RRepoGEO

REPOGEO REPORT · LITE

UMass-Embodied-AGI/3D-LLM

Default branch main · commit 40002901 · scanned 5/19/2026, 5:52:44 AM

GitHub: 1,196 stars · 75 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

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 UMass-Embodied-AGI/3D-LLM, 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
    Strengthen the README's opening paragraph to clarify unique value

    Why:

    CURRENT
    3D-LLM is the first Large Language Model that could take 3D representations as inputs. It is able to handle both object (e.g., objaverse) and scene data (e.g., scannet & hm3d).
    COPY-PASTE FIX
    3D-LLM is the first Large Language Model (LLM) designed to directly process and reason about native 3D representations, including both object-level (e.g., Objaverse) and scene-level (e.g., ScanNet, HM3D) data. This enables LLMs to understand and interact with the 3D world, bridging the gap between language and embodied perception.
  • mediumhomepage#2
    Add the project homepage URL

    Why:

    COPY-PASTE FIX
    https://vis-www.cs.umass.edu/3dllm/

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 UMass-Embodied-AGI/3D-LLM
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. PointNet++ · recommended 2×
  3. DGCNN · recommended 2×
  4. PointCLIP · recommended 2×
  5. Point-BERT · recommended 2×
  • CATEGORY QUERY
    How can I integrate 3D scene data as input into large language models?
    you: not recommended
    AI recommended (in order):
    1. CLIP
    2. PointNet++
    3. DGCNN
    4. Neural Radiance Fields (NeRFs)
    5. 3D Gaussian Splatting
    6. Hugging Face Transformers (huggingface/transformers)
    7. LAVIS
    8. BLIP-2
    9. InstructBLIP
    10. LLaVA
    11. Vicuna
    12. PointCLIP
    13. ULIP
    14. PyTorch Geometric (PyG) (pyg-team/pytorch_geometric)
    15. DGL (Deep Graph Library) (dmlc/dgl)
    16. Point-BERT
    17. Masked Autoencoders for 3D (MAE-3D)

    AI recommended 17 alternatives but never named UMass-Embodied-AGI/3D-LLM. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools allow large language models to understand and process 3D object representations?
    you: not recommended
    AI recommended (in order):
    1. Open3D-LLM
    2. GPT-4o
    3. Gemini 1.5 Pro
    4. Llama 3
    5. PointNet
    6. Point-BERT
    7. CLIP
    8. CLIP-Forge
    9. PointCLIP
    10. Instant NGP
    11. Mip-NeRF 360
    12. DreamFusion
    13. Magic3D
    14. PointNet++
    15. DGCNN
    16. Gradio
    17. Streamlit

    AI recommended 17 alternatives but never named UMass-Embodied-AGI/3D-LLM. 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 UMass-Embodied-AGI/3D-LLM?
    pass
    AI did not name UMass-Embodied-AGI/3D-LLM — 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 UMass-Embodied-AGI/3D-LLM in production, what risks or prerequisites should they evaluate first?
    pass
    AI named UMass-Embodied-AGI/3D-LLM 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 UMass-Embodied-AGI/3D-LLM solve, and who is the primary audience?
    pass
    AI named UMass-Embodied-AGI/3D-LLM 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 UMass-Embodied-AGI/3D-LLM. 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/UMass-Embodied-AGI/3D-LLM.svg)](https://repogeo.com/en/r/UMass-Embodied-AGI/3D-LLM)
HTML
<a href="https://repogeo.com/en/r/UMass-Embodied-AGI/3D-LLM"><img src="https://repogeo.com/badge/UMass-Embodied-AGI/3D-LLM.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

UMass-Embodied-AGI/3D-LLM — 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