Drop the QK dot product: attention as Gaussian fields beats SDPA on ImageNet
SSOG-Attention ditches query-key dot products for a learned field of separable Gaussian atoms, each head just two 1D filter passes instead of an N×N matrix. It hits 65.3% on ImageNet-1K and 70.4% on CIFAR-100 (dot baseline: 53.1%), with free zero-shot resolution transfer. The open question: what long-range recall trades away for the near-linear compute?