Quang-Huy (Percy) Nguyen

I am a third-year Ph.D. student in Electrical and Computer Engineering at Boston University, advised by Prof. Wei-Lun (Harry) Chao. I began my Ph.D. at The Ohio State University in Fall 2024 and continued my doctoral studies at Boston University in Fall 2026.

My research focuses on developing reliable machine learning for real-world scientific problems, with an emphasis on quantifying uncertainty, learning from imperfect data, and generalizing under distribution shift.

Before my Ph.D., I received my bachelor’s degree in Computer Engineering from Vietnam National University Ho Chi Minh City. I worked as a research assistant at the College of Engineering and Computer Science (CECS), VinUniversity and as a research resident at the FPT Software AI Center, mentored by Prof. Dung D. Le.

My email: quanghuy@bu.edu

CV (08/26) GitHub LinkedIn Google Scholar

I am currently seeking a Summer 2027 research internship. Recommendations or referrals are greatly appreciated.

selected publications

WACV
Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting

Quang-Huy Nguyen^*, Jin Zhou^*, Zhenzhen Liu^*, and 4 more authors

In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Abs Bib HTML PDF

We address OOD Object Detection by leveraging the inconsistency between generative and discriminative model outputs. We employ an off-the-shelf generative model as an auxiliary to the object detector and introduce a triplet similarity metric that captures both semantic and visual differences, enabling effective OOD object detection in a zero-shot manner.
@inproceedings{nguyen2026ronin, title = {Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting}, author = {Nguyen, Quang-Huy and Zhou, Jin and Liu, Zhenzhen and Bui, Huyen and Weinberger, Kilian Q. and Chao, Wei-Lun and Le, Dung D.}, booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, year = {2026}, }
NeurIPS
Revisiting Semi-Supervised Learning in the Era of Foundation Models

Zheda Mai^*, Ping Zhang^*, Quang-Huy Nguyen, and 1 more author

In Advances in Neural Information Processing Systems (NeurIPS), 2025

Abs Bib HTML PDF

We present a comprehensive study on Semi-Supervised Learning (SSL) using Vision Foundation Models (VFMs) and propose a simple yet effective baseline that leverages diverse predictions from multiple Parameter-Efficient Fine-Tuning (PEFT) strategies to enhance SSL performance.
@inproceedings{mai2025revisiting, title = {Revisiting Semi-Supervised Learning in the Era of Foundation Models}, author = {Mai, Zheda and Zhang, Ping and Nguyen, Quang-Huy and Chao, Wei-Lun}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, }
CVPR
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

Zheda Mai, Ping Zhang, Cheng-Hao Tu, and 4 more authors

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Highlight Abs Bib HTML PDF

Highlight (top 2.98%)

We present a unified empirical study of Parameter-Efficient Fine-Tuning (PEFT) methods in visual recognition, offering complementary perspectives to deeply understand their behaviors under different regimes (low-shot, many-shot, domain shift), and highlight their complementary predictions and robustness trade-offs.
@inproceedings{mai2025lessons, title = {Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition}, author = {Mai, Zheda and Zhang, Ping and Tu, Cheng-Hao and Chen, Hong-You and Nguyen, Quang-Huy and Zhang, Li and Chao, Wei-Lun}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, }
AAAI
Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks

Minh-Duc Nguyen, Phuong Mai Dinh, Quang-Huy Nguyen, and 2 more authors

In AAAI Conference on Artificial Intelligence (AAAI), 2025

Abs Bib HTML PDF

We investigate Expensive Multi-Objective Optimization by introducing the Stein Variational Hypernetwork for Pareto Set Learning, which alleviates fragmented and uncertain regions in surrogate models while preserving the diversity of learned solutions, demonstrating strong performance on expensive multi-objective optimization problems.
@inproceedings{nguyen2025improving, title = {Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks}, author = {Nguyen, Minh-Duc and Dinh, Phuong Mai and Nguyen, Quang-Huy and Hoang, Long P. and Le, Dung D.}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, }
IEEE Access
Enhancing Few-shot Image Classification with Cosine Transformer

Quang-Huy Nguyen, Cuong Q. Nguyen, Dung D. Le, and 1 more author

IEEE Access, 2023

Abs Bib HTML PDF

We explore Few-shot Image Classification by proposing a new cross-attention mechanism based on cosine similarity, without using softmax, to further emphasize the correlation between labeled support and unlabeled query representations, thus enhancing ViT-based few-shot algorithms across various settings and scenarios compared to conventional attention mechanisms.
@article{nguyen2023enhancing, title = {Enhancing Few-shot Image Classification with Cosine Transformer}, author = {Nguyen, Quang-Huy and Nguyen, Cuong Q. and Le, Dung D. and Pham, Hieu H.}, journal = {IEEE Access}, year = {2023}, }

news

Sep 01, 2026	I transfer to Boston University as a third-year Ph.D. student in Electrical and Computer Engineering (ECE), following my advisor Prof. Wei-Lun (Harry) Chao.
Jul 07, 2026	I successfully passed my Ph.D. qualifying exam.
Nov 15, 2025	Our paper Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting is accepted at WACV 2026.
Sep 15, 2025	Our paper Revisiting Semi-Supervised Learning in the Era of Foundation Models is accepted at NeurIPS 2025.
Apr 15, 2025	Our paper Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition is accepted at CVPR 2025 as a Highlight.