Cover Image

On the Edge of Memorization in Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Buchanan, Sam, Pai, Druv, Ma, Yi, De Bortoli, Valentin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Masked Completion via Structured Diffusion with White-Box Transformers
by: Pai, Druv, et al.
Published: (2024)

Accelerated Diffusion Models via Speculative Sampling
by: De Bortoli, Valentin, et al.
Published: (2025)

Attention-Only Transformers via Unrolled Subspace Denoising
by: Wang, Peng, et al.
Published: (2025)

Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
by: Benton, Joe, et al.
Published: (2023)

Diffusion Models for Constrained Domains
by: Fishman, Nic, et al.
Published: (2023)

Self-Speculative Masked Diffusions
by: Campbell, Andrew, et al.
Published: (2025)

From Denoising Diffusions to Denoising Markov Models
by: Benton, Joe, et al.
Published: (2022)

On quantitative Laplace-type convergence results for some exponential probability measures, with two applications
by: De Bortoli, Valentin, et al.
Published: (2021)

Simulating Diffusion Bridges with Score Matching
by: Heng, Jeremy, et al.
Published: (2021)

A Global Geometric Analysis of Maximal Coding Rate Reduction
by: Wang, Peng, et al.
Published: (2024)

Learn to Guide Your Diffusion Model
by: Galashov, Alexandre, et al.
Published: (2025)

White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?
by: Yu, Yaodong, et al.
Published: (2023)

Dynamical Regimes of Diffusion Models
by: Biroli, Giulio, et al.
Published: (2024)

Seasoning Generative Models for a Generalization Aftertaste
by: Husain, Hisham, et al.
Published: (2026)

Distributional Diffusion Models with Scoring Rules
by: De Bortoli, Valentin, et al.
Published: (2025)

Beyond Scores: Proximal Diffusion Models
by: Fang, Zhenghan, et al.
Published: (2025)

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
by: Guo, Tianyu, et al.
Published: (2024)

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
by: Wu, Ziyang, et al.
Published: (2024)

Schrödinger Bridge Flow for Unpaired Data Translation
by: De Bortoli, Valentin, et al.
Published: (2024)

Particle Denoising Diffusion Sampler
by: Phillips, Angus, et al.
Published: (2024)

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
by: Kong, Lingkai, et al.
Published: (2024)

Target Score Matching
by: De Bortoli, Valentin, et al.
Published: (2024)

On the Memorization of Consistency Distillation for Diffusion Models
by: Jiang, Bingqing, et al.
Published: (2026)

On Memorization in Diffusion Models
by: Gu, Xiangming, et al.
Published: (2023)

Provable Separations between Memorization and Generalization in Diffusion Models
by: Ye, Zeqi, et al.
Published: (2025)

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
by: Fang, Zhengyu, et al.
Published: (2024)

Manifold Generalization Provably Proceeds Memorization in Diffusion Models
by: Shen, Zebang, et al.
Published: (2026)

Canonical Factors for Hybrid Neural Fields
by: Yi, Brent, et al.
Published: (2023)

Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
by: Shah, Kulin, et al.
Published: (2025)

Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
by: Sterling, Benjamin, et al.
Published: (2026)

Deep MMD Gradient Flow without adversarial training
by: Galashov, Alexandre, et al.
Published: (2024)

Memorization and Regularization in Generative Diffusion Models
by: Baptista, Ricardo, et al.
Published: (2025)

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
by: Renaud, Marien, et al.
Published: (2023)

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
by: Renaud, Marien, et al.
Published: (2025)

Implicit Diffusion: Efficient Optimization through Stochastic Sampling
by: Marion, Pierre, et al.
Published: (2024)

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
by: Favero, Alessandro, et al.
Published: (2025)

Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
by: Rodriguez, Marta Aparicio, et al.
Published: (2026)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
by: Gretton, Arthur, et al.
Published: (2026)

Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
by: Kim, Gwangho, et al.
Published: (2026)

Memorization Control in Diffusion Models from Denoising-centric Perspective
by: Vu, Thuy Phuong, et al.
Published: (2026)