CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning 事件

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning arXiv:2606.02502v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands continuous capability expansion, making Multimodal Continual Instruction Tuning (MCIT) essential. Existing methods either update all tasks with a shared parameter set or allocate dedicated m