Zobrazeno 1 - 10
of 528
pro vyhledávání: '"Huang Zhichao"'
Publikováno v:
e-Polymers, Vol 24, Iss 1, Pp 109925-105 (2024)
The use of composite laminates is characterized by problems such as poor inter-layer bonding and susceptibility of material properties to fatigue cracking, which seriously threaten structural safety. Research on fatigue damage characteristics and fat
Externí odkaz:
https://doaj.org/article/b3dc06e6e4714fda90653a3f4188962e
In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by professional human interpreters, we utilize a novel data-driven read-write
Externí odkaz:
http://arxiv.org/abs/2407.21646
Graph classification is a pivotal challenge in machine learning, especially within the realm of graph-based data, given its importance in numerous real-world applications such as social network analysis, recommendation systems, and bioinformatics. De
Externí odkaz:
http://arxiv.org/abs/2407.01886
Publikováno v:
Nanophotonics, Vol 9, Iss 7, Pp 2025-2032 (2020)
The design of sulfur hosts with polar, sulfurphilic, and conductive network is critical to lithium-sulfur (Li-S) batteries whose potential applications are greatly limited by the lithium polysulfide shuttle effect. Mxenes, possessing layered-stacked
Externí odkaz:
https://doaj.org/article/f5e43bca605c4dad994fc5a838dcd843
Autor:
Ding, Daijun, Dong, Li, Huang, Zhichao, Xu, Guangning, Huang, Xu, Liu, Bo, Jing, Liwen, Zhang, Bowen
Stance detection aims to determine the attitude expressed in text towards a given target. Zero-shot stance detection (ZSSD) has emerged to classify stances towards unseen targets during inference. Recent data augmentation techniques for ZSSD increase
Externí odkaz:
http://arxiv.org/abs/2403.15715
Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained LLM. By integrating the large language model (LLM) with a
Externí odkaz:
http://arxiv.org/abs/2312.13585
With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization gives rise to a loss of information, consequently impairing overall perfo
Externí odkaz:
http://arxiv.org/abs/2309.00169
Publikováno v:
Gong-kuang zidonghua, Vol 41, Iss 11, Pp 60-64 (2015)
In view of problem that negative sequence components in unbalanced coal mine power system affect stable running of electric locomotive, and in order to satisfy control strategy of three-phase PWM rectifier, the characteristics of asymmetric signal un
Externí odkaz:
https://doaj.org/article/74888af24c2d4fd7bb0a8f6e8e2711d8
Autor:
Huang, Zhichao, Fan, Yanbo, Liu, Chen, Zhang, Weizhong, Zhang, Yong, Salzmann, Mathieu, Süsstrunk, Sabine, Wang, Jue
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent wor
Externí odkaz:
http://arxiv.org/abs/2206.02417
Publikováno v:
In Materials Today Communications December 2024 41