{"total":64,"rows":[{"id":"2506.03719","title":"On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity","created":"2025-06-04","cited_by_count":50,"area":"diffusion"},{"id":"2511.03202","title":"Provable Separations between Memorization and Generalization in Diffusion Models","created":"2025-11-05","cited_by_count":14,"area":"diffusion"},{"id":"2508.19897","title":"The Information Dynamics of Generative Diffusion","created":"2025-08-27","cited_by_count":13,"area":"diffusion"},{"id":"2603.05630","title":"Making Reconstruction FID Predictive of Diffusion Generation FID","created":"2026-03-05","cited_by_count":13,"area":"diffusion"},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11,"area":"diffusion"},{"id":"2512.20963","title":"Generalization of Diffusion Models Arises with a Balanced Representation Space","created":"2025-12-24","cited_by_count":11,"area":"diffusion"},{"id":"2505.24769","title":"Generalization Dynamics of Linear Diffusion Models","created":"2025-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2512.02826","title":"From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity","created":"2025-12-02","cited_by_count":8,"area":"diffusion"},{"id":"2510.24830","title":"The Generation Phases of Flow Matching: a Denoising Perspective","created":"2025-10-28","cited_by_count":7,"area":"diffusion"},{"id":"2601.21419","title":"Revisiting Diffusion Model Predictions Through Dimensionality","created":"2026-01-29","cited_by_count":7,"area":"diffusion"},{"id":"2603.14645","title":"Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion","created":"2026-03-15","cited_by_count":7,"area":"diffusion"},{"id":"2602.02908","title":"A Random Matrix Theory Perspective on the Consistency of Diffusion Models","created":"2026-02-02","cited_by_count":6,"area":"diffusion"},{"id":"2602.06021","title":"Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold","created":"2026-02-05","cited_by_count":5,"area":"diffusion"},{"id":"2603.12901","title":"A theory of learning data statistics in diffusion models, from easy to hard","created":"2026-03-13","cited_by_count":5,"area":"diffusion"},{"id":"2606.14390","title":"Local Coverage Governs Memorization in Diffusion Models","created":"2026-06-12","cited_by_count":5,"area":"diffusion"},{"id":"2603.03469","title":"Biased Generalization in Diffusion Models","created":"2026-03-03","cited_by_count":4,"area":"diffusion"},{"id":"2602.07928","title":"A Kinetic Energy Perspective of Flow Matching","created":"2026-02-08","cited_by_count":3,"area":"diffusion"},{"id":"2602.15914","title":"Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance","created":"2026-02-17","cited_by_count":3,"area":"diffusion"},{"id":"2602.17846","title":"Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models","created":"2026-02-19","cited_by_count":3,"area":"diffusion"},{"id":"2603.22962","title":"Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data","created":"2026-03-24","cited_by_count":3,"area":"diffusion"},{"id":"2607.02671","title":"Benign Overfitting Does Not Occur in Diffusion Models","created":"2026-07-02","cited_by_count":3,"area":"diffusion"},{"id":"2607.08041","title":"An exact information theory of generalization phase transitions in Bayesian diffusion models","created":"2026-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2505.20123","title":"Understanding Generalization in Diffusion Distillation via Probability Flow Distance","created":"2025-05-26","cited_by_count":2,"area":"diffusion"},{"id":"2603.13419","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","created":"2026-03-12","cited_by_count":2,"area":"diffusion"},{"id":"2603.23792","title":"Manifold Generalization Provably Proceeds Memorization in Diffusion Models","created":"2026-03-24","cited_by_count":2,"area":"diffusion"},{"id":"2605.06077","title":"Understanding diffusion models requires rethinking (again) generalization","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"id":"2601.21348","title":"Memorization Control in Diffusion Models from Denoising-centric Perspective","created":"2026-01-29","cited_by_count":1,"area":"diffusion"},{"id":"2602.00199","title":"Reducing Memorisation in Generative Models via Riemannian Bayesian Inference","created":"2026-01-30","cited_by_count":1,"area":"diffusion"},{"id":"2602.17211","title":"MGD: Moment Guided Diffusion for Maximum Entropy Generation","created":"2026-02-19","cited_by_count":1,"area":"diffusion"},{"id":"2604.07404","title":"Score Shocks: The Burgers Equation Structure of Diffusion Generative Models","created":"2026-04-08","cited_by_count":1,"area":"diffusion"},{"id":"2605.00273","title":"When Do Diffusion Models learn to Generate Multiple Objects?","created":"2026-04-30","cited_by_count":1,"area":"diffusion"},{"id":"2605.13999","title":"Support Before Frequency in Discrete Diffusion","created":"2026-05-13","cited_by_count":1,"area":"diffusion"},{"id":"2605.30642","title":"Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?","created":"2026-05-28","cited_by_count":1,"area":"diffusion"},{"id":"2606.08309","title":"Where the Score Lives: A Wavelet View of Diffusion","created":"2026-06-06","cited_by_count":1,"area":"diffusion"},{"id":"2606.09718","title":"Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles","created":"2026-06-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.24000","title":"Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2607.17585","title":"Pixel-Space Diffusion Transformers","created":"2026-07-20","cited_by_count":1,"area":"diffusion"},{"id":"2609.26392","title":"Double Descent and Malign Overfitting in Diffusion Models","created":"2026-09-22","cited_by_count":1,"area":"diffusion"},{"id":"2512.11194","title":"Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training","created":"2025-12-12","cited_by_count":0,"area":"diffusion"},{"id":"2602.02699","title":"Sparsely Supervised Diffusion","created":"2026-02-02","cited_by_count":0,"area":"diffusion"},{"id":"2602.04139","title":"Generative Neural Operators through Diffusion Last Layer","created":"2026-02-04","cited_by_count":0,"area":"diffusion"},{"id":"2602.18084","title":"Balancing Symmetry and Efficiency in Graph Flow Matching","created":"2026-02-20","cited_by_count":0,"area":"diffusion"},{"id":"2603.13421","title":"Generalization and Memorization in Rectified Flow","created":"2026-03-12","cited_by_count":0,"area":"diffusion"},{"id":"2604.10074","title":"Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs","created":"2026-04-11","cited_by_count":0,"area":"diffusion"},{"id":"2604.17673","title":"Grokking of Diffusion Models: Case Study on Modular Addition","created":"2026-04-20","cited_by_count":0,"area":"diffusion"},{"id":"2604.23552","title":"On the Memorization of Consistency Distillation for Diffusion Models","created":"2026-04-26","cited_by_count":0,"area":"diffusion"},{"id":"2605.00414","title":"Trees to Flows and Back: Unifying Decision Trees and Diffusion Models","created":"2026-05-01","cited_by_count":0,"area":"diffusion"},{"id":"2605.10647","title":"diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories","created":"2026-05-11","cited_by_count":0,"area":"diffusion"},{"id":"2605.14276","title":"Training-Free Generative Sampling via Moment-Matched Score Smoothing","created":"2026-05-14","cited_by_count":0,"area":"diffusion"},{"id":"2605.19170","title":"Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics","created":"2026-05-18","cited_by_count":0,"area":"diffusion"},{"id":"2605.20235","title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.22050","title":"Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations","created":"2026-05-21","cited_by_count":0,"area":"diffusion"},{"id":"2606.07271","title":"Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path","created":"2026-06-05","cited_by_count":0,"area":"diffusion"},{"id":"2606.22084","title":"Patched Flow Matching: Generative Wall-Pressure Reconstruction Beyond Training-Domain Scales from Sparse Sensors","created":"2026-06-20","cited_by_count":0,"area":"diffusion"},{"id":"2607.04442","title":"Tightening the Score Matching Gap for Diffusion Models","created":"2026-07-05","cited_by_count":0,"area":"diffusion"},{"id":"2607.24296","title":"PAC-DP: PAC-Bayesian Diffusion Policy Learning","created":"2026-07-27","cited_by_count":0,"area":"diffusion"},{"id":"2608.11732","title":"Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation","created":"2026-08-12","cited_by_count":0,"area":"diffusion"},{"id":"2608.19067","title":"Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification","created":"2026-08-19","cited_by_count":0,"area":"diffusion"},{"id":"2609.33210","title":"Background Gradients Shape Memorization in Flow Matching","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.39648","title":"From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.02780","title":"Controlling Polar Exposure to Delay Memorization in Diffusion Models","created":"2026-10-02","cited_by_count":0,"area":"diffusion"},{"id":"2610.11670","title":"Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"id":"2610.13786","title":"Your Discrete Graph Diffusion Model is Secretly Memorizing","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.19042","title":"Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}