AI RESEARCH
Attraction, Repulsion, and Friction: Introducing DMF, a Friction-Augmented Drifting Model
arXiv CS.LG
•
ArXi:2604.18194v1 Announce Type: new Drifting Models [Deng, 2026] train a one-step generator by evolving samples under a kernel-based drift field, avoiding ODE integration at inference. The original analysis leaves two questions open. The drift-field iteration admits a locally repulsive regime in a two-particle surrogate, and vanishing of the drift ($V_{p,q}\equi 0$) is not known to force the learned distribution $q$ to match the target $p