Hi! I am Kaizhen Tan (Chinese name: 谭楷蓁), an incoming Ph.D. student at New York University, currently pursuing my master’s degree in Artificial Intelligence at Carnegie Mellon University. I received my bachelor’s degree in Information Systems from Tongji University.

My research sits at the intersection of Urban Science, Human-centered AI, and Embodied Intelligence. Driven by the vision of harmonizing artificial intelligence with urban ecosystems, I aim to build spatially intelligent and socially aware urban AI systems that make cities more adaptive, inclusive, and governable.

To realize this vision, my work integrates:

  • Paradigms: Robotic Urbanization, Agentic Urban Digital Twins, Human-centered Urban Governance
  • Methodologies: Multimodal Learning, Geospatial & Spatiotemporal Data Analysis, Computational Social Science
  • Technologies: LLMs, VLMs, AI Agents, Embodied AI, Spatial Intelligence, World Models, Emerging Devices

Specifically, my research agenda explores four key topics:

🤖 1. Robot-Friendly Urban Space

How can dense cities integrate embodied intelligence while protecting safety, accessibility, and pedestrian experience?

  • Urban Readiness for Robots: Measure whether sidewalks, crossings, curbs, buildings, and public facilities can support safe robot operation.
  • Human-Robot Coexistence: Study conflicts, comfort, right-of-way, and interaction norms between robots, pedestrians, cyclists, and vulnerable groups.
  • Accessibility-Aware Deployment: Design routing and operation strategies that avoid reducing mobility for disabled people, older adults, and children.
  • Curbside and Low-Altitude Governance: Develop spatial rules for delivery robots and drones, including lanes, parking, corridors, privacy, noise, and safety constraints.
  • Public Acceptance and Accountability: Model public perception, responsibility boundaries, and governance mechanisms for city-scale deployment.

🏙️ 2. Agentic Urban Digital Twins

How can urban digital twins evolve from static city models into continuously updated systems for sensing, reasoning, and policy support?

  • Urban Foundation Representations: Fuse remote sensing, street-view imagery, trajectories, POI, IoT, text, and 3D data into unified urban representations.
  • Continuous Urban Sensing: Use robots, drones, mobile devices, and wearables as emerging data sources to update urban conditions over time.
  • 3D City Understanding: Support geo-localization, semantic mapping, and spatial querying across point clouds, meshes, and 3D Gaussians.
  • Urban Agents: Build LLM and VLM agents for map reasoning, spatial RAG, policy QA, public service assistance, and planning workflows.
  • Policy Sandbox: Enable what-if simulation, risk assessment, and implementation checks for urban management and public policy.

🎨 3. Multimodal Social Sensing

How can multimodal human-centered data reveal urban experience, social needs, and governance priorities?

  • AI-Enhanced Geospatial Analysis: Link urban form, environment, mobility, and public services with human behavior and social outcomes.
  • Pedestrian Experience and Accessibility: Detect walking barriers, sidewalk quality, perceived safety, and mobility challenges in everyday urban environments.
  • Urban Perception and Visual Aesthetics: Quantify streetscape quality, neighborhood imagery, and place identity to support design and regeneration decisions.
  • Socio-Cultural Signals: Extract place-based narratives from text, images, and online platforms to understand local identity and public concerns.
  • Participatory Governance: Translate social sensing results into explainable tools for planners, communities, and decision-makers.

🚀 4. Spatial Intelligence & World Models

How can spatial intelligence provide reliable reasoning, memory, and simulation capabilities for urban AI systems?

  • Embodied Spatial Representations: Unify geometry, semantics, physics, affordance, and action for robots, agents, and urban digital twins.
  • Urban World Models: Learn predictive models of how urban spaces change and how agents interact with physical and social environments.
  • Spatial Reasoning with VLMs: Improve map understanding, 3D reasoning, scene interpretation, and location-aware decision-making.
  • Lifelong Updating and Memory: Develop mechanisms for continuous learning, forgetting control, uncertainty tracking, and safe model updates.
  • Interpretable and Robust Decision Support: Make spatial AI systems transparent enough for planning, governance, and real-world deployment.

🔥 News

  • 2026.03: 🎓 I am pleased to share that I will begin my PhD at New York University in Fall 2026 under the supervision of Prof. Chenghe Guan and Prof. Zhan Guo.
  • 2026.01: 🎉 The abstract co-authored with Prof. Fan Zhang has been accepted for the XXV ISPRS Congress 2026. See you in Toronto!
  • 2025.12: 🎉 Our paper, led by my senior labmate Dr. Weihua Huan and co-authored with Prof. Wei Huang at Tongji University, was accepted by GIScience & Remote Sensing; honored to contribute as second author and big congratulations to Dr. Huan!
  • 2025.10: 🔭 Joined Prof. Yu Liu and Prof. Fan Zhang’s team at Peking University as a remote research assistant.
  • 2025.08: 🎉 Delivered an oral presentation at Hong Kong Polytechnic University after our paper was accepted to the Global Smart Cities Summit cum The 4th International Conference on Urban Informatics (GSCS & ICUI 2025).
  • 2025.07: 🎉 My undergraduate thesis was accepted by 7th Asia Conference on Machine Learning and Computing (ACMLC 2025).
  • 2025.06: 🎓 Graduated from Tongji University—grateful for the journey and excited to continue my studies at CMU.
  • 2025.04: 🔭 Completed the SITP project under the supervision of Prof. Yujia Zhai in the College of Architecture and Urban Planning.
  • 2025.01: 💼 Joined Shanghai Artificial Intelligence Laboratory as an AI Product Manager Intern.
  • 2024.09: 🌏 Conducted research at ASTAR in Singapore under the supervision of Dr. Yicheng Zhang and Dr. Sheng Zhang.
  • 2024.04: 🔭 Began my academic journey at Prof. Wei Huang’s lab in the College of Surveying and Geo-Informatics, Tongji University.

📖 Education

New York University
2026.09 – 2031.05 (expected)
Ph.D. student in Public Administration (Urban Policy)
Carnegie Mellon University
2025.08 – 2026.08
M.S. in Artificial Intelligence Systems Management
Tongji University
2021.09 – 2025.06
B.Mgt. in Information Management and Information System

💼 Experience

🔭 Research

💻 Industry

📝 Selected Papers

Peer-Reviewed

XXV ISPRS Congress
sym
UrbanVGGT: Scalable Sidewalk Width Estimation from Street View Images
Kaizhen Tan, Fan Zhang
XXV ISPRS Congress, 2026.
arXiv Abstract
Present UrbanVGGT, a measurement pipeline for estimating metrically scaled sidewalk width from a single street-view image using VGGT-based 3D reconstruction, semantic segmentation, and ground-plane fitting, achieving 0.25 m MAE on a Washington D.C. benchmark.
GSCS & ICUI 2025
sym
Decoding Tourist Perception in Historic Urban Quarters with Multimodal Social Media Data: An AI-Based Framework and Evidence from Shanghai
Kaizhen Tan, Yufan Wu, Yuxuan Liu, Haoran Zeng
Global Smart Cities Summit cum The 4th International Conference on Urban Informatics, 2025.
arXiv Slides
Developed an AI-powered multimodal framework to analyze tourist perception in historic Shanghai quarters, integrating image segmentation, color theme analysis, and sentiment mining for heritage-informed urban planning.
ACMLC 2025
sym
Multimodal Deep Learning for Modeling Air Traffic Controllers Command Lifecycle and Workload Prediction in Terminal Airspace
Kaizhen Tan
Asia Conference on Machine Learning and Computing, 2025.
DOI PDF Slides
Designed a multimodal deep learning framework linking ATCO voice commands with aircraft trajectories to model workload dynamics, enabling intelligent command generation and scheduling support.
GIScience & Remote Sensing
sym
A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks
Weihua Huan, Kaizhen Tan, Xintao Liu, Shoujun Jia, Shijun Lu, Jing Zhang, Wei Huang
GIScience & Remote Sensing, 2025.
DOI PDF
Proposed a spatiotemporal adaptive local search (STALS) method combining dynamic graph learning and spatial analytics to model and mitigate large-scale urban traffic congestion propagation.

Preprints

Preprint
sym
CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning Attribution
Kaizhen Tan, et al.
Preprint, 2026.
arXiv
A training-free interpretability framework that maps vision-language model attributions into a polar coordinate system to reveal how VLMs reason about spatial relations.
Preprint
sym
Do We Need a Robot Lane? A Simulation-Based Screening Framework for Sidewalk Delivery Robots
Kaizhen Tan, et al.
Preprint, 2026.
When should cities give sidewalk robots their own lane? An agent-based simulation framework that screens shared vs. dedicated space policies to answer this question.
Preprint
token pruning calibration
Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs
Kaizhen Tan
Preprint, 2026.
arXiv
Do visual tokens need to be kept for reliable confidence? This paper shows that moderate coverage-based pruning can make MLLMs better calibrated without noticeably hurting accuracy.
Preprint
sym
What We Lose, What We Gain: Spatio-temporal Patterns of Lost-and-Found Items in Qingdao Metro
Kaizhen Tan, et al.
Preprint, 2026.
Analyze 34,333 lost-and-found records across 173 metro stations to uncover spatio-temporal loss patterns, holiday effects, and station-level hotspots for transit service optimization.

🔬 Projects

sym
BlindNav: YOLO+LLM for Real-Time Navigation Assistance for Blind Users
Kaizhen Tan, Yufan Wang, Yixiao Li, Hanzhe Hong, Nicole Lyu
Report GitHub
BlindNav is a real-time, camera-based navigation assistant that uses YOLO for street-scene detection and a local LLM to turn those signals into concise voice guidance for blind and low-vision pedestrians.
sym
RAGCache++: Cache-Aware Document Ordering for Low-Latency RAG Serving
Kaizhen Tan, Rong Gu, Mingyuan Li
Report GitHub
Propose RAGCache++, a lightweight prompt-level optimization that reorders retrieved documents to maximize prefix sharing with cached sequences via a knowledge tree and greedy algorithm, reducing median TTFT by 20–33% with zero GPU memory cost and no serving-engine modification.

💬 Presentations

  • 2026.07 - XXV ISPRS Congress 2026
    UrbanVGGT: Scalable Sidewalk Width Estimation from Street View Images
    Toronto, Canada
  • 2025.08 - Global Smart Cities Summit cum The 4th International Conference on Urban Informatics (GSCS & ICUI 2025)
    A Multidimensional AI-powered Framework for Analyzing Tourist Perception in Historic Urban Quarters: A Case Study in Shanghai
    Hong Kong Polytechnic University (PolyU), Hong Kong SAR, China
  • 2025.07 - 7th Asia Conference on Machine Learning and Computing (ACMLC 2025)
    Multimodal Deep Learning for Modeling Air Traffic Controllers Command Lifecycle and Workload Prediction in Terminal Airspace
    Hong Kong SAR, China

📫 Contact

  • Email(CMU): kaizhent@cmu.edu
  • Email(NYU): kt3275@nyu.edu
  • Email(personal): wflps20140311@gmail.com

Please feel free to reach out if any of these research directions resonate with you. I'd be happy to chat!

🌍 Visitor Map