Skip to content
Hot eventLive

TuBA:Tucker 瓶颈注意力用于多维序列建模

1 reports1 sources4 hr ago updated

Get the story

AI overview

2026年10月8日,arXiv 机器学习理论板块发布论文,提出 Tucker Bottleneck Attention(TuBA),用于多维序列建模。该方法利用低秩张量结构实现高效全局 token 混合,将隐藏张量投影到紧凑 Tucker 核上进行多头自注意力与线性投影,从而实现亚二次计算。目前公开信息仅涉及该论文内容,尚无后续实验验证或第三方复现报道。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 8, 2026
  1. arXiv · Machine Learning Theory
    Tucker Bottleneck Attention(TuBA)用于多维序列建模

    论文提出 Tucker bottleneck attention(TuBA),利用低秩张量结构实现高效全局 token 混合,将隐藏张量投影到紧凑 Tucker 核上进行多头自注意力与线性投影,实现亚二次计算。

Heat trend

Current heat 9·Comparable peak 10(Oct 8)·Comparable change over 24 hours –

02.557.510Oct8Oct8Oct8Oct8

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.