Machine learning & interpretability. GitHub
A POMDP-based calculus tutor that plans over student misunderstanding, not just questions.
Tracking the conditioning of diagonal state-space model modes through quantization-aware training.
On effective theories, interpretability, and what success means for ML models.
Measuring the mean lifetime of cosmic-ray muons via a joint Poisson maximum-likelihood fit, and extracting the Fermi coupling constant.
Young's double-slit in the single-photon regime: Fraunhofer vs. path-integral models of diffraction.
Optical pumping experiment.