AI RESEARCH
Flow Matching with Uncertainty Quantification and Guidance
arXiv CS.LG
•
ArXi:2602.10326v2 Announce Type: replace-cross Despite the remarkable success of sampling-based generative models such as flow matching, they can still produce samples of inconsistent or degraded quality. To assess sample reliability and generate higher-quality outputs, we propose uncertainty-aware flow matching (UA-Flow), a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty. UA-Flow estimates per-sample uncertainty by propagating velocity uncertainty through the flow dynamics.