Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Hu, Renjun"'
Autor:
Li, Jiatong, Hu, Renjun, Huang, Kunzhe, Zhuang, Yan, Liu, Qi, Zhu, Mengxiao, Shi, Xing, Lin, Wei
Expert-designed close-ended benchmarks are indispensable in assessing the knowledge capacity of large language models (LLMs). Despite their widespread use, concerns have mounted regarding their reliability due to limited test scenarios and an unavoid
Externí odkaz:
http://arxiv.org/abs/2405.19740
Autor:
Yuan, Yifei, Shi, Chen, Wang, Runze, Chen, Liyi, Hu, Renjun, Zhang, Zengming, Jiang, Feijun, Lam, Wai
Generative query rewrite generates reconstructed query rewrites using the conversation history while rely heavily on gold rewrite pairs that are expensive to obtain. Recently, few-shot learning is gaining increasing popularity for this task, whereas
Externí odkaz:
http://arxiv.org/abs/2403.11873
Until recently, the question of the effective inductive bias of deep models on tabular data has remained unanswered. This paper investigates the hypothesis that arithmetic feature interaction is necessary for deep tabular learning. To test this point
Externí odkaz:
http://arxiv.org/abs/2402.02334
Autor:
Cheng, Yi, Ying, Haochao, Hu, Renjun, Wang, Jinhong, Zheng, Wenhao, Zhang, Xiao, Chen, Danny, Wu, Jian
Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the pe
Externí odkaz:
http://arxiv.org/abs/2305.04213
Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. However, the robustness of GNNs in the presence of label noise remains a largely under-explored problem. In this paper, we consider an important yet challenging
Externí odkaz:
http://arxiv.org/abs/2211.06614
Autor:
Hu, Renjun1,2 (AUTHOR), Jiang, Ripeng1,2 (AUTHOR) jiangrp@csu.edu.cn, Li, Ruiqing1,2 (AUTHOR), Li, Xiaoqian1,2,3 (AUTHOR), Zhou, Honghui1,2 (AUTHOR)
Publikováno v:
International Journal of Metalcasting. Apr2024, Vol. 18 Issue 2, p1710-1722. 13p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Hou, Junwei, Wu, Weichuang, Li, Lifu, Tong, Xin, Hu, Renjun, Wu, Weibin, Cai, Weizhi, Wang, Hailin
Publikováno v:
In Journal of Energy Storage 1 November 2022 55 Part A
This paper describes our solution for WSDM Cup 2016. Ranking the query independent importance of scholarly articles is a critical and challenging task, due to the heterogeneity and dynamism of entities involved. Our approach is called Ensemble enable
Externí odkaz:
http://arxiv.org/abs/1604.05462
Publikováno v:
IEEE Transactions on Industrial Electronics; September 2024, Vol. 71 Issue: 9 p11710-11715, 6p