NeurIPS 2026 spotlight: Phase Kernel lifts capacity of Dense Associative Memory

DimaKrotov · x · 2026-09-28

A NeurIPS 2026 spotlight paper introduces the Phase Kernel for Dense Associative Memory. Modern Hopfield networks offer theoretically exponential memory capacity, but practical capacity is limited by attractor interference. The authors construct a new class of models with nonlinear kernel functions that yield better attractors while provably retaining exponential capacity.

Original post →

More from Research

Research channel →