Python · MIT
zju3dv/INTACT-JEPA
INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.
★ 224
Stars
20 forks · 0 open issues
+3.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
22.6
Momentum / 100
see the breakdown below
3mo ago
Created
last push 28d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.0 | +3.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.70× the monthly pace |
| Freshness | 15 | 12.8 | last push 28d ago; decays to zero at 180 days |
| Scale | 15 | 6.8 | 224 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 22.6 | sum of the above |
Detail
| Topics | goal-conditioned-controlimitation-learningjepalatent-dynamicsmodel-predictive-controlpytorchrepresentation-learningrobot-learningroboticsworld-models |
| Matched on | Robotics (robotics) |
| Short window | +3 stars over 7 days = 0.4/day |
| Long window | +16 stars over 26 days = 0.6/day |
| Lifetime average | 2.24 stars/day over 100 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |