Zobrazeno 1 - 10
of 352
pro vyhledávání: '"Wang, Zhengjie"'
The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE with a dyna
Externí odkaz:
http://arxiv.org/abs/2409.00142
Autor:
Do, Andrea, Brown, Oscar, Wang, Zhengjie, Mathew, Nikhil, Liu, Zixin, Ahmed, Jawwad, Yu, Cheng
The performance of Whisper in low-resource languages is still far from perfect. In addition to a lack of training data on low-resource languages, we identify some limitations in the beam search algorithm used in Whisper. To address these issues, we f
Externí odkaz:
http://arxiv.org/abs/2309.10299
Multichannel full-space coding metasurface with linearly-circularly-polarized wavefront manipulation
Autor:
Luo Huiling, Gao Huanhuan, Wang Yanzhao, Wang Chaohui, Zhang Fan, Shao Yanzhang, Liu Tong, Wang Zhengjie, Xu He-Xiu
Publikováno v:
Nanophotonics, Vol 13, Iss 22, Pp 4169-4179 (2024)
Achieving independent multitasked wavefront control by using an ultrathin plate is a challenge to increase information capacity in integration optics and radar applications. Transmission-reflection-integrated metasurface provides an efficient recipe
Externí odkaz:
https://doaj.org/article/cf3652ff455f4cd6a8c7010f02c595cb
Autor:
Zhang Fan, Wang Chaohui, Feng Weike, Liu Tong, Wang Zhengjie, Wang Yanzhao, Wang Mingzhao, Xu He-Xiu
Publikováno v:
Nanophotonics, Vol 13, Iss 8, Pp 1509-1519 (2024)
With rapid development of holography, metasurface-based holographic communication scheme shows great potential in development of adaptive electromagnetic function. However, conventional passive metasurfaces are severely limited by poor reconfigurabil
Externí odkaz:
https://doaj.org/article/ba436fa3a0b444ceb3af9eff30bef2b1
Autor:
Li Zhui, Nina Yhap, Liu Liping, Wang Zhengjie, Xiong Zhonghao, Yuan Xiaoshu, Cui Hong, Liu Xuexiu, Ren Wei
Publikováno v:
JMIR Medical Informatics, Vol 12, Pp e55933-e55933 (2024)
AbstractThis viewpoint article explores the transformative role of large language models (LLMs) in the field of medical education, highlighting their potential to enhance teaching quality, promote personalized learning paths, strengthen clinical skil
Externí odkaz:
https://doaj.org/article/e68a6ae6a2ce4c33a7f8c60ea4772abe
Publikováno v:
In Horticultural Plant Journal November 2024 10(6):1371-1382
Autor:
Wang, Zhengjie, Zeng, Weiwei, Zhang, Kaixin, Xie, Fengyan, Yu, Genjian, Mei, Mengxia, Huang, Chunlei, Wang, Jun
Publikováno v:
In Journal of Alloys and Compounds 15 September 2024 999
Autor:
Li, Qiang, Xue, Biao, Wang, Zhengjie, Zhu, Huaze, Zhou, Hao, Deng, Hao, Song, Jiale, Ma, Xin, Du, Hao, Wang, Qi, Si, Chen, Zhu, Huayue
Publikováno v:
In Separation and Purification Technology 19 June 2024 338
Autor:
Fu, Xueqian, Zhang, Chunyu, Chang, Fuhao, Han, Lingling, Zhao, Xiaolong, Wang, Zhengjie, Ma, Qiaoyu
Publikováno v:
In Information Processing in Agriculture March 2024 11(1):127-142
Autor:
Yue, Shengzhe1 (AUTHOR) 3120215111@bit.edu.cn, Wang, Zhengjie1 (AUTHOR) wangzhengjie@bit.edu.cn, Zhang, Xiaoning1 (AUTHOR)
Publikováno v:
Sensors (14248220). May2024, Vol. 24 Issue 10, p3063. 19p.