HCloud: A trusted JointCloud serverless platform for IoT systems with blockchain von Huang, Zheng, Mi, Zeyu, Hua, Zhichao

Volltext

Prospective case-control study on pain intensity after the use of promethazine in patients undergoing videothoracoscopy von Zhou, Xiangwei, He, Benhui, Zheng, Xia, Li, Chao, Mi, Zeyu, Peng, Mingqing, Li, Min

Volltext

Efficacy and safety of transesophageal ultrasound-guided patent foramen ovale closure for migraine in adolescents von Mi, Zeyu, He, Gang, Li, Chao, Yang, Deyu, Liu, Xue, Zhao, Libo, Gao, Hongli, Li, Xing, Zhou, Xiaogang

Volltext

General and Fast Inter-Process Communication via Bypassing Privileged Software von Mi, Zeyu, Zhuang, Haoqi, Zang, Binyu, Chen, Haibo

Volltext

Hawkeye: Eliminating Kernel Address Leakage in Normal Data Flows von Mi, Zeyu, Guo, Zhi, Huang, Fuqian, Chen, Haibo

Volltext

CPU Elasticity to Mitigate Cross-VM Runtime Monitoring von Mi, Zeyu, Chen, Haibo, Zhang, Yinqian, Peng, Shuanghe, Wang, Xiaofeng, Reiter, Michael

Volltext

A Class of Jump-Diffusion Stochastic Differential System Under Markovian Switching and Analytical Properties of Solutions von Liu, Xiangdong, Mi, Zeyu, Chen, Huida

Volltext

Accelerator Virtualization Framework Based on Inter-VM Exitless Communication von Li, Dingji, Mi, Zeyu, Wu, Baodong, Chen, Xun, Zhao, Yongwang, Ding, Zuohua, Chen, Haibo

Volltext

Multi-Dimensional Optical Flow Embedded Genetic Programming for Anomaly Detection in Crowded Scenes von Mi, Zeyu, Shang, Lin, Xue, Bing

Volltext

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption von Tan, Yifan, Tan, Cheng, Mi, Zeyu, Chen, Haibo

Volltext bestellen

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU von Song, Yixin, Mi, Zeyu, Xie, Haotong, Chen, Haibo

Volltext bestellen

PowerInfer-2: Fast Large Language Model Inference on a Smartphone von Xue, Zhenliang, Song, Yixin, Mi, Zeyu, Zheng, Xinrui, Xia, Yubin, Chen, Haibo

Volltext bestellen

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters von Song, Yixin, Xie, Haotong, Zhang, Zhengyan, Wen, Bo, Ma, Li, Mi, Zeyu, Chen, Haibo

Volltext bestellen

ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs von Zhang, Zhengyan, Song, Yixin, Yu, Guanghui, Han, Xu, Lin, Yankai, Xiao, Chaojun, Song, Chenyang, Liu, Zhiyuan, Mi, Zeyu, Sun, Maosong

Volltext bestellen

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU von Song, Yixin, Mi, Zeyu, Xie, Haotong, Chen, Haibo

Volltext

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption von Tan, Yifan, Tan, Cheng, Mi, Zeyu, Chen, Haibo

Volltext

DuVisor: a User-level Hypervisor Through Delegated Virtualization von Chen, Jiahao, Li, Dingji, Mi, Zeyu, Liu, Yuxuan, Zang, Binyu, Guan, Haibing, Chen, Haibo

Volltext bestellen

PowerInfer-2: Fast Large Language Model Inference on a Smartphone von Xue, Zhenliang, Song, Yixin, Mi, Zeyu, Zheng, Xinrui, Xia, Yubin, Chen, Haibo

Volltext

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters von Song, Yixin, Xie, Haotong, Zhang, Zhengyan, Wen, Bo, Li, Ma, Mi, Zeyu, Chen, Haibo

Volltext

ReLU\(^2\) Wins: Discovering Efficient Activation Functions for Sparse LLMs von Zhang, Zhengyan, Song, Yixin, Yu, Guanghui, Xu, Han, Lin, Yankai, Xiao, Chaojun, Song, Chenyang, Liu, Zhiyuan, Mi, Zeyu, Sun, Maosong

Volltext