欢迎访问地理空间具身智能实验室 Geospatial Embodied Intelligence Lab · GeoEMI Lab
Multiple outdoor drones, a ground robot, multi-view cameras, and 3D spatial perception

About Me

I am an Associate Professor and Ph.D. supervisor at the School of Automation, Southeast University. I currently lead the Geospatial Embodied Intelligence Lab (GeoEMI Lab). Before joining Southeast University in 2017, I received my Ph.D. in Computer Engineering from Iowa State University in 2016, M.S. degree from the University of Science and Technology of China in 2012, and B.S. degree from Shandong University in 2009.

My research focuses on embodied spatial intelligence for unmanned systems, visual navigation, robot learning, autonomous localization, and multimodal environmental perception and reasoning. As first or corresponding author, I have published papers in venues including IEEE TPAMI, IEEE TMM, IEEE TNNLS, IEEE RA-L, ICLR, CVPR, ECCV, and AAAI.

News

  • One paper accepted to ACM MM 2026!
  • One paper accepted to ECCV 2026: UniDynamics!
  • One paper published in Neural Networks: W2W-BEV!
  • One paper accepted to IEEE TPAMI: ImagineNav++!
  • Two papers accepted to CVPR, including one Highlight paper!
  • One paper accepted to IEEE TMM!
  • One paper accepted to AAAI!

Research Interests

Embodied Spatial Intelligence

Spatial understanding, scene imagination, and decision making for unmanned systems.

Vision-and-Language Navigation

Navigation policies, trajectory forecasting, and language-guided robot learning.

Cross-view Geo-localization

Cross-view & cross-modal representation learning.

Event-based Vision

Event-stream 3D spatial understanding.

Selected Publications

# equal contribution, * corresponding author.

  1. Backdoor attacks in scene graph generation thumbnail ACM MM'26

    Understanding Backdoor Attacks in Scene Graph Generation via Global Context Pathway.

    Xiaoguang Chang, Tuo Chen, Chengze Jiang, Teng Wang*, Changyin Sun.

    ACM International Conference on Multimedia (ACM MM), 2026.

  2. UniDynamics future 4D dynamic scene generation thumbnail ECCV'26

    UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation.

    Daikun Liu#, Xin Zhan#, Teng Wang*, Xiaoping Wang*, Changyin Sun.

    European Conference on Computer Vision (ECCV), 2026.

  3. W2W-BEV framework thumbnail NN'26

    Window-to-window BEV Representation Learning for Limited FoV Cross-view Geo-localization.

    Lei Cheng, Daikun Liu, Lingquan Meng, Teng Wang*, Changyin Sun.

    Neural Networks, 203: 109099, 2026. DOI PDF

  4. ImagineNav++ framework thumbnail TPAMI'26

    ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination.

    Teng Wang#,*, Xinxin Zhao#, Wenzhe Cai, Changyin Sun.

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026. DOI arXiv

  5. AutoTraces trajectory forecasting thumbnail CVPR'26

    AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models.

    Teng Wang*, Yanting Lu, Ruize Wang.

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

  6. HypoDepth qualitative results thumbnail CVPR'26

    Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation.

    Daikun Liu, Teng Wang*, Changyin Sun.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. Highlight PDF

  7. Remote sensing image-text retrieval examples thumbnail TMM'26

    Multimodal Large Language Models Assisted Hierarchical Image-Caption Fusion for Remote Sensing Image-Text Retrieval.

    Teng Wang*, Ruize Wang, Lingquan Meng, Changyin Sun.

    IEEE Transactions on Multimedia (TMM), 2026. DOI

  8. First Learn, Then Review framework thumbnail AAAI'26

    First Learn, Then Review: Human-like Continual Learning for Cross-View Geo-localization with Limited Field of View.

    Lei Cheng, Daikun Liu, Zhikun Chen, Teng Wang*.

    The 40th AAAI Conference on Artificial Intelligence (AAAI), 2026. AAAI PDF

  9. Hierarchical motion aggregation optical flow thumbnail RA-L'25

    Seeing Beyond Local Events: Recurrent Optical Flow Estimation with Hierarchical Motion Aggregation.

    Daikun Liu, Teng Wang*, Changyin Sun.

    IEEE Robotics and Automation Letters, 10(11): 11721-11728, 2025.

  10. EDCFlow framework thumbnail CVPR'25

    EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation.

    Daikun Liu, Lei Cheng, Teng Wang*, Changyin Sun.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. arXiv

  11. ImagineNav framework thumbnail ICLR'25

    ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination.

    Xinxin Zhao#, Wenzhe Cai#, Likun Tang, Teng Wang*.

    International Conference on Learning Representations (ICLR), 2025. arXiv

  12. Vision-and-language navigation with LLM thumbnail RA-L'25

    Boosting Efficient Reinforcement Learning for Vision-and-Language Navigation with Open-Sourced LLM.

    Jiawei Wang, Teng Wang*, Wenzhe Cai, Lele Xu, Changyin Sun.

    IEEE Robotics and Automation Letters, 10(1): 612-619, 2025.

  13. Voxel-based multi-scale transformer event stream processing thumbnail TCSVT'24

    Voxel-based Multi-scale Transformer Network for Event Stream Processing.

    Daikun Liu, Teng Wang*, Changyin Sun.

    IEEE Transactions on Circuits and Systems for Video Technology, 34(4): 2112-2124, 2024.

  14. DeHi decoupled hierarchical architecture thumbnail TCSVT'24

    DeHi: A Decoupled Hierarchical Architecture for Unaligned Ground-to-Aerial Geo-localization.

    Teng Wang, Jiawen Li, Changyin Sun*.

    IEEE Transactions on Circuits and Systems for Video Technology, 34(3): 1927-1940, 2024.

  15. Dynamic-to-static image translation thumbnail PR'22

    A Coarse-to-Fine Approach for Dynamic-to-Static Image Translation.

    Teng Wang*, Lin Wu, Changyin Sun.

    Pattern Recognition, 123: 1-14, 2022.

  16. Attention-based road registration thumbnail TNNLS'21

    Attention-based Road Registration for GPS-denied UAS Navigation.

    Teng Wang, Ye Zhao, Jiawei Wang, Arun K. Somani, Changyin Sun*.

    IEEE Transactions on Neural Networks and Learning Systems, 32(4): 1788-1800, 2021.

Grants

  • National Natural Science Foundation of China, General Program, 2023.01-2026.12, PI.
  • National Natural Science Foundation of China, Key Program, 2023.01-2027.12, participant.
  • National Natural Science Foundation of China, Young Scientists Fund, 2019.01-2021.12, PI.

Honors

  • First Prize of Science and Technology Progress Award, Chinese Association of Automation.
  • Zhishan Young Scholar, Southeast University.