AI Paper Atlas

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

Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning

Chubin Chen, Sujie Hu, Jiashu Zhu, Meiqi Wu, Jintao Chen, Yanxun Li, Nisha Huang, Chengyu Fang, Jiahong Wu, Xiangxiang Chu, Xiu Li

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion · 20 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 learned b_v correction to reward (ablation)DanceGRPO · DivGenBench (reward HPS-v2.1)IDS (lower better): 0.348 -> 0.278Improved
add learned b_v correction to reward (ablation)DanceGRPO · DivGenBench (reward HPS-v2.1)ASC: 0.130 -> 0.205Improved
add learned b_v correction to reward (ablation)DanceGRPO · DivGenBench (reward HPS-v2.1)SDI: 0.488 -> 0.604Improved
add learned b_v correction to reward (ablation)DanceGRPO · DivGenBench (reward HPS-v2.1)PVS: 0.259 -> 0.437Improved
add learned b_v correction to reward (ablation)DanceGRPO · HPDv2 (reward HPS-v2.1)Aesthetic: 6.068 -> 6.353Improved
add learned b_v correction to reward (ablation)DanceGRPO · HPDv2 (reward HPS-v2.1)CLIP: 0.293 -> 0.311Improved
add learned b_v correction to reward (ablation)DanceGRPO · HPDv2 (reward HPS-v2.1)GenEval: 0.522 -> 0.641Improved
add learned b_v correction to reward (ablation)DanceGRPO · HPDv2 (reward HPS-v2.1)HPS-v2.1: 0.361 -> 0.319Hurt
use learned continuous vector instead of hand-picked discrete words (ablation)D2-Align · HPDv2multiple metricsImproved
use learned b_v instead of uncorrected reward (ablation)D2-Align · HPDv2multiple metricsImproved
train b_v for about 2000 steps or more (ablation)D2-Align · HPDv2performanceImproved
set guidance scale to 1.5 (ablation)D2-Align · HPDv2HPS-v2.1 and PickScoreImproved

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