Zobrazeno 1 - 10
of 675
pro vyhledávání: '"Yang Jiayu"'
Publikováno v:
Tongxin xuebao, Vol 45, Pp 151-164 (2024)
To address transmission failures in traditional Ad Hoc networks, which was caused by highly dynamic topologies, short-lived connections characteristics, a reliable forwarding strategy based on link stability and content accessibility forwarding (RF-L
Externí odkaz:
https://doaj.org/article/6e23d5ada0dc4477bd036db4df4ae084
Publikováno v:
Nanophotonics, Vol 11, Iss 9, Pp 2117-2127 (2021)
The development of information technology urgently requires ultrafast, ultra-low energy consumption and ultra-high-capacity data computing abilities. Traditional computing method of electronic chips is limited by the bottleneck of Moore’s Law. All-
Externí odkaz:
https://doaj.org/article/a69648271f6e489cba96cd66fa0f6d76
In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame redundancy. Howeve
Externí odkaz:
http://arxiv.org/abs/2412.00446
The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust. Explainable Ar
Externí odkaz:
http://arxiv.org/abs/2411.16512
Concept Bottleneck Models (CBMs) enhance model interpretability by introducing human-understandable concepts within the architecture. However, existing CBMs assume static datasets, limiting their ability to adapt to real-world, continuously evolving
Externí odkaz:
http://arxiv.org/abs/2411.17471
Large Language Models (LLMs) are powerful tools for text generation, translation, and summarization, but they often suffer from hallucinations-instances where they fail to maintain the fidelity and coherence of contextual information during decoding,
Externí odkaz:
http://arxiv.org/abs/2410.20340
Autor:
Lai, Songning, Yang, Jiayu, Huang, Yu, Hu, Lijie, Xue, Tianlang, Hu, Zhangyi, Li, Jiaxu, Liao, Haicheng, Yue, Yutao
Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs) have emerg
Externí odkaz:
http://arxiv.org/abs/2410.04823
Time series forecasting has become an increasingly popular research area due to its critical applications in various real-world domains such as traffic management, weather prediction, and financial analysis. Despite significant advancements, existing
Externí odkaz:
http://arxiv.org/abs/2406.05036
Autor:
Lai, Songning, Feng, Ninghui, Gao, Jiechao, Wang, Hao, Sui, Haochen, Zou, Xin, Yang, Jiayu, Chen, Wenshuo, Zhao, Hang, Hu, Xuming, Yue, Yutao
Publikováno v:
IJCAI2024 workshop
The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance. However, an analysis reveals certain unfaithfulness issue
Externí odkaz:
http://arxiv.org/abs/2405.19647
Autor:
Xin, C. J., Lu, Shengyuan, Yang, Jiayu, Shams-Ansari, Amirhassan, Desiatov, Boris, Magalhães, Letícia S., Ghosh, Soumya S., McGee, Erin, Renaud, Dylan, Achuthan, Nicholas, Zvyagintsev, Arseniy, Barton III, David, Sinclair, Neil, Lončar, Marko
Recent advancements in thin-film lithium niobate (TFLN) photonics have led to a new generation of high-performance electro-optic devices, including modulators, frequency combs, and microwave-to-optical transducers. However, the broader adoption of TF
Externí odkaz:
http://arxiv.org/abs/2404.12381