Mingi Kang

I am a senior at Bowdoin College, double majoring in Computer Science and a minor in Mathematics. My research lies at the intersection of computer vision, computational imaging, and machine learning. I am particularly passionate about designing deep learning algorithms and architectures that prioritize both efficiency and interpretability.

My recent work focuses on three main areas: accelerating MRI reconstruction using supervised learning, investigating novel activation functions, and developing ConvNN, a framework that replaces fixed-grid convolutions with adaptive k-NN sampling to improve global context aggregation in neural networks.

Outside of research, I enjoy snowboarding, basketball, cooking, and exploring new cafes. I am also a proud brother to a medical student sister at USC Keck and a dedicated fan of the St. Louis Cardinals, LA Dodgers, and Boston Celtics. Please feel free to reach out if you would like to connect!