GDMD replaces raw-sample rewards with distillation-gradient rewards in RL-guided diffusion distillation, yielding 4-step models that surpass their multi-step teachers on GenEval and human preference metrics.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DE-CM reaches state-of-the-art one-step FID of 1.70 on ImageNet 256x256 by decomposing PF-ODE trajectories into three critical sub-trajectories and using flow matching plus N2N mapping for stability.
citing papers explorer
-
Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
GDMD replaces raw-sample rewards with distillation-gradient rewards in RL-guided diffusion distillation, yielding 4-step models that surpass their multi-step teachers on GenEval and human preference metrics.
-
Dual-End Consistency Model
DE-CM reaches state-of-the-art one-step FID of 1.70 on ImageNet 256x256 by decomposing PF-ODE trajectories into three critical sub-trajectories and using flow matching plus N2N mapping for stability.