Xu Xun

• ACM MM 2024 Outstanding Area Chair
• EPTC 2022 Best Academic Paper
• Top 10% paper in ICIP 2015

• CAD-informed Automated Defect Detection System for BEOL Process; PI
• Heterogeneous Preference Learning for Value-Aligned Large Language Models in Multicultural Societies: A Resource-Efficient Approach; Co-I
• Towards Realistic Deep Learning for 3D Vision; Co-I
• Learning with Less Data; Co-I
• Exploiting Unlabeled Data, Cheaper Labels and Efficient Annotation for 3D Point Cloud Deep Learning; PI

1. T. Chen, Y. Li, A. Goodge, F. Teng, X. Yang, Z. Liang, T. Li, & Xun Xu*, Exploiting Vision Language Model for Training-Free 3D Point Cloud Understanding via Improved Graph Score Propagation, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

2. T. Chen, N. Liu, L. Yang, X. Yang, T. Li & X. Xu*, Test-Time Optimisation of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and Refinement, International Conference on Learning Representations (ICLR), 2026

3. Y. Su, H. Zhang, S. Li*, N. Liu, J. Liao, J. Pan, Y. Liu, X. Xing, C. Sun, C. Li, N. F. Chen, S. Yan, X. Yang & X. Xu*, Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs, International Conference on Learning Representations (ICLR), 2026

4. Y. Huang, Y. Su, X. Lin, L. Zhang & X. Xu*, Enhancing Generalisation of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularisation, The Annual AAAI Conference on Artificial Intelligence (AAAI), 2026

5. T. Chen, Y. Li, A. Goodge, F. Teng, X. Yang, T. Li & X. Xu*, Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation, IEEE/CVF International Conference on Computer Vision (ICCV), 2025

6. Y. Su, Y. Li, N. Liu, K. Jia, X. Yang, C-S Foo & X. Xu*, On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning,  International Conference on Learning Representations (ICLR), 2025

7. Y. Li, Y. Su, A. Goodge, K. Jia & X. Xu*, Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model, International Conference on Learning Representations (ICLR), 2025

8. Y. Su#, X. Xu#*, T. Li & K. Jia*, Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularised Self-Training, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

9. J. Liao, X. Xu*, M. C. Nguyen, A. Goodge & C. S. Foo, COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection, IEEE Transactions on Image Processing (TIP), 2024

10. H. Zhang, Y. Su, X. Xu* & K. Jia, Improving the Generalisation of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

11. Y. Su, X. Xu* & K. Jia, Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalisation, AAAI Conference on Artificial Intelligence (AAAI) 2024

12. Y. Li, X. Xu*, Y. Su & K. Jia*, On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion, IEEE/CVF Conference on Computer Vision (ICCV) 2023 (Oral Presentation; 1.8% acceptance rate)

13. Y. Su#, X. Xu#*, K. Jia*, Revisiting Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering, Neural Information Processing Systems (NeurIPS), 2022

14. X. Xu, C. M. Nguyen, Y. Yazici, K. Lu, H. Min & C. S. Foo, SemiCurv: Semi-Supervised Learning for Curvilinear Structure Segmentation, IEEE Transactions on Image Processing (TIP), 2022

15. Z. Jiang#, X. Xu#*, C. Zhang, C.S. Foo & C. Zhu*, MAGNet: a Multi-Attention Generative Adversarial Network for Defocus Blur Detection, IEEE Transactions on Image Processing (TIP), 2022

16. S. Deng#, X. Xu#, C. Wu, K. Chen, K. Jia, 3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

17. X. Xu, G.H. Lee, Weakly Supervised Semantic Point Cloud Segmentation: Towards 10X Fewer Labels, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

18. X. Xu, L.F. Cheong, Z. Li, 3D Rigid Motion Segmentation with Mixed and Unknown Number of Models, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019. 

19. X. Xu, L.F. Cheong & Z. Li, Motion Segmentation by Exploiting Complementary Geometric Models, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 

20. X. Xu, T. Hospedales, S. Gong, Zero-Shot Action Recognition by Word-Vector Embedding, International Journal of Computer Vision (IJCV), 2017.

21. X. Xu, T. Hospedales, S. Gong, Discovery of Shared Semantic Spaces for Multi-Scene Video Query and Summarization, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017.

22. X. Xu, T. Hospedales, & S. Gong. Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation, European Conference on Computer Vision (ECCV), 2016

23. X. Xu, T. Hospedales, S. Gong, Semantic Embedding Space for Zero-Shot Action Recognition, International Conference on Image Processing (ICIP), 2015 (Oral Presentation, Top 10% paper)

• Area Chair: NeurIPS, CVPR, ICLR, ACM MM, etc.
  Associate Editor: Neural Networks, Machine Vision & Applications
• IEEE Senior Member