Depth as Time in One-Step Generative Models okładka

Depth as Time in One-Step Generative Models

Depth as Time in One-Step Generative Models

Słuchaj bezpłatnie, bez subskrypcji

Zobacz szczegóły

Saisonale Sparangebote | 0,99 € pro Monat für die ersten 3 Monate

Danach 6,99 €/Monat. Bedingungen gelten. Monatlich kündbar.
One-step generators compress multi-step diffusion into a single forward pass, raising the question of what happens to the denoising trajectory. The authors observe "depth as time": denoising unfolds across network layers and can be recovered by decoding intermediate layers with the model's own output head. The behavior depends on the training task; MeanFlow shows both denoising and renoising, while drifting models do not. Models showing it compress well, with a MeanFlow SiT-L/2 shrunk 16.6x into one time-conditioned block. Authors: Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun, Esin Tureci, Olga Russakovsky Paper: https://arxiv.org/abs/2610.03626v1
adbl_web_anon_alc_button_suppression_t1
Brak recenzji