872 citations · 2.9k across the 35 of their papers we have counts for
3 papers · 1 filter
On Making -Invariant Networks Optimal
Tomas Karella, Emily Shinkle, Alice Elisabeth Anastasia Allen +3
Respecting a-priori known symmetries of underlying data is a key principle in designing efficient neural architectures. Convolutional neural networks are a canonical example, encod…
Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces
Javier E Santos, Zachary R. Fox, Nicholas Lubbers +1
Typical generative diffusion models rely on a Gaussian diffusion process for training the backward transformations, which can then be used to generate samples from Gaussian noise.…
Predictive Scale-Bridging Simulations through Active Learning
Satish Karra, Mohamed Mehana, Nicholas Lubbers +12
Throughout computational science, there is a growing need to utilize the continual improvements in raw computational horsepower to achieve greater physical fidelity through scale-b…