{"total":242,"rows":[{"id":"2209.11215","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions","created":"2022-09-22","cited_by_count":445,"area":"diffusion"},{"id":"2308.03686","title":"Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization","created":"2023-08-07","cited_by_count":235,"area":"diffusion"},{"id":"2211.01916","title":"Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions","created":"2022-11-03","cited_by_count":219,"area":"diffusion"},{"id":"2209.12381","title":"Convergence of score-based generative modeling for general data distributions","created":"2022-09-26","cited_by_count":181,"area":"diffusion"},{"id":"2302.07194","title":"Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data","created":"2023-02-14","cited_by_count":174,"area":"diffusion"},{"id":"2302.13834","title":"Denoising Diffusion Samplers","created":"2023-02-27","cited_by_count":149,"area":"diffusion"},{"id":"2211.01364","title":"An optimal control perspective on diffusion-based generative modeling","created":"2022-11-02","cited_by_count":147,"area":"diffusion"},{"id":"2305.11798","title":"The probability flow ODE is provably fast","created":"2023-05-19","cited_by_count":146,"area":"diffusion"},{"id":"2402.18491","title":"Dynamical Regimes of Diffusion Models","created":"2024-02-28","cited_by_count":142,"area":"diffusion"},{"id":"2412.20292","title":"An analytic theory of creativity in convolutional diffusion models","created":"2024-12-28","cited_by_count":104,"area":"diffusion"},{"id":"2211.17091","title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","created":"2022-11-28","cited_by_count":100,"area":"diffusion"},{"id":"2402.16991","title":"A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data","created":"2024-02-26","cited_by_count":93,"area":"diffusion"},{"id":"2305.16860","title":"Error Bounds for Flow Matching Methods","created":"2023-05-26","cited_by_count":91,"area":"diffusion"},{"id":"2306.09251","title":"Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models","created":"2023-06-15","cited_by_count":85,"area":"diffusion"},{"id":"2304.06648","title":"DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning","created":"2023-04-13","cited_by_count":84,"area":"diffusion"},{"id":"2505.17638","title":"Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training","created":"2025-05-23","cited_by_count":81,"area":"diffusion"},{"id":"2405.14780","title":"Metric Flow Matching for Smooth Interpolations on the Data Manifold","created":"2024-05-23","cited_by_count":77,"area":"diffusion"},{"id":"2403.03852","title":"Accelerating Convergence of Score-Based Diffusion Models, Provably","created":"2024-03-06","cited_by_count":76,"area":"diffusion"},{"id":"2303.03384","title":"Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers","created":"2023-03-06","cited_by_count":74,"area":"diffusion"},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73,"area":"diffusion"},{"id":"2402.17376","title":"Accelerating Diffusion Sampling with Optimized Time Steps","created":"2024-02-27","cited_by_count":67,"area":"diffusion"},{"id":"2408.02320","title":"A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models","created":"2024-08-05","cited_by_count":65,"area":"diffusion"},{"id":"2308.12240","title":"KL Convergence Guarantees for Score diffusion models under minimal data assumptions","created":"2023-08-23","cited_by_count":63,"area":"diffusion"},{"id":"2403.11968","title":"Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory","created":"2024-03-18","cited_by_count":63,"area":"diffusion"},{"id":"2402.07747","title":"Optimal score estimation via empirical Bayes smoothing","created":"2024-02-12","cited_by_count":61,"area":null},{"id":"2404.14743","title":"Gradient Guidance for Diffusion Models: An Optimization Perspective","created":"2024-04-23","cited_by_count":61,"area":"diffusion"},{"id":"2306.04542","title":"On the Design Fundamentals of Diffusion Models: A Survey","created":"2023-06-07","cited_by_count":60,"area":"diffusion"},{"id":"2402.07487","title":"Score-based Diffusion Models via Stochastic Differential Equations -- a Technical Tutorial","created":"2024-02-12","cited_by_count":60,"area":"diffusion"},{"id":"2211.03595","title":"From Denoising Diffusions to Denoising Markov Models","created":"2022-11-07","cited_by_count":58,"area":"diffusion"},{"id":"2307.01178","title":"Learning Mixtures of Gaussians Using the DDPM Objective","created":"2023-07-03","cited_by_count":57,"area":"diffusion"},{"id":"2310.02679","title":"Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization","created":"2023-10-04","cited_by_count":57,"area":null},{"id":"2401.17958","title":"Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances","created":"2024-01-31","cited_by_count":56,"area":"diffusion"},{"id":"2405.14861","title":"Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models","created":"2024-05-23","cited_by_count":56,"area":"diffusion"},{"id":"2405.11326","title":"On the Trajectory Regularity of ODE-based Diffusion Sampling","created":"2024-05-18","cited_by_count":55,"area":"diffusion"},{"id":"2409.02426","title":"Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions","created":"2024-09-04","cited_by_count":53,"area":"diffusion"},{"id":"2409.18959","title":"O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions","created":"2024-09-27","cited_by_count":50,"area":"diffusion"},{"id":"2402.05098","title":"Improved off-policy training of diffusion samplers","created":"2024-02-07","cited_by_count":48,"area":"diffusion"},{"id":"2402.15602","title":"Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions","created":"2024-02-23","cited_by_count":47,"area":"diffusion"},{"id":"2403.01633","title":"Critical windows: non-asymptotic theory for feature emergence in diffusion models","created":"2024-03-03","cited_by_count":47,"area":"diffusion"},{"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":"2310.12395","title":"Closed-Form Diffusion Models","created":"2023-10-19","cited_by_count":46,"area":"diffusion"},{"id":"2403.01639","title":"Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models","created":"2024-03-03","cited_by_count":46,"area":"diffusion"},{"id":"2406.01781","title":"DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform","created":"2024-06-03","cited_by_count":46,"area":"diffusion"},{"id":"2402.08095","title":"Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization","created":"2024-02-12","cited_by_count":44,"area":"diffusion"},{"id":"2404.18869","title":"Learning Mixtures of Gaussians Using Diffusion Models","created":"2024-04-29","cited_by_count":42,"area":"diffusion"},{"id":"2406.03537","title":"A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models","created":"2024-06-05","cited_by_count":42,"area":"diffusion"},{"id":"2302.10130","title":"Infinite-Dimensional Diffusion Models","created":"2023-02-20","cited_by_count":39,"area":"diffusion"},{"id":"2305.19147","title":"Conditional score-based diffusion models for Bayesian inference in infinite dimensions","created":"2023-05-28","cited_by_count":38,"area":"diffusion"},{"id":"2310.03575","title":"Analysis of learning a flow-based generative model from limited sample complexity","created":"2023-10-05","cited_by_count":38,"area":null},{"id":"2410.24060","title":"Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure","created":"2024-10-31","cited_by_count":38,"area":"diffusion"},{"id":"2302.01217","title":"A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models","created":"2023-02-02","cited_by_count":37,"area":"diffusion"},{"id":"2401.04856","title":"A Good Score Does not Lead to A Good Generative Model","created":"2024-01-10","cited_by_count":36,"area":"diffusion"},{"id":"2402.18012","title":"Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints","created":"2024-02-28","cited_by_count":35,"area":"diffusion"},{"id":"2310.17582","title":"Convergence of flow-based generative models via proximal gradient descent in Wasserstein space","created":"2023-10-26","cited_by_count":34,"area":null},{"id":"2410.05898","title":"Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion","created":"2024-10-08","cited_by_count":32,"area":"diffusion"},{"id":"2310.09031","title":"MINDE: Mutual Information Neural Diffusion Estimation","created":"2023-10-13","cited_by_count":31,"area":null},{"id":"2401.13115","title":"Contractive Diffusion Probabilistic Models","created":"2024-01-23","cited_by_count":29,"area":"diffusion"},{"id":"2406.00924","title":"Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel","created":"2024-06-03","cited_by_count":29,"area":"diffusion"},{"id":"2410.08727","title":"Losing dimensions: Geometric memorization in generative diffusion","created":"2024-10-11","cited_by_count":29,"area":"diffusion"},{"id":"2501.02298","title":"Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance","created":"2025-01-04","cited_by_count":29,"area":"diffusion"},{"id":"2402.04650","title":"An analysis of the noise schedule for score-based generative models","created":"2024-02-07","cited_by_count":27,"area":"diffusion"},{"id":"2410.23285","title":"Provable Acceleration for Diffusion Models under Minimal Assumptions","created":"2024-10-30","cited_by_count":27,"area":"diffusion"},{"id":"2402.07802","title":"Towards a mathematical theory for consistency training in diffusion models","created":"2024-02-12","cited_by_count":26,"area":"diffusion"},{"id":"2406.12839","title":"Evaluating the design space of diffusion-based generative models","created":"2024-06-18","cited_by_count":26,"area":"diffusion"},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2311.13584","title":"On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates","created":"2023-11-22","cited_by_count":25,"area":"diffusion"},{"id":"2502.12089","title":"How Compositional Generalization and Creativity Improve as Diffusion Models are Trained","created":"2025-02-17","cited_by_count":25,"area":"diffusion"},{"id":"2509.09672","title":"Locality in Image Diffusion Models Emerges from Data Statistics","created":"2025-09-11","cited_by_count":25,"area":"diffusion"},{"id":"2305.14164","title":"Improved Convergence of Score-Based Diffusion Models via Prediction-Correction","created":"2023-05-23","cited_by_count":24,"area":"diffusion"},{"id":"2403.13219","title":"Diffusion Model for Data-Driven Black-Box Optimization","created":"2024-03-20","cited_by_count":24,"area":"diffusion"},{"id":"2405.16418","title":"Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective","created":"2024-05-26","cited_by_count":24,"area":"diffusion"},{"id":"2410.02321","title":"Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis","created":"2024-10-03","cited_by_count":24,"area":"diffusion"},{"id":"2503.09583","title":"Minimax Optimality of the Probability Flow ODE for Diffusion Models","created":"2025-03-12","cited_by_count":23,"area":"diffusion"},{"id":"2504.05300","title":"Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures","created":"2025-04-07","cited_by_count":23,"area":"diffusion"},{"id":"2504.12532","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","created":"2025-04-16","cited_by_count":23,"area":"diffusion"},{"id":"2312.09236","title":"A framework for conditional diffusion modelling with applications in motif scaffolding for protein design","created":"2023-12-14","cited_by_count":22,"area":"diffusion"},{"id":"2410.13738","title":"Instance-dependent Convergence Theory for Diffusion Models","created":"2024-10-17","cited_by_count":21,"area":"diffusion"},{"id":"2508.03210","title":"Convergence of Deterministic and Stochastic Diffusion-Model Samplers: A Simple Analysis in Wasserstein Distance","created":"2025-08-05","cited_by_count":21,"area":"diffusion"},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2502.00336","title":"Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves","created":"2025-02-01","cited_by_count":20,"area":"diffusion"},{"id":"2509.16756","title":"Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees","created":"2025-09-20","cited_by_count":20,"area":"diffusion"},{"id":"2510.02305","title":"Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive","created":"2025-10-02","cited_by_count":20,"area":"diffusion"},{"id":"2306.04848","title":"Interpreting and Improving Diffusion Models from an Optimization Perspective","created":"2023-06-08","cited_by_count":19,"area":"diffusion"},{"id":"2402.17886","title":"Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion","created":"2024-02-27","cited_by_count":19,"area":"diffusion"},{"id":"2405.06780","title":"Deep MMD Gradient Flow without adversarial training","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2410.23594","title":"How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?","created":"2024-10-31","cited_by_count":19,"area":"diffusion"},{"id":"2306.01804","title":"Extracting Reward Functions from Diffusion Models","created":"2023-06-01","cited_by_count":18,"area":"diffusion"},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2311.11475","title":"Gaussian Interpolation Flows","created":"2023-11-20","cited_by_count":17,"area":null},{"id":"2402.01779","title":"Plug-and-Play image restoration with Stochastic deNOising REgularization","created":"2024-02-01","cited_by_count":17,"area":null},{"id":"2502.04849","title":"Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration","created":"2025-02-07","cited_by_count":17,"area":"diffusion"},{"id":"2502.21278","title":"Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion","created":"2025-02-28","cited_by_count":17,"area":"diffusion"},{"id":"2505.09922","title":"Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity","created":"2025-05-15","cited_by_count":17,"area":"diffusion"},{"id":"2310.18123","title":"Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2404.02538","title":"Convergence Analysis of Flow Matching in Latent Space with Transformers","created":"2024-04-03","cited_by_count":16,"area":"diffusion"},{"id":"2405.14250","title":"Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors","created":"2024-05-23","cited_by_count":16,"area":"diffusion"},{"id":"2510.27562","title":"Optimal Convergence Analysis of DDPM for General Distributions","created":"2025-10-31","cited_by_count":16,"area":"diffusion"},{"id":"2306.02063","title":"Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations","created":"2023-06-03","cited_by_count":15,"area":"diffusion"},{"id":"2405.15754","title":"Score-based generative models are provably robust: an uncertainty quantification perspective","created":"2024-05-24","cited_by_count":15,"area":"diffusion"},{"id":"2502.19499","title":"On the Interpolation Effect of Score Smoothing in Diffusion Models","created":"2025-02-26","cited_by_count":15,"area":"diffusion"}],"next_cursor":"100"}