The authors compare LeWM, DINO-WM and JEPA-WM in goal-conditioned zero-shot planning.
Compressed world models make zero-shot driving plans far faster
AD-E2E-JEPA reduces latent representations substantially while preserving competitive goal-conditioned planning on NAVSIMv2.
Academic
Haoran Zhu · Wancong Zhang · Yann LeCun · Anna Choromanska
New York University · AMI Labs
Research Digest··2 min read
Zhu and colleagues evaluate action-conditioned joint-embedding predictive architectures, or JEPAs, as driving world models without training a driving policy.
Why this paper
From New York University and AMI Labs · Released code
In one line
AD-E2E-JEPA compresses latent driving representations to accelerate world-model planning 100-fold while preserving planning quality and improving downstream imitation learning.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§