Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Cheng, Xianfu"'
Autor:
Wu, Xianjie, Yang, Jian, Chai, Linzheng, Zhang, Ge, Liu, Jiaheng, Du, Xinrun, Liang, Di, Shu, Daixin, Cheng, Xianfu, Sun, Tianzhen, Niu, Guanglin, Li, Tongliang, Li, Zhoujun
Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Despite these achievements, LLMs still encounter significant challenges wh
Externí odkaz:
http://arxiv.org/abs/2408.09174
Autor:
Cheng, Xianfu, Zhang, Hang, Yang, Jian, Li, Xiang, Zhou, Weixiao, Liu, Fei, Wu, Kui, Guan, Xiangyuan, Sun, Tao, Wu, Xianjie, Li, Tongliang, Li, Zhoujun
In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task. The advent of pre-trained multimodal models significantly empowers Document AI frameworks to extract key information from form docume
Externí odkaz:
http://arxiv.org/abs/2405.17336
Autor:
Zhang, Wei, Cheng, Xianfu, Zhang, Yi, Yang, Jian, Guo, Hongcheng, Li, Zhoujun, Yin, Xiaolin, Guan, Xiangyuan, Shi, Xu, Zheng, Liangfan, Zhang, Bo
Log parsing, a vital task for interpreting the vast and complex data produced within software architectures faces significant challenges in the transition from academic benchmarks to the industrial domain. Existing log parsers, while highly effective
Externí odkaz:
http://arxiv.org/abs/2405.13548
Autor:
Cheng, Xianfu, Zhou, Weixiao, Li, Xiang, Yang, Jian, Zhang, Hang, Sun, Tao, Zhang, Wei, Mai, Yuying, Li, Tongliang, Chen, Xiaoming, Li, Zhoujun
Scene Text Recognition (STR) is an important and challenging upstream task for building structured information databases, that involves recognizing text within images of natural scenes. Although current state-of-the-art (SOTA) models for STR exhibit
Externí odkaz:
http://arxiv.org/abs/2401.10110
Autor:
Zhou, Weixiao, Li, Gengyao, Cheng, Xianfu, Liang, Xinnian, Zhu, Junnan, Zhai, Feifei, Li, Zhoujun
Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a new pre-trained model specifically designed for multi-scenario multi-d
Externí odkaz:
http://arxiv.org/abs/2310.10285
Autor:
Zhang, Zhenyu, Ju, Weimin, Li, Xiaoyu, Cheng, Xianfu, Zhou, Yanlian, Xu, Shuhao, Liu, Chengyu, Li, Jing
Publikováno v:
In Agricultural and Forest Meteorology 1 March 2024 346
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Resources Policy January 2024 88
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Science of the Total Environment 10 September 2022 838 Part 2