| 2025 | ICLR | Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models. | Fusheng Liu, Qianxiao Li |
| 2025 | ICLR | BP-Modified Local Loss for Efficient Training of Deep Neural Networks. | Lianhai Ren, Qianxiao Li |
| 2025 | ICLR | Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images. | Aiqing Zhu, Yuting Pan, Qianxiao Li |
| 2025 | ICML | From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control. | Chi Zhang, Lianhai Ren, Jingpu Cheng, Qianxiao Li |
| 2024 | ECCV | An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers. | Chi Zhang, Jingpu Cheng, Qianxiao Li |
| 2024 | ICLR | Inverse Approximation Theory for Nonlinear Recurrent Neural Networks. | Shida Wang, Zhong Li, Qianxiao Li |
| 2024 | ICML | Parameter-Efficient Fine-Tuning with Controls. | Chi Zhang, Jingpu Cheng, Yanyu Xu, Qianxiao Li |
| 2024 | ICML | Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving. | Sohei Arisaka, Qianxiao Li |
| 2024 | ICML | From Generalization Analysis to Optimization Designs for State Space Models. | Fusheng Liu, Qianxiao Li |
| 2024 | ICML | StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization. | Shida Wang, Qianxiao Li |
| 2023 | ICML | Principled Acceleration of Iterative Numerical Methods Using Machine Learning. | Sohei Arisaka, Qianxiao Li |
| 2022 | ICLR | On the approximation properties of recurrent encoder-decoder architectures. | Zhong Li, Haotian Jiang, Qianxiao Li |
| 2022 | ICLR | Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate. | Yingtian Zou, Fusheng Liu, Qianxiao Li |
| 2021 | AAAI | Amata: An Annealing Mechanism for Adversarial Training Acceleration. | Nanyang Ye, Qianxiao Li, Xiao-Yun Zhou, Zhanxing Zhu |
| 2021 | CVPR | Adversarial Invariant Learning. | Nanyang Ye, Jingxuan Tang, Huayu Deng, Xiao-Yun Zhou, Qianxiao Li, Zhenguo Li, Guang-Zhong Yang, Zhanxing Zhu |
| 2021 | ICLR | Towards Robust Neural Networks via Close-loop Control. | Zhuotong Chen, Qianxiao Li, Zheng Zhang |
| 2021 | ICLR | On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis. | Zhong Li, Jiequn Han, Weinan E, Qianxiao Li |
| 2021 | ICML | Approximation Theory of Convolutional Architectures for Time Series Modelling. | Haotian Jiang, Zhong Li, Qianxiao Li |
| 2019 | ICML | A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent. | Yongqiang Cai, Qianxiao Li, Zuowei Shen |
| 2019 | IJCAI | Decentralized Optimization with Edge Sampling. | Chi Zhang, Qianxiao Li, Peilin Zhao |
| 2018 | ICML | An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks. | Qianxiao Li, Shuji Hao |
| 2017 | ICML | Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms. | Qianxiao Li, Cheng Tai, Weinan E |