← Back to all news
arXiv AI

AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario

arXiv:2506. 16898v2 Announce Type: replace Abstract: Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood.

Related stories

arXiv AI
Jun 8

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

arXiv:2606. 07172v1 Announce Type: cross Abstract: Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning.

By Marcelo Sartori Locatelli, Fernando Tonucci, Jea Kwon, Luiz Felipe Vecchietti, Bryan Nathanael Wijaya, Cheng Yaw Low, Virgilio Almeida, Meeyoung Cha
llmsmultimodal
More like this →
arXiv Machine Learning
Aug 19

MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models

MoRAX is a lightweight framework that augments geospatial foundation model embeddings with functional structure derived from human mobility data. By incorporating mobility flows, MoRAX preserves the coverage and consistency of existing geospatial models while adding information about functional connectivity among urban regions, enabling zero‑shot deployment in unseen cities. Experiments across four cities in two countries show that the MoRAX teacher model outperforms baseline geospatial models on eight socioeconomic and environmental prediction tasks, and the student model—without direct mobility input—approaches the teacher’s performance.

By Ya Wen, Jixuan Cai, Yulun Zhou, Alec Kirkley
rag
More like this →
arXiv AI
Aug 19

MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale

MoRA is a human‑centric geospatial representation learning framework that uses a large mobility graph as its backbone to fuse spatial tokenization, graph neural networks, and asymmetric contrastive learning. It aligns over 100 million points of interest, massive remote sensing imagery, and structured demographic data with a billion‑edge mobility graph, producing compact 128‑dimensional embeddings that capture socio‑economic context and functional roles of locations. On a benchmark of nine downstream social and economic prediction tasks, MoRA outperforms state‑of‑the‑art models by an average of 12.9% and demonstrates scaling behavior analogous to large language models.

By Ya Wen, Jixuan Cai, Qiyao Ma, Linyan Li, Xinhua Chen, Chris Webster, Yulun Zhou
llmsragnlpbenchmarks
More like this →
arXiv Computer Vision
6d ago

AlphaEarth distinguishes cities but compresses urban variation

AlphaEarth, a satellite foundation model, maps Earth’s surface into numerical embeddings that allow comparison across places and time. An audit of its representations for 1,000 urban areas in 162 countries shows that cities occupy a distinct but overlapping region on the hypersphere, with continent, climate, and degrees of urbanisation explaining a portion of the variation. The study finds that cities in developing countries exhibit less contrast in vegetation and texture, and that annual changes in a city’s representation are largely driven by model updates rather than pixel changes.

By Andrew Renninger
rag
More like this →