CommentsThe paper requires a great deal of restructuring to be beneficial to the research community. We also identified some issues with the current experiments and improvements in LLM models which we want our work to reflect
Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
基于强化学习的语言引导标记压缩在大视觉-语言模型中
Sihan Cao, Jianwei Zhang, Pengcheng Zheng, Jiaxin Yan, Caiyan Qin, Yalan Ye, Wei Dong, Peng Wang, Yang Yang, Chaoning Zhang
机构
*
School of Computer Science and Engineering(计算机科学与工程学院)
;
University of Electronic Science and Technology of China(电子科学与技术大学)
;
School of Robotics and Advanced Manufacture(机器人与先进制造学院)
;
Harbin Institute of Technology(哈尔滨工业大学)
;
College of Information and Control Engineering(信息与控制工程学院)