Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 6 - LLM Reasoning
For more information about Stanford’s graduate programs, visit: https://online.stanford.edu/graduate-education
November 7, 2025
This lecture covers:
• Reasoning models
• RL for reasoning
• GRPO
• Scaling
To follow along with the course schedule and syllabus, visit: https://cme295.stanford.edu/syllabus/
Chapters:
00:00:00 Introduction
00:12:43 Reasoning models
00:27:49 Benchmarks
00:32:04 Pass@k metric
00:48:07 Scaling with RL
00:57:44 GRPO
01:06:03 Comparison between GRPO and PPO
01:16:14 Length bias
01:25:00 DAPO, Dr. GRPO
01:29:38 DeepSeek R1 recipe
Afshine Amidi is an Adjunct Lecturer at Stanford University.
Shervine Amidi is an Adjunct Lecturer at Stanford University.
November 7, 2025
This lecture covers:
• Reasoning models
• RL for reasoning
• GRPO
• Scaling
To follow along with the course schedule and syllabus, visit: https://cme295.stanford.edu/syllabus/
Chapters:
00:00:00 Introduction
00:12:43 Reasoning models
00:27:49 Benchmarks
00:32:04 Pass@k metric
00:48:07 Scaling with RL
00:57:44 GRPO
01:06:03 Comparison between GRPO and PPO
01:16:14 Length bias
01:25:00 DAPO, Dr. GRPO
01:29:38 DeepSeek R1 recipe
Afshine Amidi is an Adjunct Lecturer at Stanford University.
Shervine Amidi is an Adjunct Lecturer at Stanford University.
Stanford Online
You can gain access to a world of education through Stanford Online, the Stanford School of Engineering’s portal for academic and professional education offered by schools and units throughout Stanford University. https://online.stanford.edu/
Our robust ...