Profile News Experience Publications
Yihong Tang
Portrait
Logo Ph.D. Candidate| Logo Visiting Researcher, Frontier AI Research| 🍁 Montreal ☃️

Hi 👋, I'm Yihong, a Ph.D. candidate at McGill University, advised by Prof. Lijun Sun, and a Visiting Researcher at ServiceNow AI Research, where I work with Valentina Zantedeschi. Prior to McGill, I received my M.Phil. in Urban Computing from The University of Hong Kong and my B.Eng. in Computer Science from BUPT.

I study multimodal AI agents and generative models, and their applications in computer, social, and urban sciences. My research has appeared in top AI venues, please check out my selected publications for details.

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

Email Google Scholar ResearchGate GitHub LinkedIn x.com WeChat Rednote
News
2026
2026-02-21
Paper "E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving" has been accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
2026-02-20
Paper "Think Before You Drive: World Model-Inspired Multimodal Grounding" has been accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
2026-02-01
Paper "Steerable adversarial scenario generation through test-time preference alignment" has been accepted to International Conference on Learning Representations (ICLR) 2026.
2026-01-20
Paper "Digital visibility, physical obscurity: Uncovering the location strategies of ghost kitchens in platform urbanism" is accepted by Journal of Retailing and Consumer Services.
2026-01-03
Paper "LLM4GKID: A Multimodal Large Language Model-driven Framework for Ghost Kitchen Identification" has been accepted to IEEE Transactions on Computational Social Systems.
2026-01-01
Paper "INTENT: Trajectory prediction framework with intention-guided contrastive clustering" has been accepted to IEEE Open Journal of Intelligent Transportation Systems.
2025
2025-09-23
Paper "RouteKG: A knowledge graph-based framework for route prediction on road networks" has been accepted to IEEE Transaction on Intelligent Transportation Systems.
2025-08-20
Paper "Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning" has been accepted to the Findings of EMNLP 2025, and was awarded the Best Paper Award at IJCAI MKLM 2025.
Education
  • McGill University
    McGill University
    Ph.D. in Geneartive AI for Mobility & Autonomous Driving
    Jan. 2025 - present
  • The University of Hong Kong
    The University of Hong Kong
    M.Phil. in Urban Computing
    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
  • ServiceNow AI Research
    ServiceNow AI Research
    Visiting Researcher, Frontier AI Research
    Jan. 2026 - Present
  • Autorité régionale de transport métropolitain
    Autorité régionale de transport métropolitain
    Research Intern
    Aug. 2025 - Dec. 2025
  • Massachusetts Institute of Technology
    Massachusetts Institute of Technology
    Summer Research Intern, JTL Transit Lab
    Apr. 2024 - Oct. 2024
  • Arizona State University
    Arizona State University
    Research Assistant, ARC Lab
    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, Mobility AI Lab
    Apr. 2021 - Aug. 2022
  • Xiaomi Corporation
    Xiaomi Corporation
    Recommendation Algorithm Intern, Xiaomi Music
    Jul. 2020 - Sept. 2020
Selected Awards
Academic Services
Journal Referees:
Humanities and Social Sciences Communications, Transportation Research Part C, Scientific Reports, IEEE Transactions on Multimedia, IEEE Transactions on Intelligent Transportation Systems, IEEE Open Journal of Intelligent Transportation Systems, Expert Systems with Applications, Artificial Intelligence for Transportation, Applied Intelligence, The Journal of Supercomputing
Conference Referees:
ICLR 2025, AAAI 2025, ISTDM 2025, ITSC 2025, NeurIPS 2025, EMNLP 2025, COLM 2025, TRB Annual Meeting 2026, ICLR 2026, ITSC 2026
Projects:
MobAgent - Large Language Model Agent for Mobility Reasoning and Synthesis (NSERC, CA$300,000)
Mentored:
Selected Publications (view all )
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
Autonomous Driving

Yihong Tang*, Haicheng Liao*, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li#, Lijun Sun#, Chengzhong Xu# (* equal contribution, # corresponding author)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

Paper

E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
Autonomous Driving

Yihong Tang*, Haicheng Liao*, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li#, Lijun Sun#, Chengzhong Xu# (* equal contribution, # corresponding author)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

Paper

LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
Human-centered Modeling LLM for Urban Science Spatial-Temporal

Yihong Tang, Menglin Kong, Junlin He, Tong Nie, Wei Ma, Lijun Sun# (# corresponding author)

Under review. 2026

Paper Code WeChat Official Accounts Report (Chinese)

LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
Human-centered Modeling LLM for Urban Science Spatial-Temporal

Yihong Tang, Menglin Kong, Junlin He, Tong Nie, Wei Ma, Lijun Sun# (# corresponding author)

Under review. 2026

Paper Code WeChat Official Accounts Report (Chinese)

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)

Findings of Empirical Methods in Natural Language Processing (EMNLP) 2025 & IJCAI MKLM 2025 Best Paper Award

Paper Code Best Paper Award

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)

Findings of Empirical Methods in Natural Language Processing (EMNLP) 2025 & IJCAI MKLM 2025 Best Paper Award

Paper Code Best Paper Award

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 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 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 Spatial-Temporal

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 Spatial-Temporal

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)

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 Spatial-Temporal

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 Spatial-Temporal

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

All publications
Visitor Statistics