Biography
I’m Yao Lu. My advisors are Xiaoniu Yang and Qi Xuan. My research interest are interpretable machine learning and efficient learning. I was graduated from Zhejiang University of Technology with a bachelor’s degree in electrical engineering and its automation on June, 2021. I am always open for academic collaboration. You can contact me through email yaolu.zjut@gmail.com.
Latest News
07/2022: One paper accepted by ECCV
02/2023: One paper accepted by ICASSP
05/2023: One papar accepted by TNNLS
10/2024: One papar accepted by Neurocomputing
12/2024: One papar accepted by TCCN
Experience
Research Intern in IS2 Lab @ Zhejiang University, supervised by Jingyi Wang.
Research Intern in Zhou Group @ A*STAR, supervised by Tianyi Zhou. (2025.04-2026.04)
Selected Publications
Conference
Understanding the Dynamics of DNNs Using Graph Modularity
Yao Lu, Wen Yang, Yunzhe Zhang, Zuohui Chen, Jinyin Chen, Qi Xuan, Zhen Wang, Xiaoniu Yang
European Conference on Computer Vision (ECCV), 2022
arXiv code poster
SR-init: An Interpretable Layer Pruning Method
Hui Tang*, Yao Lu*, Qi Xuan
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023, Oral
arXiv code
RK-core: An Established Methodology for Exploring the Hierarchical Structure within Datasets
Yao Lu, Yutian Huang, Jiaqi Nie, Zuohui Chen, Qi Xuan
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
paper code
SepPrune: Structured Pruning for Efficient Deep Speech Separation
Yuqi Li, Kai Li, Xin Yin, Zhifei Yang, Zeyu Dong, Zhengtao Yao, Haoyan Xu, Yingli Tian, Yao Lu (Corresponding author)
The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)
paper code
AutoAnnotator: A Collaborative Annotation Framework for Large and Small Language Models
Yao Lu, Zhaiyuan Ji, Jiawei Du, Shanqing Yu, Qi Xuan, Joey Tianyi Zhou
Transactions on Machine Learning Research, 2025
paper code
Reassessing Layer Pruning in LLMs: New Insights and Methods
Yao Lu, Hao Cheng, Yujie Fang, Zeyu Wang, Jiaheng Wei, Dongwei Xu, Qi Xuan, Zhaowei Zhu
International Conference on Learning Representations (ICLR), 2026
paper code
DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning
Yaxin Gao*, Yao Lu*, Zongfei Zhang, Jiaqi Nie, Shanqing Yu, Qi Xuan
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026
paper
Journal
A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models
Yao Lu, Yutao Zhu, Yuqi Li, Dongwei Xu, Yun Lin, Qi Xuan, Xiaoniu Yang
IEEE Transactions on Cognitive Communications and Networking (TCCN), 2024
Early Assess code
Dataset distillation with pre-trained models: A contrastive approach
Yao Lu, Xuguang Chen, Jianyang Gu, Yuchen Zhang, Qi Xuan, Zhaowei Zhu
Neurocomputing
Early Assess code
DUSE: A data expansion framework for low-resource automatic modulation recognition based on active learning
Yao Lu, Hongyu Gao, Zhuangzhi Chen, Zhenhua Huang, Dongwei Xu, Yun Lin, Qi Xuan, Guan Gui
Digital Signal Processing
Early Assess
HSCP : A two-stage spectral clustering framework for resource-constrained UAV identification
Maoyu Wang, Yao Lu, Bo Zhou, Zhuangzhi Chen, Yun Lin, Qi Xuan, Guan Gui
Digital Signal Processing
Early Assess
Graph-based similarity of neural network representations
Zuohui Chen*, Yao Lu*, JinXuan Hu, Qi Xuan, Zhen Wang, Xiaoniu Yang
Neurocomputing
Early Assess code
RGP: Neural Network Pruning through Its Regular Graph Structure
Zhuangzhi Chen*, Jingyang Xiang*, Yao Lu, Qi Xuan, Zhen Wang, Guanrong Chen, Xiaoniu Yang
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
Early Assess code
Academic Service
Reviewer of ICLR2025, CVPR2025, TNNLS
Honors & Awards
On behalf of all graduate students, I delivered a speech at the school opening ceremony.