Jianze Li

Shanghai Jiao Tong University — China

Mathematics · Physical Sciences

13h-index1.0kcitations57works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Tensor decomposition and applications(18), Matrix Theory and Algorithms(14), Sparse and Compressive Sensing Techniques(11), Blind Source Separation Techniques(6), Holomorphic and Operator Theory(5)

Publications57 total

SARSteer: Safeguarding Large Audio Language Models via Safe-Ablated Refusal Steering
arXiv (Cornell University)·2025Open Access
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
2025· 1 cited
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
BackdoorDM: A Comprehensive Benchmark for Backdoor Learning in Diffusion Model
arXiv (Cornell University)·2025Open Access
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
arXiv (Cornell University)·2025Open Access
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
arXiv (Cornell University)·2024Open Access
A sparse optimization approach for simultaneous orthogonal tensor diagonalization
Applied Mathematics and Computation·2024
Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator
arXiv (Cornell University)·2024Open Access
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
arXiv (Cornell University)·2024Open Access
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
arXiv (Cornell University)·2024· 1 citedOpen Access
Convergence analysis of the transformed gradient projection algorithms on compact matrix manifolds
arXiv (Cornell University)·2024Open Access
Projectively and Weakly Simultaneously Diagonalizable Matrices and their Applications
SIAM Journal on Matrix Analysis and Applications·2024· 1 cited
Lightweight Image Captioning Model Based on Knowledge Distillation
Lecture notes in computer science·2024
TAOTF: A Two-Stage Approximately Orthogonal Training Framework in Deep Neural Networks
Frontiers in artificial intelligence and applications·2023· 2 citedOpen Access
Convergence of Gradient-Based Block Coordinate Descent Algorithms for Nonorthogonal Joint Approximate Diagonalization of Matrices
SIAM Journal on Matrix Analysis and Applications·2023· 2 citedOpen Access
Polar Decomposition-based Algorithms on the Product of Stiefel Manifolds with Applications in Tensor Approximation
Journal of the Operations Research Society of China·2023· 7 cited
Jacobi-type algorithms for homogeneous polynomial optimization on Stiefel manifolds with applications to tensor approximations
Mathematics of Computation·2023· 5 cited
TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks
arXiv (Cornell University)·2022Open Access
Data-free Backdoor Removal based on Channel Lipschitzness
arXiv (Cornell University)·2022· 5 citedOpen Access
Data-Free Backdoor Removal Based on Channel Lipschitzness
Lecture notes in computer science·2022· 60 cited
page 1 of 3Next →

Frequent Co-authors

Konstantin Usevich(13), Pierre Comon(13), Thomas E. Smithgall(4), Weilin Lin(4), Li Liu(4), Xiao–Ping Zhang(3), Shuzhong Zhang(3), Stephen Jia Wang(3), Yulun Zhang(3), Yong Guo(3), Xiaokang Yang(3), Hui Xiong(3), Amy S. Lee(2), Alexander S. Banks(2), Lisa McKeag(2), Paul B. Rothman(2), Jim Rogers(2), Kristi L. Peters(2), Runkai Zheng(2), Rongjun Tang(2)