Paper Publications
-
[1] 张岩. RehearMixup: Improving rehearsal-based continual learning. Neurocomputing, 657, 2025.
-
[2] 王榕甄. A Theory for Conditional Generative Modeling on Multiple Data Sources. Forty-Second International Conference on Machine Learning (ICML 2025), 2025.
-
[3] 郑晨宇. Toward Understanding Generative Data Augmentation. 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.
-
[4] 庞腾. QFAE: Q-Function guided Action Exploration for offline deep reinforcement learning. Pattern Recognition, 158, 2024.
-
[5] 郑晨宇. Revisiting Discriminative vs. Generative Classifiers: Theory and Implications. 40th International Conference on Machine Learning, ICML 2023, 202, 42420-42477, 2023.
-
[6] 吴国强. Can Infinitely Wide Deep Nets Help Small-data Multi-label Learning?. 15th Asian Conference on Machine Learning, ACML 2023, 222, 1494-1509, 2024.
-
[7] 王丙正. DiffAIL: Diffusion Adversarial Imitation Learning. 38th AAAI Conference on Artificial Intelligence, AAAI 2024, 38, 15447-15455, 2024.
-
[8] 吴国强. Towards Understanding Generalization of Macro-AUC in Multi-label Learning. 40th International Conference on Machine Learning, ICML 2023, 202, 37540-37570, 2023.
