ArXiv TLDR

Shaopeng Fu

2 papers · Latest:

Machine Learning

Benign Overfitting in Adversarial Training for Vision Transformers

This paper provides the first theoretical analysis showing benign overfitting in adversarially trained Vision Transformers, leading to strong generalization.

2604.19724
Machine Learning

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory

This paper theoretically explains Continuous Adversarial Training (CAT) for LLMs using in-context learning and proposes an improved regularization method.

2604.12817

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.