"the people who are crazy enough to think they can change the world, are the ones who do."
I am interested in enhancing the reasoning and alignment of large language models, designing scalable multi-agent architectures, and investigating creative domains for generative AI. I also have experience in full-stack development and systems engineering.
Reach out to me at siuw@usc.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.
AI-powered tool that transforms YouTube videos into interactive quizzes with summaries and personalized learning experiences.
Production-ready LLM deployment system with comprehensive observability stack. Built for AWS Annapurna Lab's Cal Hacks 12.0 challenge.
Published Papers
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection
2025
T Yang*, J Liu*, W Siu*, J Wang, Z Qian, C Song, C Cheng, X Hu, Y Zhao
AACL 2025, Findings
Pyod 2: A python library for outlier detection with llm-powered model selection
2025
S Chen*, Z Qian*, W Siu*, X Hu, J Li, S Li, Y Qin, T Yang, Z Xiao, W Ye, ...
The Web Conference (Demo Track), 2025
* Equal contribution
Work Experience
Software Engineer Intern
FlareFlow
2025 - Present
Research Assistant
USC Viterbi School of Engineering
2024 - Present
Data Analyst Intern
Dell Technologies
2024 - 2024