RRepoGEO

REPOGEO REPORT · LITE

PKU-YuanGroup/Chat-UniVi

Default branch main · commit ec0b3db2 · scanned 6/5/2026, 5:37:47 AM

GitHub: 946 stars · 48 forks

AI VISIBILITY SCORE
33 /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
2 / 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 PKU-YuanGroup/Chat-UniVi, 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 problem/solution statement to the README's opening

    Why:

    CURRENT
    The README currently has a call to action (H5) and links immediately following the main H2 title.
    COPY-PASTE FIX
    Immediately after the main title (H2), add a paragraph: 'Chat-UniVi introduces a novel unified visual representation that empowers large language models with comprehensive understanding across both image and video modalities, enabling advanced multimodal reasoning and interaction.'
  • mediumtopics#2
    Expand topics to include 'multimodal-llm' and 'unified-representation'

    Why:

    CURRENT
    image-understanding, large-language-models, video-understanding, vision-language-model
    COPY-PASTE FIX
    image-understanding, large-language-models, video-understanding, vision-language-model, multimodal-llm, unified-representation
  • lowreadme#3
    Add a 'Key Features' or 'Why Chat-UniVi?' section to the README

    Why:

    COPY-PASTE FIX
    Add a new section titled 'Key Features' or 'Why Chat-UniVi?' that explicitly highlights its unique contributions, such as 'Unified Visual Representation for both Image and Video,' 'Seamless Integration with Large Language Models,' and 'State-of-the-Art Performance on Multimodal Benchmarks.'

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 PKU-YuanGroup/Chat-UniVi
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
CLIP
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. CLIP · recommended 2×
  2. Florence · recommended 2×
  3. DALL-E 3 · recommended 1×
  4. PaLM-E · recommended 1×
  5. Gemini · recommended 1×
  • CATEGORY QUERY
    How to empower large language models with comprehensive image and video understanding capabilities?
    you: not recommended
    AI recommended (in order):
    1. CLIP
    2. DALL-E 3
    3. PaLM-E
    4. Gemini
    5. LLaVA
    6. InstructBLIP
    7. Kosmos-1
    8. Florence
    9. VideoMAE
    10. MViT
    11. Timesformer
    12. ViT
    13. ResNet
    14. EfficientNet

    AI recommended 14 alternatives but never named PKU-YuanGroup/Chat-UniVi. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the best unified visual representation models for multimodal AI applications?
    you: not recommended
    AI recommended (in order):
    1. CLIP
    2. ALIGN
    3. Florence
    4. CoCa
    5. BLIP
    6. ViLT

    AI recommended 6 alternatives but never named PKU-YuanGroup/Chat-UniVi. 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 PKU-YuanGroup/Chat-UniVi?
    pass
    AI did not name PKU-YuanGroup/Chat-UniVi — 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 PKU-YuanGroup/Chat-UniVi in production, what risks or prerequisites should they evaluate first?
    pass
    AI named PKU-YuanGroup/Chat-UniVi 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 PKU-YuanGroup/Chat-UniVi solve, and who is the primary audience?
    pass
    AI named PKU-YuanGroup/Chat-UniVi 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 PKU-YuanGroup/Chat-UniVi. 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/PKU-YuanGroup/Chat-UniVi.svg)](https://repogeo.com/en/r/PKU-YuanGroup/Chat-UniVi)
HTML
<a href="https://repogeo.com/en/r/PKU-YuanGroup/Chat-UniVi"><img src="https://repogeo.com/badge/PKU-YuanGroup/Chat-UniVi.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

PKU-YuanGroup/Chat-UniVi — 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