Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts

ArXi:2601.02144v2 Announce Type: replace-cross Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, this router is trained once and then frozen, rendering routing decisions brittle under distribution shifts. We address this limitation by