# lucas-maes/le-wm

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Repository: https://github.com/lucas-maes/le-wm
Canonical: https://ross.abutalabs.com/products/le-wm
Homepage: https://le-wm.github.io/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-05-26T17:22:05+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 12
- inputs: {"age_days": 173, "days_push": 99, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4344, forks 634 (observed 2026-08-28T04:08:46.134176+00:00)

## What it is
LeWorldModel (LeWM) is the official PyTorch codebase for a JEPA-based world model that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a Gaussian regularizer. It is a lightweight (~15M parameter) model trainable on a single GPU in hours, supporting planning in 2D and 3D control tasks and probing of latent physical structure.

## Use cases
- train a JEPA world model from pixels on a single GPU
- plan in 2D and 3D control environments with a learned latent dynamics model
- reproduce the LeWM paper results from the official codebase
- probe latent representations for encoded physical quantities
- evaluate world models on surprise detection of physically implausible events
- benchmark lightweight world models against foundation-model-based alternatives

## When to choose
- you need a small, fast world model trainable on a single GPU
- you want a JEPA that avoids representation collapse without EMA or pretrained encoders
- you are doing research on self-supervised world models or model-based control
- you want to reproduce or extend the LeWM paper

## When to avoid
- you need a production-ready robotics or game engine world simulator
- you require large-scale foundation-model-based world models with broad generalization
- you need a no-code or turnkey ML tool rather than a research codebase

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, simulation, llm-training
- domain: machine-learning, reinforcement-learning, artificial-intelligence
- platform: python
- tags: world-model, jepa, self-supervised-learning, representation-learning, model-based-planning, research-code, pytorch, research, gpu, linux, macos

## Member repositories
- lucas-maes/le-wm (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.134176+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:35.405585+00:00, confidence not recorded.
  - readme: https://github.com/lucas-maes/le-wm (fetched 2026-08-28T04:08:46.134176+00:00, sha e70ada40ddd7)
  - homepage: https://le-wm.github.io/ (fetched 2026-08-29T09:10:37.860344+00:00, sha 224d9f809fbd)
- Data as of 2026-08-30T08:39:29.467469+00:00.