# REACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal Perception

arXiv: https://arxiv.org/abs/2609.19204 · HTML: https://mlsanity.com/paper/2609.19204/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [On the Parameterization and Initialization of Diagonal State Space Models](https://mlsanity.com/paper/2206.11893/) (2022)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [State Space Models for Event Cameras](https://mlsanity.com/paper/2402.15584/) (2024)
- [Neuromorphic Data Augmentation for Training Spiking Neural Networks](https://mlsanity.com/paper/2203.06145/) (2022)
- [An Analytical Estimation of Spiking Neural Networks Energy Efficiency](https://mlsanity.com/paper/2210.13107/) (2022)
- [Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models](https://mlsanity.com/paper/2404.18508/) (2024)
- [Learning Long Sequences in Spiking Neural Networks](https://mlsanity.com/paper/2401.00955/) (2023)
- [Asynchronous Blob Tracker for Event Cameras](https://mlsanity.com/paper/2307.10593/) (2023)
- [Balanced Resonate-and-Fire Neurons](https://mlsanity.com/paper/2402.14603/) (2024)
- [Globally Optimal Event-Based Divergence Estimation for Ventral Landing](https://mlsanity.com/paper/2209.13168/) (2022)
- [Event-Aided Time-to-Collision Estimation for Autonomous Driving](https://mlsanity.com/paper/2407.07324/) (2024)
- [Compute-in-Memory Implementation of State Space Models for Event Sequence Processing](https://mlsanity.com/paper/2511.13912/) (2025)
- [FAITH: Fast iterative half-plane focus of expansion estimation using event-based optic flow](https://mlsanity.com/paper/2102.12823/) (2021)
- [EvTTC: An Event Camera Dataset for Time-to-Collision Estimation](https://mlsanity.com/paper/2412.05053/) (2024)
- [SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks](https://mlsanity.com/paper/2506.06374/) (2025)
- [Toward Deep Representation Learning for Event-Enhanced Visual Autonomous Perception: the eAP Dataset](https://mlsanity.com/paper/2603.16303/) (2026)

## Abstract (arXiv)

Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream. Event cameras provide microsecond temporal resolution and asynchronous sensing, but most learning-based methods accumulate events into frames or temporal bins, introducing an integration delay that can limit fast reaction. Here we propose REACT, a fully spiking state-space model for event-driven temporal perception that processes raw events one by one, without temporal accumulation. REACT uses a complex-valued spiking neuron, C-SiLIF, whose continuous-time dynamics are driven by the physical inter-event interval, allowing its internal state to evolve at the temporal resolution of individual events. We evaluate REACT on gesture recognition and time-to-collision (TTC) estimation from full-field event streams, without a target bounding box or localization input. On EvTTC, REACT achieves a 9.59% relative TTC error with 4.6 ms end-to-end inference latency, within 0.15 percentage points of the best learned method while requiring no target prior. At the dataset's mean approach speed, this latency corresponds to only 4 cm of vehicle motion, compared with 1 m for the fastest competing learned method. REACT further supports anytime TTC prediction, zero-shot transfer to a different driving sequence, and INT8 quantization, reducing the estimated energy consumption from 18.5 to 2.8 mJ per 32,768 events. These results show that event-driven spiking state-space dynamics can provide low-latency, continuously updated temporal perception for reactive robotic systems.