AI RESEARCH
Distilling Latent Manifolds: Resolution Extrapolation by Variational Autoencoders
arXiv CS.CV
•
ArXi:2603.14536v1 Announce Type: new Variational Autoencoder (VAE) encoders play a critical role in modern generative models, yet their computational cost often motivates the use of knowledge distillation or quantification to obtain compact alternatives. Existing studies typically believe that the model work better on the samples closed to their