AI Paper Atlas

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

JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

Yunlong Lin, Linqing Wang, Kunjie Lin, Zixu Lin, Kaixiong Gong, Wenbo Li, Bin Lin, Zhenxi Li, Shiyi Zhang, Yuyang Peng, Wenxun Dai, Xinghao Ding and 2 more

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 29 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 the evaluator optimization loop (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 7.78 -> 8.54Improved
add selective loss masking (SLM) in the editor loop (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 7.40 -> 8.54Improved
add both evaluator loop and SLM (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 7.25 -> 8.54Improved
add the evaluator optimization loop (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)L1: 12.43 -> 8.25Improved
add SEPO RL stage after SFT (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 8.26 -> 8.54Improved
use intrinsic self-reward instead of Gemini-2.5-Pro external reward (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 8.14 -> 8.54Improved
use pairwise preference reward instead of absolute point score reward (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 8.43 -> 8.54Improved
use pairwise preference reward instead of absolute point score reward (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)L1: 8.78 -> 8.25Improved
add reflection fine-tuning (RFT) after SEPO (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)O: 8.54 -> 8.76Improved
add reflection fine-tuning (RFT) after SEPO (ablation)SEPO · ArtEdit-Bench-Lr (EN and CN, ablation)L1: 8.25 -> 7.72Improved
compare JarvisEvo with Nano-Banana (human preference)JarvisEvo · Human pairwise preference (200 samples)win rate: 49% vs 28%Improved
JarvisEvo vs Nano-Banana on pixel fidelityJarvisEvo · ArtEdit-Bench-Lr (English set)L1: 11.54 -> 7.82Improved

Later papers that compared with this method

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

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