RRepoGEO

REPOGEO REPORT · LITE

daixiangzi/Awesome-Token-Compress

Default branch master · commit 50b07670 · scanned 6/15/2026, 10:08:14 AM

GitHub: 920 stars · 43 forks

AI VISIBILITY SCORE
17 /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
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 daixiangzi/Awesome-Token-Compress, 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
  • highlicense#1
    Add a LICENSE file to the repository

    Why:

    CURRENT
    (no LICENSE file detected — the repo has no recognizable license)
    COPY-PASTE FIX
    Create a LICENSE file in the repository root with an appropriate open-source license (e.g., MIT, Apache-2.0, GPL-3.0).
  • mediumreadme#2
    Clarify the README's opening sentence to emphasize its 'awesome list' nature

    Why:

    CURRENT
    🔥🔥🔥 A paper list of some recent works about Token Compress for Vit and VLM.
    COPY-PASTE FIX
    🔥🔥🔥 A curated and comprehensive paper list of recent works on Token Compression for Vision Transformers (ViT) and Vision-Language Models (VLM).

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 daixiangzi/Awesome-Token-Compress
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
huggingface/transformers
Recommended in 3 of 2 queries
COMPETITOR LEADERBOARD
  1. huggingface/transformers · recommended 3×
  2. microsoft/onnxruntime · recommended 2×
  3. NVIDIA/TensorRT · recommended 2×
  4. PyTorch Quantization Toolkit · recommended 1×
  5. PaddlePaddle/PaddleSlim · recommended 1×
  • CATEGORY QUERY
    How to improve efficiency and reduce computational cost in large vision language models?
    you: not recommended
    AI recommended (in order):
    1. PyTorch Quantization Toolkit
    2. ONNX Runtime (microsoft/onnxruntime)
    3. TensorRT (NVIDIA/TensorRT)
    4. Hugging Face Transformers Library (huggingface/transformers)
    5. PaddlePaddle PaddleSlim (PaddlePaddle/PaddleSlim)
    6. PyTorch Pruning Utilities
    7. TensorFlow Model Optimization Toolkit (tensorflow/model-optimization)
    8. NVIDIA Apex (NVIDIA/apex)
    9. Longformer (huggingface/transformers)
    10. BigBird (huggingface/transformers)
    11. Perceiver IO (deepmind/perceiver)
    12. MobileNet
    13. EfficientNet
    14. TensorRT (NVIDIA/TensorRT)
    15. OpenVINO (openvinotoolkit/openvino)
    16. ONNX Runtime (microsoft/onnxruntime)
    17. Hugging Face PEFT Library (huggingface/peft)
    18. LoRA (Low-Rank Adaptation)

    AI recommended 18 alternatives but never named daixiangzi/Awesome-Token-Compress. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are effective token compression techniques for optimizing vision transformers and video LLMs?
    you: not recommended
    AI recommended (in order):
    1. Token Merging (ToMe)
    2. StreamingLLM
    3. Longformer
    4. Performer
    5. BigBird
    6. Perceiver IO
    7. Vision Permuter
    8. Hugging Face Optimum
    9. PyTorch Quantization APIs
    10. VQ-GAN
    11. DALL-E's VQ-VAE
    12. Swin Transformer
    13. MViT

    AI recommended 13 alternatives but never named daixiangzi/Awesome-Token-Compress. 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 daixiangzi/Awesome-Token-Compress?
    pass
    AI did not name daixiangzi/Awesome-Token-Compress — 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 daixiangzi/Awesome-Token-Compress in production, what risks or prerequisites should they evaluate first?
    pass
    AI named daixiangzi/Awesome-Token-Compress 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 daixiangzi/Awesome-Token-Compress solve, and who is the primary audience?
    pass
    AI did not name daixiangzi/Awesome-Token-Compress — 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 daixiangzi/Awesome-Token-Compress. 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/daixiangzi/Awesome-Token-Compress.svg)](https://repogeo.com/en/r/daixiangzi/Awesome-Token-Compress)
HTML
<a href="https://repogeo.com/en/r/daixiangzi/Awesome-Token-Compress"><img src="https://repogeo.com/badge/daixiangzi/Awesome-Token-Compress.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

daixiangzi/Awesome-Token-Compress — 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