{"total":297,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511,"area":null},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"area":null},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"area":null},{"id":"2206.13397","title":"Generative Modelling With Inverse Heat Dissipation","created":"2022-06-21","cited_by_count":167,"area":null},{"id":"2211.00802","title":"Concrete Score Matching: Generalized Score Matching for Discrete Data","created":"2022-11-02","cited_by_count":148,"area":null},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134,"area":null},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"area":null},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115,"area":null},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106,"area":null},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100,"area":null},{"id":"2205.13914","title":"3DILG: Irregular Latent Grids for 3D Generative Modeling","created":"2022-05-27","cited_by_count":93,"area":null},{"id":"2107.06908","title":"Understanding Failures in Out-of-Distribution Detection with Deep Generative Models","created":"2021-07-14","cited_by_count":89,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78,"area":null},{"id":"2106.09660","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","created":"2021-06-17","cited_by_count":65,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2205.13554","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","created":"2022-05-26","cited_by_count":64,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62,"area":null},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60,"area":null},{"id":"2102.08248","title":"Hierarchical VAEs Know What They Don't Know","created":"2021-02-16","cited_by_count":58,"area":null},{"id":"2201.03230","title":"Swin Transformer for Fast MRI","created":"2022-01-10","cited_by_count":56,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55,"area":null},{"id":"2112.02424","title":"Variational Wasserstein gradient flow","created":"2021-12-04","cited_by_count":53,"area":null},{"id":"2106.04627","title":"Densely connected normalizing flows","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2205.06924","title":"A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model","created":"2022-05-13","cited_by_count":44,"area":null},{"id":"2203.10897","title":"Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression","created":"2022-03-21","cited_by_count":43,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2102.07970","title":"Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2204.11824","title":"Semi-Parametric Neural Image Synthesis","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2101.00598","title":"Copula Flows for Synthetic Data Generation","created":"2021-01-03","cited_by_count":35,"area":null},{"id":"2107.06463","title":"Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules","created":"2021-07-14","cited_by_count":35,"area":null},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2303.01274","title":"Measuring axiomatic soundness of counterfactual image models","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2109.02639","title":"On the Out-of-distribution Generalization of Probabilistic Image Modelling","created":"2021-09-04","cited_by_count":33,"area":null},{"id":"2204.02960","title":"Simple and Effective Synthesis of Indoor 3D Scenes","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","created":"2022-12-14","cited_by_count":33,"area":null},{"id":"2303.14468","title":"Autoregressive Conditional Neural Processes","created":"2023-03-25","cited_by_count":33,"area":null},{"id":"2310.00234","title":"Pixel-Inconsistency Modeling for Image Manipulation Localization","created":"2023-09-30","cited_by_count":33,"area":null},{"id":"2105.06458","title":"High-Resolution Complex Scene Synthesis with Transformers","created":"2021-05-13","cited_by_count":31,"area":null},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31,"area":null},{"id":"2503.16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","created":"2025-03-20","cited_by_count":29,"area":null},{"id":"2103.16211","title":"iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression","created":"2021-03-30","cited_by_count":27,"area":null},{"id":"2104.01374","title":"Interpretable Unsupervised Diversity Denoising and Artefact Removal","created":"2021-04-03","cited_by_count":26,"area":null},{"id":"2105.05735","title":"Autoencoding Under Normalization Constraints","created":"2021-05-12","cited_by_count":26,"area":null},{"id":"2111.00965","title":"iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder","created":"2021-11-01","cited_by_count":26,"area":null},{"id":"2203.13751","title":"Efficient-VDVAE: Less is more","created":"2022-03-25","cited_by_count":26,"area":null},{"id":"2303.06519","title":"Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model","created":"2023-03-11","cited_by_count":25,"area":null},{"id":"2208.09083","title":"Out-of-distribution Detection via Frequency-regularized Generative Models","created":"2022-08-18","cited_by_count":23,"area":null},{"id":"2102.13602","title":"Distribution-Aware Testing of Neural Networks Using Generative Models","created":"2021-02-26","cited_by_count":22,"area":null},{"id":"2209.04847","title":"Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression","created":"2022-09-11","cited_by_count":22,"area":null},{"id":"2104.09859","title":"Multiscale deep context modeling for lossless point cloud geometry compression","created":"2021-04-20","cited_by_count":21,"area":null},{"id":"2107.12295","title":"A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation","created":"2021-07-26","cited_by_count":21,"area":null},{"id":"2510.02300","title":"Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models","created":"2025-10-02","cited_by_count":21,"area":null},{"id":"2102.11086","title":"Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding","created":"2021-02-22","cited_by_count":19,"area":null},{"id":"2104.00941","title":"Multi-Class Data Description for Out-of-distribution Detection","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2105.08164","title":"Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2412.01496","title":"Fr\\'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets","created":"2024-12-02","cited_by_count":19,"area":null},{"id":"2103.15089","title":"Improved Autoregressive Modeling with Distribution Smoothing","created":"2021-03-28","cited_by_count":18,"area":null},{"id":"2303.03023","title":"Guiding Energy-based Models via Contrastive Latent Variables","created":"2023-03-06","cited_by_count":18,"area":null},{"id":"2310.18677","title":"Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach","created":"2023-10-28","cited_by_count":18,"area":null},{"id":"2107.04281","title":"JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting","created":"2021-07-09","cited_by_count":17,"area":null},{"id":"2103.17015","title":"Learning Scalable $\\ell_\\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression","created":"2021-03-31","cited_by_count":16,"area":null},{"id":"2202.04895","title":"Diffusion bridges vector quantized Variational AutoEncoders","created":"2022-02-10","cited_by_count":16,"area":null},{"id":"2303.03565","title":"CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding","created":"2023-03-07","cited_by_count":16,"area":null},{"id":"2307.09072","title":"Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)","created":"2023-07-18","cited_by_count":16,"area":null},{"id":"2401.03321","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","created":"2024-01-06","cited_by_count":16,"area":null},{"id":"2102.08663","title":"Preventing Oversmoothing in VAE via Generalized Variance Parameterization","created":"2021-02-17","cited_by_count":15,"area":null},{"id":"2111.13236","title":"Joint inference and input optimization in equilibrium networks","created":"2021-11-25","cited_by_count":15,"area":null},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2212.14268","title":"Detection of out-of-distribution samples using binary neuron activation patterns","created":"2022-12-29","cited_by_count":15,"area":null},{"id":"2407.13677","title":"PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2106.02514","title":"The Image Local Autoregressive Transformer","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2106.04283","title":"NWT: Towards natural audio-to-video generation with representation learning","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2207.02390","title":"Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI","created":"2022-07-05","cited_by_count":14,"area":null},{"id":"2304.07313","title":"M2T: Masking Transformers Twice for Faster Decoding","created":"2023-04-14","cited_by_count":14,"area":null},{"id":"2305.16310","title":"Securing Deep Generative Models with Universal Adversarial Signature","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2203.13455","title":"A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training","created":"2022-03-25","cited_by_count":13,"area":null},{"id":"2504.02612","title":"Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2103.15813","title":"PixelTransformer: Sample Conditioned Signal Generation","created":"2021-03-29","cited_by_count":12,"area":null},{"id":"2106.04427","title":"On the relation between statistical learning and perceptual distances","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2112.06417","title":"LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network","created":"2021-12-13","cited_by_count":12,"area":null},{"id":"2210.11794","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","created":"2022-10-21","cited_by_count":12,"area":null}],"next_cursor":"100"}