Metraipolis › archive › dc_ca4d9d5bd0ea
Efficient World Action Model Inference with Adaptive Intermediate States — arXiv:2609.34608
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34608
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:46.139Z
- SHA-256 of the archived text
7e2eb36626ed0db33e6e49276fe0924654927c0e0677352ade94ae93a877b6c4- Stable URL of this page
https://metraipolis.com/documento/dc_ca4d9d5bd0ea
How to cite
Efficient World Action Model Inference with Adaptive Intermediate States — arXiv:2609.34608 — arXiv (en), https://arxiv.org/abs/2609.34608 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca4d9d5bd0ea (Metraipolis archive dc_ca4d9d5bd0ea, sha256 7e2eb36626ed0db33e6e49276fe0924654927c0e0677352ade94ae93a877b6c4)
BibTeX
@misc{dcca4d9d5bd0ea,
title = {Efficient World Action Model Inference with Adaptive Intermediate States — arXiv:2609.34608},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34608},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca4d9d5bd0ea; sha256 7e2eb36626ed0db33e6e49276fe0924654927c0e0677352ade94ae93a877b6c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34608. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World Action Models (WAMs) enable future-aware control by jointly modeling actions and environment dynamics. However, iterative diffusion or flow inference incurs substantial denoising latency. Prior inference state offers a natural opportunity for acceleration, yet changing planning contexts, observations, and intermediate representations can quickly render retained state stale. Preserving useful computation therefore requires adapting inference state rather than reusing it as-is. To this end, we present $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$, a training-free framework that accelerates WAM inference by preserving and adapting inference state for efficient and accurate continuation as the control loop evolves. Across closed-loop replans, Trajectory Remapping remaps replan state from the preceding replan to initialize the next replan, reducing redundant trajectory generation. Across denoising steps, Observation Rebinding performs anticipatory inference during action execution and rebinds retained denoising state to the real observation for continuation when consistency checks pass, reducing latency exposed to the control loop. Across Transformer layers, Residual Rescaling selectively rescales retained layer state and refreshes it through full computation of the middle layers when probe checks fail, reducing repeated Transformer computation. Evaluations of three representative WAM architectures on LIBERO and RoboTwin 2.0 show that $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$ achieves 1.47-3.05$\times$ speedups in observation-to-action latency and 2.23-3.27$\times$ speedups in GPU inference time per replan, while preserving 96.69-99.54% of native WAM task success.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34608 — 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 2026-10-07T20:29:03.039Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).