I am on the job market and expect to graduate in 2026.

I am a final-year Ph.D. candidate at the PLSE Lab, School of Computing, National University of Singapore, advised by Prof. Dong Jin Song. My research focuses on trustworthy AI, with current work on long-horizon agents and post-training with verifiable rewards, and earlier work on trustworthy geometric learning.

Education

Experience

Publications

From Attack Surfaces to Actual Operations: A Survey of Modern LLM Jailbreaks
ACL Findings · 2026 · [PDF]
Risk-Aware Robust Graph Network Explanation
Under Review · 2026 · [PDF]
Ignoring Directionality Leads to Compromised Graph Neural Network Explanations
IEEE S&P Workshops (HMI-SA) · 2025 · [PDF]
PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification
AAAI · 2024 · [PDF]
Repairing Failure-inducing Inputs with Input Reflection
ASE · 2022 · [PDF]
PIANO: Influence Maximization Meets Deep Reinforcement Learning
IEEE TCSS · 2022 · [PDF]
Self-Checking Deep Neural Networks in Deployment
ICSE · 2021 · [PDF]
Generalizing Neural Networks by Reflecting Deviating Data in Production
arXiv · 2021 · [PDF]
Digraph Inception Convolutional Networks
NeurIPS · 2020 · [PDF]
Directed Graph Convolutional Network
arXiv · 2020 · [PDF]
Disco: Influence Maximization Meets Network Embedding and Deep Learning
arXiv · 2019 · [PDF]