An Input-Dependent Readout Phase for Resonant Sequence Models
arXiv:2610.12496v1 Announce Type: new Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives content-dependent memory at the cost of FFT-based training, while a fixed transition keeps the O(T log T…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv cs.LG
An Input-Dependent Readout Phase for Resonant Sequence Models