AI Paper Atlas

Research map / Image generation / Editing and style transfer

AesFormer: Transform Everyday Photos into Beautiful Memories

Tianxiang Du, Hulingxiao He, Yuxin Peng

ICML 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 0 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 SFT-trained AesThinker action planner (S1a) (ablation)Qwen-Image-Edit-2511 · AesRecon, win rate vs poor (GPT-4o)win rate: 16.50 -> 61.04Improved
add GRPO-A stage (S1b) to SFT thinker and editor (ablation)AesFormer · AesRecon, win rate vs poor (GPT-4o)win rate: 61.13 -> 65.33Improved
add GRPO-A stage (ablation)AesFormer · AesRecon, win rate vs good (GPT-4o)win rate: 24.14 -> 26.25Improved
add Stage 2 AesEditor fine-tuning to SFT thinker (ablation)AesThinker S1a · AesRecon, win rate vs poor (GPT-4o)win rate: 61.04 -> 61.13No clear effect
use ordered seven-dimension actions instead of shuffled order (ablation)AesThinker S1a · AesRecon, win rate vs poor (GPT-4o)win rate: 58.69 -> 61.04Improved
use ordered seven-dimension actions instead of shuffled order (ablation)AesThinker S1a · AesRecon, win rate vs good (GPT-4o)win rate: 18.60 -> 24.58Improved
use ordered seven-dimension actions instead of shuffled order (ablation)AesThinker S1a · AesRecon, ArtiMuseArtiMuse score: 46.16 -> 47.70Improved
add off-the-shelf GPT-4o thinkerQwen-Image-Edit-2511 · AesRecon, win rate vs poor (GPT-4o)win rate: 16.50 -> 14.62Hurt
add off-the-shelf Qwen3 thinkerBagel · AesRecon, win rate vs poor (GPT-4o)win rate: 12.40 -> 3.43Hurt
add off-the-shelf GPT-4o thinkerStep1X-Edit-v1.1 · AesRecon, win rate vs poor (GPT-4o)win rate: 15.28 -> 6.20Hurt
add off-the-shelf GPT-4o thinkerFLUX.1 Kontext [Dev] · AesRecon, win rate vs poor (human)win rate: 5.88 -> 13.72Improved
add off-the-shelf GPT-4o thinkerFLUX.1 Kontext [Dev] · AesRecon, win rate vs poor (GPT-4o)win rate: 12.96 -> 12.51No 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