I am a PhD student at GLINT Lab, Nanyang Technological University. My research interest is in LLM interpretability.
Would we ever completely reverse engineer AI models? Probably not. Is still useful to do interpretabilty? Possibly yes.
Is this research fascinating? To me, very.
Selected papers:
- “Not” is Not Lost in Translation (preprint ‘26) | arxiv, code, side blog post
- Recurrence Is Not Enough (BlackBoxNLP ‘26) | arxiv, code, side blog post
Bio
I am a PhD student at CCDS, Nanyang Technological University. I am advised by Asst. Prof. Wenya Wang.
From 2025 to 2026, I was a Research Assistant at VinUniversity with Asst. Prof. Le Duy Dung. Before that, I was an intern at AUMOVIO-NTU Corporate Lab.
I received my Master’s degree in Data Science from NTU in 2025, where I was a Class Champion graduate and a Vingroup Scholar.
Once upon a time: I was a Data Analyst at One Mount Group from 2021 to 2024. Before that, I graduated with a High Distinction Bachelor’s degree in Finance from National Economics University (Vietnam) in 2022.