At Google DeepMind, my research attempts to answer:
How can intelligent agents reuse and adapt their knowledge to quickly solve new tasks?
This question drives my work on multi-task and meta-learning, with a special focus on discovering inductive biases for transfer and adaptation.
I completed my PhD at USC where I was advised by Fei Sha and collaborated closely with Maja J. Matarić. Before that, I had the chance to work on distributed optimization with Chunming Wang and build a robot cat with Francisco Valero-Cuevas, while earning degrees in computer science and mathematics.
I was and remain an avid skier.