P-Flow stabilizes flow-matching models for inverse problems via proxy gradients and Gaussian spherical projections, avoiding long-chain differentiation while maintaining prior consistency.
Substitutingt= 1into the above inequality yields: ∥ψ(x0)−ψ(x ′ 0)∥ ≤exp(L v)∥x0 −x ′ 0∥.(21) Let Lψ = exp(Lv)
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
-
P-Flow: Proxy-gradient Flows for Linear Inverse Problems
P-Flow stabilizes flow-matching models for inverse problems via proxy gradients and Gaussian spherical projections, avoiding long-chain differentiation while maintaining prior consistency.