Biography

Taylor Killian is an Assistant Professor of Computer Science at Brigham Young University, where his research focuses on sequential decision-making under uncertainty — offline and risk-sensitive reinforcement learning, representation learning, and causal inference — with applications in healthcare, scientific discovery, and the post-training of large language models. His published work appears at NeurIPS, ICML, and ICLR, and spans safety-critical clinical decision support through to reasoning within modern language models. A list of all prior work can be found at: https://scholar.google.com/citations?user=xA3RcaUAAAAJ

Taylor received a BS in Mathematics from Brigham Young University in 2013, an M.Eng. in Computational Science and Engineering from Harvard University in 2017, and a PhD in Computer Science from the University of Toronto in 2024, where he was additionally affiliated with the Vector Institute and the Institute of Medical Engineering and Science at MIT. He also works as a Principal Scientist at Lila Sciences.

He is building a new reinforcement learning research group at BYU and welcomes inquiries from interested students. Learn more at twkillian.github.io.