AI RESEARCH
DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
arXiv CS.LG
•
ArXi:2603.07904v1 Announce Type: new Vision-Language-Action (VLA) models are dominant in embodied intelligence but are constrained by inference overheads. While model quantization alleviates these bottlenecks for edge deployment, static quantization approaches remain suboptimal for VLAs due to two critical challenges: (1) Temporal-dynamic sensitivity, where fixed precision wastes resources by ignoring stage-varying error tolerances; and (2) Real-time allocation, where identifying real-time sensitivity to guide bit allocation remains unsolved.