Preprint
Sep 2026
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
DM-Align is introduced, which derives a complementary gradient direction to guide the model toward human-preferred samples, and eliminates the need for multi-step reward evaluation and complex ODE-SDE conversions inherent in traditional RL.
Jiu-Zhou Lin, Jun-Long Wu, Feilong Zuo et al.
· 1 citation