{"list":"other","total":58,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1511.05644","title":"Adversarial Autoencoders","created":"2015-11-18","cited_by_count":364},{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"2404.07724","title":"Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models","created":"2024-04-11","cited_by_count":254},{"id":"1803.06992","title":"Estimating the intrinsic dimension of datasets by a minimal neighborhood information","created":"2018-03-19","cited_by_count":250},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2211.09117","title":"MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis","created":"2022-11-16","cited_by_count":227},{"id":"1611.02648","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","created":"2016-11-08","cited_by_count":220},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2306.09305","title":"Fast Training of Diffusion Models with Masked Transformers","created":"2023-06-15","cited_by_count":176},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168},{"id":"1702.08389","title":"Equivariance Through Parameter-Sharing","created":"2017-02-27","cited_by_count":141},{"id":"2302.00294","title":"The geometry of hidden representations of large transformer models","created":"2023-02-01","cited_by_count":112},{"id":"1910.11093","title":"Scale-Equivariant Steerable Networks","created":"2019-10-14","cited_by_count":110},{"id":"1612.09346","title":"Rotation equivariant vector field networks","created":"2016-12-29","cited_by_count":99},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80},{"id":"2406.11837","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","created":"2024-06-17","cited_by_count":68},{"id":"2410.10356","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","created":"2024-10-14","cited_by_count":64},{"id":"1804.04458","title":"CubeNet: Equivariance to 3D Rotation and Translation","created":"2018-04-12","cited_by_count":59},{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51},{"id":"2403.17004","title":"SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer","created":"2024-03-25","cited_by_count":49},{"id":"2306.04632","title":"Designing a Better Asymmetric VQGAN for StableDiffusion","created":"2023-06-07","cited_by_count":45},{"id":"1803.01588","title":"N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials","created":"2018-03-05","cited_by_count":42},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39},{"id":"1809.05284","title":"Variational Autoencoder with Implicit Optimal Priors","created":"2018-09-14","cited_by_count":33},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26},{"id":"2310.14400","title":"A Pytorch Reproduction of Masked Generative Image Transformer","created":"2023-10-22","cited_by_count":25},{"id":"2205.03373","title":"DADApy: Distance-based Analysis of DAta-manifolds in Python","created":"2022-05-04","cited_by_count":22},{"id":"2307.08283","title":"Complexity Matters: Rethinking the Latent Space for Generative Modeling","created":"2023-07-17","cited_by_count":19},{"id":"2311.02922","title":"Truly Scale-Equivariant Deep Nets with Fourier Layers","created":"2023-11-06","cited_by_count":16},{"id":"2302.09301","title":"Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension","created":"2023-02-16","cited_by_count":7}],"next_cursor":null}