Python · MIT
Intellindust-AI-Lab/GTR
GTR: Gated Token Recurrence for Efficient Dense Prediction
★ 140
Stars
14 forks · 1 open issues
+1.8/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
28.8
Momentum / 100
see the breakdown below
3mo ago
Created
last push 12d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 8.4 | +1.8/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.99× the monthly pace |
| Freshness | 15 | 14.2 | last push 12d ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 140 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 28.8 | sum of the above |
Detail
| Topics | deimdeimv2deploymentdepth-estimationdetredge-aiedgecrafterinstance-segmentationintellindust-ai-lablinear-attentionobject-detectionoriented-object-detectionpose-estimationreal-timesemantic-segmentation |
| Matched on | Computer Vision (object-detection) |
| Short window | +14 stars over 8 days = 1.8/day |
| Long window | +37 stars over 21 days = 1.8/day |
| Lifetime average | 1.43 stars/day over 98 days |
| First seen here | 2026-10-15 |
| Last read | 2d ago |