Opening Overview of Transformers (Stanford CS25: Transformers United V6)
Overview of Transformers (Stanford CS25: Transformers United V6)
- Length
- 1 h 17 min
- Level
- Undergraduate
- Recorded
- Stanford University2026
Chapter 1 of 8: Before the lecture
Traces the evolution of sequence models from RNNs and LSTMs to modern transformer architectures and state space models.
Steven Feng's Stanford CS25 overview of transformers traces the move from hand-engineered features to self-supervised pre-training and on to chain-of-thought prompting. Aimed at undergraduates with basic machine learning, it also covers mechanistic interpretability and linear-scaling state space models.
Steven Feng's Stanford CS25 overview of transformers traces the move from hand-engineered features to self-supervised pre-training and on to chain-of-thought prompting. Aimed at undergraduates with basic machine learning, it also covers mechanistic interpretability and linear-scaling state space models.
Baby Scale: Investigating Models Trained on Individual Children's Language Input
Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models
This lecture
Talk 21 of 21 of Transformers United.
Choose a node to see how it connects to this lecture. What comes before is on the leftat the top. The ring is what it teaches. People and places are above. Other lectures and books are below.
Press a chosen node again to open it.
Your comment is kept while you sign up.Sign in
https://arxiv.org/abs/2604.00715
BERT Stacking
MIDAS
https://arxiv.org/abs/2506.11389
https://arxiv.org/abs/2201.11903
https://arxiv.org/abs/2305.10601
https://arxiv.org/abs/2211.10435
https://arxiv.org/abs/2205.10625
https://arxiv.org/abs/2305.14999
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
Graph of Thoughts: Solving Elaborate Problems with LLMs
An Image is Worth 16x16 Words: Transformers for Image Recognition At Scale
arXiv:2603.00786
HalluWorld paper and benchmark
A Path Towards Autonomous Machine Intelligence
Mamba: Linear-Time Sequence Modeling with Selective State Spaces