Zobrazeno 1 - 10
of 149
pro vyhledávání: '"Liu, Fangcheng"'
Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to achieve a sa
Externí odkaz:
http://arxiv.org/abs/2404.18911
Autor:
Tang, Yehui, Liu, Fangcheng, Ni, Yunsheng, Tian, Yuchuan, Bai, Zheyuan, Hu, Yi-Qi, Liu, Sichao, Jui, Shangling, Han, Kai, Wang, Yunhe
The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is facing huge challenge on the computation and memory costs, that is, tiny l
Externí odkaz:
http://arxiv.org/abs/2402.02791
Autor:
Wang, Yunhe, Chen, Hanting, Tang, Yehui, Guo, Tianyu, Han, Kai, Nie, Ying, Wang, Xutao, Hu, Hailin, Bai, Zheyuan, Wang, Yun, Liu, Fangcheng, Liu, Zhicheng, Guo, Jianyuan, Zeng, Sinan, Zhang, Yinchen, Xu, Qinghua, Liu, Qun, Yao, Jun, Xu, Chao, Tao, Dacheng
The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous GPT and Llam
Externí odkaz:
http://arxiv.org/abs/2312.17276
Publikováno v:
In Structures November 2024 69
Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often requires a fi
Externí odkaz:
http://arxiv.org/abs/2201.01102
Autor:
Chen, Yuefeng, Mao, Xiaofeng, He, Yuan, Xue, Hui, Li, Chao, Dong, Yinpeng, Fu, Qi-An, Yang, Xiao, Xiang, Wenzhao, Pang, Tianyu, Su, Hang, Zhu, Jun, Liu, Fangcheng, Zhang, Chao, Zhang, Hongyang, Zhang, Yichi, Liu, Shilong, Liu, Chang, Wang, Yajie, Zhou, Huipeng, Lyu, Haoran, Xu, Yidan, Xu, Zixuan, Zhu, Taoyu, Li, Wenjun, Gao, Xianfeng, Wang, Guoqiu, Yan, Huanqian, Guo, Ying, Zhang, Chaoning, Fang, Zheng, Wang, Yang, Fu, Bingyang, Zheng, Yunfei, Wang, Yekui, Luo, Haorong, Yang, Zhen
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this restriction. In fa
Externí odkaz:
http://arxiv.org/abs/2110.09903
Publikováno v:
In Construction and Building Materials 10 May 2024 427
Publikováno v:
In Journal of Building Engineering 1 October 2023 76
Publikováno v:
In Soil Dynamics and Earthquake Engineering March 2023 166
Publikováno v:
In Engineering Geology May 2022 301