生成模型概览 (Overview of Generative Models)
系统梳理四大主流生成模型——变分自编码器 (VAE)、生成式对抗网络 (GAN)、扩散模型 (DDPM) 和流模型 (Normalizing Flow) 的动机、数学原理及优劣势分析。
Machine Learning
Karpathy LLM 编码指南
旨在减少常见 LLM 编码错误的行事指南，源自 Andrej Karpathy 的观察。
Karpathy LLM Coding Guidelines
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations.
PML Exercise 3 Solutions
Probabilistic Machine Learning (PML) Chapter 3 Exercise Solutions.
PML Exercise 2 Solutions
Probabilistic Machine Learning (PML) Chapter 2 Exercise Solutions.
PML Exercise 5 Solutions
Probabilistic Machine Learning (PML) Chapter 5 Exercise Solutions.
PML Exercise 4 Solutions
Probabilistic Machine Learning (PML) Chapter 4 Exercise Solutions.
PML Exercise 6 Solutions
Probabilistic Machine Learning (PML) Chapter 6 Exercise Solutions.
Shapley Values and SHAP
Notes on Shapley Values and SHAP algorithms for model interpretability.
A Tutorial on Hawkes Processes for Events in Social Media
霍克斯过程（Hawkes Processes）在社交媒体事件分析中的基础教程，包括点过程基础、自激励机制、模拟采样及参数估计。
Attention Mechanism Notes
A compact machine-learning note with math, code, and references for testing the technical writing path.