New paper shows DiT latents can be linearly probed to predict pixels, skipping the VAE decoder

kwangmoo_yi · x · 2026-11-19

Chen et al.'s paper "Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers" shows you can linearly probe the DiT latent space to skip the decoder entirely. The poster raises the provocative question: was training with a V(Q)AE just a speed optimization that can now be thrown away?

Related event: DWD Paper: Diffusion Models Predict Pixels Without a Decoder(4 posts)→

Original post →

More from Research

Research channel →