Spiking vla cuts delay for efficient vision language action models
SpikingVLA: Asynchronous Spiking Vision-Language-Action Models
Computation and Language
Summary
Vision-language-action models help robots understand and act using sight and language, but making these models efficient can be slow. The authors created SpikingVLA, a new way to convert existing models into faster, energy-saving versions that use fewer steps to make decisions. They introduced special neurons to better handle activation signals and a method to run parts of the model at different times to reduce waiting. Their approach leads to much quicker responses with similar or better performance in navigation tasks.
What this means in practice
- •For robotics engineers: Integrate faster and more energy-efficient vision-language models into robots for quicker real-time navigation decisions.
- •For embedded systems developers: Deploy pretrained vision-language-action models with reduced inference latency on low-power spiking hardware for improved responsiveness.
Authors
Jingya Wang, Dehao Zhang, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li
Abstract
ANN-to-SNN conversion offers a practical route toward energy-efficient spiking Vision-Language-Action (VLA) models by bypassing the substantial cost of training large-scale SNNs from scratch. However, existing methods often require many timesteps to maintain competitive performance, resulting in substantial inference latency for real-time VLA deployment. To address this challenge, we introduce SpikingVLA, an ANN-to-SNN conversion framework that enables accurate and low-latency spiking VLA inference. Specifically, we propose a Dendritic Integrate-and-Fire (DIF) neuron that alleviates channel-wise activation outliers through dendritic mixing and adaptive somatic firing, enabling accurate ANN-to-SNN conversion with fewer timesteps. Building on DIF neurons, we further introduce an asynchronous execution mechanism that overlaps temporal computation across VLA components, reducing synchronization overhead and latency. Extensive experiments demonstrate that SpikingVLA achieves competitive navigation performance with substantially improved inference efficiency. Compared with existing spiking VLA methods, SpikingVLA improves SR and SPL by 11.9\% and 12.6\%, respectively, while reducing first-action latency by 11.2$\times$. These results establish SpikingVLA as a practical framework for deploying pretrained VLA models with high-performance and low-latency spiking inference.