About Me
I'm currently working as a software engineer in the Debora Marks Lab at Harvard Medical School, applying machine
learning methods to problems in biological sequence modeling. Previously, I received my master's in computer science
from the University of Oxford, and before that studied computer science and political science at Brown University. I'm broadly interested in
developing methods for making the behavior of deep sequence models (like protein or natural large language models) more controllable and interpretable. Additionally,
I want to use these methods to make sequence models more safe, e.g. by reducing issues like bias and unfairness, and to extract information from their internal representations
that may be useful for human understanding.
Publications
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and DesignDaniel Ritter*, Pascal Notin*, Lood Van Niekerk*, Aaron W Kollasch*, Steffanie Paul, Han Spinner, Nathan J. Rollins, Ada Shaw, Rose Orenbuch, Ruben Weitzman, Jonathan Frazer, Mafalda Dias, Dinko Franceschi, Yarin Gal, Debora S. Marks
NeurIPS, 2023
[link]
Learning from prepandemic data to forecast viral escape
Nicole N. Thadani*, Sarah Gurev*, Pascal Notin*, Noor Youssef, Nathan J. Rollins, Daniel Ritter, Chris Sander, Yarin Gal, Debora S. Marks.
Nature, 2023
[link]
TranceptEVE: Combining family-specific and family-agnostic models of protein sequences for improved fitness prediction
Pascal Notin, Lood Van Niekerk, Aaron W Kollasch, Daniel Ritter, Yarin Gal, Debora S. Marks
NeurIPS Learning Meaningful Representations of Life Workshop, 2022
[link]
Assessing the Interpretability of Large Language Models
Daniel Ritter, Lisa Schut, Andrew Jesson, Been Kim, Yarin Gal
Master's Thesis, 2022
[link]
Multiagent Planning via Partial Coordination in Markov Games
Daniel Ritter, Mark Ho, Michael Littman
Undergraduate Honor's Thesis, 2021
[link]
DeepLTLf: Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator
Homer Walke, Daniel Ritter, Carl Trimbach, Michael Littman
Arxiv preprint, 2021
[link]
*Equal author contribution