Cisco（思科）

Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control

Unicorn: 一种通用且协作的强化学习方法用于可推广的网络级交通信号控制

Yifeng Zhang, Yilin Liu, Ping Gong, Peizhuo Li, Mingfeng Fan, Guillaume Sartoretti

机构 * Department of Mechanical Engineering, National University of Singapore（新加坡国立大学机械工程系） ； State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室） ； Cisco-NUS Accelerated Digital Economy Corporate Laboratory（Cisco-NUS加速数字经济企业实验室） 纠错

AI总结 本文提出Unicorn框架，通过统一状态动作映射、通用交通表示和对比学习提升交通信号控制的适应性与协作性，解决复杂交通网络的可扩展优化问题。

Comments \c{opyright} 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding

面向大视觉-语言模型的注意力感知推理优化

Fatih Ilhan, Gaowen Liu, Ramana Rao Kompella, Selim Furkan Tekin, Tiansheng Huang, Zachary Yahn, Yichang Xu, Ling Liu

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Cisco Research（思科研究） 纠错

AI总结 本文提出AttentionPack框架，通过紧凑注意力机制和解压机制提升大视觉-语言模型解码效率，实验表明内存效率提升8倍，支持更大批次和更快推理，同时保持输出质量。