Amrit Bedi

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Transfer Q-star : Principled Decoding for LLM Alignment

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?

RealFM: A Realistic Mechanism to Incentivize Data Contribution and Device Participation

On the Possibilities of AI-Generated Text Detection: A Sample Complexity Analysis

On the Global Convergence of Natural Actor-Critic with Neural Network Parametrization

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning