LECTURES A GRATIS GLOBAL SERVICE
⌕ SEARCH GRATIS GLOBAL ↗
LECTURES
Overview of Transformers
SOURCE: YOUTUBE · NO TRACKING UNTIL YOU PRESS PLAY · TROUBLE PLAYING? WATCH AT THE SOURCE ↗

Overview of Transformers

77 MIN · EN · STATUS: [ STREAMING ]
RATE THIS
STANFORD

Stanford's CS25: Transformers United opens its course with a guided tour of the architecture that reshaped natural language processing. Presenters Steven Feng, Div Garg, Emily Bunnapradist, and Seonghee Lee trace the history of NLP leading up to the transformer, then break down how the model's attention mechanism actually works. The talk covers the architecture's rapid spread beyond text into vision and multimodal systems, recent breakthroughs, and where it still struggles, including computational cost and reasoning limits. The session closes with a discussion of AI agents built on top of transformer models, previewing themes the rest of the course will return to. Slides accompany the talk, and it serves as the entry point to the full CS25 lecture series hosted on Stanford's YouTube channel. The pace stays accessible to anyone with basic machine learning background while still naming the specific papers and mechanisms involved.

At a glance

Lecture facts

Runtime compared with the other 387 Computer Science lectures
Runtime1 h 17 m
Compared with Computer ScienceLonger than 65%
Source channelStanford Online (YouTube)