Academic Output

Publications & Awards

Peer-reviewed papers, preprints, and competition honours across multi-modal AI, VQA, and speech-vision-language systems.

Selected Publications

2026
VisRes Bench: Evaluating Visual Reasoning Capabilities of VLMs
Brigitta T., Dahou Y., Huynh N. D., et al.
CVPR 2026
2025
SVLA: A Unified Speech-Vision-Language Assistant
Huynh N. D., et al.
arXiv:2503.24164
2025
Vision-Language Models Can't See the Obvious
Dahou Y., Huynh N. D., et al.
ICCV 2025
2025
Visual Question Answering: A Survey
Huynh N. D., et al.
arXiv:2501.03939
2025
Falcon-H1: Hybrid-Head Language Models
Zuo J., et al. [Contributing Author]
arXiv:2507.22448
2024
Improving VQA Through Topic-Aware Selection Layer
Huynh N. D., et al.
SSRN:5385867
2024
SimpsonsVQA
Huynh N. D., et al.
arXiv:2410.22648
2023
Jarvis: A Voice-based Context-as-a-Service Tool
Huynh N. D., et al.
IEEE MDM 2023

Honours & Awards

🏆
Best Demo Paper — IEEE MDM
Jarvis: A Voice-based Context-as-a-Service Mobile Tool. IEEE International Conference on Mobile Data Management, 2022.
🥇
Top 9 Worldwide — Toloka VQA Challenge
WSDM Cup 2023 — competing against thousands of global participants.
🥇
Top 7 Globally — COVID Detection Challenge
Computer vision applied to real-world medical imaging (STOIC2021), 2022.
🎖️
1st Prize — Simpsons Character Classification Competition
Deakin University AI Challenge, 2021.
🎓
MSc Scholarship (2 years)
Deakin University, 2020–2021.