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.
SePPO: Semi-policy preference optimization for diffusion alignment
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
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.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
-
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.
-
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.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.