RRepoGEO

REPOGEO REPORT · LITE

thu-ml/Motus

Default branch main · commit f7712168 · scanned 6/19/2026, 6:38:16 AM

GitHub: 1,152 stars · 65 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface thu-ml/Motus, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

2 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • mediumreadme#1
    Add a 'Key Features' section to highlight technical differentiators

    Why:

    COPY-PASTE FIX
    ## Key Features

- **Unified Latent Action World Model:** Integrates understanding, action, and video generation.
- **Mixture-of-Transformers (MoT) Architecture:** Combines three specialized experts.
- **UniDiffuser-style Scheduler:** Enables flexible switching between various modeling modes (World Models, Vision-Language-Action Models, Inverse Dynamics Models, Video Generation Models, Video-Action Joint Prediction Models).
- **Latent Action Learning:** Leverages optical flow for efficient action representation.
  • lowcomparison#2
    Add a 'Comparison to Alternatives' section

    Why:

    COPY-PASTE FIX
    ## Comparison to Alternatives

Unlike general-purpose generative models such as Stable Diffusion or DALL-E 3, Motus is specifically engineered as a **unified latent action world model for robotic manipulation and vision-language-action tasks**. While other robotics models like Diffusion Policy or Robotics Transformer focus on specific aspects, Motus uniquely integrates multiple experts and modeling modes through its Mixture-of-Transformers architecture and UniDiffuser-style scheduler to provide a comprehensive framework for learning and generating actions and videos in complex environments.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface thu-ml/Motus
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Stable Diffusion
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Stable Diffusion · recommended 1×
  2. DALL-E 3 · recommended 1×
  3. Midjourney · recommended 1×
  4. Perceiver IO · recommended 1×
  5. GATO · recommended 1×
  • CATEGORY QUERY
    How to build a unified world model for robotic manipulation and video generation?
    you: not recommended
    AI recommended (in order):
    1. Stable Diffusion
    2. DALL-E 3
    3. Midjourney
    4. Perceiver IO
    5. GATO
    6. RT-2
    7. NVIDIA Isaac Gym
    8. MuJoCo
    9. Instant NGP
    10. Mip-NeRF 360
    11. PredRNN
    12. SVG
    13. DreamerV3
    14. PlaNet

    AI recommended 14 alternatives but never named thu-ml/Motus. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a diffusion model for vision-language-action tasks in robotics simulation.
    you: not recommended
    AI recommended (in order):
    1. Diffusion Policy
    2. Actuator
    3. Robotics Transformer
    4. Perceiver-Actor
    5. Diffuser

    AI recommended 5 alternatives but never named thu-ml/Motus. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of thu-ml/Motus?
    pass
    AI named thu-ml/Motus explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts thu-ml/Motus in production, what risks or prerequisites should they evaluate first?
    pass
    AI named thu-ml/Motus explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo thu-ml/Motus solve, and who is the primary audience?
    pass
    AI named thu-ml/Motus explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of thu-ml/Motus. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/thu-ml/Motus.svg)](https://repogeo.com/en/r/thu-ml/Motus)
HTML
<a href="https://repogeo.com/en/r/thu-ml/Motus"><img src="https://repogeo.com/badge/thu-ml/Motus.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

thu-ml/Motus — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite