Jupyter Notebook
facebookresearch/VLM3
[NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
★ 440
Stars
16 forks · 1 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
20.3
Momentum / 100
see the breakdown below
6mo ago
Created
last push 44d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.93× the monthly pace |
| Freshness | 15 | 11.5 | last push 44d ago; decays to zero at 180 days |
| Scale | 15 | 7.7 | 440 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 20.3 | sum of the above |
Detail
| Topics | 3d-foundation-modelcamera-pose-estimationdepth-estimationimage-matchinglarge-language-modelsobject-level-3dvlms |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +4 stars over 26 days = 0.2/day |
| Lifetime average | 2.44 stars/day over 181 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |