Depth as Time in One-Step Generative Models

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