AI RESEARCH
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
arXiv CS.LG
•
ArXi:2511.21016v3 Announce Type: replace Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy, fading summary of the past hurts recall-oriented tasks. We propose Gated KalmaNet (GKA, pronounced "gee-ka"), a layer that accounts for the full past while retaining SSM-style efficiency.