AI Paper Atlas

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

Unified Customized Generation by Disentangled Reward Modeling

Shaojin Wu, Mengqi Huang, Yufeng Cheng, Wenxu Wu, Jiahe Tian, Yiming Luo, Fei Ding, Qian He

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization

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 auxiliary style reward (ablation)USO · USO-Bench style-subject-drivenCSD: 0.413 -> 0.492Improved
add auxiliary style reward (ablation)USO · USO-Bench subject-drivenCLIP-I: 0.619 -> 0.647Improved
add auxiliary style reward (ablation)USO · USO-Bench style-drivenCSD: 0.491 -> 0.556Improved
use disentangled encoders (SigLIP for style, VAE for content) instead of one shared VAE (ablation)USO · USO-Bench style-subject-drivenCSD: 0.382 -> 0.492Improved
use disentangled encoders instead of one shared VAE (ablation)USO · USO-Bench subject-drivenCLIP-I: 0.594 -> 0.647Improved
train OmniStyle on the layout-shifted USO dataset (ablation)OmniStyle · USO-Bench style-subject-drivenCLIP-T: 0.229 -> 0.277Improved
train UNO on the USO dataset (ablation)UNO · USO-Bench subject-drivenCLIP-I / CLIP-T: CLIP-I 0.605 -> 0.596; CLIP-T 0.264 -> 0.278Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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