Selected Publications (*equal, #correspondence)

1. Xitong Gao*, Yiren Zhao*, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu. Dynamic Channel Pruning: Feature Boosting and Suppression. International Conference on Learning Representations (ICLR), 2019. [人工智能高水平会议。]

2. Yiren Zhao*#, Xitong Gao*#, Daniel Bates, Robert Mullins, Cheng-Zhong Xu. Focused Quantization for Sparse CNNs. Advances in Neural Information Processing Systems (NeurIPS), 2019. [CCF A, 人工智能高水平会议。]

3. Kafeng Wang*#, Xitong Gao*#, Yiren Zhao, Xingjian Li, Dejing Dou, Cheng-Zhong Xu. Pay Attention to Features, Transfer Learn Faster CNNs. International Conference on Learning Representations (ICLR), 2020. [人工智能高水平会议。]

4. Yunrui Yu*, Xitong Gao*, Cheng-Zhong Xu. LAFEAT: Piercing Through Adversarial Defenses with Latent Features. Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [Oral presentation, CCF A, 计算机视觉高水平会议。]

5. Yunrui Yu*, Xitong Gao*, Cheng-Zhong Xu. MORA: Improving Ensemble Robustness Evaluation with Model Reweighing Attack. Advances in Neural Information Processing Systems (NeurIPS), 2022. [CCF A, 人工智能高水平会议。]

6. Yiren Zhao#, Xitong Gao#, Ilia Shumailov, Nicolo Fusi, Robert Mullins. Rapid model architecture adaption for meta-learning. Advances in Neural Information Processing Systems (NeurIPS), 2022. [CCF A, 人工智能高水平会议。]

7. Dongping Liao*, Xitong Gao*, Yiren Zhao, Cheng-Zhong Xu. Adaptive channel sparsity for federated learning under system heterogeneity. Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [CCF A, 计算机视觉高水平会议。]

8. Xinquan Chen*, Xitong Gao*#, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu. AdvDiffuser: Natural adversarial example synthesis with diffusion models. International Conference on Computer Vision (ICCV), 2023. [CCF A, 计算机视觉高水平会议。]

9. Yunrui Yu*, Xitong Gao*, Cheng-Zhong Xu. LAFIT: Efficient and Reliable Evaluation of Adversarial Defenses With Latent Features. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. [CCF A, JCR 1区, IF=23.6, 人工智能高水平期刊。]

10. Dongping Liao*, Xitong Gao*, Cheng-Zhong Xu. Impartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization. AAAI Conference on Artificial Intelligence (AAAI), 2024. [CCF A, 人工智能高水平会议。]

11. Tianrui Qin*, Xitong Gao*#, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu. APBench: A Unified Availability Poisoning Attack and Defenses Benchmark. Transactions on Machine Learning Research (TMLR), 2024. [人工智能领域的新兴高影响力期刊。]

12. Dongping Liao*, Xitong Gao*, Yabo Xu, Cheng-Zhong Xu. Progressive Distribution Matching for Federated Semi-supervised Learning. AAAI Conference on Artificial Intelligence (AAAI), 2025. [CCF A, 人工智能高水平会议。]

13. Xuan Wang*, Xitong Gao*#, Dongping Liao, Yuliang Lu#, Cheng-Zhong Xu. A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment. Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [CCF A, 人工智能高水平会议。]

14. Tianrui Qin, Xuan Wang, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu, Xitong Gao#. On the Adversarial Robustness of Visual-Language Chat Models. International Conference on Multimedia Retrieval (ICMR), 2025. [CCF B, 多媒体高水平会议。]

15. Xinxin Liu, Aaron Thomas, Cheng Zhang, Jianyi Cheng, Yiren Zhao, Xitong Gao#. Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models. The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025. [CCF A, 自然语言处理高水平会议。]

16. Xiang An*, Zixuan Huang*, Xitong Gao*, Kejiang Ye, Cheng-Zhong Xu. BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detection. ACM Multimedia (MM), 2025. [CCF A, 多媒体高水平会议。]

17. Guanghui Song, Dongping Liao, Yiren Zhao, Kejiang Ye, Cheng-Zhong Xu, Xitong Gao#. Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. [CCF B, 自然语言处理高水平会议。]

18. Xuan Wang, Siyuan Liang#, Dongping Liao, Han Fang, Aishan Liu, Xiaochun Cao, Yu-liang Lu, Ee-Chien Chang#, Xitong Gao#. Lie Detector: Unified Backdoor Detection via Cross-Examination Framework. To appear in The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. [CCF A, 已接收, 人工智能高水平会议。]

19. Dongping Liao*, Xitong Gao*, Cheng-zhong Xu. FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning. To appear in the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. [CCF A, 已接收, 人工智能高水平会议。]

20. Tianrui Qin, Xuan Wang, Xianghuan He, Yiren Zhao, Kejiang Ye, Cheng-Zhong Xu, Xitong Gao#. Flareon: Stealthy all2all Backdoor Injection via Poisoned Augmentation. Transactions on Knowledge Discoveryfrom Data (TKDD), 2025. [CCF B, 已接收, 数据挖掘高水平期刊。]

21. Dongping Liao, Xitong Gao#, Cheng-zhong Xu#. MAIR: Model Agnostic Instance Reweighing for Heterogeneous Federated Learning. To appear in the Transactions on Mobile Computing (TMC), 2025. [CCF A, 已接收, 移动计算高水平期刊。]

已指导学生

伍泰霖  硕士研究生  085211-计算机技术  

现指导学生

陈鑫泉  硕士研究生  085404-计算机技术  

邓仕圣  硕士研究生  081200-计算机科学与技术  

何祥焕  硕士研究生  085404-计算机技术  

郑富荣  硕士研究生  085404-计算机技术  

秦天睿  硕士研究生  085404-计算机技术  

韩冰茹  硕士研究生  085404-计算机技术  

冯坤  硕士研究生  085404-计算机技术  

洪烨  硕士研究生  085404-计算机技术  

宋宇辰  硕士研究生  085404-计算机技术  

严昊  硕士研究生  085404-计算机技术  

刘晓莹  硕士研究生  085404-计算机技术