Hoyong Kim

Hoyong Kim

Hoyong Kim is a Ph.D. candidate in AI at GIST, advised by Professor Kangil Kim. His research spans representation learning, computer vision, and natural language processing. He has presented notable work at ICLR2024 and NeurIPS2022.

Publications

You can also find my articles on my Google Scholar profile.

Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation

Published in ICLR, 2024

How the collapse between class means and class weight vectors occurs in a fixed classifier when its shape is not a simplex?

Recommended citation: Kim, H. & Kim, K. (2024), Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation. The Twelfth International Conference on Learning Representations
Download Paper | Download Slides