#Artificial Intelligence #World Models Table of contents The Plan What Even is a World Model? How the World Model Learns to Predict From screenshots to embeddings Prediction loss and collapse SIGReg: keeping the embedding space useful The Pokémon Training Data Planning in the Learned World Why the First Plan Failed Rollout Fine-Tuning and the Second Attempt The End…? I think some of the most fascinating work happening in the field of Artificial Intelligence surrounds world models. There are many kinds of world models (and the term itself has become a bit overloaded), but one of the most exciting architectures for world models is Yann LeCun’s JEPA (Joint Embedding Predictive Architecture). There are many variants, and one that caught my eye in particular was LeWorldModel 1 . It seemed small enough to train locally on my RTX 3080 Ti and had a simpler design than many of the previous JEPA architectures.…