Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control

• URL: http://arxiv.org/abs/2508.21505v1
• Date: Fri, 29 Aug 2025 10:37:37 GMT
• Title: Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control
• Abstract summary: Spiking neural networks promise ultra-low-power, event-driven inference.<n>We present the Spiking Decision Transformer (SNN-DT), which embeds Leaky Integrate-and-Fire neurons into each self-attention block.<n>By marrying sequence modeling with neuromorphic efficiency, SNN-DT opens a pathway toward real-time, low-power control on embedded and wearable devices.
• Score: 0.6117371161379209
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning agents based on Transformer architectures have achieved impressive performance on sequential decision-making tasks, but their reliance on dense matrix operations makes them ill-suited for energy-constrained, edge-oriented platforms. Spiking neural networks promise ultra-low-power, event-driven inference, yet no prior work has seamlessly merged spiking dynamics with return-conditioned sequence modeling. We present the Spiking Decision Transformer (SNN-DT), which embeds Leaky Integrate-and-Fire neurons into each self-attention block, trains end-to-end via surrogate gradients, and incorporates biologically inspired three-factor plasticity, phase-shifted spike-based positional encodings, and a lightweight dendritic routing module. Our implementation matches or exceeds standard Decision Transformer performance on classic control benchmarks (CartPole-v1, MountainCar-v0, Acrobot-v1, Pendulum-v1) while emitting fewer than ten spikes per decision, an energy proxy suggesting over four orders-of-magnitude reduction in per inference energy. By marrying sequence modeling with neuromorphic efficiency, SNN-DT opens a pathway toward real-time, low-power control on embedded and wearable devices.

Related papers

• A Spiking Sequence Generator for Polar Trajectories on Neuromorphic Hardware [0.44198435146063364]
  We present a spiking neural network (SNN) architecture for generating polar trajectories, using a winner-take-all (WTA) architecture with accessory populations that induce controlled transitions in neural activity.<n>We implement the network on the SpiNNaker2 neuromorphic processor, and demonstrate a two to three orders of magnitude reduction in wall-clock step time and three to four orders of magnitude reduction in energy expenditure when compared to conventional computing platforms.
  arXiv  Detail & Related papers  (2026-07-02T20:36:46Z)
• Elastic Spiking Transformers for Efficient Gesture Understanding [6.52225846892392]
  Spiking Neural Networks (SNNs) offer energy-efficient processing of event-based sensor data for healthcare applications.<n>We introduce the Elastic Spiking Transformer, a runtime-adaptive architecture that brings elasticity into the spiking paradigm.<n>We evaluate the approach on CIFAR10/100, CIFAR10-DVS, and the EHWGesture clinical gesture understanding dataset.
  arXiv  Detail & Related papers  (2026-05-04T12:35:52Z)
• Ge$^\ ext{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer [84.8831358775386]
  Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs)<n>Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations.<n>We propose Ge$text2$mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions.
  arXiv  Detail & Related papers  (2026-04-10T02:58:46Z)
• Hebbian Attractor Networks for Robot Locomotion [44.84033948079516]
  Hebbian plasticity offers a promising path toward rapid adaptation in changing environments.<n>Hebbian Attractor Networks (HANs) induce emergent attractor dynamics.<n>Results show that slower updates, combined with averaged pre- and postsynaptic activations, promote convergence to stable weight configurations.
  arXiv  Detail & Related papers  (2026-03-23T19:20:14Z)
• Neural Dynamics Self-Attention for Spiking Transformers [59.57278823240336]
  Spiking Neural Networks (SNNs) with Transformer architectures offer a promising pathway to balance energy efficiency and performance.<n>Existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference.<n>We propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements.
  arXiv  Detail & Related papers  (2026-03-09T12:23:37Z)
• Rethinking Vision Transformer Depth via Structural Reparameterization [16.12815682992294]
  We propose a branch-based structural reparameterization technique that operates during the training phase.<n>Our approach leverages parallel branches within transformer blocks that can be systematically consolidated into streamlined single-path models.<n>When applied to ViT-Tiny, the framework successfully reduces the original 12-layer architecture to 6, 4, or as few as 3 layers while maintaining classification accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2025-11-24T21:28:55Z)
• ZeroSim: Zero-Shot Analog Circuit Evaluation with Unified Transformer Embeddings [36.00558662624576]
  ZeroSim is a transformer-based performance modeling framework designed to achieve robust in-distribution generalization across trained topologies.<n>We show that ZeroSim significantly outperforms baseline models such as multilayer perceptrons, graph neural networks and transformers.<n>When integrated into a reinforcement learning-based parameter optimization pipeline, ZeroSim achieves a remarkable speedup (13x) compared to conventional SPICE simulations.
  arXiv  Detail & Related papers  (2025-11-10T22:08:30Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• Mental Accounts for Actions: EWA-Inspired Attention in Decision Transformers [2.9385229328767983]
  We propose Experience-Weighted Attraction with Vector Quantization for Online Decision Transformers (EWA-VQ-ODT)<n>EWA-VQ-ODT is a lightweight module that maintains per-action mental accounts summarizing recent successes and failures.<n>On standard continuous-control benchmarks, EWA-VQ-ODT improves sample efficiency and average return over ODT.
  arXiv  Detail & Related papers  (2025-09-19T00:33:22Z)
• Physics-Embedded Neural ODEs for Sim2Real Edge Digital Twins of Hybrid Power Electronics Systems [6.073480880825787]
  Edge Digital Twins (EDTs) are crucial for monitoring and control of Power Electronics Systems (PES)<n>Existing modeling approaches struggle to consistently capture continuously evolving hybrid dynamics that are inherent in PES.<n>This paper proposes a Physics-Embedded Neural ODEs (PENODE) that embeds the hybrid operating mechanism as an event automaton to explicitly govern switching discrete.
  arXiv  Detail & Related papers  (2025-08-04T20:34:13Z)
• Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection [14.363929799618283]
  We propose CHain Of thOught Symbol dEtection (CHOOSE), a CoT-enhanced shallow Transformer framework for wireless symbol detection.<n>By introducing autoregressive latent reasoning steps within the hidden space, CHOOSE significantly improves the reasoning capacity of shallow models.<n> Experimental results demonstrate that our approach outperforms conventional shallow Transformers and achieves performance comparable to that of deep Transformers.
  arXiv  Detail & Related papers  (2025-06-26T08:41:45Z)
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving [62.62464518137153]
  DriveTransformer is a simplified E2E-AD framework for the ease of scaling up.<n>It is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention.<n>It achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.
  arXiv  Detail & Related papers  (2025-03-07T11:41:18Z)
• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN)<n>We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations.<n>Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer [15.93436166506258]
  Spiking Neural Networks have emerged as a promising energy-efficient alternative to traditional Artificial Neural Networks.<n>This paper introduces Accurate Addition-Only Spiking Self-Attention (A$2$OS$2$A)
  arXiv  Detail & Related papers  (2025-02-28T22:23:29Z)
• Spiking Transformer Hardware Accelerators in 3D Integration [5.426379844893919]
  Spiking neural networks (SNNs) are powerful models of computation and are well suited for on resource-constrained edge devices and neuromorphic hardware. Recently emerged showcased spiking transformers have promising performance and efficiency by capitalizing on the binary nature of spiking operations.
  arXiv  Detail & Related papers  (2024-11-11T22:08:11Z)
• Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves [69.9104427437916]
  Multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics.
  arXiv  Detail & Related papers  (2024-04-17T02:04:10Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Transformers Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.