AI RESEARCH
Topology-Aware Layer Pruning for Large Vision-Language Models
arXiv CS.CV
•
ArXi:2604.16502v1 Announce Type: new Large Language Models (LLMs) have nstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable them to process multimodal information. Despite these advances, Large Vision-Language Models (LVLMs) incur substantial computational and memory costs, hindering deployment in resource-constrained scenarios.