Research

CARROT: A Cost Aware Rate Optimal Router

• Seamus Somerstep, Felipe Maia Polo, Allysson Flavio Melo de Oliveira, Prattyush Mangal, Mírian Silva, Onkar Bhardwaj, Mikhail Yurochkin, Subha Maity
• In Submission, 2025
• Try CARROT

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families

• Felipe Maia Polo, Seamus Somerstep, Leshem Choshen, Yuekai Sun, Mikhail Yurochkin
• In Submission, 2025

A transfer learning framework for weak-to-strong generalization

• Seamus Somerstep, Felipe Maia Polo, Moulinath Banerjee, Ya’acov Ritov, Mikhail Yurochkin, Yuekai Sun
• In International Conference on Learning Representations (ICLR), 2025

Microfoundation inference for strategic prediction

• Daniele Bracale, Subha Maity, Felipe Maia Polo, Seamus Somerstep, Moulinath Banerjee, Yuekai Sun
• In International Conference on Artificial Intelligence and Statistics (AISTATS), 2025

All the lambda one’s on cyclic admissible covers

• Renzo Cavalieri, Byson Owens, Seamus Somerstep
• Accepted, Proceedings of the American Mathematical Society, 2025

Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness

• Seamus Somerstep, Ya’acov Ritov, Yuekai Sun
• In ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2024

Learning In reverse Causal Strategic Environments with Ramifications on Two Sided Markers

• Seamus Somerstep, Yuekai Sun, Ya’acov Ritov
• In International Conference on Learning Representations (ICLR), 2024

Boundary Expression for Chern Classes of the Hodge Bundle on Spaces of Cyclic Covers

• Bryson Owens, Seamus Somerstep
• In Involve: A journal of mathematics, 2021

The Supersingularity of Hurwitz Curves

• Dean Bisogno, Erin Dawson, Henry Frauenhoff, Michael Lynch, Amethyst Price, Rachel Pries, Seamus Somerstep, Eric Work
• In Involve: A journal of mathematics, 2019