AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Aligning Few-Step Diffusion Models With Dense Reward Difference Learning

Ziyi Zhang, Shen Li, Sen Zhang, Deheng Ye, Yong Luo, Miaojing Shi, Dongjing Shan, Bo Du, Dacheng Tao

TPAMI 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models

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
use SDPO instead of DDPOSD-Turbo · Unseen prompts, 1-stepAesthetic Score: 6.644 -> 7.062Improved
use SDPO instead of DDPOSD-Turbo · Unseen prompts, 8-stepAesthetic Score: 6.720 -> 8.163Improved
use SDPO instead of DDPOSD-Turbo · Unseen prompts, 1-stepImageReward: 1.380 -> 1.719Improved
use SDPO instead of DDPOSD-Turbo · Unseen prompts, 8-stepPickScore: 23.29 -> 24.05Improved
use SDPO instead of DDPOSD-Turbo · Unseen prompts, 1-stepPickScore: 22.65 -> 23.02Improved
RL finetuning with DDPO on few-step modelSD-Turbo · Unseen prompts, 1-stepPickScore: 22.69 -> 22.65No clear effect
adaptive anchor step (vs fixed anchor) for dense reward prediction (ablation)SDPO · Reward prediction accuracy (Aesthetic Score)cosine similarity: 0.3654 -> 0.4463Improved
adaptive anchor step (vs random anchor) (ablation)SDPO · Reward prediction accuracy (Aesthetic Score)cosine similarity: 0.3561 -> 0.4463Improved
add third query at anchor step (vs 2 queries & similarity) (ablation)SDPO · Reward prediction accuracy (PickScore)cosine similarity: 0.4117 -> 0.4853Improved
latent similarity interpolation (vs simple interpolation, 2 queries) (ablation)SDPO · Reward prediction accuracy (Aesthetic Score)cosine similarity: 0.3368 -> 0.3861Improved
dense reward prediction vs single final-step query copied (ablation)SDPO · Reward prediction accuracy (Aesthetic Score)cosine similarity: 2x10^-8 -> 0.4463Improved
sparse 3-query dense reward prediction vs full-step queries (ablation)SDPO · Aesthetic Score, 2-steprewardImproved

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