avatar

Jiuming Liu

PhD student
University of Cambridge
liujiuming123@gmail.com


Jiuming Liu (刘久铭)

I am a second-year PhD student in the Intelligent Interactive Systems Group, Machine Intelligence Lab from Department of Engineering, University of Cambridge, supervised by Professor Per Ola Kristensson. I also work closely with Professor Ayush Tewari and Professor Shangzhe (Elliott) Wu from the computer vision group. My doctoral study is generously fully-funded by the Trinity Hall International Scholarship and Cambridge Trust. Previously, I got my master degree at the IRMV Lab from Shanghai Jiao Tong University (SJTU), luckily supervised by Professor Hesheng Wang.

My research interests include a wide range of computer vision fields, especially how to perceive, comprehend, reconstruct, generate, and interact with realistic 2D/3D/4D worlds. I also visited the T Stone Robotics Institute at Chinese University of Hong Kong (CUHK), advised by Professor Yunhui Liu, and visited the DAMTP, University of Cambridge, advised by Professor Angelica Aviles-Rivero. I have published various top-tier papers in computer vision, machine learning, and robotics, including T-PAMI, CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI, ICRA, and IROS. I also actively served as the reviewer of conferences like CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, ICRA, IROS, and AAAI, and journals like IJCV, TCSVT, TGRS, TASE, IEEE RAL, etc.

Feel free to cooperate by contacting me at email: liujiuming123@gmail.com.

Research Interests

News

  • [Sep. 2026] Four papers are accepted by NeurIPS 2026, with one Oral.
  • [Jun. 2026] One paper about world action model in AR is accepted by ECCV2026.
  • [May. 2026] Our survey paper about interactive world model is released as preprint.
  • [Apr. 2026] One paper about vector graph-based world model is accepted by ICML2026 as Spotlight.
  • [Feb. 2026] Two papers about streamVLO and RL-based 360 saliency prediction are accepted by CVPR2026. streamVLO is selected as Highlight.
  • [Jan. 2026] One paper “ARFlow” about autoregressive optical flow estimation is accepted by ICLR2026.
  • [Nov. 2025] One paper “4DSTR” about 4D generation is accepted by AAAI2026.
  • [Oct. 2025] The journal version of our DifFlow3D about scene flow and 4D scene reconstruction is accepted by T-PAMI.
  • [Jun. 2025] Three papers about LiDAR generation, Gaussian splatting, and SLAM are accepted by IROS2025.
  • [Feb. 2025] Our paper “Mamba4D” is accepted by CVPR2025.
  • [Jan. 2025] Our paper “DVLO4D” is accepted by ICRA2025.
  • [Sep. 2024] Two papers about semantic segmentation and Gaussian Splatting-based point cloud interpolation are accepted by NeurIPS 2024.
  • [Aug. 2024] Our paper “DVLO” is selected as the Oral presentation in ECCV 2024.
  • [Jul. 2024] Our paper “DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment” is accepted to ECCV 2024.
  • [Feb. 2024] Our paper “3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling” is accepted to CVPR 2024.
  • [Feb. 2024] Our paper “DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement” is accepted to CVPR 2024.
  • [Feb. 2024] Our paper “SNI-SLAM: Semantic Neural Implicit SLAM” is accepted to CVPR 2024.

Publications

  1. NeurIPS 2026
    MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
    Jiuming Liu, Mengmeng Liu, Guangming Wang, Lihao Liu, Michael Ying Yang, Yunpeng Zhang, Francesco Nex, Hao Cheng, Hesheng Wang
    The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026
    Accepted

  2. NeurIPS 2026
    MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
    Jiuming Liu, Jianing Li, Mengmeng Liu, Hongyang He, Hesheng Wang, Per Ola Kristensson
    The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026
    Accepted

  3. NeurIPS 2026 Oral
    SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
    Xuyi Hu, Jin Lyu, Jiuming Liu, Yebin Liu, Silvia Zuffi, Liang An, Stefan Goetz
    The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026
    PDF BibTex Oral

  4. NeurIPS 2026
    UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
    Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui, Hongwei Xie, Guang Chen, Hangjun Ye, Francesco Nex, Hao Cheng, Michael Ying Yang
    The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026
    PDF BibTex Accepted

  5. Arxiv 2026
    Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
    Jiuming Liu, Chaojun Ni, Mengmeng Liu, Chensheng Peng, Fangjinhua Wang, Sitian Shen, Marc Pollefeys, Masayoshi Tomizuka, Ayush Tewari, Per Ola Kristensson
    Arxiv
    PDF Code BibTex Preprint

  6. ICLR 2026
    ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame Forecasting
    Jiuming Liu, Mengmeng Liu, Siting Zhu, Yunpeng Zhang, Jiangtao Li, Michael Ying Yang, Francesco Nex, Hao Cheng, Hesheng Wang
    The Fourteenth International Conference on Learning Representations (ICLR) 2026
    PDF Code BibTex Published

  7. ECCV 2026
    DriveVA: Video Action Models are Zero-Shot Drivers
    Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui, Hongwei Xie, Guang Chen, Hangjun Ye, Michael Ying Yang, Francesco Nex, and Hao Cheng
    The 19th European Conference on Computer Vision (ECCV) 2026
    PDF Code BibTex Published

  8. ICML 2026 Spotlight
    VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
    Chaokang Jiang, Desen Zhou, Jiuming Liu, Li Sun
    Forty-Third International Conference on Machine Learning (ICML) 2026
    PDF Code BibTex Spotlight

  9. CVPR 2026
    RL‑ScanIQA: Reinforcement-Learned Scanpaths for Blind 360° Image Quality Assessment
    Yujia Wang, Yuyan Li, Jiuming Liu, Fang-Lue Zhang, Xinhu Zheng, Neil.A Dodgson
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
    PDF Code BibTex Published

  10. CVPR 2026 Highlight
    StreamVLO: Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
    Mengmeng Liu, Jiuming Liu, Michael Ying Yang, Chaokang Jiang, Jiangtao Li, Yunpeng Zhang, Hesheng Wang, Francesco Nex, Hao Cheng
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
    PDF Code BibTex Highlight

  11. AAAI 2026
    4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation
    Mengmeng Liu, Jiuming Liu, Yunpeng Zhang, Jiangtao Li, Michael Ying Yang, Francesco Nex, Hao Cheng
    The 40th Annual AAAI Conference on Artificial Intelligence (AAAI)
    PDF Code BibTex Published

  12. T-PAMI 2025
    DifFlow3D: Hierarchical Diffusion Models for Uncertainty-Aware 3D Scene Flow Estimation
    Jiuming Liu, Weicai Ye, Guangming Wang, Chaokang Jiang, Lei Pan, Jinru Han, Zhe Liu, Guofeng Zhang, HeshengWang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
    PDF Code BibTex Published

  13. CVPR 2025
    Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
    Jiuming Liu, Jinru Han, Lihao Liu, Angelica I Aviles-Rivero, Chaokang Jiang, Zhe Liu, Hesheng Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
    PDF Code BibTex Published

  14. IROS 2025
    TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation
    Jiuming Liu, Zheng Huang, Mengmeng Liu, Tianchen Deng, Francesco Nex, Hao Cheng, Hesheng Wang
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025
    PDF Code BibTex Published

  15. ICRA 2025
    DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion
    Mengmeng Liu, Michael Ying Yang, Jiuming Liu, Yunpeng Zhang, Jiangtao Li, Oude Elberink Sander, George Vosselman, Hao Cheng
    IEEE International Conference on Robotics and Automation (ICRA), 2025
    Published

  16. ECCV 2024 Oral
    DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment
    Jiuming Liu, Dong Zhuo, Zhiheng Feng, Siting Zhu, Chensheng Peng, Zhe Liu, Hesheng Wang
    European Conference on Computer Vision (ECCV) 2024 (Oral)
    PDF Code BibTex Oral

  17. CVPR 2024
    DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement
    Jiuming Liu, Guangming Wang, Weicai Ye, Chaokang Jiang, Jinru Han, Zhe Liu, Guofeng Zhang, Dalong Du, Hesheng Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
    PDF Code BibTex Published

  18. NeurIPS 2024
    NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
    Chaokang Jiang, Dalong Du, Jiuming Liu, Siting Zhu, Zhenqiang Liu, Zhuang Ma, Zhujin Liang, Jie Zhou
    Advances in Neural Information Processing Systems, 2024
    PDF Code BibTex Published

  19. NeurIPS 2024
    Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
    Yu Zheng, Guangming Wang, Jiuming Liu, Marc Pollefeys, Hesheng Wang
    Advances in Neural Information Processing Systems, 2024
    PDF Code BibTex Published

  20. CVPR 2024
    3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
    Chaokang Jiang, Guangming Wang, Jiuming Liu, Hesheng Wang, Zhuang Ma, Zhenqiang Liu, Zhujin Liang, Yi Shan, Dalong Du
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
    PDF Code Project Page BibTex Published

  21. CVPR 2024
    Sni-slam: Semantic neural implicit slam
    Siting Zhu, Guangming Wang, Hermann Blum, Jiuming Liu, Liang Song, Marc Pollefeys, Hesheng Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
    PDF Code BibTex Published

  22. ICCV 2023
    RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration
    Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    PDF Code BibTex Published

  23. AAAI 2023
    TransLO: A Window-Based Masked Point Transformer Framework for Large-Scale LiDAR Odometry
    Jiuming Liu, Guangming Wang, Chaokang Jiang, Zhe Liu, Hesheng Wang
    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023
    PDF Code BibTex Published

Services

Conference Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.