I will soon join Zhongguancun Academy as an Assistant Professor, where I plan to advance my research in spatial intelligence, agentic intelligence, and urban science through collaboration with colleagues and students. Currently, I am a Postdoctoral Fellow in the Department of Electronic Engineering at Tsinghua University. My research primarily focuses on spatial intelligence, multi-modal large language models, human behavior modeling, urban science, and spatiotemporal data mining. To date, I have published over 40 papers in top-tier venues, including KDD, ICCV, ACL, WWW, EMNLP, NAACL, AAAI, UbiComp, and TKDE, with my work garnering more than 5,000 citations on Google Scholar. From 2021 to 2023, I served as a researcher at Meituan, specializing in intelligent decision-making and large language models. I received my B.S. and Ph.D. degrees in electronic engineering from Tsinghua University in 2016 and 2021, respectively, under the supervision of Prof. Yong Li.

Research Interests

1. Spatial Intelligence with Multi-modal Large Language Models in Open World, e.g., CityGPT-KDD2025, UrbanLLaVA-ICCV2025, CityBench-KDD2025, Hallucination-EMNLP2025.
2. Building Intelligent Agents with Large Language Models for Real-world Applications, e.g., TrajAgent-NeurIPS2025, AgentMove-NAACL2025, PIGEON-ACL2025, AutoQual-EMNLP2025.
3. Spatiotemporal Data Mining: trajectory mining, traffic forecasting, e.g., DeepMove-WWW2018, MoveSim-KDD2020, DeepSTN+-AAAI2019, UniST-KDD2024, SCDN-KDD2024.
4. Urban Science: human dynamics, urban dynamics, in-depth and data-driven analyses of urban issues.

News

Selected Publications

* Equal contribution; # Correspondence; † Work done as Intern in the Lab

Spatial Intelligence with Large Language Models

1. UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence
   Jie Feng, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yong Li
   ICCV 2025 (CCF A) Codes | PDF | Project Website
2. CityGPT: Empowering Urban Spatial Cognition of Large Language Models
   Jie Feng*, Tianhui Liu*, Yuwei Du, Siqi Guo, Yuming Lin, Yong Li
   KDD 2025 Research (CCF A) Codes | PDF | Project Website
3. CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
   Jie Feng*, Jun Zhang*, Tianhui Liu*, Xin Zhang, Tianjian Ouyang, Junbo Yan, Yuwei Du, Siqi Guo, Yong Li
   KDD 2025 D&B (CCF A) Codes PDF
4. CityLens: Benchmarking Large Vision-Language Models for Urban Socioeconomic Sensing
   Tianhui Liu, Hetian Pang†, Xin Zhang, Tianjian Ouyang, Zhiyuan Zhang, Jie Feng#, Yong Li, Hui Pan
   ICLR 2026 Codes PDF

Human Behavior Analytics and Agentic Modeling

1. TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration
   Yuwei Du*, Jie Feng*#, Jie Zhao, Yong Li#
   NeurIPS 2025 (CCF A) Codes | PDF | Project Website
2. AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction
   Jie Feng, Yuwei Du, Jie Zhao, Yong Li
   NAACL 2025 Main (CCF B) Codes PDF
3. Harvesting Efficient On-Demand Order Pooling from Skilled Couriers: Enhancing Graph Representation Learning for Refining Real-time Many-to-One Assignments
   Yile Liang, Jiuxia Zhao, Donghui Li, Jie Feng#, Chen Zhang, Xuetao Ding, Jinghua Hao, Renqing He
   KDD 2024 ADS (CCF A) PDF Link
4. DeepMove: Predicting Human Mobility with Atentional Recurrent Networks
   Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, Depeng Jin.
   WWW 2018 (CCF A) Codes(star 151) | PDF | Link | #5 Most Influential Paper in WWW 2018

Spatiotemporal Data Mining and Time Series Modeling

1. UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction
   Yuan Yuan, Jingtao Ding, Jie Feng, Depeng Jin, Yong Li
   KDD 2024 Research (CCF A) Codes(star 180) | PDF | Link | #3 Most Influential Paper at KDD 2024
2. Dynamic graph convolutional recurrent network for traffic prediction: benchmark and solution
   Fuxian Li, Jie Feng, Huan Yan, Guangyin Jin, Fan Yang, Funing Sun, Depeng Jin, Yong Li
   TKDD 2023 (CCF B) Codes(star 296) | PDF | Link | #1 Most Cited Paper in TKDD 2023
3. DeepSTN+: Context-aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis
   Ziqian Lin*, Jie Feng*, Ziyang Lu, Yong Li, Depeng Jin
   AAAI 2019 (CCF A) Codes(star 66) PDF Link

Survey

1. “A Survey of Embodied World Models”, Yu Shang, Yinzhou Tang, Xin Zhang, et al. preprint 2025.09.
2. “AI Agent Behavioral Science.”, Lin Chen, Yunke Zhang, Jie Feng, et al. preprint 2025.06.
3. “A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science.”, Jie Feng, Jinwei Zeng, et al. preprint 2025.04. Chinese article by Zhuanzhi.
4. “Urban Generative Intelligence (UGI): A foundational platform for agents in embodied city environment.”, Fengli Xu, Jun Zhang, Chen Gao, Jie Feng, Yong Li. preprint 2023.12
5. “Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.”, Fengli Xu, Qianyue Hao, et al. Cell Patterns 2025
6. “Understanding World or Predicting Future? A Comprehensive Survey of World Models.”, Jingtao Ding, Yunke Zhang, et al. ACM Computing Surveys 2025
7. “Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution.”, Fuxian Li, Jie Feng, et al. ACM TKDD 2023

Talks

1. “Utilizing LLM-based Agents for Human Mobility Modelling”, Invited Talk, PCC Young Scholars Forum @ HMCC&HHME2025, Dalian
2. “LLM-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science”, Tutorial, ACM SIGSPATIAL CHINA Saptial Data Intelligence 2025 Conference, Xiamen
3. “LLM-Based Agentic Framework: A Novel Paradigm for Modeling Human Mobility”, Invited Talk, ACM SIGSPATIAL CHINA Saptial Data Intelligence 2025 Conference, Xiamen
4. “CityGPT: From LLM to Urban Generative Intelligence”, Invited Talk, CCF ChinaData 2024 Conference, Boao