Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models

TL;DR

This paper introduces Routing Experts (RoE), a dynamic expert routing scheme for multi-modal large language models that improves efficiency and performance without structural changes.

Contribution

It proposes a novel dynamic expert routing method for MLLMs, enabling example-dependent paths and aligning training and inference schemes.

Findings

RoE enhances MLLMs' efficiency and performance.

RoE achieves an average of 3.3% performance gain across benchmarks.

RoE is faster than MoE-LLaVA while maintaining better accuracy.

Abstract

Recently, mixture of experts (MoE) has become a popular paradigm for achieving the trade-off between modal capacity and efficiency of multi-modal large language models (MLLMs). Different from previous efforts, we are dedicated to exploring the dynamic expert path in an already exist MLLM and show that a standard MLLM can be also a mixture of experts. To approach this target, we propose a novel dynamic expert scheme for MLLMs, termed Routing Experts (RoE), which can achieve example-dependent optimal path routing without obvious structure tweaks. Meanwhile, a new regularization of structure sparsity is also introduced to enforce MLLMs to learn more short-cut inference, ensuring the efficiency. In addition, we also realize the first attempt of aligning the training and inference schemes of MLLMs in terms of network routing. To validate RoE, we apply it to a set of latest MLLMs, including LLaVA-1.5, LLaVA-HR and VILA, and conduct extensive experiments on a bunch of VL benchmarks. The experiment results not only show the great advantages of our RoE in improving MLLMs' efficiency, but also yield obvious advantages than MoE-LLaVA in both performance and speed, e.g., an average performance gain of 3.3% on 5 benchmarks while being faster.