Static HTML snapshot of the model record for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Model | V-JEPA |
| Lab / Organization | Meta FAIR |
| Category | Self-Supervised World Model |
| Subtype | Joint Embedding Predictive Architecture |
| World Model Type | Self-supervised visual world model |
| Primary Domain | Video understanding |
| Architecture | Vision Transformer with joint embedding predictive objective |
| Modality | Video |
| Training Method | Self-supervised prediction in abstract representation space (no pixel reconstruction) |
| Status | active |
| Year | 2024 |
| Performance Index | 70/100 (medium confidence, v1.1) |
Main editorial body preserved directly in static HTML.
V-JEPA follows Yann LeCun's JEPA framework to learn visual world models from video without pixel-level reconstruction. Instead of predicting pixels, it predicts abstract representations of future video frames, learning a world model that captures the causal structure of visual scenes. This approach avoids the pitfalls of pixel-level prediction while learning meaningful physical dynamics.
V-JEPA is a self-supervised visual world model developed by Meta in 2024 for video understanding.
Short extractable facts for answer engines and no-JS readers.
| Signal | Value |
|---|---|
| Definition | V-JEPA is a self-supervised visual world model developed by Meta in 2024 for video understanding. |
| Short Description | Video Joint Embedding Predictive Architecture: learns visual world models through self-supervised video prediction in abstract representation space. |
| Benchmark Rows | 1 |
| FAQ Entries | 1 |
| Related Models | 1 |
| Related Guides | 1 |
| Related Research Topics | 4 |
| Last Updated | 2026-03-13 |
Key capabilities associated with this model.
Representative applications attached to this model record.
Balanced assessment surfaced in static HTML.
Published benchmark evidence attached to this model record.
| Benchmark | Metric | Result | Source |
|---|---|---|---|
| Video Understanding Tasks | K400 Accuracy 81.3 % | Competitive with supervised methods | Source |
Primary references preserved in static HTML for citation extraction.
| Reference | Link |
|---|---|
| Bardes et al., 2024. V-JEPA: Video Joint Embedding Predictive Architecture. | Open source |
Nearby models linked from the current editorial record.
| Model | Category | World Model Type | Index v1.1 |
|---|---|---|---|
| DreamerV3 | Model-Based RL | Imagination-based dynamics model | 88/100 |
Side-by-side comparisons already connected to this model.
| Comparison | Matchup | Summary |
|---|---|---|
| World Models vs LLMs | World Models vs Large Language Models | World models and LLMs represent fundamentally different approaches to AI. World models learn causal dynamics of physical environments; LLMs learn statistical patterns over text. Both are essential for the future of AI. |
| V-JEPA vs Video Generation Models | V-JEPA (Meta) vs Video Generation Models (Sora, Cosmos) | V-JEPA and video generation models like Sora both learn from video, but follow opposite philosophies: V-JEPA predicts in abstract representation space without generating pixels, while video generation models focus on producing realistic pixel outputs. |
| I-JEPA vs MAE (Masked Autoencoders) | I-JEPA (Meta FAIR) vs MAE (Meta / He et al.) | I-JEPA and MAE are both self-supervised image learning methods, but they follow opposite philosophies: I-JEPA predicts in abstract representation space, while MAE reconstructs masked pixels. |
| V-JEPA vs I-JEPA | V-JEPA vs I-JEPA | Both implement Yann LeCun's JEPA framework for self-supervised learning, but V-JEPA operates on video (temporal dynamics) while I-JEPA operates on static images (spatial structure). |
| 3D-VLA vs I-JEPA | 3D-VLA vs I-JEPA | Two approaches to learning representations for embodied intelligence: 3D-VLA combines 3D perception with language-conditioned action planning, while I-JEPA learns abstract visual representations through self-supervised prediction in latent space. |
| V-JEPA vs NVIDIA Cosmos | V-JEPA vs NVIDIA Cosmos | Two foundation-scale approaches to world understanding: V-JEPA learns predictive video representations through self-supervised masking, while Cosmos builds a full-stack world simulation platform for physical AI. |
| AMI vs Ha World Model | AMI vs Ha World Model | Two pioneering cognitive-inspired world models: Ha's 2018 World Model introduced the VAE+RNN+Controller architecture, while AMI proposes an autonomous machine intelligence framework inspired by biological cognition. |
| LWM vs V-JEPA | Large World Model (LWM) vs V-JEPA | Two approaches to learning world understanding from video. LWM uses autoregressive prediction over million-length sequences, while V-JEPA predicts abstract latent representations without pixel reconstruction. |
Crawler-readable guide links tied to this model.
| Guide | Summary |
|---|---|
| How to Read World Models Papers | A practical reading path through world-model research, from foundational concepts to latent dynamics, planning, simulators, and self-supervised approaches. |
Connected research areas surfaced directly in static HTML.
| 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. |
| World Models vs LLMs | The key differences between world models and LLMs across objective, architecture, planning, physical reasoning, and embodied AI use cases. |
| World Models: A Comprehensive Survey | A survey of AI world models covering taxonomy, leading architectures, landmark systems, open challenges, and future research directions. |
| Video World Models | How video world models learn physics, temporal consistency, and interactive simulation from large-scale video, from Sora and Genie to Cosmos and V-JEPA. |
Recent timeline events connected to this model.
| Event | Published | Source | Summary |
|---|---|---|---|
| Meta FAIR releases V-JEPA 2 checkpoints under non-commercial license | 2026-04-08 | Meta FAIR | Meta FAIR publishes V-JEPA 2 model checkpoints (ViT-L, ViT-H, ViT-g) on Hugging Face under a research-only license. |
| Meta FAIR publishes V-JEPA 2 paper: video prediction at scale without pixel reconstruction | 2026-03-10 | arXiv | Meta FAIR introduces V-JEPA 2, extending the Joint Embedding Predictive Architecture to video. |
FAQ answers rendered directly into static HTML for extractable responses.
V-JEPA predicts in abstract representation space rather than generating pixels, learning meaningful causal dynamics without reconstruction artifacts.
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 Tyler D. - Technical editor, methodology and benchmark analysis.
This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.
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: 2026-03-13.
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 model and lab sources embedded in static HTML.