AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Locality-Aware Continual Unlearning for Diffusion Models

Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 3 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
add local replay (L_retain) to unlearning loss (ablation)LACU · Loss ablation (10 steps)RR_acc: 0.32 -> 0.61Improved
add local replay (L_retain) to unlearning loss (ablation)LACU · Loss ablation (10 steps)GR_acc: 0.67 -> 0.85Improved
add l2 parameter regularization to unlearning loss (ablation)LACU · Loss ablation (10 steps)RR_acc: 0.32 -> 0.39Improved
add l2 regularization on top of unlearning plus replay (ablation)LACU · Loss ablation (10 steps)RR_acc: 0.61 -> 0.74Improved
add l2 regularization on top of unlearning plus replay (ablation)LACU · Loss ablation (10 steps)GR_acc: 0.85 -> 0.87Improved
add replay and regularization to unlearning only (ablation)LACU · Loss ablation (10 steps)U_acc: 0.94 -> 0.92Hurt
rank targets/neighbors by score-prediction distance instead of CLIP (ablation)LACU · CUL selection variants (10 steps)RR_acc: 0.61 -> 0.74Improved
rank targets/neighbors by score-prediction distance instead of CLIP (ablation)LACU · CUL selection variants (10 steps)GR_acc: 0.78 -> 0.87Improved
rank by score-prediction distance instead of direct LLM replacement (ablation)LACU · CUL selection variants (10 steps)RR_acc: 0.60 -> 0.74Improved
use score-based selection instead of naive fixed anchor (ablation)LACU · CUL selection variants (10 steps)RR_acc: 0.41 -> 0.74Improved
use LACU instead of AGE adaptive targets onlyAGE · CUL 10 stepsRR_acc: 0.15 -> 0.72Improved
use LACU instead of strongest-erasure ESD-uESD-u · CUL 10 stepsGR_acc: 0.15 -> 0.87Improved

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