ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
53:02
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)
28:23
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (Paper Explained)
9:26
A Brief History of Astronomy | Dr. Brian Keating & Dr. Andrew Huberman
27:14
Transformers (how LLMs work) explained visually | DL5
45:44
What is Q-Learning (back to basics)
22:43
How might LLMs store facts | DL7
27:48
Were RNNs All We Needed? (Paper Explained)
53:07