Views
No views yet
| File | Description |
|---|---|
config.yaml | Training configuration (ViT-tiny encoder, DiT predictor, epoch/LR schedule) |
lejepa_weights.ckpt | PyTorch Lightning training checkpoint — use this for inference (no pickle class-path dependencies) |
lejepa_epoch_50_object.ckpt | Object checkpoint pickled against private training codebase — requires missing module.* namespace; cannot be loaded with released upstream code |
lejepa_weights.ckpt.dmc_cheetah_lejepa_ckpt.tar.zst1@misc{maes_lelidec2026swm-1,
2 title={stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation},
3 author={Lucas Maes and Quentin Le Lidec and Dan Haramati and
4 Nassim Massaudi and Damien Scieur and Yann LeCun and
5 Randall Balestriero},
6 year={2026},
7 eprint={2602.08968},
8 archivePrefix={arXiv},
9 primaryClass={cs.AI},
10 url={https://arxiv.org/abs/2602.08968},
11}