AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Scaling Multi-Identity Consistency for Image Customization via Multi-to-Multi Matching Paradigm

Yufeng Cheng, Wenxu Wu, Shaojin Wu, Mengqi Huang, Fei Ding, Qian He

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis

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 ReReFL with SIR reward on top of plain SFT (ablation)UNO · XVerseBench Multi-SubjectID-Sim: 33.94 -> 65.16Improved
plain SFT on the multi-identity data (ablation)UNO · XVerseBench Multi-SubjectID-Sim: 31.82 -> 33.94No clear effect
use MIMR instead of SIR reward (ablation)UMO on UNO · XVerseBench Multi-SubjectID-Conf: 65.28 -> 78.06Improved
use MIMR instead of SIR reward (ablation)UMO on UNO · XVerseBench Multi-SubjectID-Sim: 65.16 -> 69.09Improved
apply UMO trainingUNO · XVerseBench Single-SubjectID-Sim: 47.91 -> 80.89Improved
apply UMO trainingOmniGen2 · XVerseBench Single-SubjectID-Sim: 62.41 -> 91.57Improved
apply UMO trainingOmniGen2 · XVerseBench Multi-SubjectID-Conf: 62.02 -> 77.74Improved
apply UMO trainingOmniGen2 · OmniContextOverall: 7.18 -> 7.16No clear effect
apply UMO trainingUNO · XVerseBench Single-SubjectIP-Sim: 80.40 -> 77.09Hurt
apply UMO trainingUNO · OmniContextID-Conf: 4.91 -> 6.60Improved

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