AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints

Shervin Khalafi, Alejandro Ribeiro, Dongsheng Ding

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and learned samplers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use constraint thresholds (reverse KL) instead of equal-weight penalties (ablation)reverse KL unlearning · Stable Diffusion v1.4 multi-concept unlearningKL to pretrained model at same unlearning levelImproved
use constraint thresholds (reverse KL) instead of equal-weight penalties (ablation)reverse KL unlearning · Stable Diffusion v1.4 multi-concept unlearningmax CLIP similarity to unlearned conceptsImproved
learn per-sample dual weights (forward KL constraints) instead of equal weights (ablation)forward KL unlearning · CelebA-HQ DDPM, 3 memorized imagesKID at same max SSCDImproved
use likelihood constraint instead of concept erasing (ablation)likelihood-constrained unlearning · Three-Gaussian mixtureKL to retained modes at same unlearning likelihoodImproved
use likelihood constraint instead of concept erasing (ablation)likelihood-constrained unlearning · Stable Diffusion v1.4, unlearn horse keep cowboyKID and KL to pretrained modelImproved
use likelihood constraint instead of reverse KL constraintlikelihood-constrained unlearning · Three-Gaussian mixtureretained modes preservedImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy