Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
Episode Details
EPISODE INFO
- Released
- November 14, 2025
- Duration
- 1h 47m
- Channel
- Stanford Online
- Watch on YouTube
- ▶ Open ↗
EPISODE DESCRIPTION
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. View the course playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rOCXd21gf0CF4xr35yINeOy
EPISODE SUMMARY
In this episode of Stanford Online, Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 6 - LLM Reasoning explores How LLMs learn reasoning via verifiable RL and GRPO training The lecture defines LLM reasoning as multi-step problem solving and frames “reasoning models” as models that output a reasoning chain before giving a final answer.
RELATED EPISODES
