
ellisbrown at cmu dot edu
I am a Master’s student in the Computer Science Department at CMU and a graduate student researcher in the Robotics Institute affiliated with CMU Vision. I am advised by Deepak Pathak and Alyosha Efros.
Previously I was a founding engineer at BlackRock AI Labs, where I was fortunate to work with Mykel Kochenderfer, Stephen Boyd, and Trevor Hastie on projects in machine learning, optimization, and big data applied to finance. While working in Palo Alto and NYC, I was a non-degree computer science graduate student at Stanford and Columbia. Before that, I studied computer science and mathematics at Vanderbilt and worked on computational cognitive science and artificial intelligence with Maithilee Kunda.
I am a proud member of the Osage Nation and have recently enjoyed engaging with the Native research community at AISES.
If you haven’t made time for a regular checkin with a doctor recently, please do! Even if you feel perfectly healthy.
news
May., 2023 | Defended my Master’s thesis and graduated from CMU! Excited to start a CS PhD at NYU advised by Saining Xie this fall 🎉 |
---|---|
Apr., 2023 | Our paper Internet Explorer was accepted to ICML 2023!! See you in Hawaii 🌺🏝😎 |
Jan., 2022 | Joined Deepak Pathak’s group in CMU’s Robotics Institute, and will focus on self-supervised learning and curiosity-driven exploration in computer vision. |
Aug., 2021 | Awarded the Intel Growing The Legacy Scholarship and accepted into the Lighting the Pathway to Faculty Careers program through AISES. Accepted into Google Research’s Computer Science Mentorship Program. |
Jul., 2021 | Left BlackRock AI Labs to pursue a Master’s degree in Computer Science at CMU. Bittersweet! |
selected research (more)
I’m interested in self-supervised learning, representation learning, curiosity-based exploration, and leveraging internet-scale models and data. I am keen to draw inspiration from intelligence in humans and nature—especially as a goal-post rather than a blueprint. My long-term goal is to develop intelligent agents that can generalize and continually adapt as robustly and efficiently as humans do, allowing them to be safely deployed in the real world.