{"total":142,"rows":[{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487,"area":null},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"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":"2102.08921","title":"How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models","created":"2021-02-17","cited_by_count":196,"area":null},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137,"area":null},{"id":"2103.09396","title":"Pros and Cons of GAN Evaluation Measures: New Developments","created":"2021-03-17","cited_by_count":123,"area":null},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2203.14206","title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","created":"2022-03-27","cited_by_count":46,"area":null},{"id":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41,"area":null},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36,"area":null},{"id":"2109.07001","title":"ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors","created":"2021-09-14","cited_by_count":35,"area":null},{"id":"2208.14818","title":"PyTorch Image Quality: Metrics for Image Quality Assessment","created":"2022-08-31","cited_by_count":34,"area":null},{"id":"2210.14661","title":"Full-band General Audio Synthesis with Score-based Diffusion","created":"2022-10-26","cited_by_count":32,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2204.07172","title":"Diagnosing and Fixing Manifold Overfitting in Deep Generative Models","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2305.13607","title":"Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation","created":"2023-05-23","cited_by_count":28,"area":null},{"id":"2410.14987","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","created":"2024-10-19","cited_by_count":27,"area":null},{"id":"2206.08309","title":"Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case","created":"2022-06-16","cited_by_count":26,"area":null},{"id":"2309.08009","title":"Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset","created":"2023-09-14","cited_by_count":23,"area":null},{"id":"2503.01103","title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2111.02682","title":"TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation","created":"2021-11-04","cited_by_count":21,"area":null},{"id":"2605.19376","title":"Generative Recursive Reasoning","created":"2026-05-19","cited_by_count":20,"area":null},{"id":"2106.03062","title":"On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition","created":"2021-06-06","cited_by_count":18,"area":null},{"id":"2111.10991","title":"Backdoor Attack through Frequency Domain","created":"2021-11-22","cited_by_count":18,"area":null},{"id":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18,"area":null},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2109.02081","title":"Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis","created":"2021-09-05","cited_by_count":16,"area":null},{"id":"2406.00758","title":"Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation","created":"2024-06-02","cited_by_count":16,"area":null},{"id":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2308.11206","title":"DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2403.12636","title":"A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2410.17664","title":"Deep Generative Models for 3D Medical Image Synthesis","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2502.01362","title":"Inverse Bridge Matching Distillation","created":"2025-02-03","cited_by_count":14,"area":null},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13,"area":null},{"id":"2203.04907","title":"KPE: Keypoint Pose Encoding for Transformer-based Image Generation","created":"2022-03-09","cited_by_count":12,"area":null},{"id":"2208.04139","title":"DALLE-URBAN: Capturing the urban design expertise of large text to image transformers","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2112.12625","title":"Comparison and Analysis of Image-to-Image Generative Adversarial Networks: A Survey","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2201.13019","title":"On the Robustness of Quality Measures for GANs","created":"2022-01-31","cited_by_count":11,"area":null},{"id":"2204.12007","title":"Assessing the ability of generative adversarial networks to learn canonical medical image statistics","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2211.10330","title":"GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation","created":"2022-11-18","cited_by_count":11,"area":null},{"id":"2104.03061","title":"Everything's Talkin': Pareidolia Face Reenactment","created":"2021-04-07","cited_by_count":10,"area":null},{"id":"2106.06075","title":"A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2205.10370","title":"Diversity vs. Recognizability: Human-like generalization in one-shot generative models","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2305.19216","title":"Translation-Enhanced Multilingual Text-to-Image Generation","created":"2023-05-30","cited_by_count":9,"area":null},{"id":"2312.15289","title":"Fr\\'echet Wavelet Distance: A Domain-Agnostic Metric for Image Generation","created":"2023-12-23","cited_by_count":9,"area":null},{"id":"2407.00138","title":"Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2506.18527","title":"Auto-Regressively Generating Multi-View Consistent Images","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2509.23736","title":"HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation","created":"2025-09-28","cited_by_count":8,"area":null},{"id":"2406.09160","title":"Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2103.00430","title":"Training Generative Adversarial Networks in One Stage","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2109.05652","title":"Inferential Wasserstein Generative Adversarial Networks","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2302.04855","title":"Trading Information between Latents in Hierarchical Variational Autoencoders","created":"2023-02-09","cited_by_count":6,"area":null},{"id":"2304.11961","title":"Towards Mode Balancing of Generative Models via Diversity Weights","created":"2023-04-24","cited_by_count":6,"area":null},{"id":"2404.14409","title":"CrossScore: Towards Multi-View Image Evaluation and Scoring","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2406.01843","title":"L-MAGIC: Language Model Assisted Generation of Images with Coherence","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2412.02259","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2024-12-03","cited_by_count":6,"area":null},{"id":"2112.01641","title":"Hamiltonian latent operators for content and motion disentanglement in image sequences","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2205.03239","title":"Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2210.10205","title":"Optimizing Hierarchical Image VAEs for Sample Quality","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2408.13065","title":"SIMPLE: Simultaneous Multi-Plane Self-Supervised Learning for Isotropic MRI Restoration from Anisotropic Data","created":"2024-08-23","cited_by_count":5,"area":null},{"id":"2502.11712","title":"Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2503.00811","title":"Evaluating and Predicting Distorted Human Body Parts for Generated Images","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2105.02923","title":"Hone as You Read: A Practical Type of Interactive Summarization","created":"2021-05-06","cited_by_count":4,"area":null},{"id":"2106.08285","title":"Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2412.03105","title":"Few-Shot Learning with Adaptive Weight Masking in Conditional GANs","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2507.01255","title":"AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2510.24211","title":"Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2511.18825","title":"Q-Save: Towards Scoring and Attribution for Generated Video Evaluation","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2512.05119","title":"RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering","created":"2025-10-11","cited_by_count":4,"area":null},{"id":"2103.00265","title":"A Brief Introduction to Generative Models","created":"2021-02-27","cited_by_count":3,"area":null},{"id":"2103.02870","title":"Robustness Evaluation of Stacked Generative Adversarial Networks using Metamorphic Testing","created":"2021-03-04","cited_by_count":3,"area":null},{"id":"2107.12202","title":"Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study","created":"2021-07-23","cited_by_count":3,"area":null},{"id":"2111.09991","title":"Sketch-based Creativity Support Tools using Deep Learning","created":"2021-11-19","cited_by_count":3,"area":null},{"id":"2403.05352","title":"Fr\\'echet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder","created":"2024-03-08","cited_by_count":3,"area":null},{"id":"2404.12942","title":"Purposer: Putting Human Motion Generation in Context","created":"2024-04-19","cited_by_count":3,"area":null},{"id":"2408.15640","title":"GANs Conditioning Methods: A Survey","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2410.21553","title":"Exploring the Design Space of Diffusion Bridge Models","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2411.10982","title":"Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations","created":"2024-11-17","cited_by_count":3,"area":null},{"id":"2501.15211","title":"\"Stones from Other Hills can Polish Jade\": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injection","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2508.08957","title":"QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2508.18031","title":"FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2510.06122","title":"PolyGraph Discrepancy: a classifier-based metric for graph generation","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2104.12663","title":"CAGAN: Text-To-Image Generation with Combined Attention GANs","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2109.11719","title":"A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2210.06932","title":"NoMorelization: Building Normalizer-Free Models from a Sample's Perspective","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2211.11570","title":"2CET-GAN: Pixel-Level GAN Model for Human Facial Expression Transfer","created":"2022-11-18","cited_by_count":2,"area":null},{"id":"2307.11530","title":"UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2311.12163","title":"Quantum Inception Score","created":"2023-11-20","cited_by_count":2,"area":null},{"id":"2405.04902","title":"HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2409.01138","title":"Generating Synthetic Satellite Imagery for Rare Objects: An Empirical Comparison of Models and Metrics","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2410.03430","title":"Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2412.19992","title":"An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2503.18552","title":"EvAnimate: Event-conditioned Image-to-Video Generation for Human Animation","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2512.16483","title":"FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2606.20536","title":"The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2102.10485","title":"Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data","created":"2021-02-21","cited_by_count":1,"area":null}],"next_cursor":"100"}