3 papers
cs.LG2025
ViTCAE: ViT-based Class-conditioned Autoencoder
Vahid Jebraeeli, Hamid Krim, Derya Cansever
Vision Transformer (ViT) based autoencoders often underutilize the global Class token and employ static attention mechanisms, limiting both generative control and optimization effi…
cs.LG2025
Boosting Adversarial Robustness and Generalization with Structural Prior
Zhichao Hou, Weizhi Gao, Hamid Krim +1
This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically,…
cs.LG2024
Robustness Reprogramming for Representation Learning
Zhichao Hou, MohamadAli Torkamani, Hamid Krim +1
This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustnes…