RRepoGEO

REPOGEO REPORT · LITE

HazyResearch/m2

Default branch main · commit 7d359e8c · scanned 6/7/2026, 9:43:14 PM

GitHub: 563 stars · 45 forks

AI VISIBILITY SCORE
28 /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
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 HazyResearch/m2, 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 specific topics to the repository

    Why:

    COPY-PASTE FIX
    neural-networks, deep-learning, long-context, transformer-architecture, mixer-architecture, embeddings, m2-bert, efficient-models, sub-quadratic
  • highreadme#2
    Reposition the README's opening to clearly state Monarch Mixer's purpose

    Why:

    CURRENT
    The README currently starts with an update and then lists papers.
    COPY-PASTE FIX
    Insert this paragraph immediately after the main `# Monarch Mixer` heading: "Monarch Mixer is a novel sub-quadratic neural network architecture designed for highly efficient processing of extremely long document contexts and generating high-quality embeddings. It offers a simple, GEMM-based alternative to traditional attention mechanisms, enabling significant performance gains for long-sequence tasks."
  • mediumreadme#3
    Add a sentence to the README highlighting Monarch Mixer's unique advantage

    Why:

    COPY-PASTE FIX
    Add this sentence to the README, ideally near the repositioned purpose statement: "Monarch Mixer distinguishes itself from other long-context architectures like LongNet or Hyena Hierarchy by achieving sub-quadratic complexity through a simple, GEMM-based design, making it exceptionally efficient for processing very long sequences."

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 HazyResearch/m2
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LongNet
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. LongNet · recommended 1×
  2. Striped Attention (StripedHyena) · recommended 1×
  3. Hyena Hierarchy · recommended 1×
  4. Recurrent Memory Transformer (RMT) · recommended 1×
  5. Perceiver IO · recommended 1×
  • CATEGORY QUERY
    Seeking alternative neural network architectures for processing extremely long document contexts efficiently.
    you: not recommended
    AI recommended (in order):
    1. LongNet
    2. Striped Attention (StripedHyena)
    3. Hyena Hierarchy
    4. Recurrent Memory Transformer (RMT)
    5. Perceiver IO
    6. BigBird
    7. Reformer

    AI recommended 7 alternatives but never named HazyResearch/m2. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are efficient models for generating embeddings from very long text inputs?
    you: not recommended
    AI recommended (in order):
    1. OpenAI Embeddings
    2. E5-Mistral-7B-instruct
    3. BGE-M3
    4. Cohere Embed v3
    5. Voyage AI Embeddings
    6. GTE-large
    7. Sentence-BERT (SBERT)

    AI recommended 7 alternatives but never named HazyResearch/m2. 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 HazyResearch/m2?
    pass
    AI did not name HazyResearch/m2 — 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 HazyResearch/m2 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named HazyResearch/m2 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 HazyResearch/m2 solve, and who is the primary audience?
    pass
    AI named HazyResearch/m2 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 HazyResearch/m2. 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/HazyResearch/m2.svg)](https://repogeo.com/en/r/HazyResearch/m2)
HTML
<a href="https://repogeo.com/en/r/HazyResearch/m2"><img src="https://repogeo.com/badge/HazyResearch/m2.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

HazyResearch/m2 — 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