Paper Detail

APEX: Asynchronous Prefix Denoising for Extreme Compression

David Dinkevich, Nisan Chiprut, Yoav HaCohen, Dani Lischinski

huggingface Score 6.0

Published 2026-10-09 · First seen 2026-10-14

General AI

Abstract

Fewer latent tokens promise cheaper diffusion. Yet aggressive latent compression creates a reconstruction-generation dilemma: adding channels improves reconstruction but makes generation harder. We introduce APEX, short for Asynchronous Prefix denoising for EXtreme compression, which pairs a hierarchical latent space with asynchronous denoising over channel groups. Our autoencoder orders channel prefixes from structure to detail, while one shared denoiser generates them at staggered local times without adding tokens. On ImageNet-512, APEX outperforms existing methods at every evaluated channel count under 64x and 128x compression. At matched training and guided sampling compute, it also outperforms a 256-token model at every evaluated budget, with larger gains at lower compute. Code is available at https://daviddinkevich.github.io/APEX.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{dinkevich2026apex,
  title = {APEX: Asynchronous Prefix Denoising for Extreme Compression},
  author = {David Dinkevich and Nisan Chiprut and Yoav HaCohen and Dani Lischinski},
  year = {2026},
  abstract = {Fewer latent tokens promise cheaper diffusion. Yet aggressive latent compression creates a reconstruction-generation dilemma: adding channels improves reconstruction but makes generation harder. We introduce APEX, short for Asynchronous Prefix denoising for EXtreme compression, which pairs a hierarchical latent space with asynchronous denoising over channel groups. Our autoencoder orders channel prefixes from structure to detail, while one shared denoiser generates them at staggered local times },
  url = {https://huggingface.co/papers/2610.12843},
  keywords = {code available, huggingface daily},
  eprint = {2610.12843},
  archiveprefix = {arXiv},
}

Metadata

{}