AI Paper Atlas

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

SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder

Ronen Kamenetsky, Sara Dorfman, Daniel Garibi, Roni Paiss, Or Patashnik, Danny Cohen-Or

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 13 citations (OpenAlex)

Read the paper

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 SAEdit instead of Flux SpaceFlux · User studyprompt adherence win rate: 92%Improved
use SAEdit instead of Flux Kontext (CFG) for continuous edit controlFlux · User studyoverall win rate: 70%Improved
use SAEdit instead of ConceptSlider (Flux)Flux · User studyoverall win rate: 71%Improved
add aggregation of N prompt pairs to single-pair direction (ablation)SAEdit · quantitative ablation benchmarkVQA scoreImproved
add exponential injection schedule (ablation)SAEdit · quantitative ablation benchmarkLPIPSImproved

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