SCFM augments flow matching with structured latent variables and exogenous noise in the source distribution, using a shared time-dependent recognition network to jointly perform variational inference and flow velocity estimation.
Structured Coupling for Flow Matching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structured Coupling for Flow Matching
SCFM augments flow matching with structured latent variables and exogenous noise in the source distribution, using a shared time-dependent recognition network to jointly perform variational inference and flow velocity estimation.