Výsledky vyhledávání - "Yang, Chengxu"

Report

Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing

Autor: Cheng, Gaofeng, Lu, Haitian, Yang, Chengxu, Wang, Xuyang, Li, Ta, Yan, Yonghong

Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation lexicons. In

Externí odkaz: http://arxiv.org/abs/2501.00804

Zobrazit plný text záznamu

Report

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

Autor: Liu, Xuan, Zhang, Jie, Guo, Song, Shang, Haoyang, Yang, Chengxu, Zhu, Quanyan

Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias; whether this is reflected in the decision-making process of LLM Agents remains under-explored. As LLM Agents are in

Externí odkaz: http://arxiv.org/abs/2405.14744

Zobrazit plný text záznamu

Report

On the distance-edge-monitoring numbers of graphs

Autor: Yang, Chengxu, Klasing, Ralf, Mao, Yaping, Deng, Xingchao

Foucaud et al. [Discrete Appl. Math. 319 (2022), 424-438] recently introduced and initiated the study of a new graph-theoretic concept in the area of network monitoring. For a set $M$ of vertices and an edge $e$ of a graph $G$, let $P(M, e)$ be the s

Externí odkaz: http://arxiv.org/abs/2211.04920

Zobrazit plný text záznamu

Report

Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data

Autor: Yang, Chengxu, Wang, Qipeng, Xu, Mengwei, Chen, Zhenpeng, Bian, Kaigui, Liu, Yunxin, Liu, Xuanzhe

Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in both academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and

Externí odkaz: http://arxiv.org/abs/2006.06983

Zobrazit plný text záznamu