Kevin Miao

My name is Kevin Miao! Now I have finished my Master’s, I will be working as a Data Science Lecturer at UC Berkeley’s Division of Computation, Data Science, and Society over the summer. In August, I will start as a Machine Learning Engineer at Apple’s Technology Development Group (TDG).

My interests

I am deeply curious about the intersection of explainable artificial intelligence, deep learning and computer vision. Generally, I am interested in investigating how we can make machine learning models more emergent and natural. Rather than focusing on changing up architecture and increasing compute, I want to find out how we can learn better representations faster in low-data regimes. How do we utilize our data efficiently when we cannot afford millions of data points? How can we speed up training? The answer to these questions will allow us to build safe, intelligent and efficient large systems which we can safeguard against perturbations or threats.

CV/Resume: Access here

more background 👇

In 2021, I finished my undergraduate degree at UC Berkeley in Computer Science with honors. However, my original academic interests have actually always been in Biology and Medicine until my third year of college when I first learned to code. Prior to this, I investigated the evolution of the olfactory neurons in S. Flava (a fruit fly species) under Noah Whiteman. After switching my major to Data Science (and then to Computer Science), I combined my biomedical and computative knowledge to investigate and develop precision medicine frameworks at UCSF with Julian Hong. In the summer after obtaining my bachelor’s degree in 2021, I worked as a Machine Learning Intern at Felyx, an Amsterdam-based mobility startup, and created an end-to-end computer vision pipeline to detect wrongly parked vehicles. I recently finished my Master’s degree in Electrical Engineering and Computer Science (‘22) at UC Berkeley. 🐻 Under the supervision of Joey Gonzalez and close collaboration with Trevor Darrell and Kurt Keutzer. My thesis work devised a framework for knowledge-embedded regularization in self-supervised vision transformers (Arxiv link forthcoming).

highlighted research

Miao, K., Dahle, J., Yousefi, S., Buchake, B., Kaur, P., Odisho, A. Y., Cinar, P., & Hong, J. C. (2021). Machine learning-based approach to the risk assessment of potentially preventable outpatient cancer treatment-related emergency care and hospitalizations. In Journal of Clinical Oncology (Vol. 39, Issue 28 suppl, pp. 333–333). American Society of Clinical Oncology (ASCO).

Matsunaga, T., Reisenman, C. E., Goldman-Huertas, B., Brand, P., Miao, K., Suzuki, H. C., ... & Whiteman, N. K. (2019). Evolution of olfactory receptors tuned to mustard oils in herbivorous Drosophilidae. In Molecular Biology and Evolution.


Teaching the field I love (computer science) and interacting with other enthusiasts give me energy and joy. All course notes and other resources are publicly available where possible. My belief is that education should be equitable; resources and materials should not be hidden away from the public. I am fortunate enough to have taught and be teaching courses that share this philosophy.

UC Berkeley