{"list":"other","total":142,"rows":[{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"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},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2002.09797","title":"Reliable Fidelity and Diversity Metrics for Generative Models","created":"2020-02-23","cited_by_count":434},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"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},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2311.10774","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","created":"2023-11-15","cited_by_count":150},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150},{"id":"2005.00589","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","created":"2020-05-01","cited_by_count":147},{"id":"2404.16790","title":"SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension","created":"2024-04-25","cited_by_count":146},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2212.09662","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","created":"2022-12-19","cited_by_count":133},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"2307.05356","title":"VisText: A Benchmark for Semantically Rich Chart Captioning","created":"2023-06-28","cited_by_count":112},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"1903.01949","title":"TableBank: A Benchmark Dataset for Table Detection and Recognition","created":"2019-03-05","cited_by_count":102},{"id":"2305.17306","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","created":"2023-05-26","cited_by_count":102},{"id":"2004.12629","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","created":"2020-04-27","cited_by_count":98},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95},{"id":"1706.02337","title":"Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network","created":"2017-06-07","cited_by_count":92},{"id":"1908.04729","title":"Complicated Table Structure Recognition","created":"2019-08-13","cited_by_count":92},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88},{"id":"2108.00871","title":"Constrained Graphic Layout Generation via Latent Optimization","created":"2021-08-02","cited_by_count":83},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82},{"id":"2412.02210","title":"CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy","created":"2024-12-03","cited_by_count":81},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80},{"id":"1809.00812","title":"RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes","created":"2018-09-04","cited_by_count":74},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2003.10557","title":"ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation","created":"2020-03-23","cited_by_count":69},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69},{"id":"2003.02567","title":"GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images","created":"2020-03-05","cited_by_count":68},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58},{"id":"2212.09736","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","created":"2022-12-19","cited_by_count":57},{"id":"2305.02567","title":"LayoutDM: Transformer-based Diffusion Model for Layout Generation","created":"2023-05-04","cited_by_count":57},{"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},{"id":"1907.12861","title":"LEAF-QA: Locate, Encode & Attend for Figure Question Answering","created":"2019-07-30","cited_by_count":54},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"1909.00302","title":"READ: Recursive Autoencoders for Document Layout Generation","created":"2019-09-01","cited_by_count":51},{"id":"1707.03904","title":"Quasar: Datasets for Question Answering by Search and Reading","created":"2017-07-12","cited_by_count":50},{"id":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","cited_by_count":43},{"id":"2303.05049","title":"Unifying Layout Generation with a Decoupled Diffusion Model","created":"2023-03-09","cited_by_count":41},{"id":"1801.08379","title":"DeepWriting: Making Digital Ink Editable via Deep Generative Modeling","created":"2018-01-25","cited_by_count":39},{"id":"2404.09987","title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","created":"2024-04-15","cited_by_count":39},{"id":"2104.03964","title":"Handwriting Transformers","created":"2021-04-08","cited_by_count":37},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37},{"id":"1804.02445","title":"Extracting Scientific Figures with Distantly Supervised Neural Networks","created":"2018-04-06","cited_by_count":36},{"id":"2009.00678","title":"Text and Style Conditioned GAN for Generation of Offline Handwriting Lines","created":"2020-09-01","cited_by_count":35},{"id":"2303.14736","title":"Disentangling Writer and Character Styles for Handwriting Generation","created":"2023-03-26","cited_by_count":35},{"id":"2303.15269","title":"Handwritten Text Generation from Visual Archetypes","created":"2023-03-27","cited_by_count":32},{"id":"2410.05261","title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","created":"2024-10-07","cited_by_count":32},{"id":"2402.19014","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","created":"2024-02-29","cited_by_count":30},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30},{"id":"1909.09380","title":"EATEN: Entity-aware Attention for Single Shot Visual Text Extraction","created":"2019-09-20","cited_by_count":29},{"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},{"id":"2004.08686","title":"A Large Dataset of Historical Japanese Documents with Complex Layouts","created":"2020-04-18","cited_by_count":25},{"id":"2011.06704","title":"Diffusion models for Handwriting Generation","created":"2020-11-13","cited_by_count":25},{"id":"2311.13194","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","created":"2023-11-22","cited_by_count":25},{"id":"2003.13197","title":"Cross-Domain Document Object Detection: Benchmark Suite and Method","created":"2020-03-30","cited_by_count":24},{"id":"2303.14884","title":"A large-scale dataset for end-to-end table recognition in the wild","created":"2023-03-27","cited_by_count":24},{"id":"2306.00526","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","created":"2023-06-01","cited_by_count":24},{"id":"2008.11354","title":"Generating Handwriting via Decoupled Style Descriptors","created":"2020-08-26","cited_by_count":23},{"id":"2110.09915","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","created":"2021-10-19","cited_by_count":23},{"id":"2303.13839","title":"HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures","created":"2023-03-24","cited_by_count":23},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"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},{"id":"2403.18187","title":"LayoutFlow: Flow Matching for Layout Generation","created":"2024-03-27","cited_by_count":21}],"next_cursor":"100"}