About

Welcome to my homepage! My full name is Duc-Minh Le, you can call me Minh 👋. I am currently a research resident at VinAI Research 🤖 where I am fortunate to be advised by Professor Nhat Ho 🏛️. Before that, I graduated from Hanoi University of Science and Technology with a Bachelor’s degree in Computer Science.

Email: minh611002@gmail.com

Research Interests

My research focuses on advancing Artificial Intelligence and Machine Learning, with a strong emphasis on making them scalable and efficient ⬆. I’ve explored exciting topics such as Parameter-Efficient Fine-Tuning for optimizing AI models and Mixture of Experts for enhanced scalability. Additionally, I’ve worked on Continual Learning and remain deeply curious about new ideas and interdisciplinary research.

I’m actively seeking PhD positions in Computer Science for the upcoming academic year and excited to collaborate on impactful research! 🚀

(*) denotes equal contribution.

Selected Preprints

Adaptive Prompt: Unlocking the Power of Visual Prompt Tuning
Under review
Minh Le*, Anh Nguyen*, Huy Nguyen, Chau Nguyen, Nhat Ho

RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
Under review
Tuan Truong*, Chau Nguyen*, Huy Nguyen*, Minh Le, Trung Le, Nhat Ho

On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
Under review
Nghiem T. Diep*, Huy Nguyen*, Chau Nguyen*, Minh Le, Duy M. H. Nguyen, Daniel Sonntag, Mathias Niepert, Nhat Ho

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning
Under review
Quyen Tran, Minh Le, Tuan Truong, Dinh Phung, Linh Ngo, Thien Nguyen, Nhat Ho, Trung Le

Selected Publications on Mixture of Experts

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
Proceedings of the ICLR, 2025
Minh Le*, Chau Nguyen*, Huy Nguyen*, Quyen Tran, Trung Le, Nhat Ho

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective
Proceedings of the AAAI Conference on Artificial Intelligence 39, 2025 (Oral)
Minh Le*, Tien Ngoc Luu*, An Nguyen The*, Thanh-Thien Le, Trang Nguyen, Thanh Tung Nguyen, Linh Ngo Van, Thien Huu Nguyen

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

Professional Services

  • Conference Reviewer: ICML 2025