Showing 2024Show all
2 papers · 1 filter
cs.CL2024
RecurFormer: Not All Transformer Heads Need Self-Attention
Ruiqing Yan, Linghan Zheng, Xingbo Du +3
Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs du…
cs.LG2024
Unveiling and Controlling Anomalous Attention Distribution in Transformers
Ruiqing Yan, Xingbo Du, Haoyu Deng +7
With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention…