Xixuan Hao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xixuan Hao has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Yuxuan Liang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
8 shared publications - Xingchen Zou
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
3 shared publications - Siru Zhong
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
2 shared publications - Xusen Guo
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications - Yibo Yan
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications - Yutian Jiang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1917-1928
CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1917-1928
Open AccessCoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1590-1601
Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1590-1601
Open AccessMulti-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5439-5450
AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing
Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban sensing systems struggle with limited generalization across diverse urban scenarios and poor interpretability in decision-making. In this work, we introduce AgentSense, a hybrid, training-free framework that integrates large language models (LLMs) into participatory urban sensing through a multi-agent refinement system. AgentSense initially employs a classical planner to generate baseline solutions and then iteratively refines them to adapt sensing task assignments to dynamic urban conditions and heterogeneous worker preferences, while producing natural language explanations that enhance transparency and trust. Extensive experiments across two large-scale mobility datasets and seven types of dynamic disturbances demonstrate that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods. Furthermore, compared to single-agent LLM baselines, our approach outperforms in both performance and robustness, while delivering more reasonable and transparent explanations. These results position AgentSense as a significant advancement towards deploying adaptive and explainable urban sensing systems on the web.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5439-5450
Open AccessAgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing
Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban sensing systems struggle with limited generalization across diverse urban scenarios and poor interpretability in decision-making. In this work, we introduce AgentSense, a hybrid, training-free framework that integrates large language models (LLMs) into participatory urban sensing through a multi-agent refinement system. AgentSense initially employs a classical planner to generate baseline solutions and then iteratively refines them to adapt sensing task assignments to dynamic urban conditions and heterogeneous worker preferences, while producing natural language explanations that enhance transparency and trust. Extensive experiments across two large-scale mobility datasets and seven types of dynamic disturbances demonstrate that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods. Furthermore, compared to single-agent LLM baselines, our approach outperforms in both performance and robustness, while delivering more reasonable and transparent explanations. These results position AgentSense as a significant advancement towards deploying adaptive and explainable urban sensing systems on the web.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8200-8211
Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8200-8211
Open AccessEnhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 244-256
Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 244-256
Open AccessSpace-aware Socioeconomic Indicator Inference with Heterogeneous Graphs
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14338-14339
Multimodal Learning for Spatio-Temporal Data Mining
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14338-14339
Open AccessMultimodal Learning for Spatio-Temporal Data Mining
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2799-2812
Nature Makes No Leaps: Building Continuous Location Embeddings with Satellite Imagery from the Web
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2799-2812
Open AccessNature Makes No Leaps: Building Continuous Location Embeddings with Satellite Imagery from the Web
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6307-6315
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
Urbanization challenges underscore the necessity for effective satellite image-text retrieval methods to swiftly access specific information enriched with geographic semantics for urban applications. However, existing methods often overlook significant domain gaps across diverse urban landscapes, primarily focusing on enhancing retrieval performance within single domains. To tackle this issue, we present UrbanCross, a new framework for cross-domain satellite image-text retrieval. UrbanCross leverages a high-quality, cross-domain dataset enriched with extensive geo-tags from three countries to highlight domain diversity. It employs the Large Multimodal Model (LMM) for textual refinement and the Segment Anything Model (SAM) for visual augmentation, achieving fine-grained alignment of images, segments and texts, yielding a 10% improvement in retrieval performance. Additionally, UrbanCross incorporates an adaptive curriculum-based source sampler and a weighted adversarial cross-domain fine-tuning module, progressively enhancing adaptability across various domains. Extensive experiments confirm UrbanCross's superior efficiency in retrieval and adaptation to new urban environments, demonstrating an average performance increase of 15% over its version without domain adaptation mechanisms, effectively bridging the domain gap. Our code and dataset are publicly accessible at https://github.com/siruzhong/UrbanCross.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6307-6315
Open AccessUrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
Urbanization challenges underscore the necessity for effective satellite image-text retrieval methods to swiftly access specific information enriched with geographic semantics for urban applications. However, existing methods often overlook significant domain gaps across diverse urban landscapes, primarily focusing on enhancing retrieval performance within single domains. To tackle this issue, we present UrbanCross, a new framework for cross-domain satellite image-text retrieval. UrbanCross leverages a high-quality, cross-domain dataset enriched with extensive geo-tags from three countries to highlight domain diversity. It employs the Large Multimodal Model (LMM) for textual refinement and the Segment Anything Model (SAM) for visual augmentation, achieving fine-grained alignment of images, segments and texts, yielding a 10% improvement in retrieval performance. Additionally, UrbanCross incorporates an adaptive curriculum-based source sampler and a weighted adversarial cross-domain fine-tuning module, progressively enhancing adaptability across various domains. Extensive experiments confirm UrbanCross's superior efficiency in retrieval and adaptation to new urban environments, demonstrating an average performance increase of 15% over its version without domain adaptation mechanisms, effectively bridging the domain gap. Our code and dataset are publicly accessible at https://github.com/siruzhong/UrbanCross.