Kuramoto Attention: Synchronizing Self-Attention on the Torus 事件

Kuramoto Attention: Synchronizing Self-Attention on the Torus arXiv:2606.11585v1 Announce Type: cross Abstract: We introduce Kuramoto attention, a self-attention layer in which each hidden coordinate is an angle. The layer scores tokens by gated cosine similarity, attends over previous phase states, and updates each token by the tangent component of the attention-weighted circular mean. Because the values are the raw phase states, this update is exactly the Kuramoto coupling term $\sum_u A_{t,u