Runqi Lin

---

About Me

I am currently a third-year PhD student at the University of Sydney, supervised by Prof. Tongliang Liu. Before this, I received my Bachelor's degree in Data Science & Big Data Technology from Beijing Information Science and Technology University (BISTU) in 2021.
My research area is trustworthy machine learning. The main research interests include adversarial robustness and generalization ability.

---

Publications & Preprints

• Runqi Lin, Chaojian Yu, and Tongliang Liu
  Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization.
  NeurIPS 2023

• Runqi Lin, Chaojian Yu, Bo Han, and Tongliang Liu
  On the Over-Memorization During Natural, Robust and Catastrophic Overfitting.
  ICLR 2024

• Runqi Lin, Chaojian Yu, Bo Han, Hang Su, and Tongliang Liu
  Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency.
  ICML 2024

---

Research Interests

• Adversarial Robustness
  - Single-step & Multi-step Adversarial Training.
  - Robustness in Large Language Models and Vision-Language Models.

• Generalization Ability
  - Catastrophic & Robust Overfitting.
  - Sharpness-Aware Minimization.

---

Services

• Reviewer NeurIPS, ICLR, UAI, ACM MM, etc.