Imagen de Portada

How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ambrogioni, Luca
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability
por: Ambrogioni, Luca
Publicado: (2023)

CoVAE: Consistency Training of Variational Autoencoders
por: Silvestri, Gianluigi, et al.
Publicado: (2025)

Stationarity without mean reversion in improper Gaussian processes
por: Ambrogioni, Luca
Publicado: (2023)

The Information Dynamics of Generative Diffusion
por: Stancevic, Dejan, et al.
Publicado: (2025)

Entropic Time Schedulers for Generative Diffusion Models
por: Stancevic, Dejan, et al.
Publicado: (2025)

Measuring Semantic Information Production in Generative Diffusion Models
por: Handke, Florian, et al.
Publicado: (2025)

Improved Sampling Schedules for Discrete Diffusion Models
por: Foresti, Alberto, et al.
Publicado: (2026)

The Entropic Signature of Class Speciation in Diffusion Models
por: Handke, Florian, et al.
Publicado: (2026)

Emergence of Distortions in High-Dimensional Guided Diffusion Models
por: Ventura, Enrico, et al.
Publicado: (2026)

Robust and highly scalable estimation of directional couplings from time-shifted signals
por: Rouillard, Louis, et al.
Publicado: (2024)

VCT: Training Consistency Models with Variational Noise Coupling
por: Silvestri, Gianluigi, et al.
Publicado: (2025)

Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
por: Pham, Bao, et al.
Publicado: (2026)

Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion
por: Ventura, Enrico, et al.
Publicado: (2024)

Symmetric Equilibrium Propagation for Thermodynamic Diffusion Training
por: De, Aditi
Publicado: (2026)

Noise Scheduling as Information-Guided Allocation in Diffusion Training
por: Raya, Gabriel, et al.
Publicado: (2026)

How Robust Are Energy-Based Models Trained With Equilibrium Propagation?
por: Mansingh, Siddharth, et al.
Publicado: (2024)

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory
por: Pham, Bao, et al.
Publicado: (2025)

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
por: Favero, Alessandro, et al.
Publicado: (2025)

Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
por: Zhang, Yifan F., et al.
Publicado: (2026)

Training-Free Constrained Generation With Stable Diffusion Models
por: Zampini, Stefano, et al.
Publicado: (2025)

Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model
por: Kendall, Jack
Publicado: (2026)

Pattern-Guided Diffusion Models
por: Lin, Vivian, et al.
Publicado: (2025)

Out-of-Core Dimensionality Reduction for Large Data via Out-of-Sample Extensions
por: Reichmann, Luca, et al.
Publicado: (2024)

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
por: Khanh, Truong Xuan
Publicado: (2026)

Losing dimensions: Geometric memorization in generative diffusion
por: Achilli, Beatrice, et al.
Publicado: (2024)

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
por: Seong, Kiyoung, et al.
Publicado: (2024)

How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
por: Dent, Emily, et al.
Publicado: (2026)

The Phase Is the Gradient: Equilibrium Propagation for Frequency Learning in Kuramoto Networks
por: Ahmadi, Mani Rash
Publicado: (2026)

Manifold Diffusion for Structure Generation of Transition Metal Complexes
por: Schaufelberger, Luca, et al.
Publicado: (2026)

Local Learning Rules for Out-of-Equilibrium Physical Generative Models
por: Bösch, Cyrill, et al.
Publicado: (2025)

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
por: Song, Yuxuan, et al.
Publicado: (2025)

Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks
por: Khodamoradi, Alireza, et al.
Publicado: (2024)

A Model Zoo on Phase Transitions in Neural Networks
por: Schürholt, Konstantin, et al.
Publicado: (2025)

GATE: How to Keep Out Intrusive Neighbors
por: Mustafa, Nimrah, et al.
Publicado: (2024)

Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations
por: Jacobson, Philip, et al.
Publicado: (2026)

How to Squeeze An Explanation Out of Your Model
por: Roxo, Tiago, et al.
Publicado: (2024)

SeedFlood: A Step Toward Scalable Decentralized Training of LLMs
por: Kim, Jihun, et al.
Publicado: (2026)

Reversible Deep Equilibrium Models
por: McCallum, Sam, et al.
Publicado: (2025)

Clustering with minimum spanning trees: How good can it be?
por: Gagolewski, Marek, et al.
Publicado: (2023)

Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation
por: Prashant, Mohit, et al.
Publicado: (2025)