作者位次 #3/5ACL 2026Findings· Findings of ACL
C ris P rune: Combining Contextual Relevance and Intrinsic Saliency for Efficient Visual Token Pruning in MLLM s
Ziniu Liu · Shuheng Zhou · Mingqing Liu · Hao Deng · Huijia Zhu
摘要
Visual token pruning has emerged as a pivotal strategy to alleviate the computational bottleneck in Multimodal Large Language Models (MLLMs), yet it frequently compromises the integrity of visual understanding in pursuit of efficiency. Existing methods face a fundamental tension: vision-centric a...