Back

Representative Works   

• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching. ICLR. 2026 (with my intern)
• Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction. Nexus (Cell Press). 2025 (1st author is me)
• Continual Multimodal Contrastive Learning. NeurIPS. 2025 (with my intern)
• L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models. NeurIPS. 2025 (with my intern)
• Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints. ICML. 2024 (1st author is me)
• LaVin-DiT: Large Vision Diffusion Transformer. CVPR. 2024 (with my friend)
• Part-Dependent Label Noise: Towards Instance-Dependent Label Noise. NeurIPS. 2020 (1st author is me)

Selected Publications

2026

1. X. Zhou, Z. Shi, H. Zeng, X. Xia, B. Jing, H. Wei. Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)
2. Z. Zhou, F. Ma, C. Gui, X. Xia, H. Fan, Y. Yang, T.S. Chua. AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)
3. D. Zhang, P. Chen, X. Xia, X. Su, R. Zhen, J. Xiao, S. Yang. APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)
4. R. Luo, X. Xia, L. Wang, L. Chen, R. Shan, J. Luo, M. Yang, T.S. Chua. NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching. International Conference on Learning Representations. (ICLR). (paper)
5. J. Lyu, L. Qu, W. Zhang, H. Jiang, K. Liu, Z. Zhou, X. Xia, J. Xue, T.S. Chua. AUHead: Realistic Emotional Talking Head Generation via Action Units Control. International Conference on Learning Representations. (ICLR). (paper)
6. Y. Zhou, J. Tang, S. Yang, X. Xiao, Y. Dai, W. Yang, C. Gou, X. Xia, T.S. Chua. Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models. AAAI Conference on Artificial Intelligence. (AAAI). (paper)
7. J. Su, Z. Nan, C. Chen, Y. Ma, X. Xia, X. Feng, W. Liu, X. Chen, X. Zheng. Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm. AAAI Conference on Artificial Intelligence. (AAAI). (paper)

2025

1. X. Liu, X. Xia, S.K. Ng, T.S. Chua. Continual Multimodal Contrastive Learning. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
2. R. Luo, R. Shan, L. Chen, Z. Liu, L. Wang, M. Yang, X. Xia. VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
3. X. Liu, X. Xia, W. Zhao, M. Zhang, X. Yu, X. Siu, S. Yang, S.K. Ng, T.S. Chua. L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
4. J. Guo, S. Yang, Y. Huang, Y. Long, X. Xia, X. Siu, B. Zhao, Z. Xie, L. Nie. UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
5. R. Luo, T.E. Lin, H. Zhang, Y. Wu, X. Liu, M. Yang, Y. Li, L. Chen, L. Zhang, X. Xia, H. Alinejad-Rokny, F. Huang. OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
6. X. Xia, X. Liu, J. Liu, K. Fang, L. Lu, S. Oymak, W. S. Currie, T. Liu. Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction. Nexus (Cell Press). (Nexus). (paper)
7. X. Liu, X. Xia, Z. Huang, S.K. Ng, T.S. Chua. Towards Modality Generalization: A Benchmark and Prospective Analysis. ACM International Conference on Multimedia. (ACM MM). (paper)
8. Y. Zhou, J. Tang, X. Xiao, Y. Lin, L. Liu, Z. Guo, H. Fei, X. Xia, C. Gou. Where, What, Why: Towards Explainable Driver Attention Prediction. IEEE/CVF International Conference on Computer Vision. (ICCV). (paper)
9. Z. Zhou, X. Xia, F. Ma, H. Fan, Y. Yang, T.S. Chua. DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization. International Conference on Machine Learning. (ICML). (paper)
10. 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. DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception. International Conference on Learning Representations. (ICLR). (paper)
11. L. Zhang, Y. Li, J. Li, X. Xia, J. Yang, R. Luo, M. Wang, L. Chen, J. Liu, M. Yang. Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs. AAAI Conference on Artificial Intelligence. (AAAI). (paper)
12. Z. Wang, X. Xia, R. Chen, D. Yu, C. Wang, M. Gong, T. Liu. LaVin-DiT: Large Vision Diffusion Transformer. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)

2024

1. S. Li, X. Xia, J. Deng, S. Ge, T. Liu. Transfering Annotator-and Instance-dependent Transition Matrix for Learning from Crowds. IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI). (paper)
2. J. Wang, X. Xia, L. Lan, X. Wu, J. Yu, W. Yang, B. Han, T. Liu. Tackling Noisy Labels with Network Parameter Additive Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI). (paper)
3. X. Xia, P. Lu, C. Gong, B. Han, J. Yu, J. Yu, T. Liu. Regularly Truncated M-estimators for Learning with Noisy Labels. IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI). (paper)
4. Y. Zhou, X. Xia, Z. Lin, B. Han, T. Liu. Few-Shot Adversarial Prompt Learning on Vision-Language Models. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
5. Y. Li, B. Hui, X. Xia, J. Yang, M. Yang, L. Zhang, S. Si, J. Liu, T. Liu, F. Huang, Y. Li. One Shot Learning as Instruction Data Prospector for Large Language Models. Annual Meeting of the Association for Computational Linguistics. (ACL). (paper)
6. X. Xia, J. Liu, S. Zhang, Q. Wu, H. Wei, T. Liu. Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints. International Conference on Machine Learning. (ICML). (paper)
7. M. Li, X. Xia, R. Wu, F. Huang, J. Yu, B. Han, T. Liu. Towards Realistic Model Selection for Semi-Supervised Learning. International Conference on Machine Learning. (ICML). (paper)
8. Y. Wu, J. Yao, X. Xia, J. Yu, R. Wang, B. Han, T. Liu. Mitigating Label Noise on Graph via Topological Sample Selection. International Conference on Machine Learning. (ICML). (paper)
9. S. Zhang, X. Xia, Z. Wang, L.H. Chen, J. Liu, Q. Wu, T. Liu. IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models. International Conference on Learning Representations. (ICLR). (paper)

2023

1. X. Xia, B. Han, N. Wang, J. Deng, J. Li, Y. Mao, T. Liu. Extended T: Learning with Mixed Closed-Set and Open-Set Noisy Labels. IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI). (paper)
2. H. Zheng, Q. Wang, Z. Fang, X. Xia, F. Liu, T. Liu, B. Han. Out-of-Distribution Detection Learning with Unreliable Out-of-Distribution Sources. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
3. L.H. Chen, J. Zhang, Y. Li, Y. Pang, X. Xia, T. Liu. HumanMAC: Masked Motion Completion for Human Motion Prediction. IEEE/CVF International Conference on Computer Vision. (ICCV). (paper)
4. X. Xia, B. Han, Y. Zhan, J. Yu, M. Gong, C. Gong, T. Liu. Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples. IEEE/CVF International Conference on Computer Vision. (ICCV). (paper)
5. X. Xia, J. Deng, W. Bao, Y. Du, B. Han, S. Shan, T. Liu. Holistic Label Correction for Noisy Multi-Label Classification. IEEE/CVF International Conference on Computer Vision. (ICCV). (paper)
6. Z. Huang, M. Zhu, X. Xia, L. Shen, J. Yu, C. Gong, B. Han, B. Du, T. Liu. Robust Generalization against Corruptions via Worst-Case Sharpness Minimization. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)
7. Z. Wu, T. He, X. Xia, X. Shen, J. Yu, T. Liu Conditional Consistency Regularization for Semi-Supervised Multi-Label Image Classification. IEEE Transactions on Multimedia. (TMM). (paper)
8. X. Xia, J. Liu, J. Yu, X. Shen, B. Han, T. Liu. Moderate Coreset: A Universal Method of Data Selection for Real-World Data-Efficient Deep Learning. International Conference on Learning Representations. (ICLR). (paper)
9. Z. Huang, X. Xia, L. Shen, B. Han, M. Gong, C. Gong, T. Liu. Harnessing Out-of-Distribution Examples via Augmenting Content and Style. International Conference on Learning Representations. (ICLR). (paper)
10. Y. Lin, R. Pi, W. Zhang, X. Xia, J. Gao, X. Zhou, T. Liu, B. Han. A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond. International Conference on Learning Representations. (ICLR). (paper)

2022

1. X. Xia, W. Yang, J. Ren, Y. Li, Y. Zhan, B. Han, T. Liu. Pluralistic Image Completion with Gaussian Mixture Models. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
2. S. Li, X. Xia, H. Zhang, Y. Zhan, S. Ge, T. Liu. Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
3. Y. Li, C. Wang, X. Xia, T. Liu, M. Xu, B. An. Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE. Advances in Neural Information Processing Systems. (NeurIPS). (paper)
4. X. Xia, S. Shan, M. Gong, N. Wang, F. Gao, H. Wei, T. Liu. Sample-Efficient Kernel Mean Estimation by Marginalized Corrupted Distributions. ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (KDD). (paper)
5. S. Li, X. Xia, S. Ge, T. Liu. Selective-Supervised Contrastive Learning with Noisy Labels. IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR). (paper)
6. X. Xia, T. Liu, B. Han, M. Gong, J. Yu, G. Niu, M. Sugiyama. Sample Selection with Uncertainty of Losses for Learning with Noisy Labels. International Conference on Learning Representations. (ICLR). (paper)
7. S. Yang, P. Sun, Y. Jiang, X. Xia, R. Zhang, Z. Yuan, C. Wang, P. Luo, M. Xu. Objects in Semantic Topology. International Conference on Learning Representations. (ICLR). (paper)

2021

1. S. Wu, X. Xia, T. Liu, B. Han, M. Gong, N. Wang, H. Liu, G. Niu. Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels. International Conference on Machine Learning. (ICML). (paper)
2. Z. Wu, X. Xia, R. Wang, J. Li, J. Yu, Y. Mao, T. Liu. LR-SVM+: Learning Using Privileged Information with Noisy Labels. IEEE Transactions on Multimedia. (TMM). (paper)
3. X. Xia, T. Liu, B. Han, C. Gong, N. Wang, Z. Ge, Y. Chang. Robust Early-Learning: Hindering the Memorization of Noisy Labels. International Conference on Learning Representations. (ICLR). (paper)

2020

1. X. Xia, T. Liu, B. Han, N. Wang, M. Gong, H. Liu, G. Niu, D. Tao, M. Sugiyama. Part-Dependent Label Noise: Towards Instance-Dependent Label Noise. Advances in Neural Information Processing Systems. (NeurIPS). (paper)

2019

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