Výsledky vyhledávání

Report

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Autor: Hu, Xueyu, Zhao, Ziyu, Wei, Shuang, Chai, Ziwei, Ma, Qianli, Wang, Guoyin, Wang, Xuwu, Su, Jing, Xu, Jingjing, Zhu, Ming, Cheng, Yao, Yuan, Jianbo, Li, Jiwei, Kuang, Kun, Yang, Yang, Yang, Hongxia, Wu, Fei

In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks. These tasks require agents to end-to-end solving complex tasks by interacting with an execution environment.

Externí odkaz: http://arxiv.org/abs/2401.05507

Zobrazit plný text záznamu

Report

Comprehending Semantic Types in JSON Data with Graph Neural Networks

Autor: Wei, Shuang, Mior, Michael J.

Semantic types are a more powerful and detailed way of describing data than atomic types such as strings or integers. They establish connections between columns and concepts from the real world, providing more nuanced and fine-grained information tha

Externí odkaz: http://arxiv.org/abs/2307.12807

Zobrazit plný text záznamu

Report

Security Enhancement of Quantum Noise Stream Cipher Based on Probabilistic Constellation Shaping

Autor: Liu, Sheng, Wei, Shuang, Wang, Wei, Lei, Chao, Liu, Tianhe, Li, Yajie, Li, Yunbo, Ge, Dawei, Wang, Dong, Zhao, Yongli, Zhang, Dechao, Li, Han, Zhang, Jie

We propose a QNSC pre-coding scheme based on probabilistic shaping of the basis, to reduce the probability of ciphertext bits that are easier to be intercepted. Experiment results show this scheme can improve the security performance by 100% in terms

Externí odkaz: http://arxiv.org/abs/2305.09152

Zobrazit plný text záznamu