Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms

1 August 2024

Papers citing "Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms"

1 / 1 papers shown

Title
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration Zhongzhi Yu Zheng Wang Yonggan Fu Huihong Shi Khalid Shaikh Yingyan Celine Lin 51 22 0 22 Jun 2024