Profiles2024-2026
Shaopeng Fu
Provable Responsible AI and Data Analytics (PRADA) Lab King Abdullah University of Science and Technology, Saudi Arabia
3Papers
0Last author
1Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- Understanding and Improving Continuous LLM Adversarial Training via In-context Learning TheoryAuthor 1 of 2ICLR 2026 · 1 citation
- Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical EvidenceAuthor 1 of 4NeurIPS 2025 · 15 citations
- Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK ApproachAuthor 1 of 2ICLR 2024 · 9 citations
