Paper

• FlashAttention - optimizing GPU memory for more scalable transformers Jul 20
• LoRA - low rank adaption explained in three minutes Jan 28

• Understanding the difference between weight decay and L2 regularization Sep 17

• DINO - Emerging properties in self-supervised vision transformers Mar 13
• Rethinking Batch in BatchNorm Feb 28

• P-Diff Learning Classifier with noisy labels based on probability difference distributions Oct 17
• Meta-learning from noisy labels Jun 25

• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition Nov 29
• End-to-End object detection with transformers Aug 30
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour Jun 28