Zobrazeno 1 - 10
of 859
pro vyhledávání: '"Zhu, Su"'
Autor:
Xu, Hongshen, Zhu, Su, Wang, Zihan, Zheng, Hang, Ma, Da, Cao, Ruisheng, Fan, Shuai, Chen, Lu, Yu, Kai
Large Language Models (LLMs) have extended their capabilities beyond language generation to interact with external systems through tool calling, offering powerful potential for real-world applications. However, the phenomenon of tool hallucinations,
Externí odkaz:
http://arxiv.org/abs/2412.04141
Autor:
Ma, Da, Chen, Lu, Zhang, Situo, Miao, Yuxun, Zhu, Su, Chen, Zhi, Xu, Hongshen, Li, Hanqi, Fan, Shuai, Pan, Lei, Yu, Kai
The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly regarding memory and computatio
Externí odkaz:
http://arxiv.org/abs/2412.02252
Autor:
Sun, Liangtai, Luo, Danyu, Ma, Da, Zhao, Zihan, Chen, Baocai, Shen, Zhennan, Zhu, Su, Chen, Lu, Chen, Xin, Yu, Kai
Recently, there has been a significant upsurge of interest in leveraging large language models (LLMs) to assist scientific discovery. However, most LLMs only focus on general science, while they lack domain-specific knowledge, such as chemical molecu
Externí odkaz:
http://arxiv.org/abs/2409.18412
Large language models have ushered in a new era of artificial intelligence research. However, their substantial training costs hinder further development and widespread adoption. In this paper, inspired by the redundancy in the parameters of large la
Externí odkaz:
http://arxiv.org/abs/2406.06962
Autor:
Ma, Da, Chen, Lu, Wang, Pengyu, Xu, Hongshen, Li, Hanqi, Sun, Liangtai, Zhu, Su, Fan, Shuai, Yu, Kai
Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs associated with thi
Externí odkaz:
http://arxiv.org/abs/2406.01392
Previous work on spoken language understanding (SLU) mainly focuses on single-intent settings, where each input utterance merely contains one user intent. This configuration significantly limits the surface form of user utterances and the capacity of
Externí odkaz:
http://arxiv.org/abs/2402.18258
Autor:
Zhao, Zihan, Ma, Da, Chen, Lu, Sun, Liangtai, Li, Zihao, Xia, Yi, Chen, Bo, Xu, Hongshen, Zhu, Zichen, Zhu, Su, Fan, Shuai, Shen, Guodong, Yu, Kai, Chen, Xin
Artificial intelligence (AI) has played an increasingly important role in chemical research. However, most models currently used in chemistry are specialist models that require training and tuning for specific tasks. A more generic and efficient solu
Externí odkaz:
http://arxiv.org/abs/2401.14818
Publikováno v:
Nutrition Journal, Vol 23, Iss 1, Pp 1-18 (2024)
Abstract Background Multiple Sclerosis (MS), an autoimmune disorder causing demyelination and neurological damage, has been linked to 25-hydroxyvitamin D (25OHD) levels, suggesting its role in immune response and MS onset. This study used GWAS datase
Externí odkaz:
https://doaj.org/article/4eb775b3f28a4abaa63cd89bc742b1e6
Autor:
Li, Jieyu, Chen, Lu, Cao, Ruisheng, Zhu, Su, Xu, Hongshen, Chen, Zhi, Zhang, Hanchong, Yu, Kai
Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases. Previous works provided investigations focusing on lexical diversity, including the influence of the synonym and perturbat
Externí odkaz:
http://arxiv.org/abs/2301.04790
Publikováno v:
Frontiers in Nutrition, Vol 11 (2024)
BackgroundThis study delves into the complex interplay between genetics, 25-hydroxyvitamin D (25OHD), and schizophrenia (SCZ). It leverages extensive sample data derived from Genome-Wide Association Studies (GWAS) to uncover genetic correlations.Meth
Externí odkaz:
https://doaj.org/article/a90e011c670846f0a7956117dbcbf7ce