AI RESEARCH
Midpoint Generative Models
arXiv CS.LG
•
We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincide, the corresponding drift field vanishes at the midpoint time, $t=1/2$. We extend this discrepancy beyond the midpoint by introducing randoml