Research author

Shaopeng Fu

3 AI research papers in the One9Founders library, with summaries and links to original sources.

Papers by Shaopeng Fu

Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

Hongli Shen, Shaopeng Fu, Qinbo Zhang, et al.

Benign Overfitting in Adversarial Training for Vision Transformers

Jiaming Zhang, Meng Ding, Shaopeng Fu, et al.

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

Shaopeng Fu, Di Wang

Shaopeng Fu — AI Research Papers | One9Founders