What is the accuracy-throughput Pareto frontier of SMoES MoE-VLMs versus dense models on cross-modal reasoning

Abstract

Abstract: Migrating computational intensive tasks from mobile devices to more resourceful cloud servers is a promising technique to increase the computational capacity of mobile devices while saving their battery energy. In this paper, we consider an MIMO multicell system where multiple mobile users (MUs) ask for computation offloading to a common cloud server. We formulate the offloading problem as the joint optimization of the radio resources-the transmit precoding matrices of the MUs-and the computational resources-the CPU cycles/second assigned by the cloud to each MU-in order to minimize the overal

Research Question

What is the accuracy-throughput Pareto frontier of SMoES MoE-VLMs versus dense models on cross-modal reasoning tasks (e.g., ChartQA, DocVQA) when controlling for total parameter count at 7B and 34B scales, and how does expert specialization affect per-layer latency?

Verification Level

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

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

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