Posts

记录一些常用的计算机指令

The core objective of t-SNE (t-distributed Stochastic Neighbor Embedding) is to reduce the dimensionality of high-dimensional data while preserving local neighborhood structure.

This paper proposes DINO, a self-distillation framework with no labels, to pretrain ViTs. Besides the fact that the DINO method works quite well on this kind of architecture, there are also two interesting properties emerging from the learned features:

Currently, large models are post‑trained via RLHF, making them powerful but expensive to train and deploy, while smaller models are usually fine‑tuned with SFT or KD methods and are easier to deploy and adapt but often lack the performance of larger models.

令 f\in L^2(\mathbb{R})。傅里叶变换（在 L^2 意义下）把信号表示为全局正弦基的叠加：

附录

朗之万去噪分数匹配 (SMLD) 和连续时间 Score-based 模型 (VP-SDE / VE-SDE) 是两种基于分数匹配的生成模型方法。它们通过学习数据分布的分数函数（即对数概率密度的梯度）来生成新样本。

流匹配模型