AI RESEARCH
Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
arXiv CS.AI
•
ArXi:2605.11547v1 Announce Type: cross Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefore requires using a small fixed evaluation budget effectively: the key question is not only how to integrate the flow, but where the sampler should spend its steps. We propose SharpEuler, a