The Data Addition Dilemma

38:25
How Transformers Learn Causal Structure with Gradient Descent

1:11:23
How Do Transformers Learn Variable Binding?

58:29
Allen Downey - A future of data science

32:20
Michael I. Jordan | UC Berkeley | Blending Machine Learning & Microeconomics | TransformX 2022

53:31
Charlie Snell, UC Berkeley. Title: Scaling LLM Test-Time Compute

56:02
Julia Kempe - Synthetic Data – Friend or Foe in the Age of Scaling?

1:36:34
Simons Institute for the Theory of Computing at UC Berkeley

17:02