个人简介
刘昭强，电子科技大学教授、博士生导师，国家级青年人才。2013年本科毕业于清华大学数学系，2017年博士毕业于新加坡国立大学数学系，2024年加入电子科技大学。聚焦机器学习、计算机视觉与人工智能领域，主要从事扩散模型、大语言模型、高维逆问题、深度强化学习等相关的理论分析与应用研究。发表论文40余篇，其中第一或通讯作者论文30余篇（包含CCF A类或中科院JCR一区或同等级期刊/会议如IEEE T-IT、ICML、NeurIPS、ICLR、CVPR论文20余篇）。近年来致力于扩散模型相关研究，在 ICML、NeurIPS 等 CCF A 类会议发表论文 10 篇（通讯作者论文 7 篇）。
课题组以科研为导向，2024年入职以来，已指导多位本科生及研一/博一学生以第一作者于ICML/NeurIPS/AAAI/CVPR等机器学习/计算机视觉/人工智能顶级会议发表论文，其中包含一篇扩散语言模型方向的NeurIPS Spotlight。欢迎对科研有激情的博士后、博士生、硕士生、本科生发邮件与我联系！
讲授课程：深度生成模型（研究生课程），人工智能方法（本科生课程）
部分论文列表（*标明通讯作者）：
1. Wenhao Sun, Ji Li, and Zhaoqiang Liu*. Just-in-time: Training-free spatial acceleration for diffusion Transformers, accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
2. Yang Zheng, Jiahua Liu, Tongyao Pang, Wen Li, and Zhaoqiang Liu*. Outlier-robust diffusion solvers for inverse problems, accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
3. Youming Chen and Zhaoqiang Liu*. Diffusion model based signal recovery under 1-bit quantization, accepted to AAAI Conference on Artificial Intelligence (AAAI), 2026.
4. Feiyang Fu, Tongxian Guo, and Zhaoqiang Liu*. Learnable sampler distillation for discrete diffusion models, in Conference on Neural Information Processing Systems (NeurIPS), 2025. (Spotlight Presentation)
5. Yang Zheng, Wen Li, and Zhaoqiang Liu*. Integrating intermediate layer optimization and projected gradient descent for solving inverse problems with diffusion models, in International Conference on Machine Learning (ICML), 2025.
6. Anqi Tang, Youming Chen, Shuchen Xue, and Zhaoqiang Liu*. Learning single index models with diffusion priors, in International Conference on Machine Learning (ICML), 2025.
7. Yihang Gao, Chuanyang Zheng, Enze Xie, Han Shi, Tianyang Hu, Yu Li, Michael K. Ng, Zhenguo Li, and Zhaoqiang Liu*. AlgoFormer: An efficient Transformer framework with algorithmic structures, Transactions on Machine Learning Research, Jan. 2025.
8. Junren Chen, Michael K. Ng, and Zhaoqiang Liu. Solving quadratic systems with full-rank matrices using sparse or generative priors, IEEE Transactions on Signal Processing, Volume 73, pp. 477-492, Jan. 2025.
9. Zhaoqiang Liu, Wen Li, and Junren Chen. Generalized eigenvalue problems with generative priors, in Conference on Neural Information Processing Systems (NeurIPS), 2024.
10. Junren Chen, Zhaoqiang Liu, Meng Ding, and Michael K. Ng. Uniform recovery guarantees for quantized corrupted sensing with structured or generative priors, SIAM Journal on Imaging Sciences, Volume 17, Issue 3, pp. 1909-1977, Sep. 2024.
11. Jiajun Ma, Shuchen Xue, Tianyang Hu, Wenjia Wang, Zhaoqiang Liu, Zhenguo Li, Zhi-Ming Ma, and Kenji Kawaguchi. The surprising effectiveness of skip-tuning in diffusion sampling, in International Conference on Machine Learning (ICML), 2024.
12. Shuchen Xue, Zhaoqiang Liu*, Fei Chen, Shifeng Zhang, Tianyang Hu, Enze Xie, and Zhenguo Li. Accelerating diffusion sampling with optimized time steps, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
13. Junren Chen*, Jonathan Scarlett, Michael K. Ng, and Zhaoqiang Liu*. A unified framework for uniform signal recovery in nonlinear generative compressed sensing, in Conference on Neural Information Processing Systems (NeurIPS), 2023.
14. Enze Xie, Lewei Yao, Han Shi, Zhili Liu, Daquan Zhou, Zhaoqiang Liu, Jiawei Li, and Zhenguo Li. DiffFit: Unlocking transferability of large diffusion models via simple parameter-efficient fine-tuning, in International Conference on Computer Vision (ICCV), 2023. (Oral)
15. Yuanfeng Ji, Zhe Chen, Enze Xie, Lanqing Hong, Xihui Liu, Zhaoqiang Liu, Tong Lu, Zhenguo Li, and Ping Luo. DDP: Diffusion model for dense visual prediction, in International Conference on Computer Vision (ICCV), 2023.
16. Zhaoqiang Liu, Xinshao Wang, and Jiulong Liu. Misspecified phase retrieval with generative priors, in Conference on Neural Information Processing Systems (NeurIPS), 2022.
17. Jiulong Liu and Zhaoqiang Liu*. Non-iterative recovery from nonlinear observations using generative models, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
18. Zhaoqiang Liu, Jiulong Liu, Subhroshekhar Ghosh, Jun Han, and Jonathan Scarlett. Generative principal component analysis, in International Conference on Learning Representations (ICLR), 2022.
19. Zhaoqiang Liu, Subhroshekhar Ghosh, and Jonathan Scarlett. Towards sample-optimal compressive phase retrieval with sparse and generative priors, in Conference on Neural Information Processing Systems (NeurIPS), 2021.
20. Zhaoqiang Liu and Jonathan Scarlett. The generalized Lasso with nonlinear observations and generative priors, in Conference on Neural Information Processing Systems (NeurIPS), 2020.
21. Zhaoqiang Liu, Selwyn Gomes, Avtansh Tiwari, and Jonathan Scarlett. Sample complexity bounds for 1-bit compressive sensing and binary stable embeddings with generative priors, in International Conference on Machine Learning (ICML), 2020.
22. Zhaoqiang Liu and Jonathan Scarlett. Information-theoretic lower bounds for compressive sensing with generative models, IEEE Journal on Selected Areas in Information Theory, Volume 1, Issue 1, pp. 292-303, May 2020.
23. Zhaoqiang Liu and Vincent Tan. The informativeness of -means for learning mixture models, IEEE Transactions on Information Theory, Volume 65, Issue 11, pp. 7460-7479, Nov. 2019.
24. Zhaoqiang Liu and Vincent Tan. Rank-one NMF-based initialization for NMF and relative error bounds under a geometric assumption, IEEE Transactions on Signal Processing, Volume 65, Issue 18, pp. 4717-4731, Sep. 2017.
教育经历
2013.8-2017.12
新加坡国立大学 | 数学 博士研究生
2009.8-2013.7
清华大学 | 数学 本科
研究方向
[1] 扩散模型、大语言模型、高维逆问题、深度强化学习