RRepoGEO

REPOGEO REPORT · LITE

Haiyang-W/TokenFormer

Default branch main · commit 4d56c73f · scanned 6/5/2026, 3:17:58 AM

GitHub: 590 stars · 43 forks

AI VISIBILITY SCORE
40 /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
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 Haiyang-W/TokenFormer, 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
    Reposition the README H1 to specify its role in LLM scaling and flexible architectures

    Why:

    CURRENT
    # TokenFormer: a fully attention-based neural network with tokenized model parameters. Maximizing the flexibility of Transformer by Tokenizing Anything.
    COPY-PASTE FIX
    # TokenFormer: Rethinking Transformer Scaling for Large Language Models with Tokenized Model Parameters and Flexible Attention Architectures.
  • mediumtopics#2
    Expand topics to include more specific keywords for efficient and novel transformer architectures

    Why:

    CURRENT
    architecture, attention-mechanism, foundation-models, llm, scaling-methods, transformer
    COPY-PASTE FIX
    architecture, attention-mechanism, foundation-models, llm, scaling-methods, transformer, efficient-transformers, long-context, parameter-efficiency, novel-architecture
  • lowreadme#3
    Add a comparison section to the README

    Why:

    COPY-PASTE FIX
    Add a new section, e.g., `## Comparison to Existing Architectures` or `## TokenFormer's Unique Differentiators`, explaining how TokenFormer's "tokenized model parameters" and "architectural flexibility" provide advantages over other scaling methods or novel architectures.

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 Haiyang-W/TokenFormer
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
RWKV
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. RWKV · recommended 2×
  2. Mamba · recommended 2×
  3. Longformer · recommended 1×
  4. Reformer · recommended 1×
  5. BigBird · recommended 1×
  • CATEGORY QUERY
    How to improve large language model scaling and architectural flexibility using novel transformer designs?
    you: not recommended
    AI recommended (in order):
    1. Longformer
    2. Reformer
    3. BigBird
    4. Performer
    5. Linformer
    6. Switch Transformer
    7. GLaM
    8. MegaBlocks
    9. RWKV
    10. Mamba
    11. FlashAttention

    AI recommended 11 alternatives but never named Haiyang-W/TokenFormer. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are new attention-based neural network architectures for more flexible model parameters?
    you: not recommended
    AI recommended (in order):
    1. Perceiver IO / Perceiver
    2. LongNet
    3. Hyena Hierarchy
    4. Mamba
    5. RetNet
    6. RWKV
    7. FlashAttention-2

    AI recommended 7 alternatives but never named Haiyang-W/TokenFormer. 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 Haiyang-W/TokenFormer?
    pass
    AI named Haiyang-W/TokenFormer explicitly

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

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

Subscribe to Pro for deep diagnoses

Haiyang-W/TokenFormer — 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