Metraipolis › archive › dc_e546ca23d905
CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model — arXiv:2609.23184
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23184
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:59:29.294Z
- SHA-256 of the archived text
feb81ca596fe4a6846884661e7c5bfeac2bae9393d4fe870cbcd787c89f235f0- Stable URL of this page
https://metraipolis.com/documento/dc_e546ca23d905
How to cite
CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model — arXiv:2609.23184 — arXiv (en), https://arxiv.org/abs/2609.23184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e546ca23d905 (Metraipolis archive dc_e546ca23d905, sha256 feb81ca596fe4a6846884661e7c5bfeac2bae9393d4fe870cbcd787c89f235f0)
BibTeX
@misc{dce546ca23d905,
title = {CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model — arXiv:2609.23184},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23184},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e546ca23d905; sha256 feb81ca596fe4a6846884661e7c5bfeac2bae9393d4fe870cbcd787c89f235f0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly entangled within latent representations. We introduce CausalWM, a 16B embodied world model that performs explicit causal chain-of-thought reasoning before future video prediction. CausalWM organizes useful variables into a reasoning trajectory, allowing the model to progressively capture causal dependencies underlying physical evolution. To train CausalWM, we collect 31K hours embodied data and develop a three-stage paradigm consisting of large-scale video pre-training, causal CoT mid-training, and multi-objective RL post-training. Despite using only a limited set of supervised CoT variables, CausalWM exhibits emergent in-context learning capabilities, enabling contextual visual feature guidance and efficient few-step generation. CausalWM achieves state-of-the-art performance across language-conditioned, action-conditioned, single-view and multi-view benchmarks, including Top-1 performance on TriWorldBench leaderboard. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.23184 — 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 2026-10-09T21:45:20.865Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).