# SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

arXiv: https://arxiv.org/abs/2407.04752 · HTML: https://mlsanity.com/paper/2407.04752/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 69 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 30 of 47)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2309.14717/) (2023)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)

## Built on by (most cited first, 30 of 31)

- [Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives](https://mlsanity.com/paper/2409.08290/) (2024)
- [Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions](https://mlsanity.com/paper/2409.02111/) (2024)
- [A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search](https://mlsanity.com/paper/2507.00004/) (2025)
- [Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding](https://mlsanity.com/paper/2509.18968/) (2025)
- [Spiking Manifesto](https://mlsanity.com/paper/2512.11843/) (2025)
- [SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba](https://mlsanity.com/paper/2510.04595/) (2025)
- [QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models](https://mlsanity.com/paper/2601.00679/) (2026)
- [Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation](https://mlsanity.com/paper/2506.23717/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Spatio-Temporal Pruning for Compressed Spiking Large Language Models](https://mlsanity.com/paper/2508.20122/) (2025)
- [SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition](https://mlsanity.com/paper/2511.07883/) (2025)
- [Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing](https://mlsanity.com/paper/2601.00245/) (2026)
- [SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference](https://mlsanity.com/paper/2604.22575/) (2026)
- [SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding](https://mlsanity.com/paper/2505.17674/) (2025)
- [Kirin: Improving ANN efficiency with SNN Hybridization](https://mlsanity.com/paper/2602.08817/) (2026)
- [BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation](https://mlsanity.com/paper/2605.13859/) (2026)
- [SymbolicLight V1: Spike-Gated Dual-Path Language Modeling at High Encoder Spike Sparsity](https://mlsanity.com/paper/2605.21333/) (2026)
- [SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks](https://mlsanity.com/paper/2606.27807/) (2026)
- [A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks](https://mlsanity.com/paper/2510.20683/) (2025)
- [NEXUS: Bit-Exact ANN-to-SNN Equivalence via Neuromorphic Gate Circuits with Surrogate-Free Training](https://mlsanity.com/paper/2601.21279/) (2026)
- [MAR: Efficient Large Language Models via Module-aware Architecture Refinement](https://mlsanity.com/paper/2601.21503/) (2026)
- [Matterhorn: Masked Time-to-First-Spike Encoding by Reassigning the Silent State for Sparse and Energy-Efficient Spiking Transformers](https://mlsanity.com/paper/2601.22876/) (2026)
- [Spike-driven Large Language Model](https://mlsanity.com/paper/2604.16475/) (2026)
- [LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning](https://mlsanity.com/paper/2606.12895/) (2026)
- [Otters++: A Time-to-first-spike Based Energy Efficient Optical Spiking Transformer](https://mlsanity.com/paper/2606.13016/) (2026)
- [SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models](https://mlsanity.com/paper/2608.27857/) (2026)
- [Large Language Models with At Most One Spike per Neuron](https://mlsanity.com/paper/2609.05151/) (2026)
- [URCHIN: A Horizontal Spiking Language Model for Data-Constrained Pretraining](https://mlsanity.com/paper/2609.13899/) (2026)
- [QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models](https://mlsanity.com/paper/2609.34259/) (2026)
- [Rethinking the Tradeoff Between Temporal Encoding and Nonlinear Computation in Spiking Language Models](https://mlsanity.com/paper/2610.10933/) (2026)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) with billions of parameters have improved performance in various applications, but their inference processes demand significant energy and computational resources. In contrast, the human brain, with approximately 86 billion neurons, is much more energy-efficient than LLMs with similar parameters. Inspired by this, we redesign 7~70 billion parameter LLMs using bio-plausible spiking mechanisms, emulating the efficient behavior of the human brain. We propose the first spiking large language model, SpikeLLM. Coupled with the proposed model, two essential approaches are proposed to improve spike training efficiency: Generalized Integrate-and-Fire (GIF) neurons to compress spike length from T to fracTL log2 L bits, and an Optimal Brain Spiking framework to divide outlier channels and allocate different T for GIF neurons, which further compresses spike length to approximate log2T bits. The necessity of spike-driven LLM is proved by comparison with quantized LLMs with similar operations. In the OmniQuant pipeline, SpikeLLM reduces 11.01% WikiText2 perplexity and improves 2.55% accuracy of common scene reasoning on a LLAMA-7B W4A4 model. In the GPTQ pipeline, SpikeLLM achieves direct additive in linear layers, significantly exceeding PB-LLMs.