Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models

📅 2026-05-06
📈 Citations: 0
Influential: 0
📄 PDF

career value

212K/year
📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

symmetry breaking
nonlocality
phase transitions
diffusion models
criticality
Innovation

Methods, ideas, or system contributions that make the work stand out.

symmetry breaking
nonlocality
phase transition
diffusion models
generation dynamics
🔎 Similar Papers
2023-10-03International Conference on Machine LearningCitations: 12