AI Paper Atlas

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

Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models

Xiaole Xian, Xilin He, Wenting Chen, Wenshuang Liu, wenqi mu, Yancheng He, Liang Li, Yi Zhang, Xiangyu Yue

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion

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 score enhancement to SLRM (ablation)SLRM · Pick-a-Pic val/testaccuracy: 62.49 -> 67.52Improved
add task tokens to SLRM (ablation)SLRM · Pick-a-Pic val/testaccuracy: 65.33 -> 67.52Improved
use SLRM with score enhancement as TAPO reward model (ablation)TAPO · Pick-a-Pic v1 valGenEval: 54.83 -> 64.93Improved
use task tokens in reward model for TAPO (ablation)TAPO · Pick-a-Pic v1 valGenEval: 55.27 -> 64.93Improved
increase SDE sampling number n from 4 to 8 (ablation)TAPO · Pick-a-Pic v1 valGenEval: 56.20 -> 68.93Improved
increase SDE sampling number n from 8 to 16 (ablation)TAPO · Pick-a-Pic v1 valHPSv2.1: 32.01 -> 31.29; 4.52s/iter -> 6.08s/iterNo clear effect
increase SDE sampling number n from 2 to 8 (ablation)TAPO · Pick-a-Pic v1 valMPS: 2.27 -> 3.07Improved
diffusion-based SLRM instead of LRM-3.5SLRM · Pick-a-Pic val/test (t in [501,1000])accuracy: 59.56 -> 66.35Improved
use SLRM instead of VLM-based HPSv3 on clean imagesSLRM · Pick-a-Pic val/test (clean image)accuracy: 72.80 -> 67.08Hurt
set beta to 1000 instead of 20 (ablation)TAPO · Pick-a-Pic v1 valGenEval: 60.210 -> 68.830Improved
set beta to 1000 instead of 5000 (ablation)TAPO · Pick-a-Pic v1 valGenEval: 63.700 -> 68.830Improved
TAPO versus LPOTAPO · Pick-a-Pic v1 valHPSv3: 9.10 -> 9.89Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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