AI Paper Atlas

Research map / Image generation / Editing and style transfer

Learning an Image Editing Model without Image Editing Pairs

Nupur Kumari, Sheng-Yu Wang, Nanxuan Zhao, Yotam Nitzan, Yuheng Li, Krishna Kumar Singh, Richard Zhang, Eli Shechtman, Jun-Yan Zhu, Xun Huang

ICLR 2026 · Image generation › Editing and style transfer · approach: Instruction-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
add VLM-based editing loss to DMD (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 4.93 -> 6.10Improved
add DMD loss to VLM loss (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 1.93 -> 6.10Improved
add identity-preservation question to VLM loss (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 5.76 -> 6.10Improved
use binary Yes/No cross-entropy instead of full-vocabulary CE (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 5.89 -> 6.10Improved
add LPIPS loss for input-edit alignment (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 6.10 -> 4.52Hurt
add cycle loss for input-edit alignment (ablation)NP-Edit · GEdit-Bench (4-step)VIEScore Overall (x10): 6.10 -> 5.21Hurt
larger training dataset (number of reference images) (ablation)NP-Edit · GEdit-Bench (4-step)VIEScoreImproved
larger VLM backbone as reward (ablation)NP-Edit · GEdit-Bench (4-step)VIEScoreImproved
use VLM-gradient training instead of SFT+Flow-GRPONP-Edit · GEdit-Bench (4-step)VIEScoreImproved
NP-Edit vs few-step baselinesNP-Edit 2B · GEdit-Bench (4-step)VIEScore Overall (x10): 6.10 vs 6.06 (Qwen-Image-Edit 20B)Improved

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