Výsledky vyhledávání - "Xu, Liuchang"

Report

ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing

Autor: Lin, Qingming, Hu, Rui, Li, Huaxia, Wu, Sensen, Li, Yadong, Fang, Kai, Feng, Hailin, Du, Zhenhong, Xu, Liuchang

Vector data is one of the two core data structures in geographic information science (GIS), essential for accurately storing and representing geospatial information. Shapefile, the most widely used vector data format, has become the industry standard

Externí odkaz: http://arxiv.org/abs/2410.12376

Zobrazit plný text záznamu

Report

ControlCity: A Multimodal Diffusion Model Based Approach for Accurate Geospatial Data Generation and Urban Morphology Analysis

Autor: Zhou, Fangshuo, Li, Huaxia, Hu, Rui, Wu, Sensen, Feng, Hailin, Du, Zhenhong, Xu, Liuchang

Volunteer Geographic Information (VGI), with its rich variety, large volume, rapid updates, and diverse sources, has become a critical source of geospatial data. However, VGI data from platforms like OSM exhibit significant quality heterogeneity acro

Externí odkaz: http://arxiv.org/abs/2409.17049

Zobrazit plný text záznamu

Report

Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study

Autor: Xu, Liuchang, Zhao, Shuo, Lin, Qingming, Chen, Luyao, Luo, Qianqian, Wu, Sensen, Ye, Xinyue, Feng, Hailin, Du, Zhenhong

The advent of large language models such as ChatGPT, Gemini, and others has underscored the importance of evaluating their diverse capabilities, ranging from natural language understanding to code generation. However, their performance on spatial tas

Externí odkaz: http://arxiv.org/abs/2408.14438

Zobrazit plný text záznamu