A Kinetic Energy Perspective of Flow Matching 事件

A Kinetic Energy Perspective of Flow Matching arXiv:2602.07928v2 Announce Type: replace-cross Abstract: Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corresponds to a trajectory with its own dynamical effort. Motivated by classical mechanics, we introduce Kinetic Path Energy (KPE), an action-like, per-sample diagnostic that measures the accumulated kinetic effort along