Imagen de Portada

Critical windows: non-asymptotic theory for feature emergence in diffusion models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Marvin, Chen, Sitan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Guiding a diffusion model using sliding windows
por: Adaloglou, Nikolas, et al.
Publicado: (2024)

ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
por: Karan, Aayush, et al.
Publicado: (2025)

What does guidance do? A fine-grained analysis in a simple setting
por: Chidambaram, Muthu, et al.
Publicado: (2024)

Towards Long-window Anchoring in Vision-Language Model Distillation
por: Zhou, Haoyi, et al.
Publicado: (2025)

Explore the vulnerability of black-box models via diffusion models
por: Shi, Jiacheng, et al.
Publicado: (2025)

Secure and reversible face anonymization with diffusion models
por: Labarbarie, Pol, et al.
Publicado: (2025)

FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
por: Neukirch, Nils, et al.
Publicado: (2025)

Fast constrained sampling in pre-trained diffusion models
por: Graikos, Alexandros, et al.
Publicado: (2024)

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

Blink of an eye: a simple theory for feature localization in generative models
por: Li, Marvin, et al.
Publicado: (2025)

Blue noise for diffusion models
por: Huang, Xingchang, et al.
Publicado: (2024)

Amortizing intractable inference in diffusion models for vision, language, and control
por: Venkatraman, Siddarth, et al.
Publicado: (2024)

Towards SFW sampling for diffusion models via external conditioning
por: Reyes, Camilo Carvajal, et al.
Publicado: (2025)

Boomerang: Local sampling on image manifolds using diffusion models
por: Luzi, Lorenzo, et al.
Publicado: (2022)

RelDenClu: A Relative Density based Biclustering Method for identifying non-linear feature relations
por: Jain, Namita, et al.
Publicado: (2018)

Bayesian computation with generative diffusion models by Multilevel Monte Carlo
por: Haji-Ali, Abdul-Lateef, et al.
Publicado: (2024)

Fine-tuning can cripple your foundation model; preserving features may be the solution
por: Mukhoti, Jishnu, et al.
Publicado: (2023)

Personalized federated learning based on feature fusion
por: Xing, Wolong, et al.
Publicado: (2024)

Learning few-step posterior samplers by unfolding and distillation of diffusion models
por: Mbakam, Charlesquin Kemajou, et al.
Publicado: (2025)

Generalization in diffusion models arises from geometry-adaptive harmonic representations
por: Kadkhodaie, Zahra, et al.
Publicado: (2023)

Elucidating the solution space of extended reverse-time SDE for diffusion models
por: Cui, Qinpeng, et al.
Publicado: (2023)

ADBM: Adversarial diffusion bridge model for reliable adversarial purification
por: Li, Xiao, et al.
Publicado: (2024)

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
por: Bartosh, Grigory, et al.
Publicado: (2026)

Inverse problems with diffusion models: MAP estimation via mode-seeking loss
por: Gutha, Sai Bharath Chandra, et al.
Publicado: (2025)

Reasoning emerges from constrained inference manifolds in large language models
por: Ma, Yanbiao, et al.
Publicado: (2026)

FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
por: Krey, Elias B., et al.
Publicado: (2026)

DFU: scale-robust diffusion model for zero-shot super-resolution image generation
por: Havrilla, Alex, et al.
Publicado: (2023)

PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations
por: Dai, Ting-Yu, et al.
Publicado: (2025)

Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks
por: Monji-Azad, Sara, et al.
Publicado: (2023)

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
por: Park, Yonghyun, et al.
Publicado: (2025)

A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context
por: Mateescu, Andrei, et al.
Publicado: (2025)

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model
por: Wang, Xiyao, et al.
Publicado: (2025)

HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
por: Choi, Sungik, et al.
Publicado: (2024)

On the importance of cross-task features for class-incremental learning
por: Soutif--Cormerais, Albin, et al.
Publicado: (2021)

Sampling-guided exploration of active feature selection policies
por: Bernardino, Gabriel, et al.
Publicado: (2026)

The problems with using STNs to align CNN feature maps
por: Finnveden, Lukas, et al.
Publicado: (2020)

Multi-feature Reconstruction Network using Crossed-mask Restoration for Unsupervised Industrial Anomaly Detection
por: Wang, Junpu, et al.
Publicado: (2024)

Video alignment using unsupervised learning of local and global features
por: Fakhfour, Niloufar, et al.
Publicado: (2023)

Theoretical research on generative diffusion models: an overview
por: Yeğin, Melike Nur, et al.
Publicado: (2024)

Information-geometric adaptive sampling for graph diffusion
por: Lu, Yuhui, et al.
Publicado: (2026)