{"list":"other","total":53,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2010.03743","title":"Visual News: Benchmark and Challenges in News Image Captioning","created":"2020-10-08","cited_by_count":121},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107},{"id":"2209.00179","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","created":"2022-09-01","cited_by_count":58},{"id":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44},{"id":"2204.11824","title":"Semi-Parametric Neural Image Synthesis","created":"2022-04-25","cited_by_count":37},{"id":"2305.13631","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","created":"2023-05-23","cited_by_count":27},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23},{"id":"2102.04980","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","created":"2021-02-09","cited_by_count":12}],"next_cursor":null}