👋 Hey there, you've found Andrew.
I'm a CS undergrad at NYCU, where I split my time between AI research and software engineering. Most of my work revolves around Large Language Models: I'm currently interning at Datalab where I'm researching inference acceleration, and I've previously proposed a framework for evaluating LLM explainability (AAAI'24 Student Abstract) and played around with benchmarking LLMs' reasoning abilities with chess (LLM@IJCAI'23).
I also have a habit of turning interesting ideas into real things. I served as president of NYCU's Software Development Club and previously led CommonGround, a social media platform we built to facilitate rational discourse. You'll also find me as SITCON staff and sharing tech I find interesting with Taiwan's broader CS community as speaker. You may find the following talks interesting:
- On my comprehension of how Language Models for Cognition and Preference (SITCON 2026)
- On how BitNet works and its incredibly interesting inference (COSCUP 2025 | MOPCON 2025)
- On LLMs and observations of their "reasoning" abilities (COSCUP 2024 | SITCON 2024)
Outside of work, I'm endlessly curious. Give me an interesting idea and I'll happily lose an afternoon to it. Lately I've been trying to actually understand what I drink, whether that's coffee or whiskey, but a good conversation about something I've never thought about before pairs just as well.
Still interested? You can find more about me at https://kuo.is.