JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Sampling
JIVE is introduced, a training-free framework that enhances generative diversity by injecting velocity perturbations aligned with the leading right singular subspace of the generator's endpoint Jacobian, which provably maximizes endpoint diversity while preserving sample quality.
Guang-Xun Zhang, Brian Cai, Boxuan Zhang et al.
· 0 citations