Geometric Decoupling: Diagnosing the Structural Instability of Latent

arXiv:2604.18804v1 Announce Type: new
Abstract: Latent Diffusion Models (LDMs) achieve high-fidelity synthesis but suffer from latent space brittleness, causing discontinuous semantic jumps during editing. We introduce a Riemannian framework to diagnose this instability by analyzing the generative Jacobian, decomposing geometry into textit{Local Scaling} (capacity) and textit{Local Complexity} (curvature). Our study uncovers a textbf{“Geometric Decoupling”}: while curvature in normal generation functionally encodes image detail, OOD generation exhibits a functional decoupling where extreme curvature is wasted on unstable semantic boundaries rather than perceptible details. This geometric misallocation identifies “Geometric Hotspots” as the structural root of instability, providing a robust intrinsic metric for diagnosing generative reliability.