An Axiomatic Analysis of DPO and NLHF as Reference-Dependent Probabilistic Voting Rules with Wesley H. Holliday and Adam Lesnikowski
NeurIPS 2026
EGGROLL - IPO: Pluralistic Alignment via Decentralised Post-Training with Population Preferences with A. Lamerton, B. Sarkar, and J. FoersterÂ
ICML 2026 Workshop on Pluralistic Alignment
Jackpot! Alignment as a Maximal Lottery with M. Lanctot, F. Visin and K. Larson
SC4AI'25 workshop @ AAMAS 2025
Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models with C. Nagpal, R. Patel, and F. Visin
ALA workshop @ AAMAS 2026
Soft Condorcet Optimization for Ranking of General Agents. with M. Lanctot, K. Larson, M. Kaisers, Q. Berthet, I. Gemp, M. Diaz, Y. Bachrach, A. Koop, and D. Precup
Best Paper Award AAMAS 2025
Quasi-Metrics for Possibility Results: Intergenerational Preferences and Continuity with A. Estevan and O. Valero
Mathematics 2023, 11, 395.