RRepoGEO

REPOGEO REPORT · LITE

lxtGH/OMG-Seg

Default branch main · commit 48ab9407 · scanned 5/27/2026, 2:13:07 AM

GitHub: 1,346 stars · 54 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 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 lxtGH/OMG-Seg, 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
  • hightopics#1
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    segmentation, image-segmentation, multi-modal, large-language-models, llava, computer-vision, deep-learning, cvpr-2024, neurips-2024, one-shot-learning, visual-reasoning, visual-perception
  • highreadme#2
    Clarify the relationship between OMG-Seg and OMG-LLaVA in the README's opening

    Why:

    CURRENT
    ## OMG Model Research

Our goal is to solve multiple fundamental visual perception, visual reasoning, and multi-modal large langauge tasks using **one** model, which minimize handcraft designs and maximize the functionality and performance 
in one shot.

### Short Introduction of OMG-LLaVA...
    COPY-PASTE FIX
    ## OMG-Seg: Universal Segmentation and Multi-Modal Reasoning

This repository provides the official codebase for **OMG-Seg** (CVPR-24) and **OMG-LLaVA** (NeurIPS-24), our unified framework designed to solve multiple fundamental visual perception, visual reasoning, and multi-modal large language tasks using **one** model. OMG-Seg focuses on universal segmentation, while OMG-LLaVA integrates this with powerful reasoning abilities, accepting various visual and text prompts for flexible user interaction.
  • mediumhomepage#3
    Add the project homepage URL

    Why:

    COPY-PASTE FIX
    https://lxtgh.github.io/project/omg_llava/

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 lxtGH/OMG-Seg
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
GPT-4V
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. GPT-4V · recommended 1×
  2. Gemini · recommended 1×
  3. Kosmos-2 · recommended 1×
  4. Florence-2 · recommended 1×
  5. haotian-liu/LLaVA · recommended 1×
  • CATEGORY QUERY
    What frameworks integrate visual perception with large language models for complex reasoning?
    you: not recommended
    AI recommended (in order):
    1. GPT-4V
    2. Gemini
    3. Kosmos-2
    4. Florence-2
    5. Llava (haotian-liu/LLaVA)
    6. MiniGPT-4 (Vision-CAIR/MiniGPT-4)
    7. BLIP-2 (salesforce/BLIP2)
    8. CLIP (openai/CLIP)

    AI recommended 8 alternatives but never named lxtGH/OMG-Seg. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How to perform universal image segmentation with flexible visual and text prompts?
    you: not recommended
    AI recommended (in order):
    1. Segment Anything Model (SAM)
    2. Grounding DINO
    3. CLIPSeg
    4. SEEM (Segment Everything Everywhere All at Once)
    5. OWL-ViT (Open-World Localization with Vision Transformers)
    6. OneFormer
    7. Mask2Former
    8. CLIP
    9. LAVIS (Language-Vision Assistant)

    AI recommended 9 alternatives but never named lxtGH/OMG-Seg. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    warn

    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 lxtGH/OMG-Seg?
    pass
    AI named lxtGH/OMG-Seg explicitly

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

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

Subscribe to Pro for deep diagnoses

lxtGH/OMG-Seg — 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