Large Language Models with At Most One Spike per Neuron

• URL: http://arxiv.org/abs/2609.05151v1
• Date: Fri, 04 Sep 2026 13:53:28 GMT
• Title: Large Language Models with At Most One Spike per Neuron
• Abstract summary: Time-to-first-spike (TTFS) coding generates at most one spike per neuron within a time window, yielding extremely low firing rates.<n>We introduce a reference-based strategy specifically to encode the four core LLM components.<n>We construct a fully TTFS-based SNN architecture and train it end-to-end.
• Score: 1.1175141719762662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large language models (LLMs). Time-to-first-spike (TTFS) coding generates at most one spike per neuron within a time window, yielding extremely low firing rates. However, conventional TTFS SNNs are restricted to specific structures, making it challenging to encode certain blocks in LLM -- such as layer normalization and matrix multiplication --using TTFS. To overcome this limitation, we introduce a reference-based strategy specifically to encode the four core LLM components: embedding layers, layer normalization, attention-related operations and dropout. We construct a fully TTFS-based SNN architecture and train it end-to-end. Experiments on modern LLMs like BERT and GPT-2 demonstrate that our approach achieves performance comparable to ANN counterparts on natural language understanding and common-sense reasoning, while a clear gap remains on language modeling perplexity. To the best of our knowledge, this is the first work to scale a spiking LLM to 1.5 billion parameters using TTFS coding. We also report an estimate of spike-related energy; this is a spike-count proxy under an established cost model rather than a measurement on neuromorphic hardware.

Related papers

• LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning [53.855185131868446]
  Spiking Neural Networks (SNNs) are well-regarded for their biological plausibility and energy efficiency in processing sequential data.<n>In this work, we propose LongSpike, a novel SNN framework that integrates fractional-order State-Space Modeling.<n>By extending traditional integer-order SSMs to the fractional-calculus regime, LongSpike enables the hierarchical integration of neuronal dynamics with long-memory kernels.
  arXiv  Detail & Related papers  (2026-06-11T04:54:07Z)
• SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression [46.709828328948724]
  Spiking Neural Networks (SNNs) offer inherent energy efficiency advantages on neuromorphic hardware.<n>We propose SpikeMLLM, the first spike-based framework for MLLMs.<n>We show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression.
  arXiv  Detail & Related papers  (2026-04-13T15:32:44Z)
• Spike-driven Large Language Model [49.52947423982696]
  Spiking Neural Networks (SNNs) possess spike-driven characteristics.<n>Current Large Language Models (LLMs) are primarily based on large-scale dense matrix multiplications.<n>We propose SDLLM, a spike-driven large language model that eliminates dense matrix multiplications through sparse addition operations.
  arXiv  Detail & Related papers  (2026-04-11T17:58:35Z)
• Optimal Scheduling Algorithms for LLM Inference: Theory and Practice [6.043830060363904]
  This paper develops a theoretical framework that models routing and scheduling in Large Language Model inference systems.<n>We identify two key design principles-optimal tiling and dynamic resource allocation-that are essential for achieving high throughput.<n>We show that the Resource-Aware Dynamic (RAD) scheduler achieves throughput optimality under mild conditions.
  arXiv  Detail & Related papers  (2025-08-01T18:12:21Z)
• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission [87.68447072141402]
  Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers.<n>We propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL)
  arXiv  Detail & Related papers  (2025-06-30T02:56:11Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding [55.64533786293656]
  We show that our algorithm can achieve a near-perfect mapping between the activation values of an ANN and the spike times of an SNN on a number of challenging AI tasks. The study paves the way for deploying ultra-low-power TTFS-based SNNs on power-constrained edge computing platforms.
  arXiv  Detail & Related papers  (2023-10-23T14:26:16Z)
• You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracy [51.861168222799186]
  Spiking Neural Networks (SNNs) are a type of neuromorphic, or brain-inspired network. SNNs are sparse, accessing very few weights, and typically only use addition operations instead of the more power-intensive multiply-and-accumulate operations. In this work, we aim to overcome the limitations of TTFS-encoded neuromorphic systems.
  arXiv  Detail & Related papers  (2020-06-03T15:55:53Z)

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.