5 citations · 5 across the 2 of their papers we have counts for
2 papers
cs.CL2025
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
Sungmin Han, Jeonghyun Lee, Sangkyun Lee
Transformers have profoundly influenced AI research, but explaining their decisions remains challenging -- even for relatively simpler tasks such as classification -- which hinders…
cs.LG2019★ 5 cited
Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems
Sangkyun Lee, Jeonghyun Lee
Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a lar…