Zobrazeno 1 - 10
of 373
pro vyhledávání: '"Zhang Jinghan"'
Autor:
Yin Hao, Zhang Jinghan, Zhang Chengming, Qian Yonglan, Han Yingjuan, Ge Yao, Shuai Lihua, Liu Ming
Publikováno v:
Redai dili, Vol 42, Iss 5, Pp 854-866 (2022)
Accurate information on the spatial distribution of water is of great significance for monitoring water resources and applications, urban planning, and social and economic development. Remote sensing image segmentation technology based on convolution
Externí odkaz:
https://doaj.org/article/8ea200619a704bdcbdf1fb4294ef1cf1
Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To address thes
Externí odkaz:
http://arxiv.org/abs/2411.02559
In the financial field, precise risk assessment tools are essential for decision-making. Recent studies have challenged the notion that traditional network loss functions like Mean Square Error (MSE) are adequate, especially under extreme risk condit
Externí odkaz:
http://arxiv.org/abs/2411.02558
Recent advances in large language models (LLMs) have demonstrated their potential in handling complex reasoning tasks, which are usually achieved by constructing a thought chain to guide the model to solve the problem with multi-step thinking. Howeve
Externí odkaz:
http://arxiv.org/abs/2410.24155
Textual information of data is of vital importance for data mining and feature engineering. However, existing methods focus on learning the data structures and overlook the textual information along with the data. Consequently, they waste this valuab
Externí odkaz:
http://arxiv.org/abs/2406.11177
The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and
Externí odkaz:
http://arxiv.org/abs/2406.06606
Autor:
Zhang, Xinhao, Zhang, Jinghan, Rekabdar, Banafsheh, Zhou, Yuanchun, Wang, Pengfei, Liu, Kunpeng
The representation of feature space is a crucial environment where data points get vectorized and embedded for upcoming modeling. Thus the efficacy of machine learning (ML) algorithms is closely related to the quality of feature engineering. As one o
Externí odkaz:
http://arxiv.org/abs/2406.03505
Large Language Models (LLMs) gain substantial reasoning and decision-making capabilities from thought structures. However, existing methods such as Tree of Thought and Retrieval Augmented Thoughts often fall short in complex tasks due to the limitati
Externí odkaz:
http://arxiv.org/abs/2406.02746
There is a belief that learning to compress well will lead to intelligence. Recently, language modeling has been shown to be equivalent to compression, which offers a compelling rationale for the success of large language models (LLMs): the developme
Externí odkaz:
http://arxiv.org/abs/2404.09937
Autor:
Chen, Shiqi, Zhao, Yiran, Zhang, Jinghan, Chern, I-Chun, Gao, Siyang, Liu, Pengfei, He, Junxian
Assessing factuality of text generated by large language models (LLMs) is an emerging yet crucial research area, aimed at alerting users to potential errors and guiding the development of more reliable LLMs. Nonetheless, the evaluators assessing fact
Externí odkaz:
http://arxiv.org/abs/2310.00741