Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels

arXiv:2605.12805v1 Announce Type: cross Abstract: MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. However, discrete state spaces do not have smooth trajectories or spatial derivatives, so the continuous formulation does not directly apply. We introduce Discrete MeanFlow, which replaces the motion of a point with the transport of probability mass over finite states. Our ke