Abstract
Diffusion-Map-AutoEncoder (DMAE) pairs a diffusion-map encoder (using the Nystr\"om method) with linear or RBF Gaussian-Process latent mean decoders, yielding closed-form inductive mappings and strong reconstructions.
Diffusion Map Autoencoder
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Diffusion Autoencoders: Toward a Meaningful and Decodable Representation (2021)69% match
- Latent Diffusion Models with Masked AutoEncoders (2025)68% match
- On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning (2025)67% match
- Diffusion Transformers with Representation Autoencoders (2025)66% match
- DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning (2025)66% match
- The Diffusion Encoder (2026)66% match
- Geometric Autoencoder for Diffusion Models (2026)66% match
- Diffusion Models as Masked Autoencoders (2023)66% match