Follow
Heejun Lee
Title
Cited by
Cited by
Year
Sparse token transformer with attention back tracking
H Lee, M Kang, Y Lee, SJ Hwang
The Eleventh International Conference on Learning Representations, 2023
62023
SEA: Sparse Linear Attention with Estimated Attention Mask
H Lee, J Kim, J Willette, SJ Hwang
The Twelfth International Conference on Learning Representations, arXiv …, 2023
42023
A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention
H Lee, G Park, Y Lee, J Suh, J Kim, W Jeong, B Kim, H Lee, M Jeon, ...
arXiv:2406.09827 [cs.CL], https://arxiv.org/abs/2406.09827, 2024
2*2024
Training-Free Exponential Context Extension via Cascading KV Cache
J Willette, H Lee, Y Lee, M Jeon, SJ Hwang
arXiv preprint arXiv:2406.17808, 2024
1*2024
The system can't perform the operation now. Try again later.
Articles 1–4