Publications

Conference Papers, Journal Articles

(*) beside authors' names indicates equal contributions.

(✉) beside authors' names indicates the corresponding author.

Conference Papers

1. Towards Modality Generalization: A Benchmark and Prospective Analysis.
   X. Liu, X. Xia^✉, Z. Huang, S.K. Ng, T.S. Chua.
   In ACM International Conference on Multimedia (ACM MM 2025).
   (This paper was selected for oral presentation; rate: 4%)
   

2. Where, What, Why: Towards Explainable Driver Attention Prediction.
   Y. Zhou, J. Tang, X. Xiao, Y. Lin, L. Liu, Z. Guo, H. Fei, X. Xia, C. Gou.
   In IEEE/CVF International Conference on Computer Vision (ICCV 2025).
   (This paper was selected for a highlight paper; rate: 3%)
   

3. DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization.
   Z. Zhou, X. Xia^✉, F. Ma, H. Fan, Y. Yang^✉, T.S. Chua.
   In International Conference on Machine Learning (ICML 2025).
   

4. DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception.
   R. Luo, Y. Li, L. Chen, W. He, T.E. Lin, Z. Liu, L. Zhang, Z. Song, H. Alinejad-Rokny, X. Xia, T. Liu, B. Hui, M. Yang.
   In International Conference on Learning Representations (ICLR 2025).
   (This paper was selected for spotlight presentation; rate: 5%)
   

5. Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs.
   L. Zhang, Y. Li, J. Li, X. Xia, J. Yang, R. Luo, M. Wang, L. Chen, J. Liu, M. Yang.
   In AAAI Conference on Artificial Intelligence (AAAI 2025).
   

6. LaVin-DiT: Large Vision Diffusion Transformer.
   Z. Wang, X. Xia, R. Chen, D. Yu, C. Wang, M. Gong, T. Liu.
   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025).

7. Few-Shot Adversarial Prompt Learning on Vision-Language Models.
   Y. Zhou, X. Xia, Z. Lin, B. Han, T. Liu.
   In Advances in Neural Information Processing Systems (NeurIPS 2024).

8. One Shot Learning as Instruction Data Prospector for Large Language Models.
   Y. Li, B. Hui, X. Xia, J. Yang, M. Yang, L. Zhang, S. Si, J. Liu, T. Liu, F. Huang, Y. Li.
   In Annual Meeting of the Association for Computational Linguistics (ACL 2024).

9. Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints.
   X. Xia, J. Liu, S. Zhang, Q. Wu, H. Wei, T. Liu.
   In International Conference on Machine Learning (ICML 2024).
   (This paper was selected for spotlight presentation; rate: 4%; collected by OpenAI PaperBench)
   

10. Towards Realistic Model Selection for Semi-Supervised Learning.
    M. Li, X. Xia, R. Wu, F. Huang, J. Yu, B. Han, T. Liu.
    In International Conference on Machine Learning (ICML 2024).

11. Mitigating Label Noise on Graph via Topological Sample Selection.
    Y. Wu, J. Yao, X. Xia, J. Yu, R. Wang, B. Han, T. Liu.
    In International Conference on Machine Learning (ICML 2024).

12. IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models.
    S. Zhang*, X. Xia*^✉, Z. Wang, L.H. Chen, J. Liu, Q. Wu^✉, T. Liu.
    In International Conference on Learning Representations (ICLR 2024).

13. Out-of-Distribution Detection Learning with Unreliable Out-of-Distribution Sources.
    H. Zheng, Q. Wang, Z. Fang, X. Xia, F. Liu, T. Liu, B. Han.
    In Advances in Neural Information Processing Systems (NeurIPS 2023).

14. HumanMAC: Masked Motion Completion for Human Motion Prediction.
    L.H. Chen*, J. Zhang*, Y. Li, Y. Pang, X. Xia^✉, T. Liu.
    In IEEE/CVF International Conference on Computer Vision (ICCV 2023).

15. Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples.
    X. Xia, B. Han, Y. Zhan, J. Yu, M. Gong, C. Gong, T. Liu.
    In IEEE/CVF International Conference on Computer Vision (ICCV 2023).

16. Holistic Label Correction for Noisy Multi-Label Classification.
    X. Xia, J. Deng, W. Bao, Y. Du, B. Han, S. Shan, T. Liu.
    In IEEE/CVF International Conference on Computer Vision (ICCV 2023).

17. Robust Generalization against Corruptions via Worst-Case Sharpness Minimization.
    Z. Huang*, M. Zhu*, X. Xia, L. Shen, J. Yu, C. Gong, B. Han, B. Du, T. Liu.
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023).

18. Moderate Coreset: A Universal Method of Data Selection for Real-World Data-Efficient Deep Learning.
    X. Xia, J. Liu, J. Yu, X. Shen, B. Han, T. Liu.
    In International Conference on Learning Representations (ICLR 2023).

19. Harnessing Out-of-Distribution Examples via Augmenting Content and Style.
    Z. Huang, X. Xia, L. Shen, B. Han, M. Gong, C. Gong, T. Liu.
    In International Conference on Learning Representations (ICLR 2023).

20. A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond.
    Y. Lin*, R. Pi*, W. Zhang, X. Xia, J. Gao, X. Zhou, T. Liu, B. Han.
    In International Conference on Learning Representations (ICLR 2023).
    (This paper was selected for spotlight presentation; rate: 8%)
    

21. Pluralistic Image Completion with Gaussian Mixture Models.
    X. Xia*, W. Yang*, J. Ren, Y. Li, Y. Zhan, B. Han, T. Liu.
    In Advances in Neural Information Processing Systems (NeurIPS 2022).

22. Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning.
    S. Li, X. Xia, H. Zhang, Y. Zhan, S. Ge, T. Liu.
    In Advances in Neural Information Processing Systems (NeurIPS 2022).
    (This paper was selected for spotlight presentation; rate: 5%)
    

23. Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE.
    Y. Li*, C. Wang*, X. Xia, T. Liu, M. Xu, B. An.
    In Advances in Neural Information Processing Systems (NeurIPS 2022).

24. Sample-Efficient Kernel Mean Estimation by Marginalized Corrupted Distributions.
    X. Xia*, S. Shan*, M. Gong, N. Wang, F. Gao, H. Wei, T. Liu.
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022).

25. Selective-Supervised Contrastive Learning with Noisy Labels.
    S. Li, X. Xia, S. Ge, T. Liu.
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022).

26. Sample Selection with Uncertainty of Losses for Learning with Noisy Labels.
    X. Xia, T. Liu, B. Han, M. Gong, J. Yu, G. Niu, M. Sugiyama.
    In International Conference on Learning Representations (ICLR 2022).

27. Objects in Semantic Topology.
    S. Yang, P. Sun, Y. Jiang, X. Xia, R. Zhang, Z. Yuan, C. Wang, P. Luo, M. Xu.
    In International Conference on Learning Representations (ICLR 2022).

28. Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels.
    S. Wu*, X. Xia*, T. Liu, B. Han, M. Gong, N. Wang, H. Liu, G. Niu.
    In International Conference on Machine Learning (ICML 2021).

29. Robust Early-Learning: Hindering the Memorization of Noisy Labels.
    X. Xia, T. Liu, B. Han, C. Gong, N. Wang, Z. Ge, Y. Chang.
    In International Conference on Learning Representations (ICLR 2021).

30. Part-Dependent Label Noise: Towards Instance-Dependent Label Noise.
    X. Xia, T. Liu, B. Han, N. Wang, M. Gong, H. Liu, G. Niu, D. Tao, M. Sugiyama.
    In Advances in Neural Information Processing Systems (NeurIPS 2020).
    (This paper was selected for spotlight presentation; rate: 3%)
    

31. Are Anchor Points Really Indispensable in Label-Noise Learning?
    X. Xia, T. Liu, N. Wang, B. Han, C. Gong, G. Niu, M. Sugiyama.
    In Advances in Neural Information Processing Systems (NeurIPS 2019).

Journal Articles

1. Transfering Annotator-and Instance-dependent Transition Matrix for Learning from Crowds.
   S. Li, X. Xia, J. Deng, S. Ge, T. Liu.
   In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2024).

2. Tackling Noisy Labels with Network Parameter Additive Decomposition.
   J. Wang, X. Xia, L. Lan, X. Wu, J. Yu, W. Yang, B. Han, T. Liu.
   In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2024).

3. Regularly Truncated M-estimators for Learning with Noisy Labels.
   X. Xia*, P. Lu*, C. Gong, B. Han, J. Yu, J. Yu, T. Liu.
   In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2024).

4. Extended T: Learning with Mixed Closed-Set and Open-Set Noisy Labels.
   X. Xia, B. Han, N. Wang, J. Deng, J. Li, Y. Mao, T. Liu.
   In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2023).