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.
Step-level reward for free in rl-based t2i diffusion model fine-tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.
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.
-
VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.