Welcome to my homepage, have a nice day.
About me: Hello world! I’m Quan Pham, an incoming PhD student at the National University of Singapore (NUS), where I am fortunate to be advised by Prof. Wee Sun Lee. Before that, I earned a bachelor’s in Data Science from Hanoi University of Science and Technology, then spent time as an AI Resident at two industry labs — VinAI Research (with Prof. Trung Le and Prof. Dinh Phung) and Qualcomm AI Research (with Dr. Tung Pham and Dr. Hung Bui).
Most of my days revolve around research, and I really enjoy that rhythm. The repetition does not feel boring to me; instead, it has taught me resilience, patience, and focus. Outside of research, I enjoy playing games, watching films, and, especially, traveling to new places. I like collecting moments and photos along the way, and you can browse a few of them in my travel gallery..
Writing
Updates
[Jun 2026] One paper was accepted to the ICML 2026 AI4Math workshop. Hoping it finds its way to NeurIPS next!
[Feb 2026] I received PhD admission and a research scholarship from the National University of Singapore.
[Nov 2025] I am actively looking for a PhD position. Good luck to me!
[Jun 2025] I will attend ICML 2025. Let’s connect!
[May 2025] Two papers were accepted to ICML 2025.
[Apr 2025] I joined Qualcomm AI Research as an AI Resident.
[Dec 2024] I achieved an IELTS Academic band score of 7.0!
[Aug 2024] I joined VinAI Research as an AI Resident.
[Apr 2024] My first paper was accepted at ICASSP 2024.
Research Interests
My research primarily focuses on mechanistic interpretability for large language models (LLMs). I am interested in understanding how these models learn, represent knowledge, generalize, and reason by uncovering the internal mechanisms that give rise to their behaviors.
Beyond interpretability, I am interested in agentic AI and its role in supporting scientific work. In particular, I hope to study and build agentic systems that can augment research workflows, enhance productivity, and better support researchers and the academic community.