BrainMoE: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning
Abstract
AbstractReliable cross-modal reasoning requires Multimodal Large Language Model (MLLMs) with interpretable and controllable computation. However, existing models rely on data-driven architectures that entangle multimodal processing, obscuring the functional processes underlying their outputs. Inspired by the human brain’s specialized and dynamically collaborative networks, we propose BrainMoE, a multimodal MoE model with six sensory and cognitive experts: Language, Logic, Social, World Knowledge, Vision, and Auditory. To support flexible sensory–cognitive coordination, we incorporates a layer-wise adaptive router that dynamically determines which experts are activated at each layer based on task-processing demands. Experiments on text, image, and audio reasoning benchmarks demonstrate that BrainMoE outperforms strong baselines by 1.59 and 2.2 points on text-only and multimodal benchmarks, while matching competitive external multimodal models. Routing and ablation analyses demonstrate clear expert specialization and causally important module-level contributions. Experiments on the cognitive benchmark further show that adaptive-routing BrainMoE aligns more closely with human behavioral patterns than baselines and static routing methods.