AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

Renye Yan, Jikang Cheng, Shikun Sun, Yi Sun, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Junliang Xing, Yimao Cai

CVPR 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models · 9 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 adaptive RL scope selection (AdaScope) plug-inDDPO · Simple animals promptstime per batch (min): 4.55 -> 2.65Improved
add adaptive RL scope selection (AdaScope) plug-inDPOK · Simple animals promptstime per batch (min): 5.63 -> 3.71Improved
add adaptive RL scope selection (AdaScope) plug-inD3PO · Simple animals promptstime per batch (min): 5.06 -> 3.19Improved
add adaptive RL scope selection (AdaScope) plug-inTDPO · Simple animals promptstime per batch (min): 6.37 -> 4.17Improved
add AdaScope plug-inDDPO · Simple animals prompts (PickScore reaches 22)LPIPS: 0.624 -> 0.679Improved
add AdaScope plug-inTDPO · Simple animals prompts (PickScore reaches 22)ImageReward: 0.16 -> 0.67Improved
add AdaScope plug-inDPOK · Simple animals prompts (Aesthetic reaches 7)LPIPS: 0.623 -> 0.674Improved
add AdaScope plug-inDPOK · Simple animals prompts (PickScore reaches 22)AES: 6.14 -> 6.09Hurt
add AdaScope plug-inD3PO · Simple animals prompts (Aesthetic reaches 7)ImageReward: 0.89 -> 0.76Hurt
use prompt-adaptive scope instead of fixed start/end scope ranges (ablation)AdaScope · Simple animals / SDv15reward optimizationImproved
use AdaScope on the larger SDXL backboneAdaScope · SDXLreward optimizationNo clear effect

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