RRepoGEO

REPOGEO REPORT · LITE

tsinghua-fib-lab/World-Model

Default branch main · commit 53d7623b · scanned 6/1/2026, 7:38:39 AM

GitHub: 728 stars · 36 forks

AI VISIBILITY SCORE
27 /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
1 / 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 tsinghua-fib-lab/World-Model, 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

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

OVERALL DIRECTION
  • highreadme#1
    Reposition README H1 and first sentence to emphasize survey companion role

    Why:

    CURRENT
    # Awesome-World-Model [](https://github.com/sindresorhus/awesome)
A curated list of awesome resources on World Models, based on the comprehensive survey "Understanding World or Predicting Future? A Comprehensive Survey of World Models".
    COPY-PASTE FIX
    # Understanding World or Predicting Future? A Comprehensive Survey of World Models (ACM CSUR 2025) - Official Companion Resources
This repository serves as the official companion to our comprehensive survey paper.
  • mediumtopics#2
    Add topics that describe the repository's format (survey/resource list)

    Why:

    CURRENT
    artificial-general-intelligence, embodied-intelligence, game-intelligence, societal-intelligence, urban-intelligence, world-models
    COPY-PASTE FIX
    artificial-general-intelligence, embodied-intelligence, game-intelligence, societal-intelligence, urban-intelligence, world-models, survey, literature-review, awesome-list, research-resources, academic-paper-companion
  • mediumreadme#3
    Add a dedicated 'About' section to clarify the repository's purpose and audience

    Why:

    COPY-PASTE FIX
    ## About This Repository
This repository provides a curated and regularly updated list of awesome resources, including key papers, code implementations, and datasets related to World Models. It is primarily intended for AI researchers, students, and practitioners seeking a foundational understanding and up-to-date overview of the field.

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 tsinghua-fib-lab/World-Model
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
"World Models" by Ha and Schmidhuber (2018)
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. "World Models" by Ha and Schmidhuber (2018) · recommended 1×
  2. "DreamerV3: Mastering Diverse Domains with World Models" by Hafner et al. (2023) · recommended 1×
  3. "A Survey of World Models in Reinforcement Learning" by Weng et al. (2023) · recommended 1×
  4. "Learning Latent Dynamics for Planning from Pixels" (PlaNet) by Hafner et al. (2019) · recommended 1×
  5. "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" (MuZero) by Schrittwieser et al. (2020) · recommended 1×
  • CATEGORY QUERY
    Where can I find a comprehensive overview of world models for AI research?
    you: not recommended
    AI recommended (in order):
    1. "World Models" by Ha and Schmidhuber (2018)
    2. "DreamerV3: Mastering Diverse Domains with World Models" by Hafner et al. (2023)
    3. "A Survey of World Models in Reinforcement Learning" by Weng et al. (2023)
    4. "Learning Latent Dynamics for Planning from Pixels" (PlaNet) by Hafner et al. (2019)
    5. "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" (MuZero) by Schrittwieser et al. (2020)
    6. "Recurrent World Models for Reinforcement Learning" by Ha and Schmidhuber (2018)
    7. "World Models: A Survey" by Wang et al. (2023)

    AI recommended 7 alternatives but never named tsinghua-fib-lab/World-Model. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the foundational concepts for building embodied intelligence in AI systems?
    you: not recommended
    AI recommended (in order):
    1. Intel RealSense

    AI recommended 1 alternative but never named tsinghua-fib-lab/World-Model. 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 tsinghua-fib-lab/World-Model?
    pass
    AI did not name tsinghua-fib-lab/World-Model — likely talking about a different project

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

  • If a team adopts tsinghua-fib-lab/World-Model in production, what risks or prerequisites should they evaluate first?
    pass
    AI named tsinghua-fib-lab/World-Model 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 tsinghua-fib-lab/World-Model solve, and who is the primary audience?
    pass
    AI did not name tsinghua-fib-lab/World-Model — likely talking about a different project

    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 tsinghua-fib-lab/World-Model. 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/tsinghua-fib-lab/World-Model.svg)](https://repogeo.com/en/r/tsinghua-fib-lab/World-Model)
HTML
<a href="https://repogeo.com/en/r/tsinghua-fib-lab/World-Model"><img src="https://repogeo.com/badge/tsinghua-fib-lab/World-Model.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

tsinghua-fib-lab/World-Model — 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