Wen Zhang

Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths

This paper proposes Cat-MoD, a Hybrid Query Construction module that incorporates a Hybrid Query Construction module where Guide Tokens initialized from coarse-grained linguistic priors rapidly anchor global semantic context, and randomly initialized Explorer Tokens remain active to capture fine-grained visual details.