VeloForesight: Structured Admission for Training-Free Flow Acceleration

Diffusion transformers generate high-quality videos, but repeated network evaluations make inference expensive. Predicting velocities from sparse exact evaluations can reduce this cost. However, forecasts based on sparse evaluations can become unreliable over longer prediction horizons, and their errors affect subsequent sampling states. In this paper, we introduce VeloForesight, a training-free sampler built around a structured predictor of velocity changes. The predictor estimates trend and curvature from past exact evaluations, controls their contributions separately, and progressively attenuates curvature over longer forecast horizons. Relative-norm bounds limit the size of the predicted changes before they enter the native scheduler. Across image and video generation, VeloForesight achieves up to $5.18\times$ speedup on Wan2.1-14B and $4.76\times$ on SD3.5 Large relative to 50-step sampling.