MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion
MGDT is proposed, a novel MKGC framework built on an align-then-diffuse paradigm that employs a Relation-Adaptive Semantic Routing Mixture-of-Experts module to select relation-relevant multimodal semantic transformation paths and suppress irrelevant modality interference.