AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding

Xin Zhang, Tianjian Ouyang, Yu Shang, Qingmin Liao, Yong Li

ICML 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes UrbanMLLM, a unified multimodal LLM that jointly learns from satellite and street-view imagery for urban understanding.

Problem

Existing urban MLLMs rely mainly on satellite imagery, limiting capture of fine-grained street-level appearance and cross-view relationships needed for comprehensive urban understanding.

Approach

A single MLLM trained jointly on satellite and street-view imagery so it learns cross-view relationships between macroscopic spatial structure and street-level semantics.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the cross-view perceiver (ablation)UrbanMLLM-8B · Satellite multi-scene classificationF1: 0.720 -> 0.776Improved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Satellite scene classification (single)accuracy: 0.760 -> 0.787Improved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Satellite geo-localizationaccuracy: 0.844 -> 0.871Improved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Street-view landmark recognitionaccuracy: 0.753 -> 0.795Improved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Street-view geo-localizationaccuracy: 0.852 -> 0.879Improved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Street-view beautiful-level predictionaccuracy (margin 2): 0.834 -> 0.827Hurt
add the cross-view perceiver (ablation)UrbanMLLM-8B · Satellite tasks averageaverage performance: 3.04% drop when removedImproved
add the cross-view perceiver (ablation)UrbanMLLM-8B · Street-view tasks averageaverage performance: 1.54% drop when removedImproved
add interleaved pre-training (ablation)UrbanMLLM-8B · Satellite multi-scene classificationF1: 0.759 -> 0.776Improved
add interleaved pre-training (ablation)UrbanMLLM-8B · Satellite geo-localizationaccuracy: 0.846 -> 0.871Improved
add interleaved pre-training (ablation)UrbanMLLM-8B · Satellite spatial relationship reasoningaccuracy: 0.686 -> 0.664Hurt
add interleaved pre-training (ablation)UrbanMLLM-8B · Street-view geo-localizationaccuracy: 0.882 -> 0.879Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy