A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifolds
cs.LG
Submitted: 2026-08-24
Updated: 2026-08-26
Comments: 48 pages, 15 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
- Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems
- Counterfactual Explanations via Riemannian Latent Space Traversal
- Spontaneous Symmetry Breaking in Generative Diffusion Models
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations
- PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks