1
Topology-Aware Layer Pruning for Large Vision-Language Models
提出拓扑感知层剪枝方法,有效降低大视觉语言模型的计算与内存成本,助力高效部署。
arXiv:2604.16502v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in natural language understandi…