Madeline Liao

Hi! I'm currently a Machine Learning Engineer at Gridmatic, where I work on generative modeling for renewable energy forecasting.

Previously, I received my M.S. and B.S. with departmental honors in Computer Science (AI + theory) and a minor in Film & Media Studies from Stanford, where I worked with Percy Liang, Dorsa Sadigh, and Stefano Ermon.

In my free time, I love fencing and was co-captain of the Stanford varsity fencing team for three years. My other hobbies include hiking/backpacking, cooking, and overthinking trivial decisions like what I was going to write here.


Eliciting Compatible Demonstrations for Multi-Human Imitation Learning. [paper]
Kanishk Gandhi, Siddharth Karamcheti, Madeline Liao, Dorsa Sadigh. Conference on Robot Learning (CoRL), 2022.

Featurized Density Ratio Estimation. [paper]
Kristy Choi*, Madeline Liao*, Stefano Ermon. Uncertainty in Artificial Intelligence (UAI), 2021.