Zobrazeno 1 - 10
of 743
pro vyhledávání: '"Shen, Xinyi"'
Autor:
Shen, Xinyi, Lin, Zuoquan
Transformer-based open-domain dialog models have become increasingly popular in recent years. These models typically represent context as a concatenation of a dialog history. However, there is no criterion to decide how many utterances should be kept
Externí odkaz:
http://arxiv.org/abs/2409.00315
Autor:
Lin, Zuoquan, Shen, Xinyi
The context in conversation is the dialog history crucial for multi-turn dialogue. Learning from the relevant contexts in dialog history for grounded conversation is a challenging problem. Local context is the most neighbor and more sensitive to the
Externí odkaz:
http://arxiv.org/abs/2401.17588
Autor:
Ye, Hangting, Liu, Zhining, Shen, Xinyi, Cao, Wei, Zheng, Shun, Gui, Xiaofan, Zhang, Huishuai, Chang, Yi, Bian, Jiang
Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due to the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparse
Externí odkaz:
http://arxiv.org/abs/2306.01997
Autor:
Hu, Yixin, Shen, Xinyi, Chen, Zhiwei, Liu, Min, Zhang, Xinyue, Yang, Long, Luo, Jun, Li, Wen, Pei, Yanzhong
Publikováno v:
In Materials Today Physics November 2024 48
Autor:
Yu, Hai, Ma, Yingying, Pan, Yang, Su, Liwen, Ning, Xinyu, Shen, Xinyi, Lv, Jianguo, Zhao, Min, Wang, Congrong, Wang, Cunyong, Zhang, Miao, Yang, Lei, Zhong, Jin
Publikováno v:
In Materials Science & Engineering B October 2024 308
Publikováno v:
In Heliyon 30 September 2024 10(18)
Autor:
He, Kang1,2 (AUTHOR), Shen, Xinyi3 (AUTHOR), Anagnostou, Emmanouil N.1,2 (AUTHOR) emmanouil.anagnostou@uconn.edu
Publikováno v:
Earth System Science Data. 2024, Vol. 16 Issue 6, p3061-3081. 21p.
Autor:
Cai, Chenkai, Yang, Caijie, Lu, Xuan, Chen, Yan, Wen, Jinhua, Wang, Jing, Wang, Ruotong, Zhang, Zupeng, Shen, Xinyi
Publikováno v:
In Water Resources and Industry December 2024 32
Publikováno v:
In Industrial Crops & Products 1 December 2024 221
The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expens
Externí odkaz:
http://arxiv.org/abs/2111.00207