AI RESEARCH
Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization
arXiv CS.LG
•
ArXi:2506.22304v3 Announce Type: replace Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly sampling and lacking interpretability of the intermediate states. Recent approaches accelerate sampling by straightening trajectories or distilling endpoints, yet they treat the original generative process as a black box, discarding the teacher's intermediate dynamics.