Wokring Papers

(2024). COMAL: A Convergent Meta Algorithm for Aligning LLMs with General Preferences. NeurIPS workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML). Selected for Oral Presentation.

Cite arXiv FITML workshop

(2023). Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games. Working Paper.

Cite arXiv