Hieu Phan
Australia, Vietnam
Summary
👤
SeniorVu Phan is a Research Scientist specializing in multi-modal and foundational models for medical image analysis, with eight years of experience spanning academia and industry. He has developed vision-language pretraining, generative, and LLM-based systems for open-vocabulary recognition, visual question answering, and robust localization, and has 20+ publications at top venues including CVPR, ICCV, ACL and EMNLP. Vu has translated research into impact—securing competitive grants, delivering healthcare AI solutions, and producing an ICCV25 highlighted paper—before joining Google to push foundational and vision-language models for biometrics. Trained through a PhD in deep learning for scene understanding, he pairs rigorous academic grounding with applied deployments across transportation and healthcare, and a track record of improving model robustness and reducing hallucination in multimodal systems.
8 years of coding experience
Github Skills (105)
simulator10
deep-reinforcement-learning9
computer-vision9
unreal-engine-49
ros9
simulation9
depth9
scene8
3d-reconstruction8
carla8
aspect8
autonomous-driving8
structure-from-motion8
self-driving-car8
imitation-learning8
Programming languages (6)
Github contributions (5)
HieuPhan33/REMINDER
Mar 2022 - Nov 2022
Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation
Contributions:38 commits, 2 PRs, 24 pushes in 8 months
continual-learningdeep-learningpytorchsemantic-segmentation
HieuPhan33/LCFS-BERT
Jul 2020 - Jan 2022
Contributions:9 commits, 9 pushes, 1 branch in 1 year 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.