Ph.D Student, Computer Science
University of Wisconsin - Madison
Curriculum Vitae
Email: kdnguyen7 [at] wisc [dot] edu

I am a PhD student at the University of Wisconsin-Madison, advised by Prof. Yin Li. My research focuses on machine learning and computer vision, with an emphasis on developing highly efficient models that make effective use of data and computational resources.

This summer, I join Dolby Laboratories as a PhD research intern, working with Trisha Mittal.

Previously, I spent one year as a research intern at the National University of Singapore, working with Chen Li and Prof. Gim Hee Lee. Before that, I was also a research resident at VinAI Research, working with Rang HM Nguyen, Binh-Son Hua and Quoc-Huy Tran (Retrocausal, Inc.). I received my Bachelor of Engineering degree in Computer Engineering from the Ho Chi Minh City University of Technology, Vietnam.

Publications

(*) denotes equal contribution

  1. Learning to Inference Adaptively for Multimodal Large Language Models Zhuoyan* Xu, Khoi Duc Nguyen*, Preeti Mukherjee, Saurab Bagchi, Somali Chaterji, Yingyu Liang, and Yin Li ICCV 2025, International Conference on Computer Vision. [code]
  2. PAVE: Patching and Adapting Video Large Language Models Zhuoming Liu, Yiquan Li, Khoi Duc Nguyen, Yiwu Zhong, and Yin Li CVPR 2025, Conference on Computer Vision and Pattern Recognition. [code]
  3. Adainf: Adaptive inference for resource-constrained foundation models Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee, Somali Chaterji, Yingyu Liang, and Yin Li ICML 2024 Workshop, Workshop on Efficient Systems for Foundation Models II @ ICML2024.
  4. ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation Khoi Duc Nguyen, Chen Li, and Gim Hee Lee CVPR 2024, Conference on Computer Vision and Pattern Recognition. [code]
  5. Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments Khoi D. Nguyen, Quoc-Huy Tran, Khoi Nguyen, Binh-Son Hua, and Rang Nguyen ECCV 2022, European Conference on Computer Vision. [code]
  6. POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples Duong H. Le*, Khoi D. Nguyen*, Khoi Nguyen, Quoc-Huy Tran, Rang Nguyen, and Binh-Son Hua NeurIPS 2021, Neural Information Processing Systems. [code]
Professional Services
  • Conference Reviewer: ICCV (2025), CVPR (2025, 2023), ECCV (2024), NeurIPS (2025, 2023).