{"list":"other","total":56,"rows":[{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"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":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"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":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2407.02392","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","created":"2024-07-02","cited_by_count":172},{"id":"2404.06512","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","created":"2024-04-09","cited_by_count":159},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2003.11288","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","created":"2020-03-25","cited_by_count":69},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35},{"id":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34},{"id":"2402.05472","title":"Question Aware Vision Transformer for Multimodal Reasoning","created":"2024-02-08","cited_by_count":32},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27},{"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":"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":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23},{"id":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16},{"id":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11},{"id":"2407.12594","title":"VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding","created":"2024-07-17","cited_by_count":8},{"id":"2406.08255","title":"M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation","created":"2024-06-12","cited_by_count":4}],"next_cursor":null}