Zobrazeno 1 - 10
of 187
pro vyhledávání: '"Yang, Mingchuan"'
Autor:
Zheng, Zifan, Wang, Yezhaohui, Huang, Yuxin, Song, Shichao, Yang, Mingchuan, Tang, Bo, Xiong, Feiyu, Li, Zhiyu
Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Consequently, the reasoning bottlenecks of LLMs are mainly influenced by their internal architecture. As a result, many research
Externí odkaz:
http://arxiv.org/abs/2409.03752
Autor:
Wu, Yiquan, Tang, Bo, Xi, Chenyang, Yu, Yu, Wang, Pengyu, Liu, Yifei, Kuang, Kun, Deng, Haiying, Li, Zhiyu, Xiong, Feiyu, Hu, Jie, Cheng, Peng, Wang, Zhonghao, Wang, Yi, Luo, Yi, Yang, Mingchuan
Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the proce
Externí odkaz:
http://arxiv.org/abs/2408.11609
Autor:
Zou, Hang, Du, Chenxi, Liu, Ajian, Zhang, Yuan, Liu, Jing, Yang, Mingchuan, Wan, Jun, Zhang, Hui
Iris recognition is widely used in high-security scenarios due to its stability and distinctiveness. However, the acquisition of iris images typically requires near-infrared illumination and near-infrared band filters, leading to significant and cons
Externí odkaz:
http://arxiv.org/abs/2408.09752
Autor:
Zhu, Yu, Sun, Chuxiong, Yang, Wenfei, Wei, Wenqiang, Tang, Bo, Zhang, Tianzhu, Li, Zhiyu, Zhang, Shifeng, Xiong, Feiyu, Hu, Jie, yang, Mingchuan
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. However, existing RLHF methods require a high computational cost, one main reason being that RLHF assigns bot
Externí odkaz:
http://arxiv.org/abs/2403.04283
Autor:
Yang, Mingchuan1 (AUTHOR) yangmingchuan@tricaas.com, He, Yufeng1 (AUTHOR) qhyf2019@yeah.net, Ni, Qingqing2 (AUTHOR) 13671733209@163.com, Zhou, Mengxue1 (AUTHOR) zhoumengxue@tricaas.com, Chen, Hongping1 (AUTHOR) thean27@tricaas.com, Li, Guangyun1 (AUTHOR) fqcyzx@163.com, Yu, Jizhong3 (AUTHOR) hchyu@126.com, Wu, Ximing4 (AUTHOR) hchyu@126.com, Zhang, Xiangchun1 (AUTHOR) zhangxc@tricaas.com
Publikováno v:
Pharmaceutics. Aug2024, Vol. 16 Issue 8, p972. 20p.
As deep learning becomes the mainstream in the field of natural language processing, the need for suitable active learning method are becoming unprecedented urgent. Active Learning (AL) methods based on nearest neighbor classifier are proposed and de
Externí odkaz:
http://arxiv.org/abs/2203.09174
Autor:
Yang, Mingchuan, Liu, Yang, Yue, Zhaoqian, Yang, Guang, Jiang, Xu, Cai, Yimin, Zhang, Yuqi, Yang, Xiujie, Li, Dongwei, Chen, Luyao
Publikováno v:
In Brain and Language September 2024 256
Autor:
He, Yufeng, Hao, Meng, Yang, Mingchuan, Guo, Huimin, Rayman, Margaret P., Zhang, Xiangchun, Zhang, Jinsong
Publikováno v:
In International Journal of Biological Macromolecules August 2024 274 Part 2
Autor:
Su, Boning, Yang, Mingchuan, Gao, Bin, Li, Ziyao, Zhao, Xiangjie, Zhang, Shugang, Cheng, Dongdong, Shen, Tianlin, Yao, Yuanyuan, Yang, Yuechao
Publikováno v:
In Journal of Cleaner Production 1 May 2024 452
Publikováno v:
In Computers, Environment and Urban Systems March 2024 108