Python
sunrainyg/RandOpt
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
★ 658
Stars
74 forks · 6 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
19.4
Momentum / 100
see the breakdown below
8mo ago
Created
last push 47d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 11.3 | last push 47d ago; decays to zero at 180 days |
| Scale | 15 | 8.2 | 658 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 19.4 | sum of the above |
Detail
| Topics | black-box-optimizationensemble-learninglarge-language-modelsllmloraneuroevolutionpost-trainingreasoningtransformers |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +8 stars over 26 days = 0.3/day |
| Lifetime average | 2.53 stars/day over 260 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |