{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"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":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"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":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"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":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"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":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"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":"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":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"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":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"2303.16434","title":"TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs","created":"2023-03-29","cited_by_count":184},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"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":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80},{"id":"1609.04938","title":"Image-to-Markup Generation with Coarse-to-Fine Attention","created":"2016-09-16","cited_by_count":79},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68},{"id":"2106.13488","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","created":"2021-06-25","cited_by_count":67},{"id":"2307.09474","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","created":"2023-07-18","cited_by_count":65},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28},{"id":"2210.06423","title":"Foundation Transformers","created":"2022-10-12","cited_by_count":19},{"id":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12}],"next_cursor":null}