Seonglae ChoDiT
Omni
For image tokens apply diffusion loss for transformer omni
Traditional DiT (=Diffusion Transformer) relies on outdated VAE encoders → low-dimensional (latent 4ch), complex structure, weak expressiveness. Instead of VAE, using pre-trained representation encoders (DINO, MAE, SigLIP, etc.) + lightweight decoder combination = Representation Autoencoder (RAE). L1+GAN+LPIPS loss