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.
Diffusionmodelasanoise-aware latent reward model for step-level preference optimization
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
fields
cs.CV 8verdicts
UNVERDICTED 8representative citing papers
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.
-
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
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.
-
Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
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.
-
ViPO: Visual Preference Optimization at Scale
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.
-
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
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: Unleashing GRPO on Visual Generation
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.
-
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.