Heejun Lee
~Heejun_Lee1
4
论文总数
2.0
年均投稿
平均评分
接收情况4/4
会议分布
ICLR
3
NeurIPS
1
发表论文 (4 篇)
20253 篇
4
A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
ICLR 2025Poster
4
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
NeurIPS 2025Poster
4
Training Free Exponential Context Extension via Cascading KV Cache
ICLR 2025Poster