mlsanityData to 7 Oct 2026

Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models

arXiv 2605.04830 ↗First posted 6 May 2026cs.LG cond-mat.stat-mechcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models undergo a phase transition in a critical time window during generation dynamics, with two complementary diagnoses of criticality. The symmetry breaking picture views the critical window as when trajectories bifurcate into different semantic minima of the energy landscape, whereas the nonlocality picture views the critical window as when local denoising fails. We study whether two notions of such phase transitions are concurrent in modern diffusion transformers. By evaluating the dynamics and outcomes of the generation trajectory, we observe a near-simultaneous occurrence of the non-locality and symmetry breaking critical times. Our work is the first to unify the two notions of phase transitions in practice: it provides a concrete diagnostic for when and why diffusion models rely on conditioning and global denoising, enabling principled evaluation of model efficiency and guiding the design of architectures and sampling schemes that avoid unnecessary computation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 42 of its 55 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

42 of 55 references.

Closest ancestors · 29

Same direction, newest first

  1. 2026How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models20 Mar
  2. 2026Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance17 Feb
  3. 2026The Entropic Signature of Class Speciation in Diffusion Models10 Feb
  4. 2026Emergence of Distortions in High-Dimensional Guided Diffusion Models31 Jan
  5. 2025Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models31 Oct
  6. 2025Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models26 Sep
  7. 2025Locality in Image Diffusion Models Emerges from Data Statistics11 Sep
  8. 2025The Information Dynamics of Generative Diffusion27 Aug
  9. 2025Local Diffusion Models and Phases of Data Distributions8 Aug
  10. 2025Measuring Semantic Information Production in Generative Diffusion Models12 Jun
  11. 2025Memorization to Generalization: Emergence of Diffusion Models from Associative Memory27 May
  12. 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion28 Feb
17 more
  1. 2024Towards a Mechanistic Explanation of Diffusion Model Generalization28 Nov
  2. 2024Probing the Latent Hierarchical Structure of Data via Diffusion Models17 Oct
  3. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models3 Mar
  6. 2024Dynamical Regimes of Diffusion Models28 Feb
  7. 2024A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data26 Feb
  8. 2023The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability26 Oct
  9. 2023Spontaneous Symmetry Breaking in Generative Diffusion Models31 May
  10. 2022Scalable Diffusion Models with Transformers19 Dec
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  12. 2022Classifier-Free Diffusion Guidance26 Jul
  13. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  14. 2022Perception Prioritized Training of Diffusion Models1 Apr
  15. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  16. 2020Denoising Diffusion Implicit Models6 Oct
  17. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  6. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  7. 2022Neighborhood Attention Transformercited by 235
  8. 2024DiTFastAttn: Attention Compression for Diffusion Transformer Modelscited by 109
  9. 2024An analytic theory of creativity in convolutional diffusion modelscited by 103
  10. 2025Blink of an eye: a simple theory for feature localization in generative modelscited by 10
  11. 2026Unlearnable phases of mattercited by 2
  12. 2026Learning and Generating Mixed States Prepared by Shallow Channel Circuitscited by 2
1 more
  1. 2025Stability of mixed-state phases under weak decoherencecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Breakdown of Local Denoising as Semantic Speciationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Dynamical Regimes of Multimodal Diffusion Models
  2. 2026The Geometry of Phase Transitions in Generative Dynamics via Projection Caustics
  3. 2024Demystifying Variational Diffusion Models
  4. 2025Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
  5. 2026A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
  6. 2024Nonequilbrium physics of generative diffusion models
  7. 2026Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
  8. 2025Transition Models: Rethinking the Generative Learning Objective