|
Wei-Jie Xu Currently I am a master student of School of Artificial Intelligence in Nanjing University and a member of LAMDA group, led by Prof. Zhi-Hua Zhou. In June 2024, I received my B.Eng. degree from School of Computer Science and Technology, Soochow University. In the same year, I was admitted to study for a master's degree in School of Artificial Intelligence, Nanjing University under the supervision of Prof. Kai Ming Ting. Email / Github / Google Scholar / LinkedIn / ORCID |
|
News
- [Jan.2025] Released PIP (Perturbation-based Iterative Pruning for LLMs).
- [Sep.2024] Enrolled as a master student in Nanjing University.
Research
Currently, I'm interested in Machine Learning and Data Mining, especially in anomaly detection and clustering. And I'm also interested in Large Language Models.
If you are interested in the above fields, feel free to reach out to me via email or visit Room 506 in the Yifu Building for a discussion!
PIP (Perturbation-based Iterative Pruning), a novel double-view structured pruning method to optimize LLMs, which combines information from two different views: the unperturbed view and the perturbed view, establishing it as a leading technique for optimizing LLMs in environments with constrained resources.
We propose a novel distribution-based spectral clustering. Our method constructs an \(n \times k \) bipartite graph between n data points and k distributions, enabling the eigendecomposition of only a \(k \times k\) matrix and preserving clustering quality at the same time.
Award
- New Point Software Scholarship,[link],2021-2022, School of Computer Science and Technology, Soochow University.
Service
- Assistant at the Student Work, School of Computer Science and Technology, Soochow University
- Assistant at the Graduate Student Association, School of Artificial Intelligence, Nanjing University