Research Agenda and Bio:
I lead the
Computer
Assisted Programming Group
. The focus of my research is program synthesis, an exciting
research area that lies at the intersection of Programming Systems and Artificial Intelligence.
On the one hand, program synthesis is about the use of automated reasoning and learning to help
bring more automation to the programming process. On the other hand, we believe code provides
a uniquely versatile modeling mechanism, so program synthesis can play a powerful role in helping
to build learning systems that are more predictable and robust. Over the past five years,
my group has also been working on developing neurosymbolic programming, a new class of learning
techniques that incorporate some of the benefits of
traditional programming languages, such as modularity, compositionality, and predictability.
I have BS degrees in Computer Science and Mathematics from Texas A&M Univerity and
got my PhD in 2008 from the University of California, Berkeley, where I was advised by
Rastislav Bodik.
I have been a faculty member at MIT since 2008 and have been helping to lead the
Computer Science and Artificial Intelligence Laboratory (CSAIL) as associate director since 2020.
Prospective Students:
If you are a current MIT undergraduate and are interested in doing a UROP in my group,
please send a brief description of your background to the e-mail address cap-urops[at]csail.mit.edu.
Please include a brief description of your background and the kind of project you are interested in.
I generally don't work with undergraduates who are not currently MIT students unless they come
through a formal MIT program such as the MIT Summer Research Program (MSRP).
Students interested in joining the group as PhD students should apply to the
EECS PhD program
at MIT. I can only consider students through the formal application process, so please be sure to apply!
The application deadline is usually December 1st. In your application, you can express your
interest in joining my group. Please be aware that I am usually unable to respond to
individual inquiries about the application process or about joining my group, but you can
direct questions about graduate admissions to grad-ap@eecs.mit.edu.
Sketch
Version 1.7.6 (Released Feb, 2020) :
I am no longer actively maintaining Sketch, but you it is still quite usable.
Sketch is in github and is split between two repositories:
the sketch-backend and the sketch-frontend.
You can download an
easy-to-install (relatively speaking)
source distribution from here: sketch-1.7.6.tar.gz
Working version of Sketch Manual
Teaching:
Over the last few years, I have helped with the development of a few courses:
-
Program Synthesis: Everything you wanted to know about the state of the
art in program synthesis, especially the techniques developed by the
programming languages and formal methods communities.
Here are some lecture notes I put together while on sabbatical in Mexico City in
2018.
-
6.820--Foundations of Program Analysis: This is an introduction to many of the
core techniques that one can use to reason about programs, including
different forms of semantics, type systems, program logics, abstract interpretation
and model checking. And you also learn Haskell along the way!
The course is offered every 2 years. The class was last offered in
2021.
-
6.s081-- Dynamic Computer Language Engineering:
Michael Carbin
has been mostly leading this class, but I helped with the initial version
of it. In this class, students get to build a just-in-time compiler for
a non-trivial dynamic language completely from scratch.
See here for
a recent version of this class.
In recent years, I have also been involved in teaching
6.031 (Software Construction),
6.009 (Fundamentals of Programming) and
6.01 (Introduction to EECS via Robotics).
PlaySkript:
In my free time, I created PlaySkript, an online platform that I use for creating
presentations and visualizations. It's based on a JavaScript-like domain specific language for describing diagrams and animations,
and supports both direct manipulation and automated refactoring in order to help create complex presentations more easily.
Try it out!
Phd Thesis:
Program Synthesis by Sketching, U.C. Berkeley, December 2008, Advisor: Rastislav Bodik
Publications:
Contact:
MIT Computer Science
and Artificial Intelligence
Laboratory
The Stata Center, Building 32-G742
32 Vassar Street
Cambridge, MA 02139
Accessibility
