smitha milli

humans + machines = ?

Hi, I’m Smitha! I’m a 4th-year Electrical Engineering & Computer Science major at UC Berkeley. My current research interests lie in artificial intelligence and cognitive science. I am a part of the Center for Human-Compatible AI and Berkeley Artificial Intelligence Research Lab. I’m lucky to have had the opportunity to work with Tom Griffiths, Stuart Russell, David Bamman, and Marti Hearst. I recently received the CRA Outstanding Undergraduate Researcher Award.

I spend a lot of time thinking about meta topics and iterating on my own styles of thinking and productivity. Here is some research advice I’ve found interesting. Outside of research I enjoy reading both nonfiction and fiction. I have a soft spot for philosophy and my favorite fiction author is Haruki Murakami.

If you want to talk, feel free to shoot me an email at smitha dot milli at gmail dot com.

“The unexamined life is not worth living.”-Socrates
“We are what we repeatedly do. Excellence, then, is not an act but a habit.”-Aristotle



When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?
Smitha Milli, Falk Lieder, and Thomas L. Griffiths. AAAI 2017.

Beyond Canonical Texts: A Computational Analysis of Fanfiction
Smitha Milli and David Bamman. EMNLP 2016.
[pdf] [data] [press: berkeley, OTW]


Should Robots Have Off-Switches?
Smitha Milli, Dylan Hadfield-Menell, and Stuart Russell. Reliability in Machine Learning Workshop, NIPS 2016.

Augmenting Course Material with Open Access Textbooks
Smitha Milli and Marti A. Hearst. Building Educational Applications Workshop, NAACL 2016.