Hello!你好!
I am currently working on multi-modal fusion, alignment, and reasoning of multi-modal foundation models as a Research Scientist at Altos Labs. Before this, I earn my PhD degree at University of Notre Dame, where I am working with Prof. Kevin W. Bowyer at the Computer Vision Research Lab (CVRL). The long-term goal is to increase the transfer learning, zero-shot learning, few-shot learning capabilities of the large scale foundation models and how to make models effectively learn useful knowledge from noisy data. These motivate me working on the AI for biology at Altos Labs.
Interests
- Generative AI
- Multi-modality
- AI for science
Education
PhD in Computer Science and Engineering, 2025
University of Notre Dame
BSc in Electrical Engineering, 2020
Northern Arizona University
Awards
Travel Award CVPR2024
Best paper in VDU workshop at CVPR2023
See certificateExperience
Research Scientist
Altos Labs
Research Intern
The Australian National University
Graduate Research Assistant
University of Notre Dame
Machine Learning Engineer
HopeRun Technology Corporation
Recent Publications
(2025).
Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors.
In ICLR2025.
(2024).
What is a Goldilocks Face Verification Test Set?.
In arXiv.
(2024).
Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem.
In WACVW 2023.
(2023).
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network.
In WACV2025.
(2023).
What Should Be Balanced in a "Balanced" Face Recognition Dataset?.
In BMVC2023.