I am a machine learning research scientist at Isomorphic Labs, where I work on AI for drug discovery. More broadly, I am interested in generative modeling, particularly probabilistic generative models, with a special interest in diffusion and flow models and their variational interpretations. I am also interested in representation learning: what representations models learn, what structure they should capture, and how learning objectives and inductive biases shape them.
Before joining Isomorphic Labs, I was a postdoc at Helmholtz AI and the Technical University of Munich, and previously at KTH in Stockholm. Earlier, I was an ELLIS PhD student at DTU in Copenhagen, advised by Ole Winther and Thomas Bolander (my PhD thesis is available here). During my PhD, I was a research intern at the Max Planck Institute for Intelligent Systems with Bernhard Schölkopf and Stefan Bauer, Microsoft Research with Tom Cashman and Ben Lundell, and Amazon with Francesco Locatello and Peter Gehler.