CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6622-6631
Abstract
No abstract availableFunding Information
- the national key Research and Development Program of China (2024YFC3307602)
- The Guangdong Provincial Talent Program (2023JC10X009)
- the national key Research and Development Program of China (2024YFC3307603)
- the Zhongguancun Academy (XTS0074)
- Tsinghua-Toyota Joint Research Institute Inter-disciplinary Program (Toyota-Future City Simulator)
This publication has 17 references indexed in Scilit:
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling2026
- UrbanLLaVA: A Multi-Modal Large Language Model for Urban Intelligence2025
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- Profiling Urban Streets: A Semi-Supervised Prediction Model Based on Street View Imagery and Spatial Topology2024
- RegionGPT: Towards Region Understanding Vision Language Model2024
- UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web2024
- Teaching CLIP to Count to Ten2023
- Urban visual intelligence: Uncovering hidden city profiles with street view imagesProceedings of the National Academy of Sciences, 2023
- Hierarchical Knowledge Graph Learning Enabled Socioeconomic Indicator Prediction in Location-Based Social Network2023
- A review of urban physical environment sensing using street view imagery in public health studiesAnnals of GIS, 2020