Representation alignment with pretrained visual encoders improves diffusion transformer training but requires auxiliary encoders and extra training overhead. Recent approaches instead exploit representations from the generative model's own variational autoencoder (VAE). However, reconstruction-oriented VAE features are not optimized for the semantic discrimination and spatial structure needed for generative learning.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile