下面是最新的几篇记录：
- 论文简记：Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks
- 论文简记：Expanding Large Pre-trained Unimodal Models with Multimodal Information Injection for Image-Text Multimodal Classification
- 简记：Tokens-to-Token ViT： Training Vision Transformers from Scratch on ImageNet
- 简记：Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution
- 简记：Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers