Guanzhou Ke

Guanzhou Ke

Focus on multi-modal learning with missing modalities; UAV intelligence (VLN/VLA).

🕰️ Bio

I’m (Gavin) Guanzhou Ke, a Ph.D. candidate in Information Management at Beijing Jiaotong University (B.S. in Communication Engineering and M.S. in Systems Engineering from Wuyi University, 2019 and 2022). I work on multi-view / multi-modal representation learning, with a focus on incomplete or missing views and modalities and on fusion that remains expressive when data are partial.

My research has appeared at top venues including ICML, ICCV, CVPR, AAAI, and ACM MM (see News and publications below). Along the way I have been a CSC visiting Ph.D. student at Singapore Management University (with Prof. Shengfeng He) and have interned at Microsoft Research Asia and the Institute of Automation, CAS on multimodal and reliability-oriented problems. Recently I focus on embodied AI for UAVs, linking representation learning to vision-and-language navigation (VLN) and vision–language–action (VLA)-style autonomy.

Download my full CV as English PDF or 中文 PDF.

🎯 Interested

Embodied AI (UAV), Unified Visual Understanding and Generation, Large Multimodal models, Missing modality completion.

🔥 Status

I expect to graduate from Beijing Jiaotong University in June 2026. I am currently with Avant Robotics in Shenzhen, working on UAV intelligence—including high-quality benchmarks and stronger autonomous-drone algorithms that combine VLN and VLA (and related multimodal planning and control). Colleagues and peers in similar areas are very welcome to reach out; I enjoy exchanging ideas.

📣 News

  • [05/2026] Recognized as an ICML 2026 Gold Reviewer.
  • [05/2026] One paper accepted at ICML 2026 (CCF A).
  • [03/2026] One paper accepted at CVPR 2026 Findings (CCF A).
  • [06/2025] One paper accepted at ICCV 2025 (CCF A).
  • [02/2025] One paper accepted at CVPR 2025 (CCF A).
  • [12/2024] Two papers accepted at AAAI 2025 (CCF A).
  • [10/2024] CSC visiting Ph.D. student (1 year) at Singapore Management University.
  • [02/2024] Intern, AI4Science group, Microsoft Research Asia (Shanghai).
  • [02/2024] One paper accepted at CVPR 2024 (CCF A).
  • [10/2023] One paper accepted in *Information Fusion*.
  • [07/2023] One paper accepted at ACM MM 2023 (CCF A).
  • [10/2022] One paper accepted at ICDM Workshop 2022 (CCF B).
  • [09/2022] Started Ph.D. at Beijing Jiaotong University.
  • [12/2021] One paper accepted at IEEE BigData 2021 (CCF C).

💼 Internships

  • 12/2025 – Now: Research Intern
    • Avant Robotics, Shenzhen, China.
    • Duties: Design intelligent benchmarks for UAV autonomy, and develop hierarchical “big-brain / small-brain” algorithms for drones—covering high-level vision-and-language navigation (VLN), UAV vision–language–action (UAV-VLA), and related multimodal planning and control stacks.
    • Mentor: Zhenguo Li.
  • 02/2024 – 10/2024: Research Intern
    • Microsoft Research Lab - Asia (MSRA), Shanghai AI/ML Group.
    • Duties: Study medical report automatic generation technique.
    • Mentor: Xinyang Jiang.
  • 06/2023 – 12/2023: Research Intern
    • The Institute of Automation, Chinese Academy of Sciences.
    • Duties: Collect Deepfake data, including AIGC, Face swap, etc., and train model to detect fake information. (focus on multi-modalities, such as text and images).
    • Mentor: Bo Wang.

📄 Selected Publications

    Knowledge Bridger: Towards Training-free Missing Multi-modality Completion
    Guanzhou Ke, Shengfeng He, Xiao-Li Wang, Bo Wang, Guoqing Chao, Yuanyang Zhang, Xie Yi and HeXing Su
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    Rank: CCF A , MISC: [PDF] [CODE]
    Rethinking Multi-view Representation Learning via Distilled Disentangling
    Guanzhou Ke, Bo Wang, Xiaoli Wang, Shengfeng He
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    Rank: CCF A , MISC: [PDF] [CODE]
    Disentangling Multi-view Representations Beyond Inductive Bias
    Guanzhou Ke, Yang Yu, Guoqing Chao, Xiaoli Wang, Chenyang Xu, and Shengfeng He
    The 31st ACM International Conference on Multimedia (ACM MM 2023)
    Rank: CCF A , MISC: [PDF] [CODE]
    CONAN: Contrastive Fusion Networks for Multi-view Clustering
    Guanzhou Ke, Zhiyong Hong, Zhiqiang Zeng, Zeyi Liu, Yangjie Sun, and Yannan Xie
    IEEE International Conference on Big Data (Big Data)
    Rank: CCF C , MISC: [PDF] [CODE]

📄 Full Publications

You can also find my articles on my Google Scholar profile.

2026

Reliable Neighborhood-Aware Multi-View Outlier Detection
Huijie Ma, Haoyuan Xin, Lei Meng, Guanzhou Ke, Yongyong Chen, Guoqing Chao
International Conference on Machine Learning (ICML), 2026
Rank: CCF A , MISC: [PDF] [CODE]
OKGraph: Online Knowledge Graph Probing for Open-vocabulary Recognition
Junhui Yin, Zhizhen Cai, Puze Wang, Guanzhou Ke, Jianhua Yang, Man Zhang, Qiang Zhang, and Shengfeng He
IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings Track (CVPR Findings), 2026
Rank: CCF A , MISC: [PDF] [CODE]

2025

LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning
Jiang Yuan, JI Ma, Bo Wang, Guanzhou Ke, Weiming Hu
International Conference on Computer Vision (ICCV), 2025
Rank: CCF A , MISC: [PDF] [CODE]
Knowledge Bridger: Towards Training-free Missing Multi-modality Completion
Guanzhou Ke, Shengfeng He, Xiao-Li Wang, Bo Wang, Guoqing Chao, Yuanyang Zhang, Xie Yi and HeXing Su
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Rank: CCF A , MISC: [PDF] [CODE]
Global-Semantic Alignment Distillation for Partial Multi-view Classification
Xiao-Li Wang, Anqi Huang, Yongli Wang, Guanzhou Ke, Xiaobin Hong, and Jun Liu
The 39th Annual AAAI Conference on Artificial Intelligence (AAAI)
Rank: CCF A , MISC: [PDF] [CODE]
Incomplete Multi-view Clustering via Diffusion Contrastive Generation
Yuanyang Zhang, Weiqing Yan, Yijie Lin, Li Yao, Xinhang Wan, Guangyuan Li, Chao Zhang, Guanzhou Ke, and Jie Xu
The 39th Annual AAAI Conference on Artificial Intelligence (AAAI)
Rank: CCF A , MISC: [PDF] [CODE]

2024

Rethinking Multi-view Representation Learning via Distilled Disentangling
Guanzhou Ke, Bo Wang, Xiaoli Wang, and Shengfeng He
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Rank: CCF A , MISC: [PDF] [CODE]

2023

Knowledge distillation-driven semi-supervised multi-view classification
Xiaoli Wang, Yongli Wang, Guanzhou Ke, Yupeng Wang, and Xiaobin Hong
Information Fusion
Rank: SCI Q1 , MISC: [PDF] [CODE]
A Clustering-guided Contrastive Fusion for Multi-view Representation Learning
Guanzhou Ke, Guoqing Chao, Xiaoli Wang, Chenyang Xu, Yongqi Zhu, and Yang Yu
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Rank: CCF B , MISC: [PDF] [CODE]
Disentangling Multi-view Representations Beyond Inductive Bias
Guanzhou Ke, Yang Yu, Guoqing Chao, Xiaoli Wang, Chenyang Xu, and Shengfeng He
The 31st ACM International Conference on Multimedia (ACM MM 2023)
Rank: CCF A , MISC: [PDF] [CODE]

2022

MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion
Guanzhou Ke, Yongqi Zhu, and Yang Yu
ICDM workshop
Rank: CCF B , MISC: [PDF] [CODE]
Efficient Multi-view Clustering Networks
Guanzhou Ke, Zhiyong Hong, Wenhua Yu, Xin Zhang, and Zeyi Liu
Applied Intelligence Springer
Rank: CCF C , MISC: [PDF] [CODE]

2021

CONAN: Contrastive Fusion Networks for Multi-view Clustering
Guanzhou Ke, Zhiyong Hong, Zhiqiang Zeng, Zeyi Liu, Yangjie Sun, and Yannan Xie
IEEE International Conference on Big Data (Big Data)
Rank: CCF C , MISC: [PDF] [CODE]

🤝 Services

  • Journals: IEEE TMM, T-CSVT, T-NNLS, Neurocomputing, …
  • Conferences: NeurIPS, CVPR, ICML (Gold Reviewer), AAAI, ACM MM, …
Visitor map