Homepage - Data Science & Analytics

Siru Zhong

Ph.D. Student, The Hong Kong University of Science and Technology (GZ), Ex-Huawei & Tencent & XPENG

Greetings! I am a Ph.D. student in Data Science and Analytics at HKUST(GZ), supervised by Prof. Yuxuan Liang and co-supervised by Prof. Yue Yang and Prof. Yangqiu Song. Previously, I obtained my M.Phil. degree from the same university and my B.E. degree in Computer Science from HFUT.

Currently, my research focuses on Time Series Analysis, Multimodal, and Foundation Models, etc. I also collaborate closely with Dr. Qingsong Wen from Squirrel AI, Prof. Roger Zimmermann from National University of Singapore, and Prof. Zezhi Shao from Chinese Academy of Sciences. Prior to that, I interned at Huawei (supervised by Dr. Hao Xu), XPENG (supervised by Dr. Cheng Lu), and worked as a full-time Software Engineer at Tencent from 2022 to 2023.

I am passionate about building adaptive and practical spatio-temporal systems, translating research into deployable solutions that address real-world challenges.

Feel free to reach out via email if you're interested in discussing research ideas or exploring potential collaborations!

Education

Hong Kong University of Science and Technology (GZ)

Ph.D. in Data Science and Analytics Thrust

Feb. 2025 - Jan. 2028
Hong Kong University of Science and Technology (GZ)

M.Phil. in Data Science and Analytics Thrust

Aug. 2023 - Jan. 2025
Hefei University of Technology

B.Eng. in School of Computer and Information

Sep. 2018 - Jul. 2022

Experience

2012 Laboratories, Huawei

Research Intern, Spatio-Temporal Foundation Models

Feb. 2025 - Dec. 2025
Autonomous Driving Center, XPENG

Research Intern, Multimodal Image-Text Perception

May. 2024 - Aug. 2024
CloudDev Center, Tencent

Software Engineer & Intern, Cloud Intelligent IDE

Jun. 2021 - May. 2023

News

2026

I was invited to serve as a PC member for PAKDD 2026.

Jan 15

I was invited to serve as a Reviwer for IEEE TPAMI.

Jan 15

2025

One tutorial on Multimodal Learning for Spatio-Temporal Data Mining Era of Foundation Models was accepted to ICME 2026.

Dec 24

I was invited to serve as a Reviwer for Neurocomputing.

Dec 24

One paper on vision for time series forecasting was accepted to AAAI 2026.

Nov 08

One paper on Spatio-Temporal Foundation Model was accepted to NeurIPS 2025 (spotlight).

Sep 18

I was invited to serve as a reviewer for ICLR 2026.

Sep 03

One paper on Traffic Flow Forecasting was accepted to TITS 2025.

Aug 20

I was invited to serve as a PC member for AAAI 2026 (Special Track on AI for Social Impact).

Aug 08

I was invited to serve as a PC member for AAAI 2026.

Jul 26

I was invited to serve as a reviewer for KDD 2026 Datasets and Benchmarks Track.

Jul 25

I was invited to serve as a reviewer for MM 2025 Dataset Track.

Jul 23

One paper on Multimodal Building Electricity Loads Forecasting was accepted to MM 2025.

Jul 05

One paper on Urban Heat Island Effect Forecasting was accepted to KDD 2025.

May 15

One paper on Multimodal Time Series Forecasting was accepted to ICML 2025.

May 01

I was invited to serve as a reviewer for MM 2025.

Apr 26

One tutorial on Multimodal Learning for Spatio-Temporal Data Mining was accepted to MM 2025.

Feb 28

I started to cooperate with Huawei 2012 Labs, leading the project of Spatio-temporal knowledge fusion.

Feb 06

I started my PhD studies at the Hong Kong University of Science and Technology (Guangzhou).

Feb 05

I received the Runner-Up Prize in the 2024 HKUST(GZ) DSA Excellent Research Award.

Jan 27

2024

Two papers on Urban Indicator Prediction and Air Quality Inference were accepted to AAAI 2025.

Dec 10

I successfully defended my MPhil thesis in Data Science and Analytics at HKUST(GZ).

Nov 25

I was invited to serve as a reviewer for ICLR 2025.

Aug 23

One paper on Urban Multimodal Image-Text Retrieval was accepted to MM 2024.

Jul 18

Two papers on Spatio-Temporal Prediction and Neural Networks were accepted to IJCAI 2024.

May 14

I joined XPENG as a Research Intern focusing on multimodal research in autonomous driving scenarios.

May 14

One paper on LLM-Enhanced Urban Region Profiling was accepted to WWW 2024.

Jan 23

2023

I started my MPhil studies at the Hong Kong University of Science and Technology (Guangzhou).

Aug 24

2022

I officially joined Tencent as a Software Engineer!

Jul 04

I graduated from Hefei University of Technology with Outstanding Thesis Award.

Jun 05

2021

I completed my three-month internship at Tencent and received a SP return offer.

Sep 14

Publications (view all )

DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

Siru Zhong, Yiqiu Liu, Zhiqing Cui, Zezhi Shao, Fei Wang, Qingsong Wen, Yuxuan Liang

Under review.

Action required

Education

Experience

News

Publications (view all )

DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting

Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting

Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models

Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models

Learning to Factorize Spatio-Temporal Foundation Models

Learning to Factorize Spatio-Temporal Foundation Models

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

Multimodal Learning for Spatio-Temporal Data Mining

Multimodal Learning for Spatio-Temporal Data Mining

UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation

UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation

OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting

OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting

Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting

Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting

Towards Multi-Scenario Forecasting of Building Electricity Loads with Multimodal Data

Towards Multi-Scenario Forecasting of Building Electricity Loads with Multimodal Data

Fine-grained Urban Heat Island Effect Forecasting: A Context-aware Thermodynamic Modeling Framework

Fine-grained Urban Heat Island Effect Forecasting: A Context-aware Thermodynamic Modeling Framework

AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction

UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach

Spatio-Temporal Field Neural Networks for Air Quality Inference

Spatio-Temporal Field Neural Networks for Air Quality Inference

UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web

UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web

Service

Awards

Talks

Teaching