Yuwei Cheng

Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

Probabilistic Bisection Algorithm Provably Achieves Exponential Convergence

Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning

Learning from Imperfect Human Feedback: A Tale from Corruption-Robust Dueling

Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards