Zobrazeno 81 - 90
of 39 213
pro vyhledávání: '"Chen, Liang"'
Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contrastive learning (GCL) is emerging as a promising way of leveraging vast
Externí odkaz:
http://arxiv.org/abs/2306.02117
Autor:
Gu, Xiuye, Cui, Yin, Huang, Jonathan, Rashwan, Abdullah, Yang, Xuan, Zhou, Xingyi, Ghiasi, Golnaz, Kuo, Weicheng, Chen, Huizhong, Chen, Liang-Chieh, Ross, David A
Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We use a shared representation (mask proposals with class predictions) for
Externí odkaz:
http://arxiv.org/abs/2306.01736
Autor:
Li, Jintang, Zhang, Huizhe, Wu, Ruofan, Zhu, Zulun, Wang, Baokun, Meng, Changhua, Zheng, Zibin, Chen, Liang
While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision represe
Externí odkaz:
http://arxiv.org/abs/2305.19306
Autor:
Wang, Peiyi, Li, Lei, Chen, Liang, Cai, Zefan, Zhu, Dawei, Lin, Binghuai, Cao, Yunbo, Liu, Qi, Liu, Tianyu, Sui, Zhifang
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e.g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models. We find that the quality ranking o
Externí odkaz:
http://arxiv.org/abs/2305.17926
Autor:
Wang, Qichao, Ma, Huan, Wei, Wentao, Li, Hangyu, Chen, Liang, Zhao, Peilin, Zhao, Binwen, Hu, Bo, Zhang, Shu, Zheng, Zibin, Wu, Bingzhe
The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such
Externí odkaz:
http://arxiv.org/abs/2305.18346
Autor:
Cao, Zhen, Aharonian, F., An, Q., Axikegu, Bai, Y. X., Bao, Y. W., Bastieri, D., Bi, X. J., Bi, Y. J., Cai, J. T., Cao, Q., Cao, W. Y., Cao, Zhe, Chang, J., Chang, J. F., Chen, A. M., Chen, E. S., Chen, Liang, Chen, Lin, Chen, Long, Chen, M. J., Chen, M. L., Chen, Q. H., Chen, S. H., Chen, S. Z., Chen, T. L., Chen, Y., Cheng, N., Cheng, Y. D., Cui, M. Y., Cui, S. W., Cui, X. H., Cui, Y. D., Dai, B. Z., Dai, H. L., Dai, Z. G., Danzengluobu, della Volpe, D., Dong, X. Q., Duan, K. K., Fan, J. H., Fan, Y. Z., Fang, J., Fang, K., Feng, C. F., Feng, L., Feng, S. H., Feng, X. T., Feng, Y. L., Gabici, S., Gao, B., Gao, C. D., Gao, L. Q., Gao, Q., Gao, W., Gao, W. K., Ge, M. M., Geng, L. S., Giacinti, G., Gong, G. H., Gou, Q. B., Gu, M. H., Guo, F. L., Guo, X. L., Guo, Y. Q., Guo, Y. Y., Han, Y. A., He, H. H., He, H. N., He, J. Y., He, X. B., He, Y., Heller, M., Hor, Y. K., Hou, B. W., Hou, C., Hou, X., Hu, H. B., Hu, Q., Hu, S. C., Huang, D. H., Huang, T. Q., Huang, W. J., Huang, X. T., Huang, X. Y., Huang, Y., Huang, Z. C., Ji, X. L., Jia, H. Y., Jia, K., Jiang, K., Jiang, X. W., Jiang, Z. J., Jin, M., Kang, M. M., Ke, T., Kuleshov, D., Kurinov, K., Li, B. B., Li, Cheng, Li, Cong, Li, D., Li, F., Li, H. B., Li, H. C., Li, H. Y., Li, J., Li, Jian, Li, Jie, Li, K., Li, W. L., Li, X. R., Li, Xin, Li, Y. Z., Li, Zhe, Li, Zhuo, Liang, E. W., Liang, Y. F., Lin, S. J., Liu, B., Liu, C., Liu, D., Liu, H., Liu, H. D., Liu, J., Liu, J. L., Liu, J. Y., Liu, M. Y., Liu, R. Y., Liu, S. M., Liu, W., Liu, Y., Liu, Y. N., Lu, R., Luo, Q., Lv, H. K., Ma, B. Q., Ma, L. L., Ma, X. H., Mao, J. R., Min, Z., Mitthumsiri, W., Mu, H. J., Nan, Y. C., Neronov, A., Ou, Z. W., Pang, B. Y., Pattarakijwanich, P., Pei, Z. Y., Qi, M. Y., Qi, Y. Q., Qiao, B. Q., Qin, J. J., Ruffolo, D., Sáiz, A., Semikoz, D., Shao, C. Y., Shao, L., Shchegolev, O., Sheng, X. D., Shu, F. W., Song, H. C., Stenkin, Yu. V., Stepanov, V., Su, Y., Sun, Q. N., Sun, X. N., Sun, Z. B., Tam, P. H. T., Tang, Q. W., Tang, Z. B., Tian, W. W., Wang, C., Wang, C. B., Wang, G. W., Wang, H. G., Wang, H. H., Wang, J. C., Wang, K., Wang, L. P., Wang, L. Y., Wang, P. H., Wang, R., Wang, W., Wang, X. G., Wang, X. Y., Wang, Y., Wang, Y. D., Wang, Y. J., Wang, Z. H., Wang, Z. X., Wang, Zhen, Wang, Zheng, Wei, D. M., Wei, J. J., Wei, Y. J., Wen, T., Wu, C. Y., Wu, H. R., Wu, S., Wu, X. F., Wu, Y. S., Xi, S. Q., Xia, J., Xia, J. J., Xiang, G. M., Xiao, D. X., Xiao, G., Xin, G. G., Xin, Y. L., Xing, Y., Xiong, Z., Xu, D. L., Xu, R. F., Xu, R. X., Xu, W. L., Xue, L., Yan, D. H., Yan, J. Z., Yan, T., Yang, C. W., Yang, F., Yang, F. F., Yang, H. W., Yang, J. Y., Yang, L. L., Yang, M. J., Yang, R. Z., Yang, S. B., Yao, Y. H., Yao, Z. G., Ye, Y. M., Yin, L. Q., Yin, N., You, X. H., You, Z. Y., Yu, Y. H., Yuan, Q., Yue, H., Zeng, H. D., Zeng, T. X., Zeng, W., Zha, M., Zhang, B. B., Zhang, F., Zhang, H. M., Zhang, H. Y., Zhang, J. L., Zhang, L. X., Zhang, Li, Zhang, P. F., Zhang, P. P., Zhang, R., Zhang, S. B., Zhang, S. R., Zhang, S. S., Zhang, X., Zhang, X. P., Zhang, Y. F., Zhang, Yi, Zhang, Yong, Zhao, B., Zhao, J., Zhao, L., Zhao, L. Z., Zhao, S. P., Zheng, F., Zhou, B., Zhou, H., Zhou, J. N., Zhou, M., Zhou, P., Zhou, R., Zhou, X. X., Zhu, C. G., Zhu, F. R., Zhu, H., Zhu, K. J., Zuo., X.
Publikováno v:
The Astrophysical Journal Supplement Series, 271 (2024) 25
We present the first catalog of very-high energy and ultra-high energy gamma-ray sources detected by the Large High Altitude Air Shower Observatory (LHAASO). The catalog was compiled using 508 days of data collected by the Water Cherenkov Detector Ar
Externí odkaz:
http://arxiv.org/abs/2305.17030
Autor:
Wang, Ding, Wang, Xuhong, Chen, Liang, Yao, Shengyue, Jing, Ming, Li, Honghai, Li, Li, Bao, Shiqiang, Wang, Fei-Yue, Lin, Yilun
Traffic simulation is a crucial tool for transportation decision-making and policy development. However, achieving realistic simulations in the face of the high dimensionality and heterogeneity of traffic environments is a longstanding challenge. In
Externí odkaz:
http://arxiv.org/abs/2305.15743
Efficient traffic management is crucial for maintaining urban mobility, especially in densely populated areas where congestion, accidents, and delays can lead to frustrating and expensive commutes. However, existing prediction methods face challenges
Externí odkaz:
http://arxiv.org/abs/2305.14826
Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a sin
Externí odkaz:
http://arxiv.org/abs/2305.12782
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations, such as prov
Externí odkaz:
http://arxiv.org/abs/2305.13626