Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry.
Yong-Hyun ParkMingi KwonJaewoong ChoiJunghyo JoYoungjung UhPublished in: NeurIPS (2023)
Keyphrases
- diffusion models
- latent space
- diffusion model
- information diffusion
- manifold learning
- latent variables
- gaussian process
- low dimensional
- parameter space
- lower dimensional
- social networks
- dimensionality reduction
- shape analysis
- matrix factorization
- object recognition
- high dimensional data
- probabilistic model
- euclidean space
- pairwise
- pattern recognition
- image processing