الملخص
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 https://ccdcs.github.io/LiMA_repo/
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Chen, N., Fu, Y., Zhao, J., Sun, Q., Yao, G., Wang, P., Wang, Z., & Zhang, S. (2026). LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion. https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion
MLA 9
Chen, Ning, et al. "LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion." https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion.
شيكاغو (المؤلف–التاريخ)
Chen, Ning, Yankai Fu, Junkai Zhao, Qianpu Sun, Guocai Yao, Pengwei Wang, Zhongyuan Wang, and Shanghang Zhang. 2026. "LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion." https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion.
هارفارد
Chen, N., Fu, Y., Zhao, J., Sun, Q., Yao, G., Wang, P., Wang, Z. and Zhang, S. (2026) 'LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion', Available at: https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion.
فانكوفر
Chen N, Fu Y, Zhao J, Sun Q, Yao G, Wang P, et al. LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion. https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion
IEEE
N. Chen, Y. Fu, J. Zhao, Q. Sun, G. Yao, P. Wang, Z. Wang, and S. Zhang, "LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion," https://omanscience.com/ar/articles/lima-bridging-long-term-imagination-to-real-time-dexterous-manipulation-via-asynchronous-diffusion.