SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
SpikeVLA:基于脉冲神经网络的视觉-语言-动作模型
专题命中 VLA模型 :VLA(summary_cn,abstract);vision-language-action(title,abstract);action model(title);分类 cs.RO
AI总结 提出SpikeVLA,一种脉冲VLA架构,通过事件驱动稀疏计算降低能耗,在导航和机器人控制任务中保持竞争力,适用于低功耗实时具身智能。
Comments Accepted by ICML 2026. 16 pages, 9 figures
Journal ref Proceedings of the 43rd International Conference on Machine Learning, 2026