Yihong Tang
Portrait
Logo Ph.D. Student    |    INTJ

I'm a doctoral student at McGill University, supervised by Prof. Lijun Sun. Before joining McGill, I obtained my M.Phil. in Urban Analytics and Smart Cities from The University of Hong Kong and my B.Eng. in Computer Science and Technology from BUPT. I have also held research positions at institutions including Mobility AI Lab at The Hong Kong Polytechnic University (HK PolyU), JTL Transit Lab at Massachusetts Institute of Technology (MIT), and Suo Lab at Arizona State University (ASU).

My research focuses on innovating data-driven, statistical, and AI methods to develop more connected, autonomous, intelligent, and human-centered urban and transportation systems, and to uncover the social dynamics they embody. My primary research interests span four interrelated areas: Human-centered Modeling and Synthesis, focusing on population and mobility data with equity, privacy, and intent-awareness; Large Language Models for Urban Science, aiming to build self-evolving agents for urban scientific discovery, planning, and causal reasoning; Multimodal Transportation Systems, using multi-source data fusion to understand and optimize mobility systems; and Spatiotemporal Data Modeling, developing models for forecasting, control, and behavior inference across space and time.

I am looking for collaborators and interns with the goal of conducting impactful research and publishing in top AI conferences and leading urban and transportation journals. If you are interested in collaborating or sharing thoughts, please feel free to reach out via Email or WeChat

Email Google Scholar ResearchGate LinkedIn GitHub x.com WeChat
News
2025
Paper "Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning" is accepted by IJCAI MKLM 2025.
Jun 15
Paper "RoadPowerFM: Graphormer-JEPA based Foundation Model for Road-Power Coupling Network" is published in IEEE Transaction on Smart Grid. This is my first mentored work, a proud supervision moment!
Jun 15
Paper "Vision-to-Music Generation: A Survey" is accepted by ISMIR 2025.
Jun 06
Paper "Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning" recognized as a Highly Cited Paper in Social Sciences by Essential Science Indicators.
Feb 10
2024
Paper "Activity-aware human mobility prediction with hierarchical graph attention recurrent network" has been accepted to IEEE Transaction on Intelligent Transportation Systems.
Dec 19
Paper "ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning" has been accepted to the EMNLP 2024 Industry Track, and win the Best Paper Award at KDD UrbComp 2024.
Oct 02
Paper "Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network" is published in Information Fusion.
Jun 01
Paper "Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning" is published in Accident Analysis & Prevention.
Mar 01
Invited talk at the AGI Playground Workshop, Founder Park (powered by GeekPark)
Jan 20
My startup team won the Best Zero to One Award at the Alibaba Creator @ AI Entrepreneur Hackathon Finals. Read more
Jan 15
Education
  • McGill University
    McGill University
    Ph.D. in Transportation Engineering
    Jan. 2025 - present
  • The University of Hong Kong
    The University of Hong Kong
    M.Phil. in Urban Analytics and Smart Cities
    Sep. 2022 - Jul. 2024
  • Beijing University of Posts and Telecommunications
    Beijing University of Posts and Telecommunications
    B.Eng. in Computer Science and Technology
    Sep. 2018 - Jul. 2022
Experience
  • Massachusetts Institute of Technology
    Massachusetts Institute of Technology
    Summer Research Intern
    Apr. 2024 - Oct. 2024
  • Arizona State University
    Arizona State University
    Research Assistant
    Jul. 2024 - Sep. 2024
  • TuTu. AI, Startup
    TuTu. AI, Startup
    Co-founder & Research Scientist & CIO
    May. 2023 - Feb. 2024
  • The Hong Kong Polytechnic University
    The Hong Kong Polytechnic University
    Research Assistant
    Apr. 2021 - Aug. 2022
  • Xiaomi Corporation
    Xiaomi Corporation
    Recommendation Algorithm Intern
    Jul. 2020 - Sept. 2020
Honors & Awards
  • Best Paper Award, 13th International Workshop on Urban Computing
    Aug., 2024
  • Best Zero to One Award, Alibaba Create@AI Entrepreneur Hackathon Final
    Jan., 2024
  • National Science Foundation Award, CIKM 2022
    Oct., 2022
Academic Services
Journal Referees:
Applied Intelligence, Artificial Intelligence for Transportation, IEEE Transaction on Intelligent Transportation Systems, IEEE Open Journal of Intelligent Transportation Systems, The Journal of Supercomputing
Conference Referees:
ICLR 2025, AAAI 2025, ISTDM 2025, ITSC 2025, NeurIPS 2025, EMNLP 2025
Mentor:
Selected Publications (view all )
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning
LLM for Urban Science

Yihong Tang*, Ao Qu*#, Zhaokai Wang*, Dingyi Zhuang*, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao (* equal contribution, # corresponding author)

IJCAI MKLM 2025

[Paper]

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning
LLM for Urban Science

Yihong Tang*, Ao Qu*#, Zhaokai Wang*, Dingyi Zhuang*, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao (* equal contribution, # corresponding author)

IJCAI MKLM 2025

[Paper]

RoadPowerFM: Graphormer-JEPA based Foundation Model for Road-Power Coupling Network
RoadPowerFM: Graphormer-JEPA based Foundation Model for Road-Power Coupling Network
Spatio-temporal Modeling

Zeyuan Niu*, Yihong Tang*#, Jiamei Li, Qian Ai, Xing He (* equal contribution, # corresponding author)

IEEE Transactions on Smart Grid 2025

[Paper]

RoadPowerFM: Graphormer-JEPA based Foundation Model for Road-Power Coupling Network
RoadPowerFM: Graphormer-JEPA based Foundation Model for Road-Power Coupling Network
Spatio-temporal Modeling

Zeyuan Niu*, Yihong Tang*#, Jiamei Li, Qian Ai, Xing He (* equal contribution, # corresponding author)

IEEE Transactions on Smart Grid 2025

[Paper]

Vision-to-Music Generation: A Survey
Vision-to-Music Generation: A Survey

Zhaokai Wang, Chenxi Bao, Le Zhuo, Jingrui Han, Yang Yue, Yihong Tang, Victor Shea-Jay Huang, Yue Liao

26th International Society for Music Information Retrieval Conference (ISMIR) 2025

[Paper] [Code]

Vision-to-Music Generation: A Survey
Vision-to-Music Generation: A Survey

Zhaokai Wang, Chenxi Bao, Le Zhuo, Jingrui Han, Yang Yue, Yihong Tang, Victor Shea-Jay Huang, Yue Liao

26th International Society for Music Information Retrieval Conference (ISMIR) 2025

[Paper] [Code]

From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models
From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models
LLM for Urban Science Multimodal Transportation

Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng, Jun Ma, Jinhua Zhao, Lijun Sun# (# corresponding author)

Under review. 2025

[Paper]

From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models
From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models
LLM for Urban Science Multimodal Transportation

Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng, Jun Ma, Jinhua Zhao, Lijun Sun# (# corresponding author)

Under review. 2025

[Paper]

Large Language Models for Data Synthesis
Large Language Models for Data Synthesis
Human-centered Modeling LLM for Urban Science Spatio-temporal Modeling

Yihong Tang, Menglin Kong, Lijun Sun# (# corresponding author)

Under review. 2025

[Paper] [Code] [Project] [WeChat Official Accounts Report (Chinese)]

Large Language Models for Data Synthesis
Large Language Models for Data Synthesis
Human-centered Modeling LLM for Urban Science Spatio-temporal Modeling

Yihong Tang, Menglin Kong, Lijun Sun# (# corresponding author)

Under review. 2025

[Paper] [Code] [Project] [WeChat Official Accounts Report (Chinese)]

Reimagining urban science: Scaling causal inference with large language models
Reimagining urban science: Scaling causal inference with large language models
LLM for Urban Science

Yutong Xia*, Ao Qu*, Yunhan Zheng, Yihong Tang, Dingyi Zhuang, Yuxuan Liang, Shenhao Wang, Cathy Wu, Lijun Sun, Roger Zimmermann, Jinhua Zhao# (* equal contribution, # corresponding author)

Submitted to Nature Human Behaviour 2025

[Paper]

Reimagining urban science: Scaling causal inference with large language models
Reimagining urban science: Scaling causal inference with large language models
LLM for Urban Science

Yutong Xia*, Ao Qu*, Yunhan Zheng, Yihong Tang, Dingyi Zhuang, Yuxuan Liang, Shenhao Wang, Cathy Wu, Lijun Sun, Roger Zimmermann, Jinhua Zhao# (* equal contribution, # corresponding author)

Submitted to Nature Human Behaviour 2025

[Paper]

INTENT: Trajectory prediction framework with intention-guided contrastive clustering
INTENT: Trajectory prediction framework with intention-guided contrastive clustering
Human-centered Modeling Multimodal Transportation Spatio-temporal Modeling

Yihong Tang, Wei Ma# (# corresponding author)

Under review. 2025

[Paper]

INTENT: Trajectory prediction framework with intention-guided contrastive clustering
INTENT: Trajectory prediction framework with intention-guided contrastive clustering
Human-centered Modeling Multimodal Transportation Spatio-temporal Modeling

Yihong Tang, Wei Ma# (# corresponding author)

Under review. 2025

[Paper]

Activity-aware human mobility prediction with hierarchical graph attention recurrent network
Activity-aware human mobility prediction with hierarchical graph attention recurrent network
Human-centered Modeling Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Junlin He*, Zhan Zhao# (* equal contribution, # corresponding author)

IEEE Transactions on Intelligent Transportation Systems 2024

[Paper] [Code]

Activity-aware human mobility prediction with hierarchical graph attention recurrent network
Activity-aware human mobility prediction with hierarchical graph attention recurrent network
Human-centered Modeling Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Junlin He*, Zhan Zhao# (* equal contribution, # corresponding author)

IEEE Transactions on Intelligent Transportation Systems 2024

[Paper] [Code]

ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
Human-centered Modeling LLM for Urban Science Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Zhaokai Wang*, Ao Qu*, Yihao Yan*, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao#, Zhan Zhao#, Wei Ma# (* equal contribution, # corresponding author)

Empirical Methods in Natural Language Processing (EMNLP) 2024 Industry Track & KDD UrbComp 2024 Best Paper Award

[Paper] [Code] [Poster] [Best Paper Award] [WeChat Official Accounts Report (Chinese)]

ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
Human-centered Modeling LLM for Urban Science Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Zhaokai Wang*, Ao Qu*, Yihao Yan*, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao#, Zhan Zhao#, Wei Ma# (* equal contribution, # corresponding author)

Empirical Methods in Natural Language Processing (EMNLP) 2024 Industry Track & KDD UrbComp 2024 Best Paper Award

[Paper] [Code] [Poster] [Best Paper Award] [WeChat Official Accounts Report (Chinese)]

High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Multimodal Transportation

Shaozu Ding*, Yihong Tang*, Marco De Vincenzi, Dajiang Suo# (* equal contribution, # corresponding author)

Under review. 2024

[Paper] [Code]

High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Multimodal Transportation

Shaozu Ding*, Yihong Tang*, Marco De Vincenzi, Dajiang Suo# (* equal contribution, # corresponding author)

Under review. 2024

[Paper] [Code]

Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network
Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network
Multimodal Transportation Spatio-temporal Modeling

Yuebing Liang, Zhan Zhao#, Fangyi Ding, Yihong Tang, Zhengbing He (# corresponding author)

Information Fusion 2024

[Paper]

Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network
Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network
Multimodal Transportation Spatio-temporal Modeling

Yuebing Liang, Zhan Zhao#, Fangyi Ding, Yihong Tang, Zhengbing He (# corresponding author)

Information Fusion 2024

[Paper]

Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning
Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning
Multimodal Transportation

Xujing Yu, Jun Ma#, Yihong Tang, Tianren Yang, Feifeng Jiang (# corresponding author)

Accident Analysis & Prevention 2024

[Paper]

Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning
Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning
Multimodal Transportation

Xujing Yu, Jun Ma#, Yihong Tang, Tianren Yang, Feifeng Jiang (# corresponding author)

Accident Analysis & Prevention 2024

[Paper]

Adversarial Attacks on Deep Reinforcement Learning-based Traffic Signal Control Systems with Colluding Vehicles
Adversarial Attacks on Deep Reinforcement Learning-based Traffic Signal Control Systems with Colluding Vehicles
Multimodal Transportation

Ao Qu, Yihong Tang, Wei Ma# (# corresponding author)

ACM Transactions on Intelligent Systems and Technology 2023

[Paper] [Arxiv]

Adversarial Attacks on Deep Reinforcement Learning-based Traffic Signal Control Systems with Colluding Vehicles
Adversarial Attacks on Deep Reinforcement Learning-based Traffic Signal Control Systems with Colluding Vehicles
Multimodal Transportation

Ao Qu, Yihong Tang, Wei Ma# (# corresponding author)

ACM Transactions on Intelligent Systems and Technology 2023

[Paper] [Arxiv]

RouteKG: A knowledge graph-based framework for route prediction on road networks
RouteKG: A knowledge graph-based framework for route prediction on road networks
Human-centered Modeling Spatio-temporal Modeling

Yihong Tang, Zhan Zhao#, Weipeng Deng, Shuyu Lei, Yuebing Liang, Zhanliang Ma (# corresponding author)

Under review. 2023

[Paper]

RouteKG: A knowledge graph-based framework for route prediction on road networks
RouteKG: A knowledge graph-based framework for route prediction on road networks
Human-centered Modeling Spatio-temporal Modeling

Yihong Tang, Zhan Zhao#, Weipeng Deng, Shuyu Lei, Yuebing Liang, Zhanliang Ma (# corresponding author)

Under review. 2023

[Paper]

Few-Sample Traffic Prediction With Graph Networks Using Locale as Relational Inductive Biases
Few-Sample Traffic Prediction With Graph Networks Using Locale as Relational Inductive Biases
Multimodal Transportation Spatio-temporal Modeling

Mingxi Li, Yihong Tang, Wei Ma# (# corresponding author)

IEEE Transactions on Intelligent Transportation Systems 2022

[Paper] [Arxiv] [Code]

Few-Sample Traffic Prediction With Graph Networks Using Locale as Relational Inductive Biases
Few-Sample Traffic Prediction With Graph Networks Using Locale as Relational Inductive Biases
Multimodal Transportation Spatio-temporal Modeling

Mingxi Li, Yihong Tang, Wei Ma# (# corresponding author)

IEEE Transactions on Intelligent Transportation Systems 2022

[Paper] [Arxiv] [Code]

Domain adversarial spatial-temporal network: A transferable framework for short-term traffic forecasting across cities
Domain adversarial spatial-temporal network: A transferable framework for short-term traffic forecasting across cities
Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Ao Qu*, Andy HF Chow, William HK Lam, S.C. Wong, Wei Ma*# (* equal contribution, # corresponding author)

Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM) 2022 Oral Presentation NSF Award

[Paper] [Code]

Domain adversarial spatial-temporal network: A transferable framework for short-term traffic forecasting across cities
Domain adversarial spatial-temporal network: A transferable framework for short-term traffic forecasting across cities
Multimodal Transportation Spatio-temporal Modeling

Yihong Tang*, Ao Qu*, Andy HF Chow, William HK Lam, S.C. Wong, Wei Ma*# (* equal contribution, # corresponding author)

Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM) 2022 Oral Presentation NSF Award

[Paper] [Code]

Protein residue contact prediction based on deep learning and massive statistical features from multi-sequence alignment
Protein residue contact prediction based on deep learning and massive statistical features from multi-sequence alignment

Huiling Zhang, Min Hao, Hao Wu, Hing-Fung Ting, Yihong Tang, Wenhui Xi, Yanjie Wei# (# corresponding author)

Tsinghua Science and Technology 2022

[Paper]

Protein residue contact prediction based on deep learning and massive statistical features from multi-sequence alignment
Protein residue contact prediction based on deep learning and massive statistical features from multi-sequence alignment

Huiling Zhang, Min Hao, Hao Wu, Hing-Fung Ting, Yihong Tang, Wenhui Xi, Yanjie Wei# (# corresponding author)

Tsinghua Science and Technology 2022

[Paper]

All publications
Visitor Statistics