📝 Publications

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion [Paper] [Code]
Wang Zhe Mark*, Kaixin Xu, Xue Geng, Fen Fang, Mohamed M. Sabry Aly, Xulei Yang, Min Wu, Weisi Lin

Efficient Distortion-minimized Layerwise Pruning [Paper]
Kaixin Xu, Zhe Wang, Runtao Huang, Xue Geng, Jie Lin, Xulei Yang, Min Wu, Xiaoli Li, Weisi Lin

LPViT: Low-Power Semi-structured Pruning for Vision Transformers [Paper] [Code]
Kaixin Xu, Zhe Wang, Chunyun Chen, Xue Geng, Jie Lin, Xulei Yang, Min Wu, Xiaoli Li, Weisi Lin

Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks [Paper] [Code]
Kaixin Xu, Zhe Wang, Xue Geng, Jie Lin, Min Wu, Xiaoli Li, Weisi Lin

MetaGrad: Adaptive Gradient Quantization with Hypernetworks [Paper]
Kaixin Xu, Alina Hui Xiu Lee, Ziyuan Zhao, Zhe Wang, Min Wu, Weisi Lin

Object-Aware Self-Supervised Multi-Label Learning [Paper] [Code]
Xu Kaixin, Liu Liyang, Zhao Ziyuan, Zeng Zeng, Bharadwaj Veeravalli