Runqi Lin

5 papers · 2023–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (15)

Conferences

ICLR (3) ICML (1) NIPS (1)

Top co-authors

Tongliang Liu (5) Bo Han (4) Chaojian Yu (3) Lei Feng (1) Hang Su (1) Suqin Yuan (1) Fengwang Li (1)

Keywords

adversarial robustness (1) adversarial training (1) catastrophic overfitting (1)

Papers

Understanding and Enhancing the Transferability of Jailbreaking Attacks ICLR 2025

Instance-dependent Early Stopping ICLR 2025

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting ICLR 2024

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency ICML 2024

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization NIPS 2023