Zobrazeno 1 - 10
of 7 278
pro vyhledávání: '"Li Xiaoli"'
Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a given question. Retrieval is a widely adopted approach, including two general paradigms: Retrieval-Then-Read (RTR) and post-hoc retr
Externí odkaz:
http://arxiv.org/abs/2410.16708
Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approa
Externí odkaz:
http://arxiv.org/abs/2410.09123
In knowledge graph embedding, aside from positive triplets (ie: facts in the knowledge graph), the negative triplets used for training also have a direct influence on the model performance. In reality, since knowledge graphs are sparse and incomplete
Externí odkaz:
http://arxiv.org/abs/2410.07592
Autor:
Aung, Aye Phyu Phyu, Wang, Xinrun, Wang, Ruiyu, Chan, Hau, An, Bo, Li, Xiaoli, Senthilnath, J.
In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GA
Externí odkaz:
http://arxiv.org/abs/2410.04764
Source-Free Unsupervised Domain Adaptation (SFUDA) has gained popularity for its ability to adapt pretrained models to target domains without accessing source domains, ensuring source data privacy. While SFUDA is well-developed in visual tasks, its a
Externí odkaz:
http://arxiv.org/abs/2409.19635
Remaining Useful Life (RUL) prediction is a critical aspect of Prognostics and Health Management (PHM), aimed at predicting the future state of a system to enable timely maintenance and prevent unexpected failures. While existing deep learning method
Externí odkaz:
http://arxiv.org/abs/2409.19629
Unsupervised Domain Adaptation (UDA) has emerged as a key solution in data-driven fault diagnosis, addressing domain shift where models underperform in changing environments. However, under the realm of continually changing environments, UDA tends to
Externí odkaz:
http://arxiv.org/abs/2407.17117
Autor:
Li, Zhilin, Zhao, Yongheng, Hu, Yiqing, Li, Yang, Zhang, Keyao, Gao, Zhibing, Tan, Lirou, Liu, Hanli, Li, Xiaoli, Cao, Aihua, Cui, Zaixu, Zhao, Chenguang
Background: The use of near-infrared lasers for transcranial photobiomodulation (tPBM) offers a non-invasive method for influencing brain activity and is beneficial for various neurological conditions. Objective: To investigate the safety and neuropr
Externí odkaz:
http://arxiv.org/abs/2407.09922
Autor:
Xu, Kaixin, Feng, Qingtian, Chen, Hao, Wang, Zhe, Geng, Xue, Yang, Xulei, Wu, Min, Li, Xiaoli, Lin, Weisi
Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and robotics. However, as neural network models and 3D point clouds expand
Externí odkaz:
http://arxiv.org/abs/2407.02098
Autor:
Xu, Kaixin, Wang, Zhe, Chen, Chunyun, Geng, Xue, Lin, Jie, Yang, Xulei, Wu, Min, Li, Xiaoli, Lin, Weisi
Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature,
Externí odkaz:
http://arxiv.org/abs/2407.02068