| Improving adversarial robustness via promoting ensemble diversity T Pang, K Xu, C Du, N Chen, J Zhu International Conference on Machine Learning, 4970-4979, 2019 | 534 | 2019 |
| Composite quantization for approximate nearest neighbor search T Zhang, C Du, J Wang International Conference on Machine Learning, 838-846, 2014 | 268 | 2014 |
| Better diffusion models further improve adversarial training Z Wang, T Pang, C Du, M Lin, W Liu, S Yan International conference on machine learning, 36246-36263, 2023 | 261 | 2023 |
| Towards robust detection of adversarial examples T Pang, C Du, Y Dong, J Zhu Advances in neural information processing systems 31, 2018 | 240 | 2018 |
| On evaluating adversarial robustness of large vision-language models Y Zhao, T Pang, C Du, X Yang, C Li, NMM Cheung, M Lin Advances in Neural Information Processing Systems 36, 54111-54138, 2023 | 211 | 2023 |
| Rethinking softmax cross-entropy loss for adversarial robustness T Pang, K Xu, Y Dong, C Du, N Chen, J Zhu arXiv preprint arXiv:1905.10626, 2019 | 210 | 2019 |
| Lorahub: Efficient cross-task generalization via dynamic lora composition C Huang, Q Liu, BY Lin, T Pang, C Du, M Lin arXiv preprint arXiv:2307.13269, 2023 | 180 | 2023 |
| A recipe for watermarking diffusion models Y Zhao, T Pang, C Du, X Yang, NM Cheung, M Lin arXiv preprint arXiv:2303.10137, 2023 | 140 | 2023 |
| Weak-to-strong jailbreaking on large language models X Zhao, X Yang, T Pang, C Du, L Li, YX Wang, WY Wang arXiv preprint arXiv:2401.17256, 2024 | 65 | 2024 |
| Efficient diffusion policies for offline reinforcement learning B Kang, X Ma, C Du, T Pang, S Yan Advances in Neural Information Processing Systems 36, 67195-67212, 2023 | 64 | 2023 |
| Agent smith: A single image can jailbreak one million multimodal llm agents exponentially fast X Gu, X Zheng, T Pang, C Du, Q Liu, Y Wang, J Jiang, M Lin arXiv preprint arXiv:2402.08567, 2024 | 61 | 2024 |
| Max-mahalanobis linear discriminant analysis networks T Pang, C Du, J Zhu International Conference on Machine Learning, 4016-4025, 2018 | 60 | 2018 |
| Bag of tricks for training data extraction from language models W Yu, T Pang, Q Liu, C Du, B Kang, Y Huang, M Lin, S Yan International Conference on Machine Learning, 40306-40320, 2023 | 56 | 2023 |
| On memorization in diffusion models X Gu, C Du, T Pang, C Li, M Lin, Y Wang arXiv preprint arXiv:2310.02664, 2023 | 47 | 2023 |
| Finetuning text-to-image diffusion models for fairness X Shen, C Du, T Pang, M Lin, Y Wong, M Kankanhalli arXiv preprint arXiv:2311.07604, 2023 | 42 | 2023 |
| Collaborative filtering with user-item co-autoregressive models C Du, C Li, Y Zheng, J Zhu, B Zhang Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 41 | 2018 |
| Improved techniques for optimization-based jailbreaking on large language models X Jia, T Pang, C Du, Y Huang, J Gu, Y Liu, X Cao, M Lin arXiv preprint arXiv:2405.21018, 2024 | 34 | 2024 |
| Test-time backdoor attacks on multimodal large language models D Lu, T Pang, C Du, Q Liu, X Yang, M Lin arXiv preprint arXiv:2402.08577, 2024 | 32 | 2024 |
| Learning deep generative models with doubly stochastic gradient MCMC C Du, J Zhu, B Zhang IEEE transactions on neural networks and learning systems 29 (7), 3084-3096, 2017 | 28* | 2017 |
| Robust deep learning via reverse cross-entropy training and thresholding test T Pang, C Du, J Zhu arXiv preprint arXiv:1706.00633 3, 2017 | 28 | 2017 |
Tianyu PangSenior Research Scientist, Sea AI LabE-mail megerősítve itt: sea.com
