The Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions
层归一化和动态激活函数之间的数学关系.
博物记：梅杏桃樱李梨海棠
Distinguish Flowers of Plum, Apricot, Peach, Cherry, Plum, Pear, and Crabapple.
Transformers without Normalization
无归一化的Transformer.
Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale
大规模卷积多混合语言模型的系统与算法.
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
SigLIP 2：使用改进的语义理解、定位和密集特征的多模态视觉语言编码器.
The Curse of Depth in Large Language Models
大语言模型中的深度诅咒.