一作ACL 2026Poster· Natural Language Processing
V is PCO : Visual Token Pruning Configuration Optimization via Budget-Aware P areto-Frontier Learning for Vision-Language Models
Huawei Ji · Yuanhao Sun · Yuan Jin · Cheng Deng · Jiaxin Ding · Luoyi Fu · Xinbing Wang
摘要
Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning configurations without determining whether they achieve compu...