I am an undergraduate at Columbia University. I work on machine learning research, with a focus on making ML systems reliable and aligned with human values.
Understanding the Success and Limitations of Feature Alignment (coming soon)
Collin Burns, Jacob Steinhardt
Measuring Massive Multitask Language Understanding
Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt
Aligning AI with Shared Human Values
Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, Jacob Steinhardt
Streaming Complexity of SVMs*
Alexandr Andoni, Collin Burns, Yi Li, Sepideh Mahabadi, David P. Woodruff
Interpreting Black Box Models via Hypothesis Testing
Collin Burns, Jesse Thomason, Wesley Tansey
ACM FODS 2020
Asterisk (*) denotes alphabetical order (equal contribution).
I used to be very involved in competitive Rubik’s Cube solving (“speedcubing”). In 2015 I broke the official world record for a single 3x3 solve with a time of 5.25 seconds. I’ve also had a national championship title, a continental record, and four national records.
I’m interested in effective altruism, which aims to use reason and evidence to help the world as much as possible (whether through donations or through direct work, both as individuals and as a society). I have lots of uncertainty about what this should entail in practice, but I believe the community has made some important steps in the right direction.