// ◐ Algorithms Atlas
World Models & Self-Supervised Learning
Simulating and predicting the world: World Models, Dreamer, JEPA, Genie, plus self-supervised learning like contrastive learning and MAE.
6 core1 extended2018–2024
TIMELINE
01Core algorithms
Learn these first. Sorted by year.
World Models Learn a dreamable environment model, then train the policy inside it. 2018core Dreamer (Latent Imagination) Trains behavior by imagining trajectories in a learned latent world model. 2019core Masked Autoencoders (MAE) Masks 75% of image patches and reconstructs them to learn representations. 2021core Joint-Embedding Predictive Architecture (JEPA) Predicts masked content in representation space rather than pixels. 2023core DINOv2 (Self-Supervised Visual Features) Label-free self-distillation on curated images yields general-purpose visual features. 2023core Genie (Generative Interactive Environments) Learns playable, controllable worlds from unlabeled videos. 2024core
02Extended
Variants and follow-ups worth knowing once the core is clear.