Metraipolis › archive › dc_4accba4e425d

La-JEPA: Compact Robot Policies with Latent World Modeling — arXiv:2611.08156

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08156
License (as archived)
CC0-1.0
Archived
2026-11-06T14:51:18.456Z
SHA-256 of the archived text
b99b800a7854a2bae0363e7d437ffbeb812b18cd44536210744a14454adb5891
Stable URL of this page
https://metraipolis.com/documento/dc_4accba4e425d

How to cite

La-JEPA: Compact Robot Policies with Latent World Modeling — arXiv:2611.08156 — arXiv (en), https://arxiv.org/abs/2611.08156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4accba4e425d (Metraipolis archive dc_4accba4e425d, sha256 b99b800a7854a2bae0363e7d437ffbeb812b18cd44536210744a14454adb5891)
BibTeX
@misc{dc4accba4e425d,
  title = {La-JEPA: Compact Robot Policies with Latent World Modeling — arXiv:2611.08156},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08156},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4accba4e425d; sha256 b99b800a7854a2bae0363e7d437ffbeb812b18cd44536210744a14454adb5891},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-action models adapt pretrained video generators, and vision-language-action models build on pretrained vision-language backbones; both tie policy architecture and inference cost to large transformers designed for generation rather than control. It remains unclear how much these generation-oriented choices affect control. In this work, we introduce Latent Action JEPA (La-JEPA), a compact world-action model whose policy transformer is trained from scratch in the feature space of a pretrained V-JEPA 2.1 encoder. Following Fast-WAM, La-JEPA learns to predict future features jointly with actions during training and generates only actions at inference. Among policies without embodied pretraining, La-JEPA achieves state-of-the-art performance in clean and randomized RoboTwin 2.0 scenes and on LIBERO-Plus with correct instructions, while using far fewer parameters than the strongest competing policies. It runs substantially faster than Fast-WAM at comparable performance and outperforms the closest JEPA-based methods, LeapBot-WA and JEPA-WAM, on LIBERO-Plus and RoboTwin 2.0 without their pretrained policy backbones. On four real-robot tasks, its average success is comparable to pi0.5 and above non-embodied-pretrained baselines. Through a design study of the choices behind La-JEPA, we show that JEPA features outperform video VAE latents, most clearly out of distribution, and that training-time future prediction choices significantly impact the policy even when future prediction is skipped at inference. We correct the LIBERO-Plus instructions, as the officially released evaluator corrupts them for most variants, and re-evaluate several strong open baselines. Without a generative pretrained policy backbone, La-JEPA is better and faster than far larger policies, suggesting that robot foundation models may benefit from architectures designed for control rather than inherited from generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08156 — 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 2026-11-06T14:21:42.667Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).