5 papers
Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers
Zander W. Blasingame, Chen Liu
Deep generative models based on neural differential equations have become state-of-the-art for many generation tasks. These models rely on ODE/SDE solvers that integrate from a pri…
Greed is Good: A Unifying Perspective on Guided Generation
Zander W. Blasingame, Chen Liu
Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative process of flow/diffusion models. Gene…
Strong Stochastic Flow Maps
Sam McCallum, Zander W. Blasingame, Timothy Herschell +3
Flow and diffusion models generate high-quality samples in many modalities; however, many network evaluations are required during inference due to numerical integration of an under…
Elytra: A Flexible Framework for Securing Large Vision Systems
Richard E. Neddo, Emmanuel Atindama, Zander W. Blasingame +1
Adversarial attacks have emerged as a critical threat to autonomous driving systems. These attacks exploit the underlying neural network, allowing small, almost invisible, perturba…
AdjointDEIS: Efficient Gradients for Diffusion Models
Zander W. Blasingame, Chen Liu
The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex proble…