Python · MIT
rzc156/dreamforge
Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).
★ 131
Stars
3 forks · 0 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
19.1
Momentum / 100
see the breakdown below
27d ago
Created
last push 27d 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 | 13.0 | last push 27d ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 131 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 19.1 | sum of the above |
Detail
| Topics | embodied-aiimitation-learninglerobotliberopytorchresearchroboticsvision-language-actionvlaworld-model |
| Matched on | Robotics (robotics) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +8 stars over 22 days = 0.4/day |
| Lifetime average | 5.39 stars/day over 24 days |
| First seen here | 2026-10-14 |
| Last read | 2d ago |