A platform for reproducible world model research and evaluation
-
Updated
Sep 22, 2026 - Python
A platform for reproducible world model research and evaluation
The first robot-native JEPA physical-world model.
implementing minimal versions of joint-embedding predictive architecture (JEPA)
A small proof-of-concept language model (not an LLM) incorporating latent-space prediction, internal state using recurrent trace units, and byte-by-byte output, built with MLX.
Free interactive course on world models in AI. Nine visual chapters on prediction, latent dynamics, planning, JEPA, video models, and failure modes.
INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.
Official code for AdaJEPA: An Adaptive Latent World Model
Explorations into some of the approaches advocated by Yann LeCun, and just a more wholistic architecture (JEPA) in general
Harness framework to build world model based workflows for physical AI systems.
JEPA-Anything: Learning Predictive Models across Different Worlds
[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
Experiments in Joint Embedding Predictive Architectures (JEPAs).
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
An auditable and reproducible evaluation suite for LeWM-compatible latent world models, with official-compatible and difficulty-controlled protocols.
GenBio-PathFM is a histopathology foundation model from GenBio AI.
👆PyTorch Implementation of JEDi Metric described in "Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality"
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. CA: 0x42bef487C250dd054035d5E8d69C12549d1F7Ba3
Joint Embedding Predictive Architecture for World Models, written in Rust.
Official Code for LpWM: A Case for Sparse Representations in World Models
To associate your repository with the jepa topic, visit your repo's landing page and select "manage topics."