Zobrazeno 1 - 10
of 1 626
pro vyhledávání: '"LI Shaobo"'
Autor:
Xue, Chunyu, Cui, Weihao, Zhao, Han, Chen, Quan, Zhang, Shulai, Yang, Pengyu, Yang, Jing, Li, Shaobo, Guo, Minyi
Joint consideration of scheduling and adaptive parallelism offers great opportunities for improving the training efficiency of large models on heterogeneous GPU clusters. However, integrating adaptive parallelism into a cluster scheduler expands the
Externí odkaz:
http://arxiv.org/abs/2403.16125
Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. Most existing long-tailed classification methods focus only on solving the class-wise imbalance while ignoring the attribute-wise imbalance. The deviation of
Externí odkaz:
http://arxiv.org/abs/2310.08206
Publikováno v:
Hangkong bingqi, Vol 31, Iss 5, Pp 56-66 (2024)
Facing the increasing complexity of aerial combat environments and challenges to the survivability of air platforms from new combat methods, it is necessary to adopt new hard-kill methods to counter advanced air-to-air missiles. In order to improve t
Externí odkaz:
https://doaj.org/article/045a32e2504e489fb59204d5557d2d0c
Publikováno v:
Shipin Kexue, Vol 45, Iss 19, Pp 317-331 (2024)
Monitoring of food chemical hazards (FCHs) is crucial to ensure food quality and safety. Non-targeted screening (NTS) is an effective technique to identify a wide range of potential and unknown FCHs using high performance liquid chromatography/high p
Externí odkaz:
https://doaj.org/article/5c572eca276446feaf120dc1293a8305
This paper is motivated by the analysis of a survey study of college student wellbeing before and after the outbreak of the COVID-19 pandemic. A statistical challenge in well-being survey studies lies in that outcome variables are often recorded in d
Externí odkaz:
http://arxiv.org/abs/2306.05362
Autor:
Liu, Hongwei, Yang, Jian, Zhang, Jianfeng, Shao, Dongheng, Guo, Jielong, Li, Shaobo, Tang, Xuan, Wei, Xian
Recently, 3D object detection has attracted significant attention and achieved continuous improvement in real road scenarios. The environmental information is collected from a single sensor or multi-sensor fusion to detect interested objects. However
Externí odkaz:
http://arxiv.org/abs/2304.13390
Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labeled nodes used by GCNs may lead to unstable
Externí odkaz:
http://arxiv.org/abs/2301.04381
In modern solid-state drives (SSDs), the indexing of flash pages is a critical component in their storage controllers. It not only affects the data access performance, but also determines the efficiency of the precious in-device DRAM resource. A vari
Externí odkaz:
http://arxiv.org/abs/2301.00072
Autor:
Li, Shaobo, Li, Xiaoguang, Shang, Lifeng, Sun, Chengjie, Liu, Bingquan, Ji, Zhenzhou, Jiang, Xin, Liu, Qun
Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge. To miti
Externí odkaz:
http://arxiv.org/abs/2210.11165
Publikováno v:
Shipin Kexue, Vol 45, Iss 8, Pp 257-264 (2024)
In this study, we established a method for the determination of three metabolic regulators including clomiphene, trimetazidine and meldonium in foods by pass-through solid phase extraction combined with ultra-high performance liquid chromatography-ta
Externí odkaz:
https://doaj.org/article/91bfefc9bef54da9bf7e3f673e73dd46