58 posts in total

---

2025

05-08

Differentiable Permutation Layer

05-08

Rethinking R1-like Rule-based RL

04-30

01-EM Models

02-16

RLHF -- GRPO

02-16

RLHF -- DPO

02-16

RLHF -- From Zero to PPO 代码篇

02-13

RLHF -- From Zero to PPO 理论篇

02-06

最初的sin/cos编码

2024

07-26

栈的基本应用

03-11

Mamba