Metraipolis › archive › dc_f24eb845fe77

LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion — arXiv:2609.28431

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28431
License (as archived)
CC0-1.0
Archived
2026-10-08T12:53:58.199Z
SHA-256 of the archived text
59a0901ee59ce34d9b3e93426d95ba6af3942870c55b9bbc5d01d864ab31fa34
Stable URL of this page
https://metraipolis.com/documento/dc_f24eb845fe77

How to cite

LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion — arXiv:2609.28431 — arXiv (en), https://arxiv.org/abs/2609.28431 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f24eb845fe77 (Metraipolis archive dc_f24eb845fe77, sha256 59a0901ee59ce34d9b3e93426d95ba6af3942870c55b9bbc5d01d864ab31fa34)
BibTeX
@misc{dcf24eb845fe77,
  title = {LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion — arXiv:2609.28431},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28431},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f24eb845fe77; sha256 59a0901ee59ce34d9b3e93426d95ba6af3942870c55b9bbc5d01d864ab31fa34},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28431. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dexterous manipulation demands long-term foresight and rapid reactive control. Vision-Language-Action (VLA) models, while proficient in high-level reasoning, often lack a fine-grained understanding of physical dynamics and spatial perception. Conversely, World-Action Models (WAMs) typically suffer from high inference latency due to iterative generation. These deficiencies result in a critical temporal misalignment where the model's intent fails to adapt to rapid physical contact changes. To overcome this fundamental bottleneck, we propose LiMA, an asynchronous dual-system generative framework that systematically decouples intent planning from reactive execution. LiMA organizes computation into a multi-scale hierarchy: a slow system handles sparse long-horizon spatiotemporal intent generation, while a fast system focuses on dense high-frequency motion refinement. To align sparse intent predictions with dense action trajectories, we introduce a Latent Schrödinger Bridge Coupling mechanism that formulates refinement as an entropy-regularized probabilistic transport process. LiMA reduces inference latency by 45.8% compared with Cosmos-Policy via asynchronous decoupling. Evaluated across six bimanual dexterous manipulation tasks spanning multiple horizons, LiMA achieves an overall success rate of 70.8% and an average subtask success rate of 78.9%, while maintaining performance in unseen scenarios. The project website is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.28431 — 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 2026-10-08T12:21:19.519Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).