AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Vision-Language Models (VLMs) have exhibited impressive performance across diverse visual scenarios. However, this success comes at the cost of explosive growth in visual tokens, which imposes substantial memory and computational overhead during inference, ultimately increasing latency. To improve VLM inference efficiency, a typical class of visual token pruning methods estimates token importance by aggregating attention scores across all heads in the pruning layer of the Large Language Model (LLM) backbone and prunes tokens based on aggregated scores. However, in this paper, we reveal a compe

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T09:42:05.193Z. This is not the publication date.