Metraipolis › archive › dc_455d26249f2a

Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination — arXiv:2609.38984

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38984
License (as archived)
CC0-1.0
Archived
2026-10-07T12:44:42.879Z
SHA-256 of the archived text
70d057c4753efc28d8a45d5ee02f1196c0b7653b66494d1ac3b17de5a480c0d0
Stable URL of this page
https://metraipolis.com/documento/dc_455d26249f2a

How to cite

Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination — arXiv:2609.38984 — arXiv (en), https://arxiv.org/abs/2609.38984 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_455d26249f2a (Metraipolis archive dc_455d26249f2a, sha256 70d057c4753efc28d8a45d5ee02f1196c0b7653b66494d1ac3b17de5a480c0d0)
BibTeX
@misc{dc455d26249f2a,
  title = {Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination — arXiv:2609.38984},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38984},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_455d26249f2a; sha256 70d057c4753efc28d8a45d5ee02f1196c0b7653b66494d1ac3b17de5a480c0d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38984. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-action models (WAMs) leverage pretrained video models to improve generalization in robot control by jointly predicting future visual states and actions. This capability comes at a substantial inference cost, as dense future-frame tokens are repeatedly processed during denoising. Prior methods address this by token pruning that prioritizes visual fidelity to reduce denoising costs in video diffusion models. However, these methods do not use action relevance to determine which future-frame tokens to retain during joint denoising in WAMs. In this paper, we propose Sparse-WAM, a training-free framework for action-guided sparse imagination that selectively processes future-frame tokens to accelerate WAM inference. We observe substantial overlap in the spatial distribution of attention from action tokens to future-frame tokens (action-to-future attention) between consecutive denoising steps, despite continued updates to the future representations. Motivated by this, we develop Action-Guided Token Selection to retain frame-specific action-relevant regions together with cross-frame context. However, a naive implementation can incur attention-scoring and token-packing overhead that offsets the computational savings from pruning. We therefore introduce Pilot, an efficient engine that reduces sparse inference overhead through lightweight scoring and cross-step reuse of token selections. On LIBERO with FastWAM-Joint and RoboLab-120 with Cosmos 3 Edge, Sparse-WAM achieves inference speedups of approximately $2.0\times$ and $1.8\times$, respectively, over dense eager inference on an NVIDIA RTX 4090, while largely preserving task performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38984 — 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 2026-10-07T12:14:13.992Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).