{"total":108,"rows":[{"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,"area":null},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"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,"area":null},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279,"area":null},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235,"area":null},{"id":"2305.19327","title":"Cones 2: Customizable Image Synthesis with Multiple Subjects","created":"2023-05-30","cited_by_count":101,"area":null},{"id":"2403.11641","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","created":"2024-03-18","cited_by_count":101,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2506.07977","title":"OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation","created":"2025-06-09","cited_by_count":87,"area":null},{"id":"2307.06925","title":"Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models","created":"2023-07-13","cited_by_count":85,"area":null},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68,"area":null},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2307.13125","title":"Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review","created":"2023-07-24","cited_by_count":48,"area":null},{"id":"2408.05939","title":"UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization","created":"2024-08-12","cited_by_count":47,"area":null},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"area":null},{"id":"2312.17334","title":"Improving Image Restoration through Removing Degradations in Textual Representations","created":"2023-12-28","cited_by_count":36,"area":null},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36,"area":null},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34,"area":null},{"id":"2403.17008","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","created":"2024-03-25","cited_by_count":31,"area":null},{"id":"2311.17060","title":"Material Palette: Extraction of Materials from a Single Image","created":"2023-11-28","cited_by_count":28,"area":null},{"id":"2403.14617","title":"Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion","created":"2024-03-21","cited_by_count":27,"area":null},{"id":"2502.01720","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","created":"2025-02-03","cited_by_count":25,"area":null},{"id":"2303.04587","title":"A Prompt Log Analysis of Text-to-Image Generation Systems","created":"2023-03-08","cited_by_count":24,"area":null},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2502.13081","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey","created":"2025-02-18","cited_by_count":20,"area":null},{"id":"2311.03355","title":"SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis","created":"2023-11-06","cited_by_count":18,"area":null},{"id":"2412.02030","title":"NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training","created":"2024-12-02","cited_by_count":17,"area":null},{"id":"2511.11483","title":"ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation","created":"2025-11-14","cited_by_count":17,"area":null},{"id":"2404.02697","title":"Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution","created":"2024-04-03","cited_by_count":16,"area":null},{"id":"2404.16212","title":"An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape","created":"2024-04-24","cited_by_count":16,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2301.12811","title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","created":"2023-01-30","cited_by_count":14,"area":null},{"id":"2405.00196","title":"Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet","created":"2024-04-30","cited_by_count":13,"area":null},{"id":"2409.00342","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation","created":"2024-08-31","cited_by_count":13,"area":null},{"id":"2310.01105","title":"Energy-Guided Continuous Entropic Barycenter Estimation for General Costs","created":"2023-10-02","cited_by_count":12,"area":null},{"id":"2509.21318","title":"SD3.5-Flash: Distribution-Guided Distillation of Generative Flows","created":"2025-09-25","cited_by_count":11,"area":null},{"id":"2508.06082","title":"SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment","created":"2025-08-08","cited_by_count":10,"area":null},{"id":"2309.17175","title":"TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2505.13437","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2310.17705","title":"A Wireless AI-Generated Content (AIGC) Provisioning Framework Empowered by Semantic Communication","created":"2023-10-26","cited_by_count":8,"area":null},{"id":"2312.10718","title":"CogCartoon: Towards Practical Story Visualization","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2503.17760","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization","created":"2025-03-22","cited_by_count":8,"area":null},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2304.01999","title":"Revisiting the Evaluation of Image Synthesis with GANs","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2302.01287","title":"Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains","created":"2023-02-02","cited_by_count":6,"area":null},{"id":"2405.17111","title":"Diffusion Bridge AutoEncoders for Unsupervised Representation Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2502.15856","title":"A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Styles","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2405.16570","title":"ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2509.24935","title":"Scalable GANs with Transformers","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2605.00503","title":"End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2305.13517","title":"Statistical Guarantees of Group-Invariant GANs","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2306.02083","title":"Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distribution","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2412.02632","title":"Scaling Image Tokenizers with Grouped Spherical Quantization","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2505.23161","title":"Implicit Inversion turns CLIP into a Decoder","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2508.09959","title":"LIA-X: Interpretable Latent Portrait Animator","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2601.14103","title":"Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2304.07410","title":"Text-Conditional Contextualized Avatars For Zero-Shot Personalization","created":"2023-04-14","cited_by_count":3,"area":null},{"id":"2308.09717","title":"Smoothness Similarity Regularization for Few-Shot GAN Adaptation","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2402.15919","title":"Learning to See Through Dazzle","created":"2024-02-24","cited_by_count":3,"area":null},{"id":"2407.11104","title":"Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conception","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2408.07116","title":"Generative Photomontage","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2602.00849","title":"RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2304.13742","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2306.07716","title":"Dynamically Masked Discriminator for Generative Adversarial Networks","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2307.08995","title":"Revisiting Latent Space of GAN Inversion for Real Image Editing","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2404.00521","title":"CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2409.12399","title":"I2I-Galip: Unsupervised Medical Image Translation Using Generative Adversarial CLIP","created":"2024-09-19","cited_by_count":2,"area":null},{"id":"2508.17874","title":"Vocoder-Projected Feature Discriminator","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2512.21867","title":"DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.09605","title":"Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2304.00964","title":"Robust Text-driven Image Editing Method that Adaptively Explores Directions in Latent Spaces of StyleGAN and CLIP","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2308.15472","title":"Learning Modulated Transformation in GANs","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2310.08921","title":"Feature Proliferation -- the \"Cancer\" in StyleGAN and its Treatments","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2312.02192","title":"DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding","created":"2023-12-02","cited_by_count":1,"area":null},{"id":"2401.06035","title":"RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2407.05527","title":"Rethinking Image Skip Connections in StyleGAN2","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2407.05546","title":"AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2410.01638","title":"Data Extrapolation for Text-to-image Generation on Small Datasets","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2502.01507","title":"End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2503.08133","title":"MGHanD: Multi-modal Guidance for authentic Hand Diffusion","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2506.01493","title":"Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2511.03735","title":"Friction on Demand: A Generative Framework for the Inverse Design of Metainterfaces","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2605.24843","title":"Adversarial Error Correction for Visual Autoregressive Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2303.04001","title":"ELODIN: Naming Concepts in Embedding Spaces","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2305.03977","title":"Unlocking the Power of GANs in Non-Autoregressive Text Generation","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2310.09999","title":"Outlier Detection Using Generative Models with Theoretical Performance Guarantees","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2401.10526","title":"On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss","created":"2024-01-19","cited_by_count":0,"area":null},{"id":"2404.01984","title":"Fashion Style Editing with Generative Human Prior","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2405.02332","title":"Efficient Exploration of Image Classifier Failures with Bayesian Optimization and Text-to-Image Models","created":"2024-04-26","cited_by_count":0,"area":null},{"id":"2410.07663","title":"Co-learning Single-Step Diffusion Upsampler and Downsampler with Two Discriminators and Distillation","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.03226","title":"Feature Map Similarity Reduction in Convolutional Neural Networks","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2503.05974","title":"LapLoss: Laplacian Pyramid-based Multiscale loss for Image Translation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2508.09844","title":"On the Generalization Limits of Quantum Generative Adversarial Networks with Pure State Generators","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.04576","title":"SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.25609","title":"Revisiting GAN with Bayes-Optimal Discrimination","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.01517","title":"NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation","created":"2025-11-03","cited_by_count":0,"area":null}],"next_cursor":"100"}