Preprint
Aug 2026
SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching
Structural Parameter-free Affinity Regularization (SPARE), a regularizer that matches the pairwise affinities of intermediate tokens to those of the clean latents across images, is proposed, a regularizer that attains the lowest FID among parameter-free regularizers in every tested setting.
Zong-Wei Hong, Jinglun Li, Shen Zhang et al.
· 0 citations