Zobrazeno 1 - 10
of 174
pro vyhledávání: '"Yang, Kaiwen"'
Autor:
Yang, Kaiwen, Xu, Hao, Sun, Yunqing, Qian, Jiacheng, Zhou, Zihan, Zhang, Xiaoshuai, Liu, Erwu, Zhang, Lei, I, Chih-Lin
Blockchain technology holds promise for Web 3.0, but scalability remains a critical challenge. Here, we present a mathematical theory for a novel blockchain network topology based on fractal N-dimensional simplexes. This Hyper-simplex fractal network
Externí odkaz:
http://arxiv.org/abs/2410.00583
Autor:
Yang, Kaiwen, Shen, Tao, Tian, Xinmei, Geng, Xiubo, Tao, Chongyang, Tao, Dacheng, Zhou, Tianyi
Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level captions
Externí odkaz:
http://arxiv.org/abs/2312.01598
Though many deep learning (DL)-based vulnerability detection approaches have been proposed and indeed achieved remarkable performance, they still have limitations in the generalization as well as the practical usage. More precisely, existing DL-based
Externí odkaz:
http://arxiv.org/abs/2308.11237
Autor:
Yang, Kaiwen, Sun, Yanchao, Su, Jiahao, He, Fengxiang, Tian, Xinmei, Huang, Furong, Zhou, Tianyi, Tao, Dacheng
Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on automatic data augmentation learn a policy to form a sequence of augmentat
Externí odkaz:
http://arxiv.org/abs/2211.00824
Publikováno v:
Shanghai Jiaotong Daxue xuebao, Vol 58, Iss 5, Pp 760-775 (2024)
In recent years, in order to achieve the goal of “carbon peaking and carbon neutrality” of the electrified railway, a number of railroad energy optimization initiatives have been implemented, but with little success. To further reduce the carbon
Externí odkaz:
https://doaj.org/article/1d68c3475f9f4c538d78182d256e7b9b
Just-In-Time defect prediction (JIT-DP) models can identify defect-inducing commits at check-in time. Even though previous studies have achieved a great progress, these studies still have the following limitations: 1) useful information (e.g., semant
Externí odkaz:
http://arxiv.org/abs/2204.04856
Publikováno v:
In Displays December 2024 85
Autor:
Zhou, Hao, Leng, Ping, Wang, Yang, Yang, Kaiwen, Li, Chen, Ojcius, David M., Wang, Pengfei, Jiang, Shibo
Publikováno v:
In Science Bulletin 15 August 2024 69(15):2456-2470
Autor:
Yang, Kaiwen, Tian, Xinmei
Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial learning
Externí odkaz:
http://arxiv.org/abs/2106.15206