Brian Cheung
I study at the intersection of Artificial Intelligence and Natural Intelligence. As we witness enormous progress in this space, what makes the two different? I believe most profound aspects of intelligence will be the things that still set us apart, not what makes us the same.
Currently at the Center for Brains, Minds and Machines (CBMM) at Massachusetts Institute of Technology (MIT). Interested in collaborations? Please reach out:
briancheung
Papers I'm thinking about lately
-
The Platonic Representation Hypothesis
Minyoung Huh*, Brian Cheung*, Tongzhou Wang*, Phillip Isola*
TLDR: As all models continue to improve, the representations they use are converging. -
System Identification of Neural Systems: If We Got It Right, Would We Know?
Yena Han, Tomaso Poggio, Brian Cheung, ICML 2023 [Paper]
TLDR: Even if we had a perfect model of the brain, we probably wouldn't know it. -
Superposition of many models into one
Brian Cheung, Alex Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen, Neurips 2019 [Paper]
TLDR: You can add a bunch of model parameters together and still get good performance. -
Emergence of foveal image sampling from learning to attend in visual scenes
Brian Cheung, Eric Weiss, Bruno Olshausen [Paper] [Blog]
TLDR: If you simulate the evolution of a retina with a goal to attend, a fovea emerges. - All of my papers