Yuhang Li

MINT: Multiplier-less Integer Quantization for Spiking Neural Networks

May 20, 2023
Ruokai Yin, Yuhang Li, Abhishek Moitra, Priyadarshini Panda

* 11 pages

Access Paper or Ask Questions

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Apr 25, 2023
Yuhang Li, Youngeun Kim, Hyoungseob Park, Priyadarshini Panda

Figure 2 for Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Figure 3 for Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Figure 4 for Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

* Published in Transactions on Machine Learning Research (TMLR)

Access Paper or Ask Questions

Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Apr 18, 2023
Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang, Ruihao Gong, Jinyang Guo, Xianglong Liu

Figure 2 for Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Figure 3 for Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Figure 4 for Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Access Paper or Ask Questions

Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer

Apr 12, 2023
Yuhang Li, Jingxi Li, Yifan Zhao, Tianyi Gan, Jingtian Hu, Mona Jarrahi, Aydogan Ozcan

$Figure 1 for Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer$

$Figure 2 for Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer$

$Figure 3 for Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer$

$Figure 4 for Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer$

* 33 Pages, 7 Figures

Access Paper or Ask Questions

SEENN: Towards Temporal Spiking Early-Exit Neural Networks

Apr 02, 2023
Yuhang Li, Tamar Geller, Youngeun Kim, Priyadarshini Panda

Figure 2 for SEENN: Towards Temporal Spiking Early-Exit Neural Networks

Figure 3 for SEENN: Towards Temporal Spiking Early-Exit Neural Networks

Figure 4 for SEENN: Towards Temporal Spiking Early-Exit Neural Networks

Access Paper or Ask Questions

Workload-Balanced Pruning for Sparse Spiking Neural Networks

Feb 13, 2023
Ruokai Yin, Youngeun Kim, Yuhang Li, Abhishek Moitra, Nitin Satpute, Anna Hambitzer, Priyadarshini Panda

Figure 2 for Workload-Balanced Pruning for Sparse Spiking Neural Networks

Figure 3 for Workload-Balanced Pruning for Sparse Spiking Neural Networks

Figure 4 for Workload-Balanced Pruning for Sparse Spiking Neural Networks

Access Paper or Ask Questions

Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network

Jan 19, 2023
Yuhang Li, Yi Luo, Deniz Mengu, Bijie Bai, Aydogan Ozcan

$Figure 1 for Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network$

$Figure 2 for Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network$

$Figure 3 for Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network$

$Figure 4 for Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network$

* 27 Pages, 7 Figures

Access Paper or Ask Questions

Yuhang Li

MINT: Multiplier-less Integer Quantization for Spiking Neural Networks

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer

SEENN: Towards Temporal Spiking Early-Exit Neural Networks

Workload-Balanced Pruning for Sparse Spiking Neural Networks

Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network

Exploring Temporal Information Dynamics in Spiking Neural Networks

Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies