A platform for reproducible world model research and evaluation
-
Updated
Jun 11, 2026 - Python
#
jepa
Here are 113 public repositories matching this topic...
implementing minimal versions of joint-embedding predictive architecture (JEPA)
-
Updated
May 19, 2026 - Python
The first robot-native JEPA physical-world model.
-
Updated
May 28, 2026 - Python
Harness framework to build world model based workflows for physical AI systems.
-
Updated
Jun 5, 2026 - Python
[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
machine-learning computer-vision representation-learning anomalydetection clip anomaly-detection few-shot-learning anomaly-detection-algorithm anomaly-segmentation anomaly-localization foundation-models dinov2 jepa few-shot-anomaly-detection siglip dinov3
-
Updated
Mar 16, 2026 - Python
Experiments in Joint Embedding Predictive Architectures (JEPAs).
-
Updated
Jan 5, 2024 - Python
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
computer-vision robotics representation-learning video-understanding vla reasoning multimodal self-supervised-learning video-representation video-modeling dexterous-robotic-hand semantic-guidance dexterous-manipulation large-language-model vision-language-model jepa world-model multimodal-reasoning latent-world-model thinkjepa
-
Updated
Apr 30, 2026 - Python
GenBio-PathFM is a histopathology foundation model from GenBio AI.
-
Updated
Apr 9, 2026 - Python
👆PyTorch Implementation of JEDi Metric described in "Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality"
computer-vision jedi mmd fvd video-generation video-representation-learning video-quality-assessment jepa video-metrics
-
Updated
Dec 8, 2024 - Python
Joint Embedding Predictive Architecture for World Models, written in Rust.
-
Updated
Mar 16, 2026 - Rust
An open-source attempt at training a variant of LeCun's energy-based models (EBM) to reason in latent space and solve Sudoku.
benchmarking neural-networks sudoku-solver kona world-models yann-le-cunn jepa llms-reasoning latent-reasoning
-
Updated
Mar 10, 2026 - Python
A tiny, fully-reproducible JEPA world model that learns the physics of a bouncing DVD logo in representation space, dreams its future, and detects anomalies. Trains on a CPU in ~10s. Interactive browser demo.
machine-learning deep-learning reproducible-research pytorch representation-learning anomaly-detection self-supervised-learning video-prediction world-models interactive-demo jepa i-jepa v-jepa
-
Updated
Jun 13, 2026 - Python
This VL-JEPA implimentation takes direct insperation from the original VL-JEPA paper
-
Updated
Jan 18, 2026 - Python
Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
natural-language-processing computer-vision visual-question-answering visual-perception llava jepa multimodal-large-language-models
-
Updated
Mar 14, 2026 - Python
Run existing World Models from ROS 2 — runtime, adapters, benchmark, visualization.
robotics ros autonomous-driving rviz ros2 autoware model-based-rl world-models nav2 rosbag2 foundation-models jepa world-model lerobot physical-ai
-
Updated
Jun 8, 2026 - Python
A Video Joint Embedding Predictive Architecture (JEPA) that runs on a personal computer.
-
Updated
Nov 8, 2024 - Python
Ten-ABC cognitive architecture for autonomous AI with forward compatibility . Route any architecture current or future without.
-
Updated
Jun 15, 2026 - Python
A commit-and-audit proof system for deterministic, quantized inference of a JEPA-style world model (LeWorldModel)
-
Updated
Jun 12, 2026 - Rust
Improve this page
Add a description, image, and links to the jepa topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the jepa topic, visit your repo's landing page and select "manage topics."