← Search

Wenqi Mu

2 accepted papers

2026

Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models

ICLR 2026poster

Recent advances in diffusion models for visual generation have sparked interest in human preference alignment, similar to developments in Large Language Models. While reward model (RM) based approaches enable trajectory-aware optimization by evaluating intermediate timesteps, they face two critical…

Cited by 0SourceScholar