{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"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":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"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":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"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":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139},{"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":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"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":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2303.17605","title":"SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer","created":"2023-03-30","cited_by_count":60},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50},{"id":"2303.08685","title":"Making Vision Transformers Efficient from A Token Sparsification View","created":"2023-03-15","cited_by_count":29},{"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":"2205.13724","title":"V-Doc : Visual questions answers with Documents","created":"2022-05-27","cited_by_count":19},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18},{"id":"1808.04614","title":"Explaining Queries over Web Tables to Non-Experts","created":"2018-08-14","cited_by_count":5}],"next_cursor":null}