AI RESEARCH
Exploring and Exploiting Stability in Latent Flow Matching
arXiv CS.LG
•
ArXi:2605.08398v1 Announce Type: new In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by their tendency to generate similar outputs under identical noise seeds. We provide a perspective relating this phenomenon to flow matching theory, which indicates that this stability is inherent to the FM objective. We further exploit this stability to derive practical algorithms for efficient.