UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
Paper
•
2506.23219
•
Published
•
7
Urban Spatial Intelligence
-
-
CityGPT: Empowering Urban Spatial Cognition of Large Language Models
Paper • 2406.13948 • Published • 1 -
CityBench: Evaluating the Capabilities of Large Language Model as World Model
Paper • 2406.13945 • Published • 1 -
A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science
Paper • 2504.09848 • Published -
CityLens: Benchmarking Large Language-Vision Models for Urban Socioeconomic Sensing
Paper • 2506.00530 • Published • 2 -
CityRiSE: Reasoning Urban Socio-Economic Status in Vision-Language Models via Reinforcement Learning
Paper • 2510.22282 • Published • 2 -
AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction
Paper • 2408.13986 • Published -
CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulation
Paper • 2506.13599 • Published • 3 -
Tianhui-Liu/CityGPT-Data
Preview • Updated • 38 -
EmbodiedCity/UrbanVideo-Bench
Viewer • Updated • 5.36k • 3k • 8 -
3D Question Answering for City Scene Understanding
Paper • 2407.17398 • Published • 22 -
OpenCity3D: What do Vision-Language Models know about Urban Environments?
Paper • 2503.16776 • Published • 3 -
ai4ce/CityWalker
Preview • Updated • 130 • 6 -
ivc-lrp/STSBench
Viewer • Updated • 971 • 64 • 4 -
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
Paper • 2412.06781 • Published • 23 -
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
Paper • 2507.19586 • Published -
suhaisheng0527/RoboSense
Updated • 969 • 4 -
Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
Paper • 2506.19433 • Published • 3 -
z-hb/OpenSatMap
Updated • 898 • 10 -
Reconstructing 4D Spatial Intelligence: A Survey
Paper • 2507.21045 • Published • 35 -
EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion
Paper • 2507.16535 • Published • 20 -
spatialverse/InteriorGS
Updated • 13.4k • 146 -
WINDop/OpenGPT-4o-Image
Updated • 1.05k • 18 -
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
Paper • 2511.15705 • Published • 93 -
jise/simworld-20k-balanced
Viewer • Updated • 3.31k • 415 • 6