AI RESEARCH
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
arXiv CS.CV
•
ArXi:2604.16462v1 Announce Type: new High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategies, such as token pruning or layer sparsity, suffer from severe "backbone dependency", performing well on Vicuna or Mistral architectures (e.g., LLaVA) but causing significant performance degradation when transferred to architectures like Qwen.