Stanford CME 295 Lecture 4 released: Teaching reinforcement learning with LLMs
English text is being prepared.
The Stanford course CME 295 Transformers & Large Language Models has been updated to Lecture 4, Reinforcement learning with LLMs, and both the video and lecture notes are now public. This lecture goes from RL and Reward Design to PPO, GRPO, RLVR, and DAPO, explaining the notation in each one by one. The course is taught by Afshine and Shervine Amidi, with 9 lectures in total, covering Transformer architecture, attention variants, RoPE, LoRA fine-tuning, RLHF/GRPO training, Flash Attention inference optimization, MCP and AI Agents, and diffusion language models.
Why read this
AI score 55
Stanford CME 295 Lecture 4 explains the notation systems from RL to PPO, GRPO, RLVR, and DAPO in depth, making it suitable for systematically filling in the foundations of reinforcement learning.
Topics
View original postStanford @stanfordnlp's new course CME 295, taught by the twin brothers @afshinea @shervinea, covers the entire LLM landscape in 9 lectures: from Transformer architecture, attention variants, and RoPE, to LoRA fine-tuning and RLHF/GRPO training, and then to Flash Attention inference optimization, MCP and AI Agents, and diffusion language models. Both the course and the well-known cheat sheets are fully public. https://t.co/FjHGTco5iS
View original
斯坦福 @stanfordnlp 新课 CME 295，双胞胎兄弟 @afshinea @shervinea 主讲，9 讲走完 LLM 全部版图：从 Transformer 架构、注意力变体、RoPE，到 LoRA 微调、RLHF/GRPO 训练，再到 Flash Attention 推理优化、MCP 与 AI Agent、扩散语言模型。 课程和知名速查表全部公开。 https://t.co/FjHGTco5iS
Body
斯坦福新课 CME 295：Transformers & Large Language Models
@stanfordnlp 双胞胎兄弟（Afshine & Shervine Amidi @afshinea @shervinea 的课程已经来到了第四讲： Reinforcement learning with LLMs
这一讲，从 RL、Reward Design 一直降到 PPO、GRPO、RLVR 和 DAPO，把每个符号都讲清楚了，非常适合用来系统补充 RL 知识！