Quoc-Huy Trinh

Deep Generative Model · Computer Vision · NLP · Multimodal

Hi 👋, I'm Huy — a Vietnamese Computer Science researcher. I graduated with honors with a Master's degree in Computer Science from Aalto University, and a Bachelor's degree in Information Technology (Honor Program) from Ho Chi Minh University of Science, VNU-HCM. I'm passionate about exploring new ideas at the frontier of deep learning and computer vision, and I love building things just to see how they work. Outside of research, I enjoy reading, soccer, music, and films.

My research is supervised by Prof. Minh-Triet Tran, Prof. Ulas Bagci, Prof. Sebastian Szyller, Prof. Bo Zhao, Dr. Debesh Jha, and Msc. Hai-Dang Nguyen.

Research Interests

Deep Generative Model Computer Vision NLP Audio Generation Medical Image Analysis Trustworthy AI

More about my experience, education and awards on the About page.

News

Aug 2026

New preprint: Rad-JEPA 3D, a joint-embedding predictive model for 3D computed tomography.

🤗 Model

Jul 2026

New preprint: How Context Attribution Handles What the Model Already Knows, together with the WMDP++ evaluation set.

arXiv 🤗 Dataset

Jul 2026

🎉 Beyond Medical Diagnostics (SpatialMed) was accepted at the ECCV Workshop 2026.

arXiv Webpage

Jun 2026

🎉 Huy presented PRS-Med and Firebolt-VL at the CVPR Workshop 2026.

PRS-Med Firebolt-VL

May 2026

🎉 SRMA-Mamba was accepted at MICCAI 2026.

Selected Publications

PRS-Med: Position Reasoning Segmentation in Medical Imaging

Quoc-Huy Trinh, Minh-Van Nguyen, Jung Zeng, Gorkem Durak, Ulas Bagci*, Debesh Jha*

CVPRW 2026 Webpage Code

Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space (SpatialMed)

Quoc-Huy Trinh, Xi Ding, Yang Liu, Zhenyue Qin, Xingjian Li, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Ulas Bagci, Min Xu

ECCVW 2026 Webpage 🤗 Dataset

SAM-EG: Segment Anything Model with Edge Guidance framework for efficient Polyp Segmentation

Quoc-Huy Trinh, Hai-Dang Nguyen, Bao-Tram Nguyen Ngoc, Debesh Jha, Ulas Bagci, Minh-Triet Tran

BMVC 2024 Poster

KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation

Quoc-Huy Trinh, Minh-Van Nguyen, Phuoc-Thao Vo Thi

ICME 2024 — IEEE Oral

All publications Works, models & datasets