AI Paper Atlas

Research map / Image generation / Editing and style transfer

X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning

Jian Ma, Xujie Zhu, Zihao Pan, Qirong Peng, Xu Guo, Chen Chen, Haonan Lu

AAAI 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 12 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
add task embedding to MoE-LoRA gating (ablation)MoE-LoRA (6 experts, rank 128) · GEdit-Bench++ CNImgEdit-Judge overall: 7.943 -> 8.087Improved
use MoE-LoRA instead of single LoRA (ablation)FLUX.1 editing LoRA · GEdit-Bench++ CNImgEdit-Judge overall: 7.834 -> 7.943Improved
more experts with proportionally lower rank (6x128 -> 12x64) (ablation)MoE-LoRA w/TA · GEdit-Bench++ ENImgEdit-Judge overall: 7.985 -> 8.084Improved
add task-aware contrastive regularization (cosine, 4th layer) (ablation)MoE-LoRA w/TA 12x64 · GEdit-Bench++ CNImgEdit-Judge overall: 8.161 -> 8.253Improved
squared L2 distance instead of cosine similarity in contrastive loss (ablation)X2Edit (4th layer) · GEdit-Bench++ CNImgEdit-Judge overall: 8.253 -> 8.289Improved
apply contrastive loss on all 19 layers instead of only the 4th (ablation)X2Edit · GEdit-Bench++ ENImgEdit-Judge overall: 8.120 -> 8.334Improved
apply contrastive loss on all layers instead of 4th (ablation)X2Edit · GEdit-Bench++ CNImgEdit-Judge overall: 8.289 -> 8.313Improved
plug X2Edit into FLUX.1 community variants (Schnell, Krea-dev, etc.)X2Edit · GEdit-Bench++ (Table 4)ImgEdit-Judge overall: 8.313 vs 8.254 to 8.458 (CN)No clear effect
X2Edit vs full-parameter fine-tuned Bagel and KontextX2Edit (0.9B) · KontextBenchVIEScore (Qwen2.5-VL-72B): 7.606 vs Bagel 7.929Hurt

Later papers that compared with this method

1 later accepted paper reports X2Edit as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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