MC-RFM achieves superior few-shot adaptation by representing features on a mixed hyperbolic-Euclidean manifold and learning task-conditioned continuous transport via Riemannian flow matching to hybrid prototypes.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
RK4 at 80 function evaluations matches Euler at 200 in sliced Wasserstein quality for flow matching sampling, with the adaptive solver concentrating steps near t=1 due to stiffening velocity fields.
citing papers explorer
-
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
MC-RFM achieves superior few-shot adaptation by representing features on a mixed hyperbolic-Euclidean manifold and learning task-conditioned continuous transport via Riemannian flow matching to hybrid prototypes.
-
From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models
RK4 at 80 function evaluations matches Euler at 200 in sliced Wasserstein quality for flow matching sampling, with the adaptive solver concentrating steps near t=1 due to stiffening velocity fields.