Issue #124 Foundation Edwin Dong
Decision Models, World Action Models, Egocentric Video (PRO)
This week’s PRO issue includes a Colab notebook where we’ll run our own experiments with Looped Transformers.
Please do read the full article before attempting the code tutorial.
As always, the code in this issue can be executed on a normal home PC and does not require a large amount of VRAM.
Welcome back to AI, but simple, your AI research beacon with visual explanations.
In this issue, we’ll unpack and visually explain the three directions that each gained a cluster of new papers over the past few weeks.
Decision models (e.g., Jev) have become their own class of model, and the open question is now whether those probabilities can be trusted.
World action models are now considering how much of the future the model actually needs to simulate.
New pipelines turn first-person (egocentric) video into 3D records of human activity that models can learn from.
