Preprint
Oct 2026
Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matching
We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas standard conditional flow matching (FM) incorporates conditioning through the vector field and draws source samples from a standard Gaussian, CNP-Flow uses a conditional n...
Kuan-Hsun Tu, Hsuan-Chi Liu, Jia-Wei Liao et al.
· 0 citations