Metraipolis › archive › dc_018cbf6ebecf

LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC — arXiv:2610.12407

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.12407
License (as archived): CC0-1.0
Archived: 2026-10-09T06:03:56.224Z
SHA-256 of the archived text: 90c38190b5834ef016c7f7cd441dc31bb1baa8ae4a841e58f9c1525caf8b45bf
Stable URL of this page: https://metraipolis.com/documento/dc_018cbf6ebecf

How to cite

LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC — arXiv:2610.12407 — arXiv (en), https://arxiv.org/abs/2610.12407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_018cbf6ebecf (Metraipolis archive dc_018cbf6ebecf, sha256 90c38190b5834ef016c7f7cd441dc31bb1baa8ae4a841e58f9c1525caf8b45bf)

BibTeX

@misc{dc018cbf6ebecf,
  title = {LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC — arXiv:2610.12407},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12407},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_018cbf6ebecf; sha256 90c38190b5834ef016c7f7cd441dc31bb1baa8ae4a841e58f9c1525caf8b45bf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream predictions. We introduce LeWAM, a bidirectional transformer for forward, backward, inverse dynamics and policy prediction, on a decoder-free JEPA latent trained end-to-end through all four modes. We see the following benefits: 1) Alignment: linear probes read robot and object state from LeWAM's latent better than from a regular Le World Model (a forward-only JEPA world model), while the latent ignores visual distractors as well as LeWM does and far better than a reconstruction-based WAM. 2) Acting: Closed-loop evaluations of LeWAM match a regular flow-matching policy trained on the same encoder at matched size, while also providing a world model. 3) Planning: Sampling raw actions when planning with WAMs lets MPC exploit dynamics-model inaccuracies; planning in the noise space of the policy head instead improves the closed-loop performance of these WAMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12407 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:02.203Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).