Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Zhang, Jize"'
Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs' applicat
Externí odkaz:
http://arxiv.org/abs/2409.18009
This paper introduces a novel approach to integrating large language model (LLM) agents into automated production systems, aimed at enhancing task automation and flexibility. We organize production operations within a hierarchical framework based on
Externí odkaz:
http://arxiv.org/abs/2407.08550
Autor:
Cheng, Hao, Xiao, Erjia, Yang, Jiayan, Cao, Jiahang, Zhang, Qiang, Yang, Le, Zhang, Jize, Xu, Kaidi, Gu, Jindong, Xu, Renjing
Recently, Multimodal Large Language Models (MLLMs) achieve remarkable performance in numerous zero-shot tasks due to their outstanding cross-modal interaction and comprehension abilities. However, MLLMs are found to still be vulnerable to human-imper
Externí odkaz:
http://arxiv.org/abs/2405.20090
Autor:
Cheng, Hao, Xiao, Erjia, Gu, Jindong, Yang, Le, Duan, Jinhao, Zhang, Jize, Cao, Jiahang, Xu, Kaidi, Xu, Renjing
Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which disrupt Visio
Externí odkaz:
http://arxiv.org/abs/2402.19150
Autor:
Cheng, Hao, Cao, Jiahang, Xiao, Erjia, Sun, Mengshu, Yang, Le, Zhang, Jize, Lin, Xue, Kailkhura, Bhavya, Xu, Kaidi, Xu, Renjing
Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial neural networks (ANNs). To facilitate deployment on memory-constraine
Externí odkaz:
http://arxiv.org/abs/2311.12060
Autor:
Cheng, Hao, Duan, Jinhao, Li, Hui, Zhang, Lyutianyang, Cao, Jiahang, Wang, Ping, Zhang, Jize, Xu, Kaidi, Xu, Renjing
Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with the previous convolution-based structures, the Transformer-based struc
Externí odkaz:
http://arxiv.org/abs/2309.13245
Publikováno v:
In Reliability Engineering and System Safety November 2024 251
Publikováno v:
In Coastal Engineering October 2024 193
Existing unpaired low-light image enhancement approaches prefer to employ the two-way GAN framework, in which two CNN generators are deployed for enhancement and degradation separately. However, such data-driven models ignore the inherent characteris
Externí odkaz:
http://arxiv.org/abs/2112.13107
Imputation of missing data is a task that plays a vital role in a number of engineering and science applications. Often such missing data arise in experimental observations from limitations of sensors or post-processing transformation errors. Other t
Externí odkaz:
http://arxiv.org/abs/2111.02823