Andrea Zanette

Variance-Reduced Reinforcement Learning for Large Reasoning Models via James-Stein Baselines

Can Large Reasoning Models Self-Train?

Accelerating Unbiased LLM Evaluation via Synthetic Feedback

Training Language Models to Reason Efficiently

Training Large Language Models to Reason Efficiently

Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement