Hi 👋, I am a current B.S. in Computer Science at the University of Southern California ✌️.
I build and evaluate LLM agents and ML systems. My research at USC and in open source focuses on LLM post-training, data-centric ML, and agentic systems. I like working across the stack, from model training to user-facing products.
Reach out to me at siuw [at] usc [dot] edu
Selected Projects
Everyday menu of USC dining hall - an mobile app helping USC students easily access daily dining hall menus and food locations.
Multi-agent framework for automating anomaly detection across different data modalities using LLMs.
RLM-as-a-service platform enabling AI coding agents to perform persistent, recursive reasoning over arbitrarily large contexts via MCP integration.
Open-source initiative curating datasets for training agents.
Published Papers
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection
2025
T Yang*, J Liu*, W Siu*, et al.
Findings of IJCNLP-AACL, 2025
Pyod 2: A python library for outlier detection with llm-powered model selection
2025
S Chen*, Z Qian*, W Siu*, et al.
The Web Conference 2025, Demo Track
* Equal contribution
Work Experience
Research Assistant
USC Viterbi School of Engineering
Aug 2024 - Present
Software Engineer Intern
FlareFlow
Sep 2025 - Jan 2026
Data Analyst Intern
Dell Technologies
May 2024 - Aug 2024