{"list":"other","total":64,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2010.00904","title":"Autoregressive Entity Retrieval","created":"2020-10-02","cited_by_count":334},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2004.01804","title":"Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval","created":"2020-04-03","cited_by_count":309},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113},{"id":"1410.0210","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","created":"2014-10-01","cited_by_count":112},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"2004.07202","title":"Entities as Experts: Sparse Memory Access with Entity Supervision","created":"2020-04-15","cited_by_count":100},{"id":"2311.08377","title":"Learning to Filter Context for Retrieval-Augmented Generation","created":"2023-11-14","cited_by_count":83},{"id":"2006.01969","title":"REL: An Entity Linker Standing on the Shoulders of Giants","created":"2020-06-02","cited_by_count":61},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","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":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36},{"id":"2110.02369","title":"EntQA: Entity Linking as Question Answering","created":"2021-10-05","cited_by_count":34},{"id":"2210.08901","title":"Contrastive Language-Image Pre-Training with Knowledge Graphs","created":"2022-10-17","cited_by_count":34},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31},{"id":"2311.03250","title":"Instructed Language Models with Retrievers Are Powerful Entity Linkers","created":"2023-11-06","cited_by_count":18},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14},{"id":"2204.05990","title":"Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem","created":"2022-04-12","cited_by_count":11},{"id":"2112.07133","title":"CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision","created":"2021-12-14","cited_by_count":7},{"id":"2310.07795","title":"Ontology Enrichment for Effective Fine-grained Entity Typing","created":"2023-10-11","cited_by_count":3},{"id":"2311.03253","title":"Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency","created":"2023-11-06","cited_by_count":3}],"next_cursor":null}