56 citations · 74 across the 4 of their papers we have counts for
4 papers
KellyBench: A Benchmark for Long-Horizon Sequential Decision Making
Thomas Grady, Kip Parker, Iliyan Zarov +3
Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with op…
Learned multiphysics inversion with differentiable programming and machine learning
Mathias Louboutin, Ziyi Yin, Rafael Orozco +7
We present the Seismic Laboratory for Imaging and Modeling/Monitoring (SLIM) open-source software framework for computational geophysics and, more generally, inverse problems invol…
Model-Parallel Fourier Neural Operators as Learned Surrogates for Large-Scale Parametric PDEs
Thomas J. Grady, Rishi Khan, Mathias Louboutin +5
Fourier neural operators (FNOs) are a recently introduced neural network architecture for learning solution operators of partial differential equations (PDEs), which have been show…
A Linear Algebraic Approach to Model Parallelism in Deep Learning
Russell J. Hewett, Thomas J. Grady
Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitat…