About

Hi, I'm Dylan! I'm a fourth year PhD student in the Machine Learning Department at CMU, where I am fortunate to be advised by Zico Kolter. My work is supported by a NSF Graduate Research Fellowship.

I'm broadly interested in making large frontier models behave in safe, controllable, and predictible ways. Recently, this has invovled creating safe large language models and curating better training data. In the past, this has involved studying the behavior and generalization of deep learning models and their interactions with weak supervision/domain knowledge.

Before, I studied math and computer science at Brown University, where I was advised by Stephen Bach. In the past, I served as a student researcher at Google Research, and a research intern at Amazon AWS, the Bosch Center for AI, and NASA JPL. If you are interested in my work, feel free to get in touch. I am always looking to chat about research and form new collaborations!

News

• [Feb 2025]: Excited to share my summer internship work at Google on studying how to measure similarity for LLM pretraining data curation!
• [Jan 2025]: Just released new work on predicting the performance of LLMs in a black-box fashion!
• [May 2024]: Spending the summer at Google Research in NYC, where I'll be working on data curation for LLM pretraining.
• [Apr 2024]: I'll be traveling to AISTATS to present "Auditing Fairness under Unobserved Confounding" and to ICLR to present work on providing generalization bounds for prompt engineering VLMs.
• [Sep 2023]: Our work on analyzing the benefits of explanations/prior knowledge from a learning theoretic perspective is accepted to NeurIPS 2023!
• [Jul 2023]: I'm giving a talk on BNNs with domain knowledge at the KLR workshop @ ICML 2023!
• [Sep 2022]: I'm visiting Germany for the 9th Heidleberg Laureate Forum, as a PhD scholar!
• [May 2022]: Spending the summer as an AWS applied scientist intern in Santa Clara!
• [Aug 2021]: Started my PhD in the Machine Learning Department @ CMU!