Fengshuo Bai

PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives

Generalizable Opponent Exploitation in LLM Agents via Mixed Best-Responses Training

FPDou: Mastering DouDizhu with Fictitious Play

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

Iterative Training of Language Models with Opponent Modeling for Red Teaming Data Generation