About me

Welcome to my homepage! I’m Huyen Trang. At present, I am a research resident at VinAI Research where I am fortunate to be advised by Professor Nhat Ho and Professor Tan Nguyen. Before that, I graduated from Hanoi University of Science and Technology with a Bachelor’s degree in Data Science and Artificial Intelligence. During my undergraduate study, I was also a research student at Data Science Lab, conducting research under the guidance of Dr. Linh Ngo and Professor Khoat Than.

Email: pvhtrang0811@gmail.com

Research Interests

My current research focuses on advancing the mathematical principles that underpin the effectiveness of state-of-the-art machine learning models, particularly Mixture of Experts (MoE). To achieve this, I aim to deepen the theoretical understanding and foundational mathematics of MoE architectures and leverage this knowledge to inspire and drive innovations in their applications to areas such as Continual Learning, Visual State Space Models and Large Language Models. Additionally, I strive to develop faster and more efficient optimal transport distances that preserve topological properties while significantly reducing computational costs, which opens up their broader application to a wide range of machine learning challenges that were previously constrained by inefficiency.

(*) denotes equal contribution, (**) denotes equal advising.

Selected Publications

[P.1] Statistical Advantages of Perturbing Cosine Router in Mixture of Experts. Proceedings of the ICLR, 2025.
Huy Nguyen, Pedram Akbarian*, Trang Pham*, Trang Nguyen*, Shujian Zhang, Nhat Ho
[P.2] Distance-Based Tree-Sliced Wasserstein Distance. Proceedings of the ICLR, 2025.
Hoang V. Tran*, Khoi N.M. Nguyen*, Trang Pham, Thanh T. Chu, Tam Le**, Tan Nguyen**
[P.3] Spherical Tree-Sliced Wasserstein Distance. Proceedings of the ICLR, 2025.
Hoang V. Tran*, Thanh T. Chu*, Khoi N.M. Nguyen, Trang Pham, Tam Le**, Tan Nguyen**
[P.4] Mixture of Experts Meets Prompt-Based Continual Learning. Advances in NeurIPS, 2024.
Minh Le, An Nguyen*, Huy Nguyen*, Trang Nguyen*, Trang Pham*, Linh Van Ngo, Nhat Ho

Selected Preprints

[A.1] Tree-Sliced Wasserstein Distance on a System of Lines. Under review.
Hoang V. Tran*, Trang Pham*, Tho Tran, Tam Le**, Tan Nguyen**

Professional Services

• Conference Reviewer: ICLR (2025) and AISTATS (2025).

Teaching Experience

• Undergraduate Teaching Assistant: Object-oriented programming (IT3100E) and Introduction to Data Science (IT4142E).