作者位次 #3/11ICML 2026Poster
LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining
Qiuwu Chen · Zimo Liu · Yuchen Li · Ying Sun · Yifan Zhang · Zhijie Qiu · Zeng You · Ryan Dong · Simeng Ma · Yaofo Chen · Mingkui Tan