LipsFlower constrains flow matching to stabilize generative image restoration
LipHDiT uses spectral normalization, bounded modulation and finite-radius gain penalties, tested on blind face restoration.
Stories per day · 30 days
1 RSS
Relatedadversarial-robustness1control-systems1diffusion-transformer1flow-matching1image-restoration1model-predictive-control1neural-approximation1stability1
2 stories, newest first · one card per story
Stories tagged #lipschitz
Neural approximation can inherit robust MPC safety and stability guarantees
Design conditions treat network error as a bounded disturbance so feasibility and stability hold before deployment.