RRepoGEO

REPOGEO REPORT · LITE

facebookresearch/tuna-2

Default branch main · commit b53594e3 · scanned 6/14/2026, 11:53:26 AM

GitHub: 713 stars · 28 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 facebookresearch/tuna-2, 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
  • highreadme#1
    Add a concise introductory paragraph to the README to clearly state the project's nature

    Why:

    CURRENT
    The README currently starts with the H1: # TUNA-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
    COPY-PASTE FIX
    Add the following text immediately after the H1:

This repository contains the official PyTorch implementation of **Tuna-2**, a novel unified multimodal model (UMM) that simplifies vision-language understanding and generation. Tuna-2 achieves state-of-the-art performance by directly processing raw pixel inputs with patch embedding layers, eliminating the need for complex vision encoders.
  • mediumhomepage#2
    Add the project homepage to the repository metadata

    Why:

    COPY-PASTE FIX
    https://tuna-ai.org/tuna-2

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 facebookresearch/tuna-2
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
PyTorch
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. PyTorch · recommended 1×
  2. PyTorch Lightning · recommended 1×
  3. Hugging Face Transformers · recommended 1×
  4. Hugging Face Diffusers · recommended 1×
  5. JAX · recommended 1×
  • CATEGORY QUERY
    How to build a unified multimodal model directly from pixel data for understanding and generation?
    you: not recommended
    AI recommended (in order):
    1. PyTorch
    2. PyTorch Lightning
    3. Hugging Face Transformers
    4. Hugging Face Diffusers
    5. JAX
    6. Flax
    7. Hugging Face JAX/Flax
    8. TensorFlow
    9. Keras
    10. Keras 3.0
    11. OpenAI CLIP
    12. DALL-E 2
    13. GPT-4V
    14. Meta AI ImageBind
    15. Meta AI SeamlessM4T

    AI recommended 15 alternatives but never named facebookresearch/tuna-2. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a vision model that uses raw pixel embeddings instead of complex vision encoders.
    you: not recommended
    AI recommended (in order):
    1. MLP-Mixer
    2. Perceiver IO
    3. Vision Transformer (ViT)
    4. CNNs (Convolutional Neural Networks)
    5. Autoencoders (especially Variational Autoencoders - VAEs)
    6. Self-Organizing Maps (SOMs)

    AI recommended 6 alternatives but never named facebookresearch/tuna-2. 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 facebookresearch/tuna-2?
    pass
    AI did not name facebookresearch/tuna-2 — 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 facebookresearch/tuna-2 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named facebookresearch/tuna-2 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 facebookresearch/tuna-2 solve, and who is the primary audience?
    pass
    AI named facebookresearch/tuna-2 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 facebookresearch/tuna-2. 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/facebookresearch/tuna-2.svg)](https://repogeo.com/en/r/facebookresearch/tuna-2)
HTML
<a href="https://repogeo.com/en/r/facebookresearch/tuna-2"><img src="https://repogeo.com/badge/facebookresearch/tuna-2.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

facebookresearch/tuna-2 — 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