Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Wang Peisong"'
Autor:
Tao Yaoding, Zhang Shouyun, Xu Mei, Shu Qiang, Gao Shang, Liu Yanan, Wang Peisong, Cheng Ruijia
Publikováno v:
e-Polymers, Vol 24, Iss 1, Pp 53-7 (2024)
In this study, we realized a highly luminescent polyester fiber using a special spinneret orifice comprised of eight C-shaped pores and specific process parameters. A moderate amount of reversible photochromism materials was added along with the spec
Externí odkaz:
https://doaj.org/article/0a1b463b699a485cb441793e9785aa36
Autor:
Wang Peisong
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
The application of deep learning is becoming a research hotspot in education, especially in student sentiment analysis and classroom feedback prediction. Accurate sentiment analysis can help teachers understand their students’ learning status and i
Externí odkaz:
https://doaj.org/article/e00bcd99e69b462693ff636f7c54fff0
Autor:
Wang Peisong, Cao Zhen
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
Internationalization of higher education has become an inevitable trend under the impetus of world economic integration and informationization. This paper adopts the information diffusion technique in the fuzzy information optimization method to cons
Externí odkaz:
https://doaj.org/article/71b212b2da67448281799abde3130877
Autor:
Li, Yuhan, Wang, Peisong, Zhu, Xiao, Chen, Aochuan, Jiang, Haiyun, Cai, Deng, Chan, Victor Wai Kin, Li, Jia
The emergence of large language models (LLMs) has revolutionized the way we interact with graphs, leading to a new paradigm called GraphLLM. Despite the rapid development of GraphLLM methods in recent years, the progress and understanding of this fie
Externí odkaz:
http://arxiv.org/abs/2407.07457
Autor:
Chen, Tianqi, Li, Zhe, Xu, Weixiang, Zhu, Zeyu, Li, Dong, Tian, Lu, Barsoum, Emad, Wang, Peisong, Cheng, Jian
Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers a solution
Externí odkaz:
http://arxiv.org/abs/2406.07177
With the development of foundation models such as large language models, zero-shot transfer learning has become increasingly significant. This is highlighted by the generative capabilities of NLP models like GPT-4, and the retrieval-based approaches
Externí odkaz:
http://arxiv.org/abs/2402.11235
Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous succ
Externí odkaz:
http://arxiv.org/abs/2311.12399
Autor:
Conde, Marcos V., Timofte, Radu, Huang, Yibin, Peng, Jingyang, Chen, Chang, Li, Cheng, Pérez-Pellitero, Eduardo, Song, Fenglong, Bai, Furui, Liu, Shuai, Feng, Chaoyu, Wang, Xiaotao, Lei, Lei, Zhu, Yu, Li, Chenghua, Jiang, Yingying, A, Yong, Wang, Peisong, Leng, Cong, Cheng, Jian, Liu, Xiaoyu, Yin, Zhicun, Zhang, Zhilu, Li, Junyi, Liu, Ming, Zuo, Wangmeng, Jiang, Jun, Kim, Jinha, Zhang, Yue, Zou, Beiji, Zong, Zhikai, Liu, Xiaoxiao, Vega, Juan Marín, Sloth, Michael, Schneider-Kamp, Peter, Röttger, Richard, Kınlı, Furkan, Özcan, Barış, Kıraç, Furkan, Leyi, Li, Uddin, SM Nadim, Ghosh, Dipon Kumar, Jung, Yong Ju
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white ba
Externí odkaz:
http://arxiv.org/abs/2210.11153
Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary
Externí odkaz:
http://arxiv.org/abs/2204.01234
User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy decrease. In thi
Externí odkaz:
http://arxiv.org/abs/2203.03106