1. Information Title: Locating and Editing Factual Associations in GPT Link: ROME Paper Source: Conference on Neural Information Processing Systems (NeurIPS) Date: 2022 2. Summary 本文提出了一种方法，用于在训练完成的 G

1. Information Title: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Link: BERT Paper Source: The North American Chapter of the Association for Computational Linguist

1. Information Title: Attention Is All You Need Link: Transformer Source: Conference on Neural Information Processing Systems (NeurIPS) Date: 2017 2. Summary 本文提出了 Transformer 模型，这是一种用于序列转换任务（特别是机器翻译）

1. Information Title: ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design Link: ShuffleNet V2 Paper Source: European Conference on Computer Vision (ECCV) Date: 2018 2. Summary 本文

1. Information Title: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications Link: MobileNets: Efficient CNNs for Mobile Applications Source: IEEE Conference on Computer Vi

1. Information Title: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices Link: ShuffleNet Paper Source: IEEE Conference on Computer Vision and Pattern Recognition (CVPR

1. Information Title: Densely Connected Convolutional Networks Link: DenseNet Paper Source: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Date: 2017 2. Summary 本文提出了 DenseNet，一种新的深

1. Information Title: Aggregated Residual Transformations for Deep Neural Networks Link: ResNeXt Paper Source: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Date: 2017 2. Summary 本

1. Information Title: Rethinking the Inception Architecture for Computer Vision Link: Inception V3 Paper Source: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Date: 2016 2. Summary

1. Information Title: Deep Residual Learning for Image Recognition Link: ResNet Paper Source: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Date: 2016 2. Summary 本文提出了一种新型的深度学习架构——