Yibo Miao

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

Exploring Recursive Doubt in Large Language Models

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Information-theoretically Safe Bias Classifier Against Adversarial Attacks