α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Heejun Lee
Heejun Lee
3
papers
15
total citations
papers (3)
A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
ICLR 2025
arXiv
9
citations
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
NEURIPS 2025
arXiv
3
citations
Training Free Exponential Context Extension via Cascading KV Cache
ICLR 2025
arXiv
3
citations