Playlist · Stanford Online

Stanford CS25 - Transformers United

by Stanford Online · 50 videos

Listed in Best free generative AI and LLM courses on YouTube, ranked by total hours

Total watch time

2d 7h 37m

at 1× speed · exactly 2 days, 7 hours, 37 minutes, 19 seconds at 1×

At an hour a day you'd finish in 56 days

The shape of the course

50 videos in blocks of 10 · each column is a block's total, to scale

9h 32m
11h 27m
11h 57m
10h 57m
11h 45m

WatchedTo watch

Compare Open on YouTube JSON

Next time, skip the copying: change youtube.com to playlistduration.com in any playlist, video or channel address and it opens here. Or see the total on YouTube itself, with our extension for Chrome, Firefox or Edge.

Your plan

Plan to finish

About 56 days at an hour a day

Pick a daily pace and the days you'll watch. Ticked videos are skipped.

Days

At one hour a day, every day, this playlist takes about 56 days. Turn on JavaScript to plan around your week.

Videos (50)

2d 7h 37m in total · tick what you've watched

Tick videos you've watched — progress is saved in this browser. Titles open on YouTube in a new tab.

Videos to
Watched Leave out of the total
1 Stanford CS25: V1 I Transformers United: DL Models that have revolutionized NLP, CV, RL 22:44 2022-07-08
2 Stanford CS25: V1 I Transformers in Language: The development of GPT Models, GPT3 48:39 2022-07-11
3 Stanford CS25: V1 I Transformers in Vision: Tackling problems in Computer Vision 1:08:37 2022-07-12
4 Stanford CS25: V1 I Decision Transformer: Reinforcement Learning via Sequence Modeling 1:20:43 2022-07-13
5 Stanford CS25: V1 I Mixture of Experts (MoE) paradigm and the Switch Transformer 1:05:44 2022-07-14
6 Stanford CS25: V1 I DeepMind's Perceiver and Perceiver IO: new data family architecture 58:59 2022-07-15
7 Stanford CS25: V1 I Self Attention and Non-parametric transformers (NPTs) 1:05:43 2022-07-16
8 Stanford CS25: V1 I Transformer Circuits, Induction Heads, In-Context Learning 59:34 2022-07-17
9 Stanford CS25: V1 I Audio Research: Transformers for Applications in Audio, Speech, Music 48:19 2022-07-18
10 Stanford CS25: V2 I Represent part-whole hierarchies in a neural network, Geoff Hinton 52:48 2022-08-11
11 Stanford CS25: V2 I Introduction to Transformers w/ Andrej Karpathy 1:11:41 2023-05-19
12 Stanford CS25: V2 I Language and Human Alignment 1:06:21 2023-05-20
13 Stanford CS25: V2 I Emergent Abilities and Scaling in LLMs 1:07:49 2023-05-21
14 Stanford CS25: V2 I Strategic Games 53:21 2023-05-22
15 Stanford CS25: V2 I Robotics and Imitation Learning 1:16:08 2023-05-23
16 Stanford CS25: V2 I Common Sense Reasoning 1:15:06 2023-05-24
17 Stanford CS25: V2 I Biomedical Transformers 1:08:10 2023-05-25
18 Stanford CS25: V2 I Neuroscience-Inspired Artificial Intelligence 1:22:14 2023-09-01
19 Stanford CS25: V3 I Low-level Embodied Intelligence w/ Foundation Models 1:18:14 2023-12-08
20 Stanford CS25: V3 I Generalist Agents in Open-Ended Worlds 47:48 2023-12-09
21 Stanford CS25: V3 I How I Learned to Stop Worrying and Love the Transformer 1:20:38 2024-01-17
22 Stanford CS25: V3 I Recipe for Training Helpful Chatbots 1:08:49 2023-12-14
23 Stanford CS25: V3 I No Language Left Behind: Scaling Human-Centered Machine Translation 52:28 2023-12-15
24 Stanford CS25: V3 I Beyond LLMs: Agents, Emergent Abilities, Intermediate-Guided Reasoning, BabyLM 1:00:14 2023-12-15
25 Stanford CS25: V3 I Retrieval Augmented Language Models 1:19:27 2024-01-25
26 Stanford CS25: V4 I Overview of Transformers 1:17:29 2024-04-23
27 Stanford CS25: V4 I Jason Wei & Hyung Won Chung of OpenAI 1:17:07 2024-05-06
28 Stanford CS25: V4 I Aligning Open Language Models 1:16:21 2024-05-10
29 Stanford CS25: V4 I Demystifying Mixtral of Experts 1:04:32 2024-05-16
30 Stanford CS25: V4 I Transformers that Transform Well Enough to Support Near-Shallow Architectures 1:19:56 2024-05-23
31 Stanford CS25: V4 I From Large Language Models to Large Multimodal Models 1:20:04 2024-05-30
32 Stanford CS25: V4 I Behind the Scenes of LLM Pre-training: StarCoder Use Case 1:01:37 2024-06-07
33 Stanford CS25: V4 I Hyung Won Chung of OpenAI 36:31 2024-06-11
34 Stanford CS25: V5 I Overview of Transformers 1:01:28 2025-04-18
35 Stanford CS25: V5 I RL as a Co-Design of Product and Research, Karina Nguyen 1:12:11 2025-04-29
36 Stanford CS25: V5 I The Advent of AGI, Div Garg 1:01:01 2025-05-13
37 Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind 1:06:07 2025-05-21
38 Stanford CS25: V5 I On the Biology of a Large Language Model, Josh Batson of Anthropic 1:12:32 2025-06-05
39 Stanford CS25: V5 I Multimodal World Models for Drug Discovery, Eshed Margalit of Noetik.ai 1:11:02 2025-06-13
40 Stanford CS25: V5 I Transformers in Diffusion Models for Image Generation and Beyond 1:14:32 2025-06-24
41 Stanford CS25: V5 I Transformers for Video Generation, Andrew Brown of Meta 1:13:35 2025-07-03
42 Stanford CS25: Transformers United V6 I Overview of Transformers 1:16:46 2026-04-22
43 Stanford CS25: Transformers United V6 I From Representation Learning to World Modeling 1:11:03 2026-04-22
44 Stanford CS25: Transformers United V6 I On the Tradeoffs of State Space Models and Transformers 1:17:08 2026-04-27
45 Stanford CS25: Transformers United V6 I The Ultra-Scale Talk: Scaling Training to Thousands of GPUs 1:01:48 2026-05-11
46 Stanford CS25: Transformers United V6 I From Next-Token Prediction to Next-Generation Intelligence 57:57 2026-05-11
47 Stanford CS25: Transformers United V6 I Advancing Science and Medicine with Collaborative AI Agents 1:06:33 2026-05-27
48 Stanford CS25: Transformers United V6 I Distinct Modes of Generalization from Parameters and Context 1:12:30 2026-05-20
49 Stanford CS25: Transformers United V6 I Serving Transformers: Lessons from the Trenches 1:22:31 2026-06-04
50 Stanford CS25: Transformers United V6 I From Language Models to Native Multimodal Intelligence 1:04:40 2026-06-04
For your README

Embed a badge

Show the watch time in a README or course description — it links back here and updates itself

Watch time: 2d 7h 37m · 50 videos

Markdown
[![Watch time: 2d 7h 37m · 50 videos](https://playlistduration.com/badge/playlist/PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM.svg)](https://playlistduration.com/playlist/PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM)
HTML
<a href="https://playlistduration.com/playlist/PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM"><img src="https://playlistduration.com/badge/playlist/PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM.svg" alt="Watch time: 2d 7h 37m · 50 videos" width="221" height="20"></a>

Add ?speed=1.5 to the image URL for the time at that speed, ?label=Course to change the left text, or ?style=flat-square for square corners.

Want the numbers themselves? GET https://playlistduration.com/api/v1/playlist/PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM returns them as JSON — free, no key. API docs →

Data from the YouTube Data API as of 2026-11-17 (cached). Private or deleted videos are excluded from totals.

Changed the playlist? Saved copies are kept up to a week.