RRepoGEO

REPOGEO REPORT · LITE

Time-MoE/Time-MoE

Default branch main · commit 915bfda4 · scanned 5/31/2026, 12:13:25 AM

GitHub: 971 stars · 113 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 Time-MoE/Time-MoE, 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
    Add a direct, concise opening sentence to the README

    Why:

    COPY-PASTE FIX
    Time-MoE is the first billion-scale time series foundation model, leveraging a Mixture-of-Experts architecture for universal forecasting. This repository provides the official implementation and the largest open-access time series dataset, Time-300B.
  • mediumabout#2
    Refine the repository description for clearer AI categorization

    Why:

    CURRENT
    [ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"
    COPY-PASTE FIX
    Time-MoE: The first billion-scale time series foundation model with Mixture of Experts, enabling universal forecasting. Official ICLR 2025 Spotlight implementation.
  • mediumreadme#3
    Add a 'Why Time-MoE?' section to the README

    Why:

    COPY-PASTE FIX
    ## Why Time-MoE?

Time-MoE stands out as the **first work** to scale time series foundation models up to **2.4 billion** parameters, trained from scratch. Unlike existing solutions, our Mixture-of-Experts architecture combined with the **Time-300B** dataset (the largest open-access time series data collection) provides unparalleled capabilities for universal forecasting with arbitrary prediction horizons and context lengths.

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 Time-MoE/Time-MoE
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
aws-samples/amazon-chronos
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. aws-samples/amazon-chronos · recommended 1×
  2. Nixtla/lag-llama · recommended 1×
  3. TimeGPT · recommended 1×
  4. huggingface/transformers · recommended 1×
  5. GPT-2 · recommended 1×
  • CATEGORY QUERY
    How to build or use large-scale foundation models for time series forecasting?
    you: not recommended
    AI recommended (in order):
    1. Chronos (aws-samples/amazon-chronos)
    2. Lag-Llama (Nixtla/lag-llama)
    3. TimeGPT
    4. Hugging Face Transformers Library (huggingface/transformers)
    5. GPT-2
    6. BART
    7. T5
    8. PyTorch Forecasting (jdb78/pytorch-forecasting)
    9. GluonTS (awslabs/gluon-ts)
    10. Google Cloud Vertex AI

    AI recommended 10 alternatives but never named Time-MoE/Time-MoE. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What deep learning techniques scale time series models to billions of parameters effectively?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers library
    2. PyTorch Lightning
    3. TensorFlow/Keras
    4. PyTorch
    5. JAX/Flax
    6. DeepSpeed (Microsoft)
    7. PyTorch Geometric (PyG)
    8. Deep Graph Library (DGL)
    9. PyTorch Distributed Data Parallel (DDP)
    10. Fully Sharded Data Parallel (FSDP)
    11. TensorFlow Distributed Strategy API
    12. NVIDIA Apex
    13. Google Cloud TPUs

    AI recommended 13 alternatives but never named Time-MoE/Time-MoE. 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 Time-MoE/Time-MoE?
    pass
    AI named Time-MoE/Time-MoE explicitly

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

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

Subscribe to Pro for deep diagnoses

Time-MoE/Time-MoE — 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