RRepoGEO

REPOGEO REPORT · LITE

kepengxu/PRISM-VL

Default branch main · commit c73957b0 · scanned 6/17/2026, 10:13:47 PM

GitHub: 476 stars · 15 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 kepengxu/PRISM-VL, 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
  • hightopics#1
    Add specific topics to improve categorization

    Why:

    COPY-PASTE FIX
    vision-language-models, raw-sensor-data, measurement-domain, vlm-pretraining, computer-vision, deep-learning, ai-research, multimodal-ai, image-processing, sensor-fusion
  • mediumhomepage#2
    Add the project page URL to the repository homepage field

    Why:

    COPY-PASTE FIX
    https://kepengxu.github.io/projects/prism-vl/

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 kepengxu/PRISM-VL
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. Hugging Face Transformers library · recommended 2×
  3. ViLT · recommended 2×
  4. OpenCLIP · recommended 1×
  5. LAION-5B · recommended 1×
  • CATEGORY QUERY
    How to improve vision-language model performance using raw sensor data inputs?
    you: not recommended
    AI recommended (in order):
    1. CLIP
    2. OpenCLIP
    3. LAION-5B
    4. Perceiver IO
    5. Perceiver AR
    6. Hugging Face Transformers library
    7. Flamingo
    8. OpenFlamingo
    9. ViLT
    10. METER
    11. CoCa
    12. Hugging Face Transformers library
    13. MMDetection3D
    14. NeRF
    15. Nerfstudio
    16. LERF
    17. CLIP-NeRF
    18. RT-2
    19. VIMA

    AI recommended 19 alternatives but never named kepengxu/PRISM-VL. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking methods for vision-language models that utilize measurement-domain observations instead of RGB images.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers (huggingface/transformers)
    2. CLIP
    3. ViLT
    4. BLIP
    5. LLaVA (haotian-liu/LLaVA)
    6. OpenCLIP (mlfoundations/open_clip)
    7. MMDetection3D (open-mmlab/mmdetection3d)
    8. MMDetection (open-mmlab/mmdetection)
    9. MMSegmentation (open-mmlab/mmsegmentation)
    10. PyTorch Geometric (pyg-team/pytorch_geometric)
    11. MONAI (Project-MONAI/MONAI)
    12. PyTorch (pytorch/pytorch)
    13. TensorFlow (tensorflow/tensorflow)

    AI recommended 13 alternatives but never named kepengxu/PRISM-VL. 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 kepengxu/PRISM-VL?
    pass
    AI named kepengxu/PRISM-VL explicitly

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

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

Subscribe to Pro for deep diagnoses

kepengxu/PRISM-VL — 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