← Authors

Qianxiao Li

29 papers · 2017–2025 · 8 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (8) πŸƒ Academic Marathon (8) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) πŸ—ΊοΈ Taxonomy Completionist (30) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ† Keyword Champion (2) πŸ’Ž Century Club (29) ⚑ Prolific Year (9) πŸ—ƒοΈ Keyword Collector (77) πŸ”₯ Unstoppable (5)

Conferences

ICML (10) ICLR (8) JMLR (5) NIPS (2) AAAI (1) CVPR (1) ECCV (1) IJCAI (1)

Top co-authors

Weinan E (5) Zhong Li (5) Chi Zhang (4) Cheng Tai (3) Fusheng Liu (3) Haotian Jiang (3) REN Lianhai (2) Xiao-Yun Zhou (2) Shida Wang (2) Jiequn Han (2)

Keywords

optimal control (3) adversarial training (2) approximation theory (2) stochastic modified equation (2) adversarial attack (2) recurrent neural network (2) dynamical system (2) stochastic differential equation (2) weak approximation (2) pontryagin maximum principle (2) stochastic gradient descent (2) batch normalization (1) robust optimization (1) universal approximation (1) attention mechanism (1) model robustness (1) transformer architecture (1) sparse learning (1) deep learning (1) domain generalization (1)

Papers

From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control ICML 2025
Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images ICLR 2025
Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models ICLR 2025
BP-Modified Local Loss for Efficient Training of Deep Neural Networks ICLR 2025
Learning Macroscopic Dynamics from Partial Microscopic Observations NIPS 2024
Approximation Rate of the Transformer Architecture for Sequence Modeling NIPS 2024
An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers ECCV 2024
Inverse Approximation Theory for Nonlinear Recurrent Neural Networks ICLR 2024
Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving ICML 2024
From Generalization Analysis to Optimization Designs for State Space Models ICML 2024
StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization ICML 2024
Parameter-Efficient Fine-Tuning with Controls ICML 2024
Deep Neural Network Approximation of Invariant Functions through Dynamical Systems JMLR 2024
Principled Acceleration of Iterative Numerical Methods Using Machine Learning ICML 2023
Self-Healing Robust Neural Networks via Closed-Loop Control JMLR 2022
Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks JMLR 2022
Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate ICLR 2022
On the approximation properties of recurrent encoder-decoder architectures ICLR 2022
Adversarial Invariant Learning CVPR 2021
Approximation Theory of Convolutional Architectures for Time Series Modelling ICML 2021
Amata: An Annealing Mechanism for Adversarial Training Acceleration AAAI 2021
On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis ICLR 2021
Towards Robust Neural Networks via Close-loop Control ICLR 2021
A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent ICML 2019
Decentralized Optimization with Edge Sampling IJCAI 2019
Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations JMLR 2019
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks ICML 2018
Maximum Principle Based Algorithms for Deep Learning JMLR 2018
Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms ICML 2017