RRepoGEO

REPOGEO REPORT · LITE

Ucas-HaoranWei/Vary

Default branch main · commit 9d06a142 · scanned 5/12/2026, 2:03:42 PM

GitHub: 1,891 stars · 145 forks

AI VISIBILITY SCORE
30 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 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 Ucas-HaoranWei/Vary, 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
    Add a concise introductory paragraph to the README

    Why:

    COPY-PASTE FIX
    Vary is the official code implementation for our ECCV 2024 paper, focusing on scaling up the vision vocabulary of Large Vision Language Models (LVLMs). It introduces novel approaches to enhance LVLM performance and efficiency, particularly excelling in complex tasks such as multi-page document understanding and chart parsing.
  • hightopics#2
    Add specific topics to improve categorization

    Why:

    COPY-PASTE FIX
    large-vision-language-models, vlm, vision-language-models, multi-modal, document-understanding, chart-parsing, eccv2024, computer-vision, deep-learning, llm-vision
  • highlicense#3
    Add a LICENSE file to the repository root

    Why:

    CURRENT
    (no LICENSE file detected — the repo has no recognizable license)
    COPY-PASTE FIX
    Create a LICENSE file (e.g., MIT, Apache-2.0, or a suitable open-source license) in the repository root directory.

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 Ucas-HaoranWei/Vary
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
microsoft/unilm
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. microsoft/unilm · recommended 2×
  2. mlfoundations/open_clip · recommended 1×
  3. huggingface/transformers · recommended 1×
  4. ViT (Vision Transformer) · recommended 1×
  5. BEiT (Bidirectional Encoder representations from Image Transformers) · recommended 1×
  • CATEGORY QUERY
    Seeking frameworks to enhance the vision vocabulary and understanding of large language models.
    you: not recommended
    AI recommended (in order):
    1. OpenCLIP (mlfoundations/open_clip)
    2. Hugging Face Transformers (huggingface/transformers)
    3. ViT (Vision Transformer)
    4. BEiT (Bidirectional Encoder representations from Image Transformers)
    5. CLIP
    6. MMDetection (open-mmlab/mmdetection)
    7. MMDetection3D (open-mmlab/mmdetection3d)
    8. Detectron2 (facebookresearch/detectron2)
    9. OWL-ViT (Open-Vocabulary Object Detection with Vision Transformers) (google-research/owlvit)
    10. BLIP (salesforce/BLIP)
    11. BLIP-2 (salesforce/LAVIS)

    AI recommended 11 alternatives but never named Ucas-HaoranWei/Vary. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are effective approaches for multi-page document understanding using vision language models?
    you: not recommended
    AI recommended (in order):
    1. LayoutLMv3 (microsoft/unilm)
    2. LayoutXLM (microsoft/unilm)
    3. Donut (naver-ai/donut)
    4. Nougat (facebookresearch/nougat)
    5. GPT-4V
    6. Gemini 1.5 Pro
    7. Pix2Struct (google-research/pix2struct)

    AI recommended 7 alternatives but never named Ucas-HaoranWei/Vary. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    fail

    Suggestion:

  • 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 Ucas-HaoranWei/Vary?
    pass
    AI named Ucas-HaoranWei/Vary explicitly

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

  • If a team adopts Ucas-HaoranWei/Vary in production, what risks or prerequisites should they evaluate first?
    pass
    AI named Ucas-HaoranWei/Vary 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 Ucas-HaoranWei/Vary solve, and who is the primary audience?
    pass
    AI named Ucas-HaoranWei/Vary 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 Ucas-HaoranWei/Vary. 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/Ucas-HaoranWei/Vary.svg)](https://repogeo.com/en/r/Ucas-HaoranWei/Vary)
HTML
<a href="https://repogeo.com/en/r/Ucas-HaoranWei/Vary"><img src="https://repogeo.com/badge/Ucas-HaoranWei/Vary.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

Ucas-HaoranWei/Vary — 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