Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

VL2Spike: Spike-driven Distillation from VLMs for Low-Power Visual Perception in Embodied AI

About

Spiking neural networks (SNNs) are brain-inspired, event-driven models that compute with sparse spikes, which enables highly efficient visual perception in resource-constrained embodied AI models. The emergence of Spiking-Transformer models with spike self-attention has substantially improved the learning capacity of pure SNNs. Although SNNs are energy efficient, their performance is still limited by the spike-based architecture and optimization challenges, as standard gradient descent rules cannot be directly applied. Recently, vision-language models (VLMs) have shown rich multi-modal knowledge representation capabilities for visual perception. Thus, it is promising to leverage VLMs for better Spikformer training. To this end, we present VL2Spike, a novel spike-based knowledge distillation (KD) framework that bridges multi-modal knowledge from VLMs with compact Spikformer models. This design enhances the learning capacity of Spikformer models while preserving their energy-efficiency merits, thereby offering a practical pathway toward low-power robotic perception. Our VL2Spike brings two key technical contributions. To align with spiking dynamics, we first propose spatial-temporal visual spike (SVS) distillation, which achieves (1) shared manifold alignment between VLM image features and spike tokens, and (2) warm-started temporal consistency on membrane potentials and spike rates. We then design a novel spike prototype-guided linguistic (SPL) distillation strategy that aligns Spikformer's class prototypes and logits with promptable VLM text embeddings. Extensive experiments show that VL2Spike achieves 6.81% gain across three static datasets with only 15.7% energy consumption. It also exhibits strong generalization capacity on robotic visual place recognition (VPR) with a gain of 6.63%, highlighting its potential for low-power perception in embodied AI.

Zinan Liu, Eric Zheng, Soumyaratna Debnath, Hao Shi, Ling Xiao, Lin Wang• 2026

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10--
973
Event-based action recognitionDVS128 Gesture
Top-1 Acc98.51
12
Neuromorphic Event ClassificationDVS-Lip
Accuracy54.35
9
Event-based RecognitionDVS-CIFAR10
Top-1 Accuracy81.14
6
Event-based RecognitionN-Caltech101
Top-1 Accuracy70.03
5
Visual Place RecognitionNordland
Precision@100% Recall57.24
5
Visual Place RecognitionOxford RobotCar
Precision at 100% Recall53.75
5
Showing 7 of 7 rows

Other info

Follow for update