{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2303.09833","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","created":"2023-03-17","cited_by_count":294},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"2305.01644","title":"Key-Locked Rank One Editing for Text-to-Image Personalization","created":"2023-05-02","cited_by_count":194},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2211.06956","title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","created":"2022-11-13","cited_by_count":144},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123},{"id":"1609.03126","title":"Energy-based Generative Adversarial Network","created":"2016-09-11","cited_by_count":119},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2303.05334","title":"Natural scene reconstruction from fMRI signals using generative latent diffusion","created":"2023-03-09","cited_by_count":97},{"id":"1908.03835","title":"AutoGAN: Neural Architecture Search for Generative Adversarial Networks","created":"2019-08-11","cited_by_count":94},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89},{"id":"2306.16934","title":"DreamDiffusion: Generating High-Quality Images from Brain EEG Signals","created":"2023-06-29","cited_by_count":56},{"id":"2308.04249","title":"MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion","created":"2023-08-08","cited_by_count":47},{"id":"2312.13691","title":"DreamTuner: Single Image is Enough for Subject-Driven Generation","created":"2023-12-21","cited_by_count":41},{"id":"2308.06725","title":"CLE Diffusion: Controllable Light Enhancement Diffusion Model","created":"2023-08-13","cited_by_count":30},{"id":"2312.14871","title":"BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction","created":"2023-12-22","cited_by_count":30},{"id":"2404.03913","title":"Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models","created":"2024-04-05","cited_by_count":23},{"id":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18},{"id":"2303.18181","title":"A Closer Look at Parameter-Efficient Tuning in Diffusion Models","created":"2023-03-31","cited_by_count":15},{"id":"2403.19103","title":"Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation","created":"2024-03-28","cited_by_count":12},{"id":"2312.05915","title":"Diffusion for Natural Image Matting","created":"2023-12-10","cited_by_count":11},{"id":"2401.17664","title":"Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation","created":"2024-01-31","cited_by_count":9},{"id":"2302.04841","title":"Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics","created":"2023-02-09","cited_by_count":7},{"id":"2403.20231","title":"U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation","created":"2024-03-29","cited_by_count":7},{"id":"2306.11504","title":"Align, Adapt and Inject: Sound-guided Unified Image Generation","created":"2023-06-20","cited_by_count":6}],"next_cursor":null}