# CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities

arXiv: https://arxiv.org/abs/2605.26036 · HTML: https://mlsanity.com/paper/2605.26036/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 17 of 17)

- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery](https://mlsanity.com/paper/2311.17179/) (2023)
- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [A Review of Location Encoding for GeoAI: Methods and Applications](https://mlsanity.com/paper/2111.04006/) (2021)
- [Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding](https://mlsanity.com/paper/2001.11101/) (2020)
- [Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions](https://mlsanity.com/paper/2306.17624/) (2023)
- [TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis](https://mlsanity.com/paper/2506.20380/) (2025)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Importance of spatial predictor variable selection in machine learning applications -- Moving from data reproduction to spatial prediction](https://mlsanity.com/paper/1908.07805/) (2019)
- [City Foundation Models for Learning General Purpose Representations from OpenStreetMap](https://mlsanity.com/paper/2310.00583/) (2023)
- [MuseCL: Predicting Urban Socioeconomic Indicators via Multi-Semantic Contrastive Learning](https://mlsanity.com/paper/2407.09523/) (2024)
- [Enriching Location Representation with Detailed Semantic Information](https://mlsanity.com/paper/2506.02744/) (2025)
- [MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale](https://mlsanity.com/paper/2506.01297/) (2025)
- [OBSR: Open Benchmark for Spatial Representations](https://mlsanity.com/paper/2510.05879/) (2025)

## Built on by (most cited first, 5 of 5)

- [TESSERA v2: Scaling Pixel-wise Earth Foundation Models](https://mlsanity.com/paper/2607.03949/) (2026)
- [LE4Mob: Towards Inductive, Distance-Aware and General-Purpose Location Embedding for Human Mobility Modelling](https://mlsanity.com/paper/2609.22117/) (2026)
- [Modelling daily activity patterns from mobile phone location data via deep representation learning](https://mlsanity.com/paper/2609.22121/) (2026)
- [Annual Earth-observation embeddings encode wildfire disturbance and support simplified burned area mapping](https://mlsanity.com/paper/2609.25731/) (2026)
- [AlphaEarth distinguishes cities but compresses urban variation](https://mlsanity.com/paper/2609.30356/) (2026)

## Abstract (arXiv)

Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.