AI Paper Atlas

Research map / Image generation / Editing and style transfer

Semantic Editing with Coupled Stochastic Differential Equations

Jianxin Zhang, Clayton Scott

ICML 2026 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing

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
couple source and target reverse SDEs with the same backward Brownian path (sync-SDE) instead of baseline editing methodssync-SDE · Flux.1[dev], 306 editing triplets from 91 imagesCLIP score vs L1/LPIPS distanceImproved
start coupling at larger t0 (ablation)sync-SDE · qualitative, t0 studyedit strength vs source preservationMixed
use detailed source and target prompts of similar granularity (ablation)sync-SDE · qualitative prompt studyedit faithfulnessImproved
use misspecified or minimal source prompts (ablation)sync-SDE · qualitative prompt studyidentity preservationHurt
remove Brownian term from target update and resample reference (resampling-ODE) (ablation)sync-SDE variant · LPIPS vs CLIPtrade-offMixed
reduce integration steps from 28 to 14 or 7 (ablation)sync-SDE · qualitative discretization studyedit qualityNo clear effect

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