Zobrazeno 1 - 10
of 13 051 372
pro vyhledávání: '"Wang An-An"'
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
The pioneering work of Oono and Suzuki [ICLR, 2020] and Cai and Wang [arXiv:2006.13318] initializes the analysis of the smoothness of graph convolutional network (GCN) features. Their results reveal an intricate empirical correlation between node cla
Externí odkaz:
http://arxiv.org/abs/2410.14604
With the rapid advancements in wireless communication fields, including low-altitude economies, 6G, and Wi-Fi, the scale of wireless networks continues to expand, accompanied by increasing service quality demands. Traditional deep reinforcement learn
Externí odkaz:
http://arxiv.org/abs/2410.14481
Autor:
Yang, Enneng, Shen, Li, Wang, Zhenyi, Guo, Guibing, Wang, Xingwei, Cao, Xiaocun, Zhang, Jie, Tao, Dacheng
Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models without requiring access to raw training data. However, in this paper, we examine the merged model's representation distribu
Externí odkaz:
http://arxiv.org/abs/2410.14389
Text documents with numerical values involved are widely used in various applications such as scientific research, economy, public health and journalism. However, it is difficult for readers to quickly interpret such data-involved texts and gain deep
Externí odkaz:
http://arxiv.org/abs/2410.14331
Autor:
Hu, Xiang, Fu, Hongyu, Wang, Jinge, Wang, Yifeng, Li, Zhikun, Xu, Renjun, Lu, Yu, Jin, Yaochu, Pan, Lili, Lan, Zhenzhong
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited ability i
Externí odkaz:
http://arxiv.org/abs/2410.14255
Autor:
Liu, Zihan, Zeng, Ruinan, Wang, Dongxia, Peng, Gengyun, Wang, Jingyi, Liu, Qiang, Liu, Peiyu, Wang, Wenhai
In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code generation,
Externí odkaz:
http://arxiv.org/abs/2410.14209
This paper focuses on the development of an advanced intelligent article scoring system that not only assesses the overall quality of written work but also offers detailed feature-based scoring tailored to various article genres. By integrating the p
Externí odkaz:
http://arxiv.org/abs/2410.14165
As a bridge connecting the matching polynomial and the Laplacian matching polynomial of graphs, the subdivision method is expected to be useful for investigating the Laplacian matching polynomial. In this paper, we study applications of the method fr
Externí odkaz:
http://arxiv.org/abs/2410.14112
Autor:
Yang, Yuzhe, Zhang, Yifei, Hu, Yan, Guo, Yilin, Gan, Ruoli, He, Yueru, Lei, Mingcong, Zhang, Xiao, Wang, Haining, Xie, Qianqian, Huang, Jimin, Yu, Honghai, Wang, Benyou
This paper introduces the UCFE: User-Centric Financial Expertise benchmark, an innovative framework designed to evaluate the ability of large language models (LLMs) to handle complex real-world financial tasks. UCFE benchmark adopts a hybrid approach
Externí odkaz:
http://arxiv.org/abs/2410.14059