Imagen de Portada

CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Haotian, Hu, Yue, Zhu, Zhengqiu, Gao, Chen, Wang, Ziyou, Rao, Junreng, Lu, Wenhao, Li, Weishi, Yin, Quanjun, Li, Yong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation
por: Xu, Haotian, et al.
Publicado: (2025)

Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology
por: Ji, Yatai, et al.
Publicado: (2025)

UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces
por: Zhao, Baining, et al.
Publicado: (2025)

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
por: Zhao, Yong, et al.
Publicado: (2025)

Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution
por: Liu, Beidan, et al.
Publicado: (2025)

NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
por: Yuan, Fang, et al.
Publicado: (2025)

Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation
por: Chen, Bin, et al.
Publicado: (2026)

Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events
por: Liu, Mengzhu, et al.
Publicado: (2025)

Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMs
por: Anand, Dhruv, et al.
Publicado: (2025)

The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study
por: Zhang, Weichen, et al.
Publicado: (2025)

Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing
por: Zhao, Yong, et al.
Publicado: (2024)

Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach
por: Zhu, Zhengqiu, et al.
Publicado: (2024)

DLW-CI: A Dynamic Likelihood-Weighted Cooperative Infotaxis Approach for Multi-Source Search in Urban Environments Using Consumer Drone Networks
por: Zhang, Xiaoran, et al.
Publicado: (2025)

CityRiSE: Reasoning Urban Socio-Economic Status in Vision-Language Models via Reinforcement Learning
por: Liu, Tianhui, et al.
Publicado: (2025)

CityGPT: Empowering Urban Spatial Cognition of Large Language Models
por: Feng, Jie, et al.
Publicado: (2024)

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
por: Zhang, Jun, et al.
Publicado: (2025)

Clash of the Titans: ultra-high energy KM3NeT event versus IceCube data
por: Li, Shirley Weishi, et al.
Publicado: (2025)

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
por: Gao, Chen, et al.
Publicado: (2024)

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models
por: Zhang, Jiahuan, et al.
Publicado: (2025)

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
por: Lee, Youngwan, et al.
Publicado: (2026)

SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments
por: Li, Tianshun, et al.
Publicado: (2025)

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
por: Jia, Mengdi, et al.
Publicado: (2025)

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning
por: Zhao, Baining, et al.
Publicado: (2025)

Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
por: He, Lixuan, et al.
Publicado: (2025)

UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
por: Feng, Jie, et al.
Publicado: (2025)

CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing
por: Liu, Tianhui, et al.
Publicado: (2025)

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
por: Huang, Xinmiao, et al.
Publicado: (2025)

A Multi-Agent Reinforcement Learning Approach for Cooperative Air-Ground-Human Crowdsensing in Emergency Rescue
por: Lu, Wenhao, et al.
Publicado: (2025)

How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace
por: Zhao, Baining, et al.
Publicado: (2026)

DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation
por: Liu, Ting, et al.
Publicado: (2023)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
por: Wang, Wei, et al.
Publicado: (2026)

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
por: Zhao, Yanpeng, et al.
Publicado: (2026)

SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments
por: Jiang, Wen, et al.
Publicado: (2026)

Chinese Digital Economy and Urban Green Innovation Quality and Efficiency: The Threshold Effect Analysis Based on Chinese Cities Agglomeration
por: Li Yue, et al.
Publicado: (2025)

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
por: Li, Hongxing, et al.
Publicado: (2025)

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
por: Liu, Ting, et al.
Publicado: (2024)

UrbanWorld: An Urban World Model for 3D City Generation
por: Shang, Yu, et al.
Publicado: (2024)

Self-test loss functions for learning weak-form operators and gradient flows
por: Gao, Yuan, et al.
Publicado: (2024)

MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers
por: Tian, Yang, et al.
Publicado: (2025)

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
por: Jin, Song, et al.
Publicado: (2026)