Zobrazeno 1 - 10
of 137
pro vyhledávání: '"Lv, Hairong"'
Offering rich contexts to Large Language Models (LLMs) has shown to boost the performance in various tasks, but the resulting longer prompt would increase the computational cost and might exceed the input limit of LLMs. Recently, some prompt compress
Externí odkaz:
http://arxiv.org/abs/2409.15395
Molecular property prediction is a crucial foundation for drug discovery. In recent years, pre-trained deep learning models have been widely applied to this task. Some approaches that incorporate prior biological domain knowledge into the pre-trainin
Externí odkaz:
http://arxiv.org/abs/2408.10124
Autor:
Zhang, Tianyu, Hou, Chengbin, Jiang, Rui, Zhang, Xuegong, Zhou, Chenghu, Tang, Ke, Lv, Hairong
Node Importance Estimation (NIE) is a task of inferring importance scores of the nodes in a graph. Due to the availability of richer data and knowledge, recent research interests of NIE have been dedicating to knowledge graphs for predicting future o
Externí odkaz:
http://arxiv.org/abs/2402.17791
Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged. However, the statistical heterogeneity challenge on non-IID data, such as class imbalance in clas
Externí odkaz:
http://arxiv.org/abs/2304.04972
Publikováno v:
Methods in Ecology and Evolution, 14, 3020-3034 (2023)
Identification of fossil species is crucial to evolutionary studies. Recent advances from deep learning have shown promising prospects in fossil image identification. However, the quantity and quality of labeled fossil images are often limited due to
Externí odkaz:
http://arxiv.org/abs/2302.08062
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations. Nonetheless, for downstream inference, CLIP-like models suffer from either 1) degraded accuracy and robustnes
Externí odkaz:
http://arxiv.org/abs/2210.04287
Training multiple deep neural networks (DNNs) and averaging their outputs is a simple way to improve the predictive performance. Nevertheless, the multiplied training cost prevents this ensemble method to be practical and efficient. Several recent wo
Externí odkaz:
http://arxiv.org/abs/2110.00959
Autor:
Wang, Shu, Zhu, Yunqiang, Qi, Yanmin, Hou, Zhiwei, Sun, Kai, Li, Weirong, Hu, Lei, Yang, Jie, Lv, Hairong
Publikováno v:
In Geoscience Frontiers September 2023 14(5)
Autor:
Wang, Tianheng, Zheng, Ling, Lv, Hairong, Zhou, Chenghu, Shen, Yunheng, Qiu, Qinjun, Li, Yan, Li, Pufan, Wang, Guorui
Publikováno v:
In Expert Systems With Applications 1 March 2023 213 Part C
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.