AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks

Ruiqi Song, Dujun Nie, Siyu Teng, Baiyong Ding, Xiaotong Zhang, Dong Li, Chenming Zhang, Yuchen Li, Hangbin Wu, Long Chen

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace dense ANN VLA with spiking SpikeVLANaVILA · R2R-CE Val-Unseenenergy (J): 141.25 -> 49.09Improved
replace dense ANN VLA with spiking SpikeVLANaVILA · R2R-CE Val-UnseenSR: 53.9 -> 53.3No clear effect
replace dense ANN VLA with spiking SpikeVLANaVILA · R2R-CE Val-UnseenSPL: 49.3 -> 47.9Hurt
replace dense ANN VLA with spiking SpikeVLANaVILA · R2R-CE Val-UnseenOS: 61.5 -> 63.4Improved
replace dense ANN VLA with spiking SpikeVLANaVILA · RxR-CE Val-UnseenSR: 52.3 -> 51.9No clear effect
replace dense ANN VLA with spiking SpikeVLANaVILA-R · VLN-CE-IsaacSR: 36.5 -> 32.7Hurt
replace dense ANN VLA with spiking SpikeVLANaVILA-R · VLN-CE-Isaacenergy (J): 141.25 -> 44.23Improved
use spiking action policy instead of ANN policyNaVILA low-level policy · closed-loop locomotionlinear velocity error: 0.23 -> 0.42Hurt
use spiking action policy instead of ANN policyNaVILA low-level policy · closed-loop locomotionangular velocity error: 0.38 -> 0.29Improved
use spiking action policy instead of ANN policyNaVILA low-level policy · closed-loop locomotionenergy (uJ): 5.80 -> 0.31Improved
INT4 quantization of ANN VLA (ablation)NaVILA · R2R Val-UnseenSR: 53.9 -> 48.2Hurt
INT4 quantization of ANN VLA (ablation)NaVILA · R2R Val-Unseenenergy (J): 141.25 -> 72.49Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy