AI Paper Atlas

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

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models

Ouxiang Li, Yuan Wang, Xinting Hu, Houcheng Jiang, Tao Liang, Yanbin Hao, Guojun Ma, Fuli Feng

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models

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 Invariant Equality Constraints (ablation)SPEED null-space editing · Erase Van Gogh, non-target FID (avg 4 styles)non-target FID: 50.43 -> 48.17Improved
add Influence-based Prior Filtering (ablation)SPEED + IEC · Erase Van Gogh, non-target FID (avg 4 styles)non-target FID: 48.17 -> 38.02Improved
add Directed Prior Augmentation (vs random augmentation) (ablation)SPEED + IEC + IPF · Erase Van Gogh, non-target FID (avg 4 styles)non-target FID: 32.62 -> 29.35Improved
add random prior augmentation (ablation)SPEED + IEC + IPF · Erase Van Gogh, non-target FID (avg 4 styles)non-target FID: 38.02 -> 32.62Improved
add random prior augmentation (ablation)SPEED + IEC + IPF · Erase Van Gogh, MS-COCOFID: 20.57 -> 20.99Hurt
null-space constrained editing vs weighted least squares (UCE)SPEED · Erase 100 celebritiesAcc_r: 20.92 -> 85.54Improved
use SPEED instead of MACEconcept erasure · Erase 100 celebritiesruntime: 1736 s -> 5.0 sImproved
use SPEED instead of MACEconcept erasure · Erase 100 celebritiesAcc_e: 4.80 -> 5.87Hurt
increase target concepts from 1 to 3SPEED vs UCE · Pikachu non-targetFID: SPEED +4.59 (16.81 -> 21.40) vs UCE +10.14Improved
use SPEED rather than RECE for target erasurefew-concept erasure · Erase Snoopytarget CS: 23.50 vs 18.38Hurt

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