PhD @ HKUST Guangzhou, On Data-Centric Multimodal LearningI am an M.Phil. student and an incoming Ph.D. student in Data Science and Analytics at the Hong Kong University of Science and Technology (Guangzhou), under the supervision of Prof. Yuxuan Liang and Prof. Yangqiu Song. I earned my B.E. from the School of Computer and Information at Hefei University of Technology.
My research interests include Multimodal Machine Learning and Data Mining, with a focus on Spatio-Temporal and Urban scenarios. I aim to derive insights from large-scale, heterogeneous, cross-domain data.
Previously, I was a Research Intern at XPENG, working on visual multimodal research and contributing to the XNGP System. I also worked as a Software Engineer at Tencent, where I enhanced QQ’s performance and developed cloud-native tools like CodeSpaces and the Workflow Engine.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Hong Kong University of Science and Technology (Guangzhou)Ph.D. in Data Science and AnalyticsFeb. 2025 - Feb. 2028
-
Hong Kong University of Science and Technology (Guangzhou)M.Phil. in Data Science and AnalyticsAug. 2023 - Jan. 2025
-
Hefei University of TechnologyB.S. in School of Computer and InformationSep. 2018 - Jul. 2022
Experience
-
XPENG, GuangzhouResearch Intern, Autonomous Driving CenterMay. 2024 - Jul. 2024 -
HKUST, GuangzhouResearch Assistant, CityMind LabMay. 2023 - Aug. 2023
-
Tencent, ShenzhenSoftware Engineer, CloudIDE TeamJul. 2022 - May. 2023 -
Tencent, BeijingSoftware Intern, Fiber TeamJun. 2021 - Sep. 2023
Honors & Awards
-
Best Project Award (1/15) in Data Science Computing (DSAA 5021) at HKUST(GZ)2024
-
Outstanding Student Award (Top 10%) of the Red Bird Challenge Camp at HKUST(GZ)2024
-
iCode Certification at Tencent2022
-
Silver Award (2/12) of Code World Program at Tencent2022
-
Outstanding Student Award (8/100) of Graduates Training at Tencent2022
-
Outstanding Graduation Thesis Award (Top 2%) at HFUT}2022
-
Third Prize in National College English Competition2021
-
First Prize in CSDN Technology Blogger Competition (Top 10)2020
-
Second Prize in Robotics Competition (2D Project Team) at HFUT2020
News
Selected Publications (view all )
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
Siru Zhong, Xixuan Hao, Yibo Yan, Ying Zhang, Yangqiu Song, Yuxuan Liang
ACM International Conference on Multimedia (ACM MM) 2024 Poster
First-ever cross-domain framework that integrates the power of LMM and SAM into satellite image-text retrieval.
Spatio-Temporal Field Neural Networks for Air Quality Inference
Yutong Feng, Qiongyan Wang, Yutong Xia, Junlin Huang, Siru Zhong, Kun Wang, Shifen Cheng, Yuxuan Liang
The International Joint Conference on Artificial Intelligence (IJCAI) 2024
A pioneering Spatio-Temporal Field Neural Network model integrates two distinct perspectives on space and time to perform air quality inference.
Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach
Huaiwu Zhang, Yutong Xia, Siru Zhong, Kun Wang, Zekun Tong, Qingsong Wen, Roger Zimmermann, Yuxuan Liang
The International Joint Conference on Artificial Intelligence (IJCAI) 2024
A novel deep-learning prediction model for real-time parking availability in Singapore, analyzing external factors, introducing a new dataset.
UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web
Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, Yuxuan Liang
The International World Wide Web Conference (WWW) 2024 Oral
First-ever cross-domain framework that integrates the power of LMM and SAM into satellite image-text retrieval.
Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting
Jianxiang Zhou, Erdong Liu, Wei Chen, Siru Zhong, Yuxuan Liang
Under review. 2024
Introduce the Spatio-Temporal Graph Transformer (STGormer), a model that integrates attribute and structure information in traffic data to learn spatio-temporal correlations and uses a mixture-of-experts module to capture heterogeneity, leading to state-of-the-art performance in traffic forecasting.
UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction
Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, Yuxuan Liang
Under review. 2024
First urban region representation learning framework that explores multi-granularity cross-modal alignment.