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.

Spherization Layer: Representation Using Only Angles

Published in NeurIPS, 2022

Spherization layer is an explicit solution for the dispersion to completely eliminate the interference of the Euclidean norms in training without drawbacks

Recommended citation: Kim, H. & Kim, K. (2022). Spherization Layer: Representation Using Only Angles. Advances in Neural Information Processing Systems, 35, 16398-16410
Download Paper | Download Slides