Mass-Editing Memory in a Transformer

批量编辑Transformer中的记忆.

Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale

Amos:一种面向模型的自适应权重衰减的Adam风格优化器.

Fast Fourier Convolution

快速傅里叶卷积.

Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation

特征蒸馏使对比学习在微调时击败了掩码图像建模.

Parametric Instance Classification for Unsupervised Visual Feature Learning

无监督视觉特征学习的参数化实例分类.

Self-Supervised Learning based on Heat Equation

基于热传导方程的自监督学习.