All Posts

RL Post-training for Large Language Models

Jul 14 2026 · 12 min read

#reinforcement-learning #large-language-models #rlhf #ppo #dpo #grpo

Table of Contents

Introduction

Reinforcement Learning (RL) has become one of the core ingredients of modern Large Language Model (LLM) post-training. While pre-training teaches a model to predict the next token from massive text corpora, …

Post-training a Mixture-of-Experts Language Model with Reinforcement Learning

Jun 1 2026 · 11 min read

#reinforcement-learning #large-language-models #mixture-of-experts #lora #qlora #gsm8k

Table of Contents

Introduction

Large Language Models (LLMs) are everywhere and are substantially changing the way we perform many daily tasks. Recently, I noticed a growing number of positions related to the post-training of such models. Interestingly, two …