MambaFormer: Token-Level Guided Routing Mixture-of-Experts for Accurate and Effi

Abstract

Abstract: The deployment of large language models (LLMs) in real-world clinical applications is constrained by the fundamental trade-off between computational cost and the efficiency of linear-time models. To address this, we propose an LLM-based MambaFormer hybrid Mixture-of-Experts (MoE) framework for efficient medical question-answering (QA) and clinical assistance. The MambaFormer employs a lightweight gating mechanism that performs token-level dynamic routing to a customized Transformer expert (ET5) for short, complex queries or to a State Space Model expert (EMamba) for long, high-throughput seque

Research Question

How does the throughput-accuracy trade-off of dynamic expert specialization in MoE-VLMs compare to fixed top-2 routing on VQA v2 and GQA benchmarks when scaling active parameters from 1B to 10B?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance