Posts by Collection

portfolio

publications

VAE 与 Diffusion Model 学习笔记

Published in , 2026

从潜变量、变分下界与重参数化出发,完整推导 DDPM 的前向边缘、条件后验、变分目标、噪声预测与采样,再连接潜空间图像、视频生成和生成后训练。

RLHF 数学笔记:从策略梯度到 PPO 与 GRPO

Published in , 2026

从轨迹概率、策略梯度与优势估计出发,逐步推导 GAE、TRPO、PPO 和 GRPO,再连接 RLOO、DAPO、Dr. GRPO、GSPO 与 DPO,理解后训练算法中的采样、裁剪与归一化。

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.