cs.LGSep 14, 2026

Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration

Authors: Arthur StéphanovitchEddie Aamari

Organizations: Centre de recherche en économie et statistique · ENSAE, IP Paris · Département de Mathématiques et Applications · CNRS, École Normale Supérieure, PSL

Abstract

Drifting models offer a promising route to faster generative AI: they perform gradual transport during training, while generating new samples in a single step. This paper asks whether the underlying drifting process can converge rapidly to a target distribution under ideal conditions, before finite-data or optimization effects are introduced. We show that its convergence rate depends critically on how it handles spatial scale. With a single fixed resolution, fine-scale features of the target can become nearly invisible, leading to extremely slow convergence. We introduce a multihead approach that combines scale-normalized information across a continuum of resolutions. We prove that this multihead approach restores exponential convergence near standard reference distributions. These results identify fixed resolution as a key bottleneck and provide a simple route to faster one-step generative models.

Explore similar work

CardsList
  1. Drift Flow Matching

    May 17, 2026Chenrui Ma, Xi Xiao, Lin Zhao +3Generative ModelsDiscrete Diffusion Model

  2. Second Order Drifting Models

    Aug 8, 2026Drake Brown, Yuhao Huang, Shih-Hsin Wang +1Generative ModelsOrder