3 papers were presented at this group meeting.
| Paper and research focus | Presenter | Publication | Resources |
|---|---|---|---|
Analyzing the typology and livability of 15-minute travel at metro stations in high-density cities: A case study of Singapore | Cities 2025-03 | Not available | |
Modeling realistic human behavior using generative agents in a multimodal transport system: Software architecture and Application to Toulouse在真实、复杂的城市多模式交通系统中,系统性地将大语言模型驱动的生成式智能体与成熟的空间仿真平台 GAMA 进行深度集成,并通过 城市交通真实运行数据 与 OpenTripPlanner模块 构建了一个可运行、可学习、可形成出行习惯的人类出行行为仿真框架。 | arXiv 2025-10 | Not available | |
Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts本文创新点在于提出了一种基于图神经网络(GNN)的图表问答(CQA)模型,通过多模态图表示学习整合图表结构和问题文本,引入位置和结构编码以捕捉空间关系,使用图注意力网络(GAT)和图同构网络(GIN)高效处理图数据,并结合零样本学习(ZSL)解决词汇外(OOV)问题,以及硬负样本挖掘(HNM)提升模型鲁棒性。 | arXiv 2025-11 | Not available |