About Me

Gen Li is a third-year Ph.D. student at Clemson University, under the supervision of Prof. Xiaolong Ma and co-advised by Prof. Linlke Guo. His primary research focuses on efficient Machine Learning, algorithm-hardware co-design for mobile devices, and fairness and robustness in broad AI applications.

🔥 News

09/2024, One paper is accepted in NeurIPS 2024

09/2024, One paper is accepted in S&P 2025

07/2024, One paper is accepted in ECCV 2024

05/2024, Two papers are accepted in ICML 2024.

01/2024, One paper is accepted in ICLR 2024.

09/2023, One paper is accepted in NeurIPS 2023.

02/2023, One paper is accepted with spotlight presentation at the ICLR SNN workshop.

02/2023, One paper is accepted as highlight paper (top 2.5%) in CVPR 2023.

Selected Publications

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design

Gen Li, Zhihao Shu, Jie Ji, Minghai Qin, Fatemeh Afghah, Wei Niu, Xiaolong Ma

ECCV '24 · Acceptance rate: 27.9%

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

Jie Ji*, Gen Li*, Lu Yin, Minghai Qin, Geng Yuan, Linke Guo, Shiwei Liu, Xiaolong Ma

ICML '24 · Acceptance rate: 27.5%

Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity

Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Gen Li, Ajay Jaiswal, Mykola Pechenizkiy, Yi Liang, Michael Bendersky, Zhangyang Wang, Shiwei Liu

ICML '24 · Acceptance rate: 27.5%

NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization

Gen Li, Lu Yin, Jie Ji, Wei Niu, Minghai Qin, Bin Ren, Linke Guo, Shiwei Liu, Xiaolong Ma

ICLR '24

Dynamic Sparsity Is Channel-Level Sparsity Learner

Lu Yin, Gen Li, Meng Fang, Li Shen, Tianjin Huang, Zhangyang Wang, Vlado Menkovski, Xiaolong Ma, Mykola Pechenizkiy, Shiwei Liu

NeurIPS '23 · Acceptance rate: 26.1%

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

Gen Li, Jie Ji, Minghai Qin, Wei Niu, Bin Ren, Fatemeh Afghah, Linke Guo, Xiaolong Ma

CVPR '23 · Highlight paper: top 2.5%