Xinlin Li

Affiliations:
  • Microsoft, Mississauga, ON, Canada
  • Huawei Montreal Research Centre, Montreal, QC, Canada


According to our database1, Xinlin Li authored at least 15 papers between 2019 and 2023.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
Deep Neural Networks Pruning via the Structured Perspective Regularization.
SIAM J. Math. Data Sci., December, 2023

EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models.
SN Comput. Sci., September, 2023

Mathematical Challenges in Deep Learning.
CoRR, 2023

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DenseShift : Towards Accurate and Efficient Low-Bit Power-of-Two Quantization.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
DenseShift: Towards Accurate and Transferable Low-Bit Shift Network.
CoRR, 2022

Low-bit Shift Network for End-to-End Spoken Language Understanding.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

EuclidNets: Combining Hardware and Architecture Design for Efficient Training and Inference.
Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods, 2022

2021
S<sup>3</sup>: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks.
CoRR, 2021

S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Tensor train decompositions on recurrent networks.
CoRR, 2020

Clustering Causal Additive Noise Models.
CoRR, 2020

Importance of Data Loading Pipeline in Training Deep Neural Networks.
CoRR, 2020

2019
Random Bias Initialization Improving Binary Neural Network Training.
CoRR, 2019


  Loading...