Kevin T. Carlberg

AI Research Science Manager

Facebook Reality Labs

University of Washington


Kevin Carlberg is an AI Research Science Manager at Meta Reality Labs Research and an Affiliate Associate Professor of Applied Mathematics and Mechanical Engineering at the University of Washington . He leads a multidisciplinary research team focused on enabling the future of interaction in augmented and virtual reality by developing AI breakthroughs across the domains of embodied AI, multimodal machine learning, conversational AI, and AI-accelerated computational physics. His individual research combines concepts from machine learning, computational physics, and high-performance computing to drastically reduce the cost of simulating nonlinear dynamical systems at extreme scale.

Previously, Kevin was a Distinguished Member of Technical Staff at Sandia National Laboratories in Livermore, California, where he led a research group of PhD students, postdocs, and technical staff in applying these techniques to a range of national-security applications in mechanical and aerospace engineering.

His recent plenary talk at the ICERM Workshop on Scientific Machine Learning summarizes his work.


  • Machine learning
  • Computational physics
  • Model reduction
  • Deep learning
  • Dimensionality reduction
  • Numerical optimization
  • Uncertainty quantification
  • High-performance computing


  • PhD in Aeronautics and Astronautics, 2011

    Stanford University

  • MS in Aeronautics and Astronautics, 2006

    Stanford University

  • BS in Mechanical Engineering, 2005

    Washington University in St. Louis


New adventure

Moving to Facebook Research

Data-driven time-parallelism accepted into SISC

Data-driven coarse propagation to accelerate convergence

Paper on machine learning error models published in CMAME

Using regression to model approximate-solution errors

Joining SISC editorial board

Becoming Associate Editor

Preprint on model reduction on nonlinear manifolds using deep convolutional autoencoders now available

Using deep learning to overcome Komolgorov-width limitation

Recent Publications

Online adaptive basis refinement and compression for reduced-order models via vector-space sieving

In many applications, projection-based reduced-order models (ROMs) have demonstrated the ability to provide rapid approximate solutions …

Time-series machine-learning error models for approximate solutions to parameterized dynamical systems

This work proposes a machine-learning framework for modeling the error incurred by approximate solutions to parameterized dynamical …

Model reduction for hypersonic aerodynamics via conservative LSPG projection and hyper-reduction

High-speed aerospace engineering applications rely heavily on computational fluid dynamics (CFD) models for design and analysis due to …

Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders

Nearly all model-reduction techniques project the governing equations onto a linear subspace of the original state space. Such …

Windowed least-squares model reduction for dynamical systems

This work proposes a windowed least-squares (WLS) approach for model-reduction of dynamical systems. The proposed approach sequentially …



Teaching assistant