Výsledky vyhledávání - "Mao, Junyuan"

Report

NetSafe: Exploring the Topological Safety of Multi-agent Networks

Autor: Yu, Miao, Wang, Shilong, Zhang, Guibin, Mao, Junyuan, Yin, Chenlong, Liu, Qijiong, Wen, Qingsong, Wang, Kun, Wang, Yang

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information remains unexplor

Externí odkaz: http://arxiv.org/abs/2410.15686

Zobrazit plný text záznamu

Report

Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia

Autor: Yu, Miao, Mao, Junyuan, Zhang, Guibin, Ye, Jingheng, Fang, Junfeng, Zhong, Aoxiao, Liu, Yang, Liang, Yuxuan, Wang, Kun, Wen, Qingsong

Research into the external behaviors and internal mechanisms of large language models (LLMs) has shown promise in addressing complex tasks in the physical world. Studies suggest that powerful LLMs, like GPT-4, are beginning to exhibit human-like cogn

Externí odkaz: http://arxiv.org/abs/2410.01677

Zobrazit plný text záznamu

Report

Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model

Autor: Duan, Yifan, Zhao, Jian, pengcheng, Mao, Junyuan, Wu, Hao, Xu, Jingyu, Wang, Shilong, Ma, Caoyuan, Wang, Kai, Wang, Kun, Li, Xuelong

Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in n

Externí odkaz: http://arxiv.org/abs/2409.19608

Zobrazit plný text záznamu

Report

CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks

Autor: Duan, Yifan, Zhang, Guibin, Wang, Shilong, Peng, Xiaojiang, Ziqi, Wang, Mao, Junyuan, Wu, Hao, Jiang, Xinke, Wang, Kun

Credit card fraud poses a significant threat to the economy. While Graph Neural Network (GNN)-based fraud detection methods perform well, they often overlook the causal effect of a node's local structure on predictions. This paper introduces a novel

Externí odkaz: http://arxiv.org/abs/2402.14708

Zobrazit plný text záznamu