Ultralytics YOLOv8

Ultralytics YOLOv8：实时目标检测和图像分割模型的最新版本.

Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers

为什么GPT可以上下文学习？语言模型隐式地作为元优化器执行梯度下降.

Refiner: Refining Self-attention for Vision Transformers

Refiner：精炼视觉Transformer中的自注意力机制.

Improve Vision Transformers Training by Suppressing Over-smoothing

通过抑制过度平滑改进视觉Transformer.

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Twins：重新思考视觉Transformer中的空间注意力设计.

All Tokens Matter: Token Labeling for Training Better Vision Transformers

LV-ViT：使用标志标签更好地训练视觉Transformers.