AI RESEARCH
HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
arXiv CS.CV
•
ArXi:2604.07812v1 Announce Type: new In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning is a promising strategy for reducing the cost of MLLM inference by removing redundant visual tokens. Existing research usually assumes that all attention heads contribute equally to the visual interpretation.