Skip to content
RobothecaBeta
Log in

JEPA world models (jepa-wms)

  • AI model
  • Humanoids and robot learning

A PyTorch release of JEPA-WMs, joint-embedding predictive world models for physical planning, with pretrained models, datasets and training and evaluation code from Meta AI Research.

  • Non-commercial
  • Non-commercial weights

Made by Meta, United States (checked on github.com/facebookresearch (opens in a new tab)).

Source on GitHub: github.com/facebookresearch/jepa-wms (opens in a new tab). Facts read at commit 13cf1d9 (opens in a new tab).

Licenses

Code
CC-BY-NC-4.0 (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (CC-BY-NC-4.0) at commit 13cf1d9 (opens in a new tab), on 16 Oct 2026.

Commercial use
No

The code and weights licenses do not allow commercial use.

Labels

  • Non-commercialThe code license (CC-BY-NC-4.0) does not allow commercial use.
  • Non-commercial weightsThe weights license (CC-BY-NC-4.0) does not allow commercial use.

What it does

  • Provides pretrained JEPA-WM world models for DROID and RoboCasa, Metaworld, Push-T, PointMaze and Wall environments.
  • Also ships reproduced DINO-WM baseline models and a V-JEPA-2-AC(fixed) baseline for the same environments.
  • Includes optional VM2M decoder heads for visualizing predictions and rollouts; they are not needed for training or planning.
  • Offers training entry points with configs for each environment, plus automatic planning evaluations during training.
  • Supplies planning evaluation scripts, grid evaluation over hyperparameters or checkpoints, and unroll decode evaluation for counterfactual actions.
  • Downloads datasets from Hugging Face, with optional DROID data via gsutil, and loads models through torch.hub or Hugging Face Hub.

Written by Robotheca from the project's README (opens in a new tab) at commit 13cf1d9.

Getting started

Difficulty
Advanced

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
11 Apr 2026 on main
Latest release
None published on GitHub

Checked on GitHub on 16 Oct 2026.

Links

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.