DRM turns a pre-trained diffusion model into a step-wise reward model and uses it for dense RL training (Step-wise GRPO) and guided sampling to improve final image quality.
Diffusionmodelasanoise-aware latent reward model for step-level preference optimization
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
fields
cs.CV 9verdicts
UNVERDICTED 9representative citing papers
PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
A feature supervision approach using SigLIP 2 extracts multi-granularity vision-aligned text representations to supervise MM-DiT image branches, pushing the Pareto frontier for portrait generation across alignment, realism, and aesthetics.
Poly-DPO improves robustness to noisy preference data in visual models, and the new ViPO dataset enables superior performance, with the method reducing to standard DPO on high-quality data.
Semi-DPO applies semi-supervised learning to noisy preference data in diffusion DPO by training first on consensus pairs then iteratively pseudo-labeling conflicts, yielding state-of-the-art alignment with complex human preferences.
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.
citing papers explorer
-
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.