Flow-based Spectral Kernel Learning for Nonstationary Attention
arXiv:2610.30465v1 Announce Type: new Abstract: Kernelized attention provides a useful perspective for understanding self-attention as a similarity-based aggregation mechanism, but existing approaches often rely on fixed or stationary kernels, limiting their ability to adapt the similarity structur…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv stat.ML
Flow-based Spectral Kernel Learning for Nonstationary Attention