AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Distribution Matching Distillation Meets Reinforcement Learning

Dengyang Jiang, Dongyang Liu, Zanyi Wang, Qilong Wu, Liuzhuozheng Li, Heng-Zhuang Li, Xin Jin, Zhen Li, Changsheng Lu, Mengmeng Wang, Steven Hoi, Peng Gao and 1 more

ECCV 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models · 50 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 joint RL stage 2 to stage 1 init (ablation)DMDR · DPG-Bench (SD3-M)overall: 82.4371 -> 85.30Improved
use ReFL instead of DPO in stage 2 (ablation)DMDR · DPG-Bench (SD3-M)overall: 85.00 -> 85.30Improved
use ReFL instead of GRPO in stage 2 (ablation)DMDR · DPG-Bench (SD3-M)overall: 85.08 -> 85.30Improved
raise lambda_rl from 0.5 to 2.0 (ablation)DMDR · DPG-Bench (SD3-M)overall: 85.30 -> 82.48Hurt
lower lambda_rl from 0.5 to 0.1 (ablation)DMDR · HP Score (SD3-M)HP Score: 32.1145 -> 31.6565Hurt
raise lambda_rl from 0.5 to 1.0 (ablation)DMDR · HP Score (SD3-M)HP Score: 32.1145 -> 32.8982Improved
combine CLIP and HPS rewards instead of CLIP only (ablation)DMDR · HP Score (SD3-M)HP Score: 28.0507 -> 32.1145Improved
combine CLIP and HPS rewards instead of HPS only (ablation)DMDR · DPG-Bench (SD3-M)overall: 85.04 -> 85.30Improved
increase lambda_rl 0.1 to 1 (diversity cost) (ablation)DMDR · LPIPS diversity (SD3-M)LPIPS: 0.5602 -> 0.5266Hurt
add RL reward to distillation (no CFG) (ablation)one-step SiT distillation · ImageNet 256FID: 2.13 -> 6.95Hurt
add CFG 4 to distillation (no RL) (ablation)one-step SiT distillation · ImageNet 256FID: 2.13 -> 15.70Hurt
distill and RL jointly (DMDR) instead of distill then RL (DMD2-PSO)SDXL-Base 4-step · ShareGPT-4o-Image promptsHP Score: 29.8732 -> 32.9832Improved

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