Posts

  • Machine Learning Kerr Combs

    We will be presenting some work on the inverse design of Kerr combs at the Machine Learning and the Physical Sciences Workshop @ NeurIPS. We train a generative neural network on Lugiato-Lefever equation simulations using variational autoencoders and flow-matching models.

  • Topology and Edge States

    We recently published a paper in Physical Review Letters on a new topological invariant for edge states in simple, one-dimensional models. The arXiv version is also available here.