Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models

ArXi:2603.21085v1 Announce Type: new Latent diffusion models have emerged as the dominant framework for high-fidelity and efficient image generation, owing to their ability to learn diffusion processes in compact latent spaces. However, while previous research has focused primarily on reconstruction accuracy and semantic alignment of the latent space, we observe that another critical factor, robustness to sampling perturbations, also plays a crucial role in determining generation quality.