Zobrazeno 1 - 10
of 5 232
pro vyhledávání: '"JI Rong"'
Autor:
WANG Tongyu, GUO Yunchang, WU Yangbo, ZHANG Xiaohong, CHEN Lili, DUAN Hongbo, JI Rong, LI Ning, MA Xiaochen, FU Ping
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 34, Iss 5, Pp 1048-1053 (2022)
ObjectiveTo provide scientific basis for preventing foodborne outbreaks and carrying out targeted prevention and control measures， the seasonal characteristics of foodborne diarrheagenic Escherichia coli outbreaks in China’s Mainland from 2010 to
Externí odkaz:
https://doaj.org/article/10015ab119fc4f249c6aa66dc3af8b9f
Autor:
MA Lingling, LI Weiwei, LYU Zhongqi, LI Juanjuan, WANG Yafang, SONG Jian, JI Rong, FU Ping, LI Ning
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 34, Iss 5, Pp 1041-1047 (2022)
ObjectiveTo provide the bases to build up the prevention and control measures， the epidemiology and changes of foodborne disease caused by plant and animal toxicants in China’s Mainland was studied.MethodsThe data reported from 2010 to 2020 was c
Externí odkaz:
https://doaj.org/article/a2e397cedb4440cdb46fce70ce5bb4fd
Autor:
LIU Tingting, CUI Chunxia, SONG Zhuangzhi, GUO Yunchang, LIU Changqing, XU Lizi, SANG Xianglai, JI Rong, FU Ping, LI Ning
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 34, Iss 5, Pp 1029-1034 (2022)
ObjectiveTo understand the distribution characteristics of trigger factors of foodborne disease outbreaks caused by Staphylococcus aureus and its enterotoxin in China.MethodsThe data from the national foodborne disease outbreak monitoring system and
Externí odkaz:
https://doaj.org/article/e7d1359b648444bf845c5d6e54bd224e
Autor:
Cheng, Yiruo, Mao, Kelong, Zhao, Ziliang, Dong, Guanting, Qian, Hongjin, Wu, Yongkang, Sakai, Tetsuya, Wen, Ji-Rong, Dou, Zhicheng
Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG
Externí odkaz:
http://arxiv.org/abs/2410.23090
Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage
Externí odkaz:
http://arxiv.org/abs/2410.20215
Autor:
Du, Yifan, Huo, Yuqi, Zhou, Kun, Zhao, Zijia, Lu, Haoyu, Huang, Han, Zhao, Wayne Xin, Wang, Bingning, Chen, Weipeng, Wen, Ji-Rong
Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation,
Externí odkaz:
http://arxiv.org/abs/2410.13694
Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a
Externí odkaz:
http://arxiv.org/abs/2410.12327
Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective for all moda
Externí odkaz:
http://arxiv.org/abs/2410.11582
Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) align
Externí odkaz:
http://arxiv.org/abs/2410.09584
Autor:
Qu, Changle, Dai, Sunhao, Wei, Xiaochi, Cai, Hengyi, Wang, Shuaiqiang, Yin, Dawei, Xu, Jun, Wen, Ji-Rong
Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a
Externí odkaz:
http://arxiv.org/abs/2410.08197