AI RESEARCH
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
arXiv CS.LG
•
ArXi:2603.09936v1 Announce Type: new Generative Modeling via Drifting has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet the success is largely empirical and its theoretical foundations remain poorly understood. In this paper, we make the following observation: \emph{under a Gaussian kernel, the drift operator is exactly a score difference on smoothed distributions