| Cluster Alignment with a Teacher for Unsupervised Domain Adaptation Z Deng, Y Luo, J Zhu IEEE International Conference on Computer Vision 2019, 2019 | 323 | 2019 |
| Adversarial distributional training for robust deep learning Y Dong*, Z Deng*, T Pang, H Su, J Zhu Advances in Neural Information Processing Systems 33, 2020 | 172 | 2020 |
| Black-box Detection of Backdoor Attacks with Limited Information and Data Y Dong, X Yang, Z Deng, T Pang, Z Xiao, H Su, J Zhu ICCV 2021, 2021 | 161 | 2021 |
| Online speculative decoding X Liu, L Hu, P Bailis, I Stoica, Z Deng, A Cheung, H Zhang ICML, 2024 | 123 | 2024 |
| Batch Virtual Adversarial Training for Graph Convolutional Networks Z Deng, Y Dong, J Zhu AI Open, 2023 | 113 | 2023 |
| LiBRe: A Practical Bayesian Approach to Adversarial Detection Z Deng, X Yang, S Xu, H Su, J Zhu IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021, 2021 | 106 | 2021 |
| Exploring memorization in adversarial training Y Dong, K Xu, X Yang, T Pang, Z Deng, H Su, J Zhu ICLR 2022, 2022 | 105 | 2022 |
| Structured generative adversarial networks Z Deng, H Zhang, X Liang, L Yang, S Xu, J Zhu, EP Xing Advances in Neural Information Processing Systems, 2017 | 78 | 2017 |
| CLLMs: Consistency Large Language Models S Kou, L Hu, Z He, Z Deng, H Zhang ICML, 2024 | 63 | 2024 |
| Improved Operator Learning by Orthogonal Attention Z Xiao, Z Hao, B Lin, Z Deng, H Su ICML, 2024 | 41 | 2024 |
| Evaluating the robustness of text-to-image diffusion models against real-world attacks H Gao, H Zhang, Y Dong, Z Deng arXiv preprint arXiv:2306.13103, 2023 | 41 | 2023 |
| Autosync: Learning to synchronize for data-parallel distributed deep learning H Zhang, Y Li, Z Deng, X Liang, L Carin, E Xing Advances in Neural Information Processing Systems 33, 906-917, 2020 | 38 | 2020 |
| Realsafe-r1: Safety-aligned deepseek-r1 without compromising reasoning capability Y Zhang, Z Zeng, D Li, Y Huang, Z Deng, Y Dong arXiv preprint arXiv:2504.10081, 2025 | 35 | 2025 |
| Improved visual-spatial reasoning via r1-zero-like training Z Liao, Q Xie, Y Zhang, Z Kong, H Lu, Z Yang, Z Deng arXiv preprint arXiv:2504.00883, 2025 | 35 | 2025 |
| Cavs: An efficient runtime system for dynamic neural networks S Xu, H Zhang, G Neubig, W Dai, JK Kim, Z Deng, Q Ho, G Yang, EP Xing 2018 USENIX Annual Technical Conference (USENIX ATC 18), 937-950, 2018 | 33 | 2018 |
| NeuralEF: Deconstructing Kernels by Deep Neural Networks Z Deng, J Shi, J Zhu International Conference on Machine Learning (ICML) 162, https://proceedings …, 2022 | 32 | 2022 |
| Efficient detection of LLM-generated texts with a Bayesian surrogate model Y Miao, H Gao, H Zhang, Z Deng ACL 2024 Findings, 2024 | 31 | 2024 |
| AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models Z Zeng, Y Miao, H Gao, H Zhang, Z Deng Findings of EMNLP, 2024 | 30 | 2024 |
| Accelerated Linearized Laplace Approximation for Bayesian Deep Learning Z Deng, F Zhou, J Zhu Advances in Neural Information Processing Systems, 2022 | 27 | 2022 |
| Optimizing speculative decoding for serving large language models using goodput X Liu, C Daniel, L Hu, W Kwon, Z Li, X Mo, A Cheung, Z Deng, I Stoica, ... arXiv preprint arXiv:2406.14066, 2024 | 26 | 2024 |
Jun ZhuProfessor of Computer Science, Tsinghua University; IEEE/AAAI FellowVerified email at mail.tsinghua.edu.cn
