{"list":"other","total":52,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"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":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"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":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"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":"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":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105},{"id":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2004.07464","title":"PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks","created":"2020-04-16","cited_by_count":72},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71},{"id":"2406.08660","title":"Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification","created":"2024-06-12","cited_by_count":70},{"id":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67},{"id":"2005.00642","title":"Spatial Dependency Parsing for Semi-Structured Document Information Extraction","created":"2020-05-01","cited_by_count":65},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64},{"id":"2405.00732","title":"LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report","created":"2024-04-29","cited_by_count":47},{"id":"1910.06611","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","created":"2019-10-15","cited_by_count":35},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35},{"id":"2402.00841","title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?","created":"2024-02-01","cited_by_count":33},{"id":"2212.08153","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","created":"2022-12-15","cited_by_count":31},{"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":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","cited_by_count":24},{"id":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23},{"id":"2212.09621","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","created":"2022-12-19","cited_by_count":20},{"id":"1912.10016","title":"A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages","created":"2019-12-20","cited_by_count":16},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12},{"id":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11},{"id":"2009.05169","title":"Sparsifying Transformer Models with Trainable Representation Pooling","created":"2020-09-10","cited_by_count":9},{"id":"2405.18433","title":"Notes on Applicability of GPT-4 to Document Understanding","created":"2024-05-28","cited_by_count":7},{"id":"2401.02823","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","created":"2024-01-05","cited_by_count":6},{"id":"1905.12817","title":"Deep Learning Approach for Receipt Recognition","created":"2019-05-30","cited_by_count":3}],"next_cursor":null}