I'm a fourth-year Ph.D. candidate at 
University of Illinois Urbana-Champaign (UIUC) advised by Jiaqi Ma, and I also work closely with Han Zhao.
Previously, I was an 
Anthropic AI Safety Research Fellow and a Ph.D. ML intern at 
Susquehanna International Group, and I've also spent time at 
Amazon AWS AI Lab and 
National Institute of Informatics. I obtained my Master degree from UIUC and dual Bachelor degree from 
University of Michigan and 
Shanghai Jiao Tong University.
🔬 Research
Research-wise, I'm interested in the broad area of ML and AI, with the goal being to draw theoretical insights from practical problems and develop algorithms with provable guarantees and desirable properties such as efficiency, robustness, and fairness. Recently, my research focuses on understanding data, including the following three aspects:
- Data Attribution: Understanding how training data influences AI models.
- Data Curation: How to curate/generate/augment (synthetic) data that further helps models generalize?
- Data-Centric Privacy: Can above be done without compromising privacy when safety-critical or sensitive data is involved? This includes (differential) privacy, machine unlearning, etc.
Previously I have worked on graph neural networks with Jiaqi Ma and fast graph algorithms with Thatchaphol Saranurak. Generally speaking, I held (actually hold) a strong interest in theoretical stuffs that involves geometry.
🗞️ News
- Aug 2026
🎤 Giving a talk on Dr. Post-Training at
Google DeepMind! - Aug 2026
🎤 Giving a talk on Towards Market Data Valuation under Complex Training at
SIG! - Jun 2026
💼 Interning at
SIG Deep Learning team, come hanging out in Philly! - May 2026
🎤 Giving a talk on Science of Data: Predictable, Optimizable, and Scalable at
Citadel GQS! - May 2026
🎤 Giving a talk on Agentic Backdoor via Pre-Training Poisoning at
Anthropic! - Feb 2026
🏛️ We are organizing the Data Foundations of AI, come check out if you work on data as well!
- Jan 2026
📝 One paper accepted by ICLR 2026.
PNL - Jan 2026
💼 Starting as an AI safety fellow at
Anthropic, come hanging out in San Francisco! - Oct 2025
🏛️ We are organizing the Symposium on Information Retrieval and Language Models at
UIUC! - Oct 2025
- Sep 2025
📝 Please check out our new survey paper on data attribution!
Survey - Sep 2025
📝 Two papers accepted by NeurIPS 2025!
GraSS · Unlearning - Aug 2025
🎓 Get my M.S. Applied Math Degree at
UIUC! - Jul 2025
🏛️ We are organizing the 3rd Workshop on Regulatable Machine Learning in conjunction with NeurIPS 2025!
- Jul 2025
🎤 Giving a talk on Data Attribution at the Guided Generation Group (GGG)!
Slide - Jun 2025
✈️ Attending the first AI Startup School held by Y Combinator, see you in San Francisco!
- Mar 2025
💼 Interning at
Amazon AWS AI Deep Engine Science team, come hanging out in New York! - Jan 2025
📝 One paper accepted by ICLR 2025.
Adversarial DA - Nov 2024
🏆 Received the Graduate Conference Travel Award from
UIUC! - Oct 2024
🏆 Received the NeurIPS 2024 Scholar Award, see you in Vancouver!
- Sep 2024
- Jun 2024
📖 We launched the ongoing Data Attribution Reading Group.
- May 2024
💼 Interning at
NII, come hanging out in Tokyo!
📄 Selected Research
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
A Unified Theory of Random Projection for Influence Functions
Most Influential Subset Selection: Challenges, Promises, and Beyond
🔖 Misc
I'm from Taiwan 🇹🇼! In my spare time, I enjoy street photography 📷 and playing drums 🥁.
