RRepoGEO

REPOGEO REPORT · LITE

LiyuanLucasLiu/RAdam

Default branch master · commit d9fd30a3 · scanned 6/20/2026, 9:33:35 PM

GitHub: 2,548 stars · 331 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
71 /100
Needs work
Category recall
1 / 2
Avg rank #2.0 when recommended
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 LiyuanLucasLiu/RAdam, 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
    Expand repository topics to include problem domains

    Why:

    CURRENT
    adam, adam-optimizer, optimizer, warmup
    COPY-PASTE FIX
    adam, adam-optimizer, optimizer, warmup, deep-learning-stability, adaptive-learning-rate, training-instability, neural-network-optimization
  • mediumreadme#2
    Clarify the README's immediate opening statement

    Why:

    CURRENT
    We are in an early-release beta. Expect some adventures and rough edges.
    COPY-PASTE FIX
    RAdam is a theoretically sound variant of the Adam optimizer designed to improve training stability, particularly in the early stages, by addressing the large variance of adaptive learning rates. We are in an early-release beta. Expect some adventures and rough edges.
  • lowcomparison#3
    Add a dedicated comparison section to the README

    Why:

    COPY-PASTE FIX
    Add a new section, e.g., 'RAdam vs. Other Optimizers', briefly outlining how RAdam differentiates itself from Adam, AdamW, or other adaptive learning rate optimizers in terms of stability and performance.

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
1 / 2
50% of queries surface LiyuanLucasLiu/RAdam
Avg rank
#2.0
Lower is better. #1 = top recommendation.
Share of voice
7%
Of all named tools, what % are you?
Top rival
AdamW
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. AdamW · recommended 2×
  2. PyTorch · recommended 1×
  3. TensorFlow/Keras · recommended 1×
  4. Hugging Face transformers · recommended 1×
  5. fastai · recommended 1×
  • CATEGORY QUERY
    Why is my deep learning model training unstable with adaptive learning rate optimizers?
    you: not recommended
    AI recommended (in order):
    1. PyTorch
    2. TensorFlow/Keras
    3. Hugging Face transformers
    4. fastai
    5. AdamW
    6. RMSprop
    7. Adagrad
    8. SGD with Momentum

    AI recommended 8 alternatives but never named LiyuanLucasLiu/RAdam. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How to mitigate large variance in adaptive learning rate optimizers during training?
    you: #2
    AI recommended (in order):
    1. AdamW
    2. RAdam ← you
    3. Lookahead
    4. SGD
    5. AdaBelief
    6. LARS
    7. LAMB
    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 LiyuanLucasLiu/RAdam?
    pass
    AI named LiyuanLucasLiu/RAdam explicitly

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

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

Subscribe to Pro for deep diagnoses

LiyuanLucasLiu/RAdam — 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
LiyuanLucasLiu/RAdam — RepoGEO report