# Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models

arXiv: https://arxiv.org/abs/2604.25570 · HTML: https://mlsanity.com/paper/2604.25570/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Token pruning and merging for ViTs, one of 12 directions in Efficient LLM inference and serving.
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

- Efficient LLM inference and serving / [Token pruning and merging for ViTs](https://mlsanity.com/inference/token-pruning-and-merging-for-vits/)

## Builds on (most cited first, 30 of 39)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [LocalMamba: Visual State Space Model with Windowed Selective Scan](https://mlsanity.com/paper/2403.09338/) (2024)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [State Space Models for Event Cameras](https://mlsanity.com/paper/2402.15584/) (2024)
- [Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model](https://mlsanity.com/paper/2405.14174/) (2024)
- [Mamba-R: Vision Mamba ALSO Needs Registers](https://mlsanity.com/paper/2405.14858/) (2024)
- [Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2312.06372/) (2023)
- [TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks](https://mlsanity.com/paper/2206.10177/) (2022)
- [Spiking PointNet: Spiking Neural Networks for Point Clouds](https://mlsanity.com/paper/2310.06232/) (2023)
- [Exploring Token Pruning in Vision State Space Models](https://mlsanity.com/paper/2409.18962/) (2024)
- [SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding](https://mlsanity.com/paper/2404.01174/) (2024)
- [High-performance deep spiking neural networks with 0.3 spikes per neuron](https://mlsanity.com/paper/2306.08744/) (2023)
- [Spiking Vision Transformer with Saccadic Attention](https://mlsanity.com/paper/2502.12677/) (2025)
- [SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models](https://mlsanity.com/paper/2408.14909/) (2024)
- [Rethinking Token Reduction for State Space Models](https://mlsanity.com/paper/2410.14725/) (2024)

## Built on by (most cited first, 1 of 1)

- [RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision](https://mlsanity.com/paper/2609.32537/) (2026)

## Abstract (arXiv)

Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-driven nature of spiking neural computation. To address this limitation, we propose Vision SmolMamba, an energy-efficient spiking state-space architecture that integrates spike-driven dynamics with linear-time selective recurrence. The key idea is a Spike-Guided Spatio-Temporal Token Pruner (SST-TP), which estimates token importance using both spike activation strength and first-spike latency. This mechanism progressively removes redundant tokens while preserving salient spatio-temporal information, enabling efficient scaling with token sparsity. Based on this mechanism, the proposed SmolMamba block incorporates spike events directly into bidirectional state-space recurrence, forming a spiking state-space vision backbone for efficient long-range modeling. Extensive experiments on both static and event-based benchmarks, including ImageNet-1K, CIFAR10/100, CIFAR10-DVS, and DVS128 Gesture, demonstrate that Vision SmolMamba consistently achieves superior accuracy-efficiency trade-offs. In particular, it reduces the estimated energy cost by at least 1.5x compared with prior spiking Transformer baselines and a Spiking Mamba variant while maintaining competitive or improved accuracy. These results demonstrate that combining spike-guided token sparsity with state-space modeling offers a scalable and energy-efficient paradigm for spiking vision systems.