Skip to content
Fred Xu
About Me
Philosophy
AI
Film
Research & Papers
Menu
About Me
Philosophy
AI
Film
Research & Papers
Tagged
Optimal Transport
Nov 18, 2026
· 47 min read
Improving Function Space Flow Matching with Kernel Optimal Transport
kFFM replaces the random noise–data pairing of Functional Flow Matching with entropic optimal transport under a kernel-induced cost, the coupling behind the Hilbert Sinkhorn Divergence: a signature kernel for paths, a Sobolev or Euclidean RBF for fields. Same network, same loss, 5–7% more training time, and better samples on eight time-series and PDE benchmarks.