AI RESEARCH

A Unified Framework for Diffusion Model Unlearning with f-Divergence

arXiv CS.LG

ArXi:2509.21167v2 Announce Type: replace Most existing methods for concept unlearning in text-to-image diffusion models minimize a mean squared error (MSE) loss between the denoiser outputs conditioned on a target and an anchor concept, which is implicitly the KL divergence between two Gaussians. We generalize this objective to any $f$-divergence, recovering MSE as the KL instance, and identify a family of $\alpha$-divergences whose Gaussian closed-form yields cheap, MSE-like