arXiv Machine Learning
techCenter
ClusterAttention: A training-free speedup of bidirectional attentiontranslating…
1 min readUnknownarXiv Digital Media
arXiv:2608.26965v1 Announce Type: new
Abstract: This paper introduces ClusterAttention, a general training-free speedup of bidirectional attention layers. Existing sparse attention methods either rely on structure in the input, such as order in language or spatial proximity in…