Zobrazeno 51 - 60
of 14 416
pro vyhledávání: '"Li, Xian"'
Autor:
Li, Xian, Li, Xiaofei
Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data. SSL has achieved promising results in various domains. This work addr
Externí odkaz:
http://arxiv.org/abs/2204.12076
Autor:
Tang, Yun, Gong, Hongyu, Dong, Ning, Wang, Changhan, Hsu, Wei-Ning, Gu, Jiatao, Baevski, Alexei, Li, Xian, Mohamed, Abdelrahman, Auli, Michael, Pino, Juan
We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A se
Externí odkaz:
http://arxiv.org/abs/2204.05409
Autor:
Li, Xiaobo, Ge, Mingyu, Lin, Lin, Zhang, Shuang-Nan, Song, Liming, Cao, Xuelei, Zhang, Bing, Lu, Fangjun, Xu, Yupeng, Xiong, Shaolin, Tuo, Youli, Tan, Ying, Jiang, Weichun, Qu, Jinlu, Zhang, Shu, Wang, Lingjun, Wang, Jieshuang, Zhang, Binbin, Zhang, Peng, Li, Chengkui, Liu, Congzhan, Li, Tipei, Bu, Qingcui, Cai, Ce, Chen, Yong, Chen, Yupeng, Chang, Zhi, Chen, Li, Chen, Tianxian, Chen, Yibao, Cui, Weiwei, Du, Yuanyuan, Gao, Guanhua, Gao, He, Gu, Yudong, Guan, Ju, Guo, Chengcheng, Han, Dawei, Huang, Yue, Huo, Jia, Jia, Shumei, Jin, Jing, Kong, Lingda, Li, Bing, Li, Gang, Li, Wei, Li, Xian, Li, Xufang, Li, Zhengwei, Liang, Xiaohua, Liao, Jinyuan, Liu, Hexin, Liu, Hongwei, Liu, Xiaojing, Lu, Xuefeng, Luo, Qi, Luo, Tao, Ma, Binyuan, Ma, Ruican, Ma, Xiang, Meng, Bin, Nang, Yi, Nie, Jianyin, Ou, Ge, Ren, Xiaoqin, Sai, Na, Song, Xinying, Sun, Liang, Tao, Lian, Wang, Chen, Wang, Pengju, Wang, Wenshuai, Wang, Yusa, Wen, Xiangyang, Wu, Bobing, Wu, Baiyang, Wu, Mei, Xiao, Shuo, Yang, Sheng, Yang, Yanji, Yi, Qibin, Yin, Qianqing, You, Yuan, Yu, Wei, Zhang, Fan, Zhang, Hongmei, Zhang, Juan, Zhang, Wanchang, Zhang, Wei, Zhang, Yifei, Zhang, Yuanhang, Zhao, Haisheng, Zhao, Xiaofan, Zheng, Shijie, Zhou, Dengke
The origin(s) and mechanism(s) of fast radio bursts (FRBs), which are short radio pulses from cosmological distances, have remained a major puzzle since their discovery. We report a strong Quasi-Periodic Oscillation(QPO) of 40 Hz in the X-ray burst f
Externí odkaz:
http://arxiv.org/abs/2204.03253
All-MLP architectures have attracted increasing interest as an alternative to attention-based models. In NLP, recent work like gMLP shows that all-MLPs can match Transformers in language modeling, but still lag behind in downstream tasks. In this wor
Externí odkaz:
http://arxiv.org/abs/2203.06850
Autor:
Li‐Xian Wang, Wouter Beugeling, Fabian Schmitt, Lukas Lunczer, Julian‐Benedikt Mayer, Hartmut Buhmann, Ewelina M. Hankiewicz, Laurens W. Molenkamp
Publikováno v:
Advanced Science, Vol 11, Iss 19, Pp n/a-n/a (2024)
Abstract The band inversion of topological materials in three spatial dimensions is intimately connected to the parity anomaly of 2D massless Dirac fermions, known from quantum field theory. At finite magnetic fields, the parity anomaly reveals itsel
Externí odkaz:
https://doaj.org/article/a4bd35ca2729427a9ce0c504a6f20b6f
Autor:
Li Xian Liu, Zhiyue Sun
Publikováno v:
Applied Finance Letters, Vol 13 (2024)
Drawing on the concept of organisation capital as an intangible asset perspective, we examine the relationship between organisation capital and Australia firms’ performance and its moderating effects during the last two crisis periods, i.e., Global
Externí odkaz:
https://doaj.org/article/7191ca45725d4ef4b01fbbbe5a6f843b
Although product graphs (PGs) have gained increasing attentions in recent years for their successful applications in product search and recommendations, the extensive power of PGs can be limited by the inevitable involvement of various kinds of error
Externí odkaz:
http://arxiv.org/abs/2202.09747
Autor:
Artetxe, Mikel, Bhosale, Shruti, Goyal, Naman, Mihaylov, Todor, Ott, Myle, Shleifer, Sam, Lin, Xi Victoria, Du, Jingfei, Iyer, Srinivasan, Pasunuru, Ramakanth, Anantharaman, Giri, Li, Xian, Chen, Shuohui, Akin, Halil, Baines, Mandeep, Martin, Louis, Zhou, Xing, Koura, Punit Singh, O'Horo, Brian, Wang, Jeff, Zettlemoyer, Luke, Diab, Mona, Kozareva, Zornitsa, Stoyanov, Ves
Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide ran
Externí odkaz:
http://arxiv.org/abs/2112.10684
Autor:
Lin, Xi Victoria, Mihaylov, Todor, Artetxe, Mikel, Wang, Tianlu, Chen, Shuohui, Simig, Daniel, Ott, Myle, Goyal, Naman, Bhosale, Shruti, Du, Jingfei, Pasunuru, Ramakanth, Shleifer, Sam, Koura, Punit Singh, Chaudhary, Vishrav, O'Horo, Brian, Wang, Jeff, Zettlemoyer, Luke, Kozareva, Zornitsa, Diab, Mona, Stoyanov, Veselin, Li, Xian
Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting their cro
Externí odkaz:
http://arxiv.org/abs/2112.10668
Autor:
Alemanno, Francesca, An, Qi, Azzarello, Philipp, Barbato, Felicia Carla Tiziana, Bernardini, Paolo, Bi, Xiao-Jun, Cai, Ming-Sheng, Casilli, Elisabetta, Catanzani, Enrico, Chang, Jin, Chen, Deng-Yi, Chen, Jun-Ling, Chen, Zhan-Fang, Cui, Ming-Yang, Cui, Tian-Shu, Cui, Yu-Xing, Dai, Hao-Ting, De Benedittis, Antonio, De Mitri, Ivan, de Palma, Francesco, Deliyergiyev, Maksym, Di Santo, Margherita, Ding, Qi, Dong, Tie-Kuang, Dong, Zhen-Xing, Donvito, Giacinto, Droz, David, Duan, Jing-Lai, Duan, Kai-Kai, D'Urso, Domenico, Fan, Rui-Rui, Fan, Yi-Zhong, Fang, Fang, Fang, Kun, Feng, Chang-Qing, Feng, Lei, Fusco, Piergiorgio, Gao, Min, Gargano, Fabio, Gong, Ke, Gong, Yi-Zhong, Guo, Dong-Ya, Guo, Jian-Hua, Han, Shuang-Xue, Hu, Yi-Ming, Huang, Guang-Shun, Huang, Xiao-Yuan, Huang, Yong-Yi, Ionica, Maria, Jiang, Wei, Kong, Jie, Kotenko, Andrii, Kyratzis, Dimitrios, Lei, Shi-Jun, Li, Shang, Li, Wen-Hao, Li, Wei-Liang, Li, Xiang, Li, Xian-Qiang, Liang, Yao-Ming, Liu, Cheng-Ming, Liu, Hao, Liu, Jie, Liu, Shu-Bin, Liu, Yang, Loparco, Francesco, Luo, Chuan-Ning, Ma, Miao, Ma, Peng-Xiong, Ma, Tao, Ma, Xiao-Yong, Marsella, Giovanni, Mazziotta, Mario Nicola, Mo, Dan, Mu, Maria, Niu, Xiao-Yang, Pan, Xu, Parenti, Andrea, Peng, Wen-Xi, Peng, Xiao-Yan, Perrina, Chiara, Qiao, Rui, Rao, Jia-Ning, Ruina, Arshia, Shangguan, Zhi, Shen, Wei-Hua, Shen, Zhao-Qiang, Shen, Zhong-Tao, Silveri, Leandro, Song, Jing-Xing, Stolpovskiy, Mikhail, Su, Hong, Su, Meng, Sun, Hao-Ran, Sun, Zhi-Yu, Surdo, Antonio, Teng, Xue-Jian, Tykhonov, Andrii, Wang, Jin-Zhou, Wang, Lian-Guo, Wang, Shen, Wang, Shu-Xin, Wang, Xiao-Lian, Wang, Ying, Wang, Yan-Fang, Wang, Yuan-Zhu, Wei, Da-Ming, Wei, Jia-Ju, Wei, Yi-Feng, Wu, Di, Wu, Jian, Wu, Li-Bo, Wu, Sha-Sha, Wu, Xin, Xia, Zi-Qing, Xu, En-Heng, Xu, Hai-Tao, Xu, Zhi-Hui, Xu, Zun-Lei, Xu, Zi-Zong, Xue, Guo-Feng, Yang, Hai-Bo, Yang, Peng, Yang, Ya-Qing, Yao, Hui-Jun, Yu, Yu-Hong, Yuan, Guan-Wen, Yuan, Qiang, Yue, Chuan, Zang, Jing-Jing, Zhang, Sheng-Xia, Zhang, Wen-Zhang, Zhang, Yan, Zhang, Yi, Zhang, Yong-Jie, Zhang, Yun-Long, Zhang, Ya-Peng, Zhang, Yong-Qiang, Zhang, Zhe, Zhang, Zhi-Yong, Zhao, Cong, Zhao, Hong-Yun, Zhao, Xun-Feng, Zhou, Chang-Yi, Zhu, Yan, Liang, Yun-Feng
Publikováno v:
Science Bulletin, Volume 67, Issue 7, 15 April 2022, Pages 679-684
The DArk Matter Particle Explorer (DAMPE) is well suitable for searching for monochromatic and sharp $\gamma$-ray structures in the GeV$-$TeV range thanks to its unprecedented high energy resolution. In this work, we search for $\gamma$-ray line stru
Externí odkaz:
http://arxiv.org/abs/2112.08860