Metraipolis › archive › dc_7258b951efd6

Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence — arXiv:2611.01677

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01677
License (as archived)
CC0-1.0
Archived
2026-11-03T10:22:18.088Z
SHA-256 of the archived text
11792804f23066781f6dcddebc67e4990e704270aa0fa7fa98f03e703a3f82c9
Stable URL of this page
https://metraipolis.com/documento/dc_7258b951efd6

How to cite

Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence — arXiv:2611.01677 — arXiv (en), https://arxiv.org/abs/2611.01677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7258b951efd6 (Metraipolis archive dc_7258b951efd6, sha256 11792804f23066781f6dcddebc67e4990e704270aa0fa7fa98f03e703a3f82c9)
BibTeX
@misc{dc7258b951efd6,
  title = {Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence — arXiv:2611.01677},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01677},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7258b951efd6; sha256 11792804f23066781f6dcddebc67e4990e704270aa0fa7fa98f03e703a3f82c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Xiaomi Auto World Model 2.0, a unified streaming causal world model for Physical AI. It models and generates causal physical evolution in the real world, and unifies heterogeneous conditioning inputs for view-consistent generation. The architecture integrates View-Temporal Attention (VTA) to capture cross-view spatial dependencies and temporal dynamics, together with Multi-view Rotary Position Encoding (RoPE) to encode positional relationships across views and time. WorldRec 2.0 reconstructs static and dynamic 3D Gaussians from multi-view, multi-temporal observations in a single forward pass and uses their renderings as explicit scene context to preserve geometry and appearance during long-horizon generation. Conditioning inputs are fused through VAE latent concatenation in a shared representation space. We incorporate Gated Linear Attention (GLA) into the temporal layers of VTA for efficient streaming inference, reducing computation and KV-cache memory during multi-view rollouts. A physical-interaction data pipeline covers diverse interactions and long-tailed events. From Pre-train onward, these data are combined with large-scale videos and heterogeneous visual modalities to learn visual, geometric, and dynamic priors. During Mid-train, training across diverse view configurations further improves the model's ability to capture how actions and object states shape subsequent scene evolution. After distillation-based Post-train, we apply the model to closed-loop simulation, closed-loop training, and World Action Model (WAM) applications. These applications generate physically consistent future states and support world-state prediction, policy learning, and action generation for Physical AI.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01677 — 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 2026-11-03T10:19:49.827Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).