# thu-ml/Motus

Official code of Motus: A Unified Latent Action World Model

Repository: https://github.com/thu-ml/Motus
Canonical: https://ross.abutalabs.com/products/motus
Homepage: https://motus-robotics.github.io/motus
Language: Python
License: Apache-2.0
License Family: permissive
Topics: robotics, world-model, video-generation, unidiffuser, robotic-manipulation, diffusion-model, vision-language-action-model
Last push: 2026-01-05T16:44:07+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 60, release rhythm 35, longevity 18
- inputs: {"age_days": 264, "days_push": 240, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1246, forks 73 (observed 2026-08-28T04:04:07.231394+00:00)

## What it is
Motus is the official implementation of a unified latent action world model for robotics, combining a video generation model, a vision-language model, and action/understanding experts via a Mixture-of-Transformers architecture. It supports multiple modeling modes including world modeling, vision-language-action prediction, inverse dynamics, and video-action joint prediction, with pretrained checkpoints and training/inference code.

## Use cases
- train a vision-language-action model for robotic manipulation
- generate future video predictions conditioned on robot actions
- pretrain robot policies on large-scale unlabeled video using latent actions
- run inverse dynamics model inference to extract actions from video
- evaluate multi-task robot policies in RoboTwin 2.0 simulation
- experiment with unified diffusion-based world models

## When to choose
- you need a unified world model and VLA in one codebase
- you want to leverage pretrained video and vision-language backbones for robotics
- you need cross-embodiment action pretraining from raw video via optical-flow latent actions

## When to avoid
- you need a lightweight real-time robot controller rather than a research model
- you lack GPU resources for an ~8B parameter diffusion model
- you need a production-ready deployment stack rather than research code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, simulation, llm-inference
- domain: robotics, artificial-intelligence, machine-learning
- platform: python
- tags: world-model, vision-language-action, diffusion-model, latent-actions, robotic-manipulation, optical-flow, mixture-of-transformers, video-generation, video, gpu, linux

## Member repositories
- thu-ml/Motus (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.231394+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 2026-08-30T05:08:05.884683+00:00, confidence not recorded.
  - readme: https://github.com/thu-ml/Motus (fetched 2026-08-28T04:04:07.231394+00:00, sha 57d26d730bb0)
  - homepage: https://motus-robotics.github.io/motus (fetched 2026-08-29T12:19:30.956807+00:00, sha 0e6548baa330)
- Data as of 2026-08-30T08:39:29.467469+00:00.