Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score
cond-mat.dis-nn, cond-mat.stat-mech, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Comments: 25 pages, 7 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Losing dimensions: Geometric memorization in generative diffusion
- Weighting Schedules Govern What and When Score-Based Generative Models Learn from Multimodal Data
- Critical windows: non-asymptotic theory for feature emergence in diffusion models
- Sampling from Mean-Field Gibbs Measures via Diffusion Processes
- Sampling, Diffusions, and Stochastic Localization
- Sampling from Spherical Spin Glasses in Total Variation via Algorithmic Stochastic Localization
- Score Shocks: The Burgers Equation Structure of Diffusion Generative Models
- Emergence of Distortions in High-Dimensional Guided Diffusion Models
Related papers
- Topological metal-insulator transitions in one-dimensional non-Hermitian quasicrystals: beyond PT-symmetry
- Microscopic and collective signatures of feature learning in neural networks
- Synchronous and asynchronous Monte Carlo dynamics of mean-field spin glasses with rotationally invariant couplings: what they share and where they differ
- Reentrant Localization Length in a Quasiperiodic Thue-Morse Chain
- Beyond Ground States: Learning Many-Body Hamiltonians for p-Bit Invertible Arithmetic
- Linear equivalence of nonlinear recurrent neural networks