نسخة أولية وصول مفتوح
MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across vision and language tasks. However, their massive computational and memory demands hinder real-world deployment. While recent efforts reduce costs by employing lightweight language backbones, existing paradigms remain co …