Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs
Hyunsoo Song, Seungwhan Kim, Seungkyu Lee
Variational autoencoders (VAEs), one of the most widely used generative models, are known to suffer from posterior collapse, a phenomenon that reduces the diversity of generated sa…
cs.CV2025
Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
Samra Irshad, Seungkyu Lee, Nassir Navab +2
The presence of adversarial examples in the physical world poses significant challenges to the deployment of Deep Neural Networks in safety-critical applications such as autonomous…