Metraipolis › archive › dc_69df52033e47
Depth as Time in One-Step Generative Models — arXiv:2610.03626
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03626
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:44.827Z
- SHA-256 of the archived text
22c8a6e988bb47594df4b499a669c574cbdd2df8e859c77396e9d4acb4173172- Stable URL of this page
https://metraipolis.com/documento/dc_69df52033e47
How to cite
Depth as Time in One-Step Generative Models — arXiv:2610.03626 — arXiv, https://arxiv.org/abs/2610.03626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69df52033e47 (Metraipolis archive dc_69df52033e47, sha256 22c8a6e988bb47594df4b499a669c574cbdd2df8e859c77396e9d4acb4173172)
BibTeX
@misc{dc69df52033e47,
title = {Depth as Time in One-Step Generative Models — arXiv:2610.03626},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03626},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69df52033e47; sha256 22c8a6e988bb47594df4b499a669c574cbdd2df8e859c77396e9d4acb4173172},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The recent wave of one-step generative models, which compress the multi-step trajectory of diffusion via either distillation or learned flow maps, has reached an inflection point where they can generate high-quality images. Here, we ask a natural question that follows from these advances: what happens to the denoising trajectory of multi-step diffusion when generation is compressed into a single forward pass? We offer an empirical observation we call \textit{depth as time}: the denoising computation that multi-step diffusion performs across sampling steps appears to unfold across the depth of a single forward pass, and can be recovered by decoding intermediate layers with the model's own output head. Most interestingly, we show that this depthwise computation depends on the transport task a flow map is trained to solve. The most surprising case is MeanFlow, where probing shorter transport intervals reveals both denoising and renoising within a single network evaluation. In contrast, generators trained without a time-indexed transport task, such as drifting models, do not exhibit the same depthwise denoising. Consequently, we show that models that exhibit the depthwise denoising phenomenon are more compressible across the layerwise computation: a MeanFlow \texttt{SiT-L/2} model can be compressed by $16.6\times$ in parameters into a single time-conditioned block. We offer an explanation for this denoise-then-renoise behavior and show that, when we treat the layerwise computation explicitly as a flow, a single time-conditioned block can be trained to denoise across layers, compressing a MeanFlow \texttt{SiT-L/2} model by $16.6\times$ in parameters. Together, these results suggest that the temporal computation of diffusion is not eliminated by one-step generation, but reorganized across network depth.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03626 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.712Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).