.14879","title":"Easter2.0: Improving convolutional models for handwritten text recognition","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2212.05525","title":"Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2302.06308","title":"Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2305.17337","title":"Benchmarking Diverse-Modal Entity Linking with Generative Models","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2306.07033","title":"When Vision Fails: Text Attacks Against ViT and OCR","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2308.09370","title":"TrOMR:Transformer-Based Polyphonic Optical Music Recognition","created":"2023-08-18","cited_by_count":5,"area":null},{"id":"2310.10050","title":"EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2404.18722","title":"Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2501.17441","title":"Towards Making Flowchart Images Machine Interpretable","created":"2025-01-29","cited_by_count":5,"area":null},{"id":"2503.21172","title":"Model as a Game: On Numerical and Spatial Consistency for Generative Games","created":"2025-03-27","cited_by_count":5,"area":"wm"},{"id":"2303.10848","title":"Weakly-Supervised Text Instance Segmentation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2304.11966","title":"ICDAR 2023 Competition on Reading the Seal Title","created":"2023-04-24","cited_by_count":4,"area":null},{"id":"2306.06823","title":"Weakly supervised information extraction from inscrutable handwritten document images","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2308.09368","title":"A tailored Handwritten-Text-Recognition System for Medieval Latin","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2308.13173","title":"DISGO: Automatic End-to-End Evaluation for Scene Text OCR","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2404.12734","title":"Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2409.00751","title":"Self-Supervised Vision Transformers for Writer Retrieval","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2409.11656","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2409.17095","title":"General Detection-based Text Line Recognition","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2410.18277","title":"KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2411.17835","title":"Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction","created":"2024-11-19","cited_by_count":4,"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":"2302.01660","title":"The Learnable Typewriter: A Generative Approach to Text Analysis","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2303.03127","title":"ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2303.05077","title":"Learning the Legibility of Visual Text Perturbations","created":"2023-03-09","cited_by_count":3,"area":null},{"id":"2304.03427","title":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2307.04245","title":"A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2308.15004","title":"PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2308.15037","title":"Is it an i or an l: Test-time Adaptation of Text Line Recognition Models","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2310.09091","title":"Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI","created":"2023-10-13","cited_by_count":3,"area":null},{"id":"2312.09037","title":"Impact of Ground Truth Quality on Handwriting Recognition","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2403.02127","title":"LOCR: Location-Guided Transformer for Optical Character Recognition","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2503.22714","title":"TRIDIS: A Comprehensive Medieval and Early Modern Corpus for HTR and NER","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2505.01435","title":"AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine","created":"2025-04-23","cited_by_count":3,"area":null}],"next_cursor":"100"}