Merge pull request #41 from yiliu30/new_paper

Add Outlier Suppression and Outlier Suppression+

README.md

@@ -127,6 +127,7 @@ Deep Neural Networks.
 - [[arxiv](https://arxiv.org/abs/2303.12557)] Q-HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction. 
 - [[arxiv](https://arxiv.org/abs/2303.12270)] EBSR: Enhanced Binary Neural Network for Image Super-Resolution. [__`bnn`__] 
 - [[arxiv](https://arxiv.org/abs/2303.15493)] Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis. [__`bnn`__] 
+- [[arxiv](https://arxiv.org/pdf/2304.09145.pdf)] Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling.
 
 
 
@@ -213,7 +214,7 @@ Deep Neural Networks.
 - [[TCCN](https://ieeexplore.ieee.org/abstract/document/9703679)] Low-Bitwidth Convolutional Neural Networks for Wireless Interference Identification. 
 - [[ASE](https://dl.acm.org/doi/abs/10.1145/3551349.3556916)] QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks. 
 - [[IJCNN](https://ieeexplore.ieee.org/abstract/document/9892671)] Accuracy Evaluation of Transposed Convolution-Based Quantized Neural Networks. 
-
+- [[NeurIPS]](https://arxiv.org/abs/2209.13325) Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models. [[code](https://github.com/wimh966/outlier_suppression)]
 
 ### 2021