{"total":193,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636,"area":"diffusion"},{"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":"2305.01140","title":"Geometric Latent Diffusion Models for 3D Molecule Generation","created":"2023-05-02","cited_by_count":186,"area":"diffusion"},{"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":"2108.07960","title":"SynFace: Face Recognition with Synthetic Data","created":"2021-08-18","cited_by_count":106,"area":null},{"id":"2201.00308","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","created":"2022-01-02","cited_by_count":104,"area":"diffusion"},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100,"area":null},{"id":"2106.06819","title":"D2C: Diffusion-Denoising Models for Few-shot Conditional Generation","created":"2021-06-12","cited_by_count":96,"area":null},{"id":"2207.02862","title":"Verifying the Union of Manifolds Hypothesis for Image Data","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2311.00265","title":"Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study","created":"2023-11-01","cited_by_count":64,"area":"diffusion"},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51,"area":null},{"id":"2106.01413","title":"Rectangular Flows for Manifold Learning","created":"2021-06-02","cited_by_count":50,"area":null},{"id":"2309.01700","title":"ControlMat: A Controlled Generative Approach to Material Capture","created":"2023-09-04","cited_by_count":50,"area":"diffusion"},{"id":"2112.12047","title":"Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications","created":"2021-12-22","cited_by_count":47,"area":null},{"id":"2404.02954","title":"Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections","created":"2024-04-03","cited_by_count":47,"area":"diffusion"},{"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":"2411.00113","title":"A Geometric Framework for Understanding Memorization in Generative Models","created":"2024-10-31","cited_by_count":40,"area":null},{"id":"2206.03066","title":"Recent Advances for Quantum Neural Networks in Generative Learning","created":"2022-06-07","cited_by_count":39,"area":null},{"id":"2305.11463","title":"Generative Sliced MMD Flows with Riesz Kernels","created":"2023-05-19","cited_by_count":37,"area":null},{"id":"2106.05275","title":"Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows","created":"2021-06-09","cited_by_count":31,"area":null},{"id":"2202.01356","title":"Direct Molecular Conformation Generation","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2203.10808","title":"AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder","created":"2022-03-21","cited_by_count":29,"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":"2206.02416","title":"Embrace the Gap: VAEs Perform Independent Mechanism Analysis","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2208.09191","title":"Synthetic Data in Human Analysis: A Survey","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2105.00026","title":"Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder","created":"2021-04-30","cited_by_count":27,"area":null},{"id":"2206.00386","title":"DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder","created":"2022-06-01","cited_by_count":27,"area":"diffusion"},{"id":"2204.12965","title":"Particle algorithms for maximum likelihood training of latent variable models","created":"2022-04-27","cited_by_count":26,"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":"2103.01648","title":"Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior","created":"2021-03-02","cited_by_count":24,"area":null},{"id":"2202.04777","title":"Exact Solutions of a Deep Linear Network","created":"2022-02-10","cited_by_count":24,"area":null},{"id":"2209.07370","title":"A Geometric Perspective on Variational Autoencoders","created":"2022-09-15","cited_by_count":24,"area":null},{"id":"2111.12506","title":"Generalized Normalizing Flows via Markov Chains","created":"2021-11-24","cited_by_count":23,"area":null},{"id":"2103.01071","title":"A survey on Variational Autoencoders from a GreenAI perspective","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2107.11191","title":"Regularising Inverse Problems with Generative Machine Learning Models","created":"2021-07-22","cited_by_count":22,"area":null},{"id":"2209.05434","title":"3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation","created":"2022-09-12","cited_by_count":22,"area":null},{"id":"2302.11756","title":"Learning Manifold Dimensions with Conditional Variational Autoencoders","created":"2023-02-23","cited_by_count":20,"area":null},{"id":"2109.00055","title":"Sentence Bottleneck Autoencoders from Transformer Language Models","created":"2021-08-31","cited_by_count":19,"area":null},{"id":"2209.10584","title":"Continuous Mixtures of Tractable Probabilistic Models","created":"2022-09-21","cited_by_count":19,"area":null},{"id":"2307.08283","title":"Complexity Matters: Rethinking the Latent Space for Generative Modeling","created":"2023-07-17","cited_by_count":19,"area":"diffusion"},{"id":"2209.08739","title":"Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model","created":"2022-09-19","cited_by_count":18,"area":null},{"id":"2211.10794","title":"NVDiff: Graph Generation through the Diffusion of Node Vectors","created":"2022-11-19","cited_by_count":18,"area":"diffusion"},{"id":"2210.10318","title":"Gaussian-Bernoulli RBMs Without Tears","created":"2022-10-19","cited_by_count":17,"area":null},{"id":"2303.15244","title":"Manifold Learning by Mixture Models of VAEs for Inverse Problems","created":"2023-03-27","cited_by_count":17,"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":"2310.12743","title":"Canonical normalizing flows for manifold learning","created":"2023-10-19","cited_by_count":15,"area":null},{"id":"2101.02149","title":"Cauchy-Schwarz Regularized Autoencoder","created":"2021-01-06","cited_by_count":13,"area":null},{"id":"2310.03218","title":"Learning Energy-Based Prior Model with Diffusion-Amortized MCMC","created":"2023-10-05","cited_by_count":13,"area":null},{"id":"2410.03655","title":"Geometric Representation Condition Improves Equivariant Molecule Generation","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2102.09310","title":"VAE Approximation Error: ELBO and Exponential Families","created":"2021-02-18","cited_by_count":12,"area":null},{"id":"2207.06812","title":"Comparing the latent space of generative models","created":"2022-07-14","cited_by_count":12,"area":null},{"id":"2103.05290","title":"A prior-based approximate latent Riemannian metric","created":"2021-03-09","cited_by_count":11,"area":null},{"id":"2112.06868","title":"Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias","created":"2021-12-13","cited_by_count":11,"area":null},{"id":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","cited_by_count":11,"area":null},{"id":"2106.00792","title":"Latent Space Refinement for Deep Generative Models","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2106.06245","title":"Model Selection for Bayesian Autoencoders","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2106.16091","title":"Exploring the Latent Space of Autoencoders with Interventional Assays","created":"2021-06-30","cited_by_count":10,"area":null},{"id":"2112.14278","title":"Beta-VAE Reproducibility: Challenges and Extensions","created":"2021-12-28","cited_by_count":10,"area":null},{"id":"2203.11556","title":"VQ-Flows: Vector Quantized Local Normalizing Flows","created":"2022-03-22","cited_by_count":10,"area":null},{"id":"2205.08399","title":"How do Variational Autoencoders Learn? Insights from Representational Similarity","created":"2022-05-17","cited_by_count":10,"area":null},{"id":"2205.11640","title":"Generalization Gap in Amortized Inference","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2402.19009","title":"Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding","created":"2024-02-29","cited_by_count":10,"area":"diffusion"},{"id":"2302.11294","title":"Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation","created":"2023-02-22","cited_by_count":9,"area":null},{"id":"2306.04445","title":"Multi-modal Latent Diffusion","created":"2023-06-07","cited_by_count":9,"area":"diffusion"},{"id":"2307.06431","title":"Energy Discrepancies: A Score-Independent Loss for Energy-Based Models","created":"2023-07-12","cited_by_count":9,"area":null},{"id":"2311.09952","title":"Score-based generative models learn manifold-like structures with constrained mixing","created":"2023-11-16","cited_by_count":9,"area":"diffusion"},{"id":"2106.10591","title":"Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation","created":"2021-06-20","cited_by_count":8,"area":null},{"id":"2306.06323","title":"Learning Joint Latent Space EBM Prior Model for Multi-layer Generator","created":"2023-06-10","cited_by_count":8,"area":null},{"id":"2406.10513","title":"Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space","created":"2024-06-15","cited_by_count":8,"area":"diffusion"},{"id":"2510.23972","title":"An efficient probabilistic hardware architecture for diffusion-like models","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2602.15030","title":"Image Generation with a Sphere Encoder","created":"2026-02-16","cited_by_count":8,"area":"diffusion"},{"id":"2109.12679","title":"Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders","created":"2021-09-26","cited_by_count":7,"area":null},{"id":"2205.01668","title":"End-to-End Visual Editing with a Generatively Pre-Trained Artist","created":"2022-05-03","cited_by_count":7,"area":null},{"id":"2206.06632","title":"Explainable AI for High Energy Physics","created":"2022-06-14","cited_by_count":7,"area":null},{"id":"2209.07007","title":"Gromov-Wasserstein Autoencoders","created":"2022-09-15","cited_by_count":7,"area":null},{"id":"2103.07292","title":"VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts","created":"2021-03-12","cited_by_count":6,"area":"moe"},{"id":"2106.13739","title":"Re-parameterizing VAEs for stability","created":"2021-06-25","cited_by_count":6,"area":null},{"id":"2205.12510","title":"Exact Phase Transitions in Deep Learning","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2212.01265","title":"Denoising Deep Generative Models","created":"2022-11-30","cited_by_count":6,"area":null},{"id":"2306.02565","title":"Coupled Variational Autoencoder","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2310.09604","title":"Learning Hierarchical Features with Joint Latent Space Energy-Based Prior","created":"2023-10-14","cited_by_count":6,"area":null},{"id":"2311.07693","title":"Matching aggregate posteriors in the variational autoencoder","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2405.13910","title":"Learning Latent Space Hierarchical EBM Diffusion Models","created":"2024-05-22","cited_by_count":6,"area":"diffusion"},{"id":"2501.10901","title":"ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2206.11267","title":"Neural Implicit Manifold Learning for Topology-Aware Density Estimation","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2209.12806","title":"FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders","created":"2022-09-26","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":"2302.04246","title":"Shortcut Detection with Variational Autoencoders","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2405.02504","title":"Functional Imaging Constrained Diffusion for Brain PET Synthesis from Structural MRI","created":"2024-05-03","cited_by_count":5,"area":null},{"id":"2502.12987","title":"Ensemble Kalman filter in latent space using a variational autoencoder pair","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2510.12311","title":"Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2511.06863","title":"VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling","created":"2025-11-10","cited_by_count":5,"area":null},{"id":"2106.15962","title":"On the Generative Utility of Cyclic Conditionals","created":"2021-06-30","cited_by_count":4,"area":null},{"id":"2109.14216","title":"Spread Flows for Manifold Modelling","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2203.12130","title":"Pixel VQ-VAEs for Improved Pixel Art Representation","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2205.03130","title":"SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning","created":"2022-05-06","cited_by_count":4,"area":"offlinerl"},{"id":"2205.09546","title":"Deterministic training of generative autoencoders using invertible layers","created":"2022-05-19","cited_by_count":4,"area":null}],"next_cursor":"100"}