Editorial definition preserved directly in static HTML.
A framework proposed by Yann LeCun where models learn by predicting representations of future states in abstract embedding space, rather than reconstructing raw pixels. V-JEPA demonstrates this approach for video understanding and physical dynamics learning.
JEPA (Joint Embedding Predictive Architecture) is a glossary concept in the architecture layer of the world models knowledge base.
Static glossary definition snapshot for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Term | JEPA (Joint Embedding Predictive Architecture) |
| Category | Architecture |
| Definition | A framework proposed by Yann LeCun where models learn by predicting representations of future states in abstract embedding space, rather than reconstructing raw pixels. V-JEPA demonstrates this approach for video understanding and physical dynamics learning. |
| Related Models | 1 |
| Related Research | 1 |
| Model | Lab | Category |
|---|---|---|
| V-JEPA | Meta | Self-Supervised World Model |
| Topic | Summary |
|---|---|
| Self-Supervised World Models | How self-supervised world models learn environment dynamics without rewards, from JEPA and V-JEPA to predictive latent representations. |
| Term | Category | Definition |
|---|---|---|
| Latent Space | Architecture | A compressed, abstract representation of data learned by a neural network. In world models, the latent space encodes environment states in a compact form that captures essential dynamics while discarding irrelevant details. Models like DreamerV3 and PlaNet operate entirely in latent space for efficient planning. |
| Self-Supervised Learning | Training | A learning paradigm where the model generates its own training signal from unlabeled data, typically by predicting parts of the input from other parts. Self-supervised world models learn environment dynamics without explicit reward signals. |
Short extractable summary preserved directly in static HTML.
Editorial provenance and refresh policy preserved directly in static HTML.
Published by world-models.io editorial board.
Lead editor Bernard Grenat.
This glossary page publishes stable definitions linked to related models, research topics, and primary-source context.
Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-06-21.
Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.
Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.
Primary sources related to this term, surfaced directly in static HTML.