AI Paper Atlas

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

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models

Kaiyuan Deng, Gen Li, Yang Xiao, Bo Hui, Xiaolong Ma

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 6 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 ScaPre closed-form unlearning instead of RECESD v1.5 Imagenette unlearning · Imagenette (10 classes)avg unlearn accuracy (%): 4.9 -> 0.8Improved
use ScaPre instead of UCE/RECE for 50-concept unlearningSD v1.5 · ImageNet-Diversi50 (50 classes)CLIP score (COCO): UCE 22.23 -> ScaPre 29.41Improved
use ScaPre instead of UCE for precise unlearningSD v1.5 · ImageNet-Confuse5preserve accuracy (%): 5.6 -> 76.3Improved
use ScaPre instead of UCESD v1.5 · ImageNet-Confuse5unlearn accuracy (%): 2.9 -> 5.8Hurt
use ScaPre instead of MACE for generation qualitySD v1.5 · Imagenette (10 classes)CLIP score (COCO): 31.02 -> 30.43Hurt
use ScaPre for explicit-content removalSD v1.4 · I2P NudeNet total detectionstotal detections: 743 -> 54Improved
use ScaPre against white-box UnlearnDiffAtkunlearned SD · Robustness: UnlearnDiffAtkattack success rate (%): 67.1 -> 60.9Improved

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