Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating
arXiv:2604.06014v2 Announce Type: replace
Abstract: We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (R…