Trendoday

Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers

Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion trans

  • Upvotes4
–Rank now
#10Peak rank
2Days on list
232Score · 7d
Nov 19, 2026First seen
Rank · 7 days

About this paper

A method that removes the decoder from latent diffusion models by adding a final-step prediction head to a finetuned diffusion transformer, reducing inference cost and improving pixel quality in image and video generation.

Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion transformer produce final pixels directly through a linear head. Unlike previous methods, where the denoising output leads to final pixels, DWD separates the two roles: the original denoising head continues to drive sampling, then the new DWD head predicts the pixels at the final step. We extend pretrained latent models with DWD efficiently by finetuning only the last few transformer blocks, training the DWD head with pixel quality losses while anchoring the denoising head to the pretrained model…

latent diffusion modelsdecoderdenoised latentsdiffusion transformerlinear headdenoising headDWD headpretrained latent modelsfinetuningtransformer blocks
Upvotes
4
Authors
7
Published
Nov 17, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #10 of 30, reached on Nov 19, 09:29 UTC. It dropped off the list after Nov 20, 03:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 03:2809:2915:2921:2903:29 Nov 19, 03:28 UTC · #28Nov 19, 05:28 UTC · #15Nov 19, 07:29 UTC · #11Nov 19, 09:29 UTC · #10Nov 19, 11:29 UTC · #11Nov 19, 13:29 UTC · #12Nov 19, 15:29 UTC · #12Nov 19, 17:29 UTC · #13Nov 19, 19:29 UTC · #12Nov 19, 21:29 UTC · #12Nov 19, 23:29 UTC · #12Nov 20, 01:29 UTC · #12Nov 20, 03:29 UTC · #13

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

04812 03:2809:2915:2921:2903:29 Nov 19, 03:28 UTC · 4Nov 19, 05:28 UTC · 8Nov 19, 07:29 UTC · 10Nov 19, 09:29 UTC · 10Nov 19, 11:29 UTC · 10Nov 19, 13:29 UTC · 10Nov 19, 15:29 UTC · 10Nov 19, 17:29 UTC · 11Nov 19, 19:29 UTC · 12Nov 19, 21:29 UTC · 12Nov 19, 23:29 UTC · 12Nov 20, 01:29 UTC · 12Nov 20, 03:29 UTC · 12

Questions

Is Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 20, 03:29 UTC, after 2 days of trending.

What is the highest rank Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers reached?

#10 on Hugging Face · Daily papers, on Nov 19, 09:29 UTC. Trendoday checks this list every 120 minutes.

How long has Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers been trending?

It was first seen on Nov 19, 2026 and has been on the list on 2 days (13 checks) since.