SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global