HiRED: Attention-Guided Token Dropping for Efficient Inference of
High-Resolution Vision-Language Models in Resource-Constrained Environments

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments

20 August 2024

Kazi Hasan Ibn Arif

Dimitrios S. Nikolopoulos

Hans Vandierendonck

Papers citing "HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments"

3 / 3 papers shown

Title
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning Junwei Luo Yingying Zhang Xiaoyu Yang Kang Wu Qi Zhu Lei Liang Jingdong Chen Yansheng Li 67 1 0 10 Mar 2025
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction Long Xing Qidong Huang Xiaoyi Dong Jiajie Lu Pan Zhang ... Yuhang Cao Zeang Sheng Jiaqi Wang Feng Wu Dahua Lin VLM 50 28 0 22 Oct 2024
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering Pan Lu Swaroop Mishra Tony Xia Liang Qiu Kai-Wei Chang Song-Chun Zhu Oyvind Tafjord Peter Clark Ashwin Kalyan ELM ReLM LRM 211 1,113 0 20 Sep 2022