Zobrazeno 1 - 10
of 393
pro vyhledávání: '"Liu Xiaojiang"'
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
This paper introduces a comprehensive smart grid big data solution, focusing on the processing and analysis of vast grid data to facilitate critical applications such as data resource management, real-time monitoring of grid conditions, and predictiv
Externí odkaz:
https://doaj.org/article/ab36d7c3835544b5bc827de777fa43a1
Autor:
Tian, Runchu, Li, Yanghao, Fu, Yuepeng, Deng, Siyang, Luo, Qinyu, Qian, Cheng, Wang, Shuo, Cong, Xin, Zhang, Zhong, Wu, Yesai, Lin, Yankai, Wang, Huadong, Liu, Xiaojiang
Positional bias in large language models (LLMs) hinders their ability to effectively process long inputs. A prominent example is the "lost in the middle" phenomenon, where LLMs struggle to utilize relevant information situated in the middle of the in
Externí odkaz:
http://arxiv.org/abs/2410.14641
Autor:
Liu, Aiwei, Bai, Haoping, Lu, Zhiyun, Sun, Yanchao, Kong, Xiang, Wang, Simon, Shan, Jiulong, Jose, Albin Madappally, Liu, Xiaojiang, Wen, Lijie, Yu, Philip S., Cao, Meng
Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is treated as a sin
Externí odkaz:
http://arxiv.org/abs/2410.04350
Autor:
Liang, Shihao, Tian, Runchu, Zhu, Kunlun, Qin, Yujia, Wang, Huadong, Cong, Xin, Liu, Zhiyuan, Liu, Xiaojiang, Sun, Maosong
Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions. It is shown that increasing the diversity and number of instructions in the training data can consistently enhance generalizati
Externí odkaz:
http://arxiv.org/abs/2307.15504
While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e.g.},
Externí odkaz:
http://arxiv.org/abs/2206.02369
Autor:
Sun, Lanfang, Cen, Yixin, Liu, Xiaojiang, Wei, Jinfei, Ke, Xiaoyu, Wang, Yanan, Liao, Qianling, Chang, Mengchun, Zhou, Meng, Wu, Wencan
Publikováno v:
In Experimental Eye Research July 2024 244
Publikováno v:
In EngMedicine June 2024 1(1)
Publikováno v:
In Tunnelling and Underground Space Technology incorporating Trenchless Technology Research January 2024 143
Autor:
Liu, Xiaojiang1 (AUTHOR), Guo, Zongfeng2 (AUTHOR), Li, Jun1 (AUTHOR), Wu, Demo1 (AUTHOR), Liu, Zhongping1 (AUTHOR), Guan, Cheng1 (AUTHOR), Guan, Yixiang1 (AUTHOR) ntdxlxj@sina.com, Lu, Xiaomin3 (AUTHOR) ntdxlxj@sina.com
Publikováno v:
Bio-Medical Materials & Engineering. 2024, Vol. 35 Issue 3, p279-292. 14p.
Sentence function is an important linguistic feature indicating the communicative purpose in uttering a sentence. Incorporating sentence functions into conversations has shown improvements in the quality of generated responses. However, the number of
Externí odkaz:
http://arxiv.org/abs/2010.01495