AI Researcher & Engineer
Hoang‑Son Vo.
Working across Computer Vision and Human‑Computer Interaction — from brain tumor segmentation to emotion‑controllable talking‑head synthesis.
News
About
I’m Hoang‑Son — an AI researcher and engineer from Vietnam. I hold a B.Sc. in Information Technology from HUFLIT and an M.Sc. in AI Convergence from Chonnam National University, South Korea. My work sits at the intersection of Computer Vision and Human‑Computer Interaction, with recent focus on audio‑driven talking‑head generation.
Research Interests
Where vision meets people.
Education
Two schools, one thread.
2024 — 2026
M.Sc. in Artificial Intelligence
College of AI Convergence — Chonnam National University · Korea
2019 — 2023
B.Sc. in Information Technology
Faculty of Information Technology — HCMC University of Foreign Languages (HUFLIT) · Vietnam
Brain Tumor Detection using Deep Learning, advised by MSc. Tran Nguyen Quynh Tram, co-advised by PhD Nhu-Tai Do (Grade: 9.5/10)
Work Experience
From internship to teaching.
Publications
18 papers, 2023 — 2026.
† Equal contribution
Bui Van Hung, Hoang-Son Vo, Mai Duc Minh Huy, Dang Thanh Vu, Soo-Hyung Kim
MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching
BMVC 2026
Bui Van Hung, Dang Thanh Vu, Hoang-Son Vo, Mai Duc Minh Huy, Mai Tien Dung, Soo-Hyung Kim
Conditional Flow Matching for Local Synthesis of Healthy Brain Tissue in 3D MRI
MICCAI BraTS 2026 Challenge
Hoang-Son Vo, Bui Van Hung, Mai Duc Minh Huy, Mai Tien Dung, Soo-Hyung Kim
CHASMBrain: Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction
Under review
Bui Van Hung, Dang Thanh Vu, Hoang-Son Vo, Mai Duc Minh Huy, Mai Tien Dung, Soo-Hyung Kim
StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching
Under review
Hoang-Son Vo, Huy Mai, Van-Hung Bui, Tien-Dung Mai, Duc Vu, Thanh-Vu Dang, Soo-Hyung Kim
Pseudo-Healthy Anatomy for the Unscored Tumor Region in 3D Brain MRI Inpainting
Under review
Hoang-Son Vo, Karina Kolmogortseva, Ngumimi Karen Iyortsuun, Hong-Duyen Vo, Soo-Hyung Kim
GlobalizeEd: A Multimodal Translation System that Preserves Speaker Identity in Academic Lectures
Under review
Hoang-Son Vo, Quang-Vinh Nguyen, Minh-Duc Nguyen, Soo-Hyung Kim
Image Sequentialization via Mamba-based Encoder for Contrastive Radiology Report Generation
Under review
Hoang-Son Vo, Hyung-Jeong Yang, Soo-Hyung Kim
Emotionally Disentangled Talking Head Generation with Vector Quantization and Attention Fusion
IEEE Multimedia
Hoang-Son Vo, Quang-Vinh Nguyen, Soonja Yeom, Soo-Hyung Kim
ATL-Diff: Audio-Driven Talking Head Generation with Early Landmarks-Guide Noise Diffusion
AVSS 2025 — IEEE Int. Conf. on Advanced Visual and Signal Based Systems, Tainan, Taiwan
Quang Vinh Nguyen, Minh Duc Nguyen, Hoang-Son Vo, Hyung-Jeong Yang, Soo-Hyung Kim
Anatomical Attention Alignment Representation for Radiology Report Generation
ICIP 2025 — IEEE Int. Conf. on Image Processing, Anchorage, Alaska
Reviewer Service