AI RESEARCH

SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs

arXiv CS.CV

ArXi:2604.23996v1 Announce Type: new Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or modality-agnostic, relying on idealized priors that ignore the layer-dependent modality fusion patterns in MoE-VLMs and provide little guidance for expert specialization.