{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"1909.07083","title":"Controllable Text-to-Image Generation","created":"2019-09-16","cited_by_count":187},{"id":"2106.09232","title":"Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction","created":"2021-06-17","cited_by_count":129},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86},{"id":"2108.12724","title":"DEGREE: A Data-Efficient Generation-Based Event Extraction Model","created":"2021-08-29","cited_by_count":83},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"1809.09078","title":"Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation","created":"2018-09-24","cited_by_count":73},{"id":"2005.02472","title":"Cross-media Structured Common Space for Multimedia Event Extraction","created":"2020-05-05","cited_by_count":61},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60},{"id":"2202.12109","title":"Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction","created":"2022-02-24","cited_by_count":54},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50},{"id":"2105.14485","title":"CLEVE: Contrastive Pre-training for Event Extraction","created":"2021-05-30","cited_by_count":36},{"id":"2211.03044","title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning","created":"2022-11-06","cited_by_count":36},{"id":"2210.03765","title":"Visualize Before You Write: Imagination-Guided Open-Ended Text Generation","created":"2022-10-07","cited_by_count":30},{"id":"2105.14924","title":"Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker","created":"2021-05-31","cited_by_count":29},{"id":"2305.03701","title":"LMEye: An Interactive Perception Network for Large Language Models","created":"2023-05-05","cited_by_count":27},{"id":"2009.09654","title":"Generative Imagination Elevates Machine Translation","created":"2020-09-21","cited_by_count":22},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19},{"id":"2204.08535","title":"Imagination-Augmented Natural Language Understanding","created":"2022-04-18","cited_by_count":19},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16},{"id":"1612.00901","title":"Commonly Uncommon: Semantic Sparsity in Situation Recognition","created":"2016-12-03","cited_by_count":13},{"id":"1703.06233","title":"Recurrent Models for Situation Recognition","created":"2017-03-18","cited_by_count":13},{"id":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13},{"id":"2107.02126","title":"A Survey on Deep Learning Event Extraction: Approaches and Applications","created":"2021-07-05","cited_by_count":12},{"id":"2012.10608","title":"Uncertainty-Aware Label Refinement for Sequence Labeling","created":"2020-12-19","cited_by_count":11},{"id":"1804.07881","title":"Event Extraction with Generative Adversarial Imitation Learning","created":"2018-04-21","cited_by_count":3}],"next_cursor":null}