AI RESEARCH
Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems
arXiv CS.AI
•
ArXi:2605.24764v1 Announce Type: cross [Abridged] - Spectral Retrieval is a plug-in re-ranking stage that interpolates between per-token MaxSim and mean-pool retrieval through a multi-scale sinc convolution over token embeddings. In standard dense retrieval each document is one mean-pooled vector; when relevance localises into a short subspan, the signal averages into noise. Spectral Retrieval reuses per-token embeddings from a late-interaction index and convolves them with a normalised sinc kernel at multiple scales.