← Full profile

Hoang-Son Vo

AI Researcher & Engineer · Ho Chi Minh City, Vietnam

hoangson.vothanh@gmail.comwww.sowwn.devGoogle Scholargithub.com/sowwnnlinkedin.com/in/sowwn

Research Interests

Computer Vision · Medical Image Analysis · Brain-Computer Interaction · Video Generation

Education

M.Sc. in Artificial Intelligence2024 – 2026
College of AI Convergence — Chonnam National University, Korea
  • Global Scholarship
  • Gold Award — 2025 AI Hackathon & Industry-Academia Collaboration Competition
B.Sc. in Information Technology2019 – 2023
Faculty of Information Technology — HCMC University of Foreign Languages and Information Technology (HUFLIT), Vietnam
  • Excellent Student — Top 1, AY 2022–2023
  • Talented Student Scholarship

Experience

AI ResidentAug 2026 – Present
Qualcomm
Teaching Assistant2026 – Present
AI Vietnam
Research Assistant2024 – 2026
PRLab
AI Consultant (Freelancer)2024 – Present
V-Star Data
AI Engineer, Octokit2023 – 2024
Marvy Co.
Project Developer (Internship)2023
DKiV

Publications

† Equal contribution.

Peer-Reviewed Publications

  1. [1]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. ACM MMAsia 2026 — ACM Multimedia Asia, 2026.
  2. [2]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, 2026.
  3. [3]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, 2026.
  4. [4]Hoang-Son Vo, Hyung-Jeong Yang, Soo-Hyung Kim. Emotionally Disentangled Talking Head Generation with Vector Quantization and Attention Fusion. IEEE Multimedia, 2025.
  5. [5]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, 2025.
  6. [6]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, 2025.
  7. [7]Quang Vinh Nguyen, Hoang-Son Vo, Sae-Ryung Kang, Soo-Hyung Kim. Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model. ACCV 2024 — Asian Conference on Computer Vision, Hanoi, Vietnam, 2024. doi:10.1007/978-981-96-0901-7_11
  8. [8]Hoang-Son Vo, Quang-Vinh Nguyen, Hyung-Jeong Yang, Jaewook Shin, Soo-Hyung Kim. Individual Audio-Driven Talking Head Generation based on Sequence of Landmark. ACK 2024 — Annual Conference of KIPS, Gwangju, Korea, 2024. doi:10.3745/PKIPS.y2024m10a.553
  9. [9]Quang Vinh Nguyen, Hoang-Son Vo, Hoang Chau Truong Vinh, Duc Duy Nguyen, Nhat Huy Nguyen Minh, Soo-Hyung Kim. Rethinking Top Probability from Multi-view for Distracted Driver Behavior Localization. BIGDAS 2024 — 12th Int. Conf. on Bigdata Applications and Services, Jeju, Korea, 2024. (Best Paper Award)
  10. [10]Nhu-Tai Do†, Hoang-Son Vo†, Tram-Tran Nguyen-Quynh†, Soo-Hyung Kim. 3D-DDA: 3D Dual-Domain Attention for Brain Tumor Segmentation. ICIP 2023 — IEEE Int. Conf. on Image Processing, Kuala Lumpur, Malaysia, 2023. doi:10.1109/ICIP49359.2023.10222602
  11. [11]Hoang-Son Vo, Tram-Tran Nguyen-Quynh, Nhu-Tai Do, Soo-Hyung Kim. 3D Dual-Fusion Attention Network: A fusion attention network for Brain Tumor Segmentation. ASK 2023 — Annual Spring Conference of KIPS, 2023. doi:10.3745/PKIPS.y2023m05a.496
  12. [12]Tai Do Nhu†, Hoang-Son Vo†, Tram Tran Nguyen Quynh, Huy Nguyen Thanh, Thanh Nguyen Thi Ngoc, Huy Nguyen Quoc, Soo-Hyung Kim. Brain Tumor Segmentation Based on Deep Supervision and Context Feature Fusion. FAIR 2023 — 16th National Conference on Fundamental and Applied IT Research, 2023. doi:10.15625/vap.2023.0017
  13. [13]Hoang-Son Vo, Tram Tran Nguyen Quynh, Huy Nguyen Quoc, Tai Do Nhu. DCDynUnet: Deep Supervision Attention Context for Brain Segmentation. ICTA 2023 — Lecture Notes in Networks and Systems, vol. 847, Springer, 2023. doi:10.1007/978-3-031-49529-8_17

Under Review

  1. [14]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, 2026.
  2. [15]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, 2026.
  3. [16]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, 2026.
  4. [17]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, 2025.

Preprints

  1. [18]Hoang-Son Vo, Quang-Vinh Nguyen, Soo-Hyung Kim. KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation. arXiv preprint arXiv:2409.05330, 2024. arxiv.org/abs/2409.05330

Honors & Awards

Gold Award — 2025 AI Hackathon & Industry-Academia Collaboration Competition2025
Best Paper Award — BIGDAS 20242024
Global Scholarship — Chonnam National University2024
Excellent Student (Top 1), AY 2022–2023 — HUFLIT2023
Talented Student Scholarship — HUFLIT2022

Academic Service

Reviewer: ICME 2025,2026; AVSS 2025; ICASSP 2026

Skills

Research: Computer Vision, Medical Image Analysis, 3D Segmentation, Generative Models (Diffusion, Flow Matching), Brain-Computer Interaction

Engineering: Python, PyTorch, GPU-accelerated training, Mamba / Transformer architectures, MONAI, Docker

Languages: Vietnamese (native), English (professional), Korean (basic)