Metraipolis › archive › dc_7969b2a62016
EVEWorld: Physical Evolution Supervision for Embodied World Models — arXiv:2610.03374
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.03374
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:08:18.578Z
- SHA-256 of the archived text
6888413b51b1c8dee543a7fb531461f5c17ec365cf56cb3cbd314880d9a54c19- Stable URL of this page
https://metraipolis.com/documento/dc_7969b2a62016
How to cite
EVEWorld: Physical Evolution Supervision for Embodied World Models — arXiv:2610.03374 — arXiv (en), https://arxiv.org/abs/2610.03374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7969b2a62016 (Metraipolis archive dc_7969b2a62016, sha256 6888413b51b1c8dee543a7fb531461f5c17ec365cf56cb3cbd314880d9a54c19)
BibTeX
@misc{dc7969b2a62016,
title = {EVEWorld: Physical Evolution Supervision for Embodied World Models — arXiv:2610.03374},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.03374},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7969b2a62016; sha256 6888413b51b1c8dee543a7fb531461f5c17ec365cf56cb3cbd314880d9a54c19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Embodied world models enable scalable simulation of embodied interactions for robot learning. However, existing models are prone to Model Laziness, as they focus on visual fidelity at the expense of physical reasoning and lack process-level supervision over the temporal dynamics of manipulated objects. In this work, we propose EVEWorld, a physical evolution-supervision framework for physically consistent target evolution. EVEWorld consists of two components: Instance-Guided Restoration (IGR) and Temporal Instance Alignment (TIA). First, IGR promotes instance consistency through restoration supervision. Second, TIA promotes cross-frame consistency by aligning target instances across adjacent frames. We further introduce the Model Laziness Rate (MLR), a metric that measures persistent violations of instance consistency in generated trajectories. Extensive experiments on DreamGenBench, EWMBench, and PBench demonstrate the effectiveness of EVEWorld, notably achieving an 87.5% reduction in MLR compared with GigaWorld-0. On the WorldArena 2.0 Track 1 leaderboard, our model ranks 6th in JEPA Similarity and 17th overall, which further validates the performance of our evolution supervision strategy. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.03374 — 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 2026-10-06T08:21:44.237Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).