Stanford DWD paper: linear head predicts pixels directly, ditching the diffusion decoder

kwangmoo_yi · x · 2026-11-19

Researchers from Stanford, Luma AI, and Caltech introduce DWD (Decoding Without a Decoder), letting a finetuned diffusion transformer produce final pixels via a linear head, removing the decoder from latent diffusion pipelines.

Key ideas:

Results:

Code is coming soon; the authors suggest the V(Q)AE used in training may have been just a speedup that can be discarded entirely.

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

Original post →

More from Multimodal

Multimodal channel →