mlsanityData to 7 Oct 2026

FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning

arXiv 2504.01257 ↗First posted 2 Apr 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose FLAMES (Fast Long-range Adaptive Memory for Event-based Systems), a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the textitSpike-Aware HiPPO (SA-HiPPO) mechanism dynamically adjusts memory retention based on inter-spike intervals, preserving both short- and long-range dependencies. To maintain computational efficiency, we introduce a normal-plus-low-rank (NPLR) decomposition, reducing complexity from O(N2) to O(Nr). FLAMES achieves state-of-the-art results on the Long Range Arena benchmark and event datasets like HAR-DVS and Celex-HAR. By bridging neuromorphic computing and structured sequence modeling, FLAMES enables scalable long-range reasoning in event-driven systems.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 72 of its 97 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

72 of 97 references.

References · 72

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  8. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  9. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  10. 2021Video Swin Transformercited by 1,090
  11. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  12. 2019Event-based Vision: A Surveycited by 1,010
38 more
  1. 2024VMamba: Visual State Space Modelcited by 955
  2. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  3. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  4. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 696
  5. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  6. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  7. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  8. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  9. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  10. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  11. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  12. 2022Transformer Quality in Linear Timecited by 189
  13. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  14. 2020Liquid Time-constant Networkscited by 160
  15. 2023Spike-driven Transformercited by 141
  16. 2020TAM: Temporal Adaptive Module for Video Recognitioncited by 139
  17. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 135
  18. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 121
  19. 2022The Devil in Linear Transformercited by 98
  20. 2024Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architecturescited by 97
  21. 2023Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baselinecited by 73
  22. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  23. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 67
  24. 2021ACTION-Net: Multipath Excitation for Action Recognitioncited by 63
  25. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  26. 2020Temporal Binary Representation for Event-Based Action Recognitioncited by 50
  27. 2022Online Training Through Time for Spiking Neural Networkscited by 48
  28. 2023Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacingscited by 48
  29. 2022HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensorscited by 46
  30. 2020Surrogate gradients for analog neuromorphic computingcited by 38
  31. 2021A Voxel Graph CNN for Object Classification with Event Camerascited by 38
  32. 2020Brain-Inspired Learning on Neuromorphic Substratescited by 35
  33. 2021Accurate online training of dynamical spiking neural networks through Forward Propagation Through Timecited by 33
  34. 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and Morecited by 33
  35. 2024Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Modelscited by 31
  36. 2023TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modellingcited by 21
  37. 2023Learning Long Sequences in Spiking Neural Networkscited by 19
  38. 2024Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMambacited by 18

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Visioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
  2. 2024SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models
  3. 2024PRF: Parallel Resonate and Fire Neuron for Long Sequence Learning in Spiking Neural Networks
  4. 2024SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning
  5. 2026LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
  6. 2025Delays in Spiking Neural Networks: A State Space Model Approach
  7. 2025Scaling Up Resonate-and-Fire Networks for Fast Deep Learning
  8. 2025SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks