|
Fangzhou Wu
I'm a Ph.D. candidate at University of Wisconsin–Madison, where I am fortunate to be co-advised by Kristin Eschenfelder and Sandeep Silwal.
Prior to coming to Madison, I earned my bachelor's degree from Huazhong University of Science and Technology (HUST). I was a Student Researcher at Google DeepMind and am an incoming Quantitative Research Intern at Citadel Securities.
I am seeking full-time research roles in industry beginning in 2027. Please feel free to reach out if you think there may be a good fit.
Email /
Scholar /
X /
LinkedIn /
Github
|
|
Research
I am broadly interested in developing provably efficient algorithms to accelerate training and inference for foundation models and agents. My research aims to bridge theoretical insights and practical system design by integrating these algorithms into modern foundation-model-based applications.
|
Experience
|
Incoming Quantitative Research Intern, Citadel Securities
Quantitative research internship
|
January 2027 |
Student Researcher, Google DeepMind
Research internship on coding agents
|
May 2026 |
Selected Work
|
NEW
Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning
Fangzhou Wu,
Haike Xu,
Sandeep Silwal
Preprint, 2026
code
/
arXiv
|
DynMuon: A Dynamic Spectral Shaping View of Muon
Fangzhou Wu,
Rikhav Shah,
Sandeep Silwal,
Qiuyi (Richard) Zhang
Oral, HiLD@ICML, 2026
code
/
arXiv
|
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
Fangzhou Wu,
Sandeep Silwal,
Qiuyi (Richard) Zhang
NeurIPS, 2026
code
/
arXiv
|
Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
Fangzhou Wu,
Sandeep Silwal,
Qiuyi (Richard) Zhang
ICLR, 2026
code
/
arXiv
|
Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
Fangzhou Wu,
Sandeep Silwal
NeurIPS, 2025
code
/
arXiv
|
System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
Fangzhou Wu,
Ethan Cecchetti,
Chaowei Xiao
arXiv, 2024
code
/
arXiv
|
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
Fangzhou Wu,
Ning Zhang,
Somesh Jha,
Patrick McDaniel,
Chaowei Xiao
arXiv, 2024
project page
/
arXiv
|
Academic Service
|
| Reviewer, ICLR |
2024–2027 |
| Reviewer, NeurIPS |
2024–2026 |
| Reviewer, ICML |
2024, 2026 |
Teaching
|
|
TA, Applied Database Design (LIS 464), UW–Madison
|
SP24–FA25
|
|