Exploring and Exploiting Stability in Latent Flow Matching 事件

Exploring and Exploiting Stability in Latent Flow Matching arXiv:2605.08398v2 Announce Type: replace-cross Abstract: 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 these models' tendency to generate similar outputs under identical noise seeds. We provide a perspective relating this phenomenon to flow matching theory, which indicates that this sta