Pith. sign in

REVIEW 7 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.04752 v3 pith:BLI67QJ6 submitted 2024-07-05 cs.LG cs.CLcs.NE

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

classification cs.LG cs.CLcs.NE
keywords spikingllmsspikellmbrainlanguagelargemodelneurons
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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$\sim$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 $\frac{T}{L} \log_2 L$ 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 $log_2T$ 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Otters++: A Time-to-first-spike Based Energy Efficient Optical Spiking Transformer

    cs.AI 2026-06 unverdicted novelty 7.0

    Otters++ realizes TTFS via measured device decay in optical synapses, uses hybrid QNN-equivalent training with noise awareness, and reports 84.17% average GLUE score with energy gains over prior spiking transformers.

  2. LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining s...

  3. Winner-Take-All Spiking Transformer for Language Modeling

    cs.NE 2026-04 unverdicted novelty 7.0

    Winner-take-all spiking self-attention replaces softmax in spiking transformers to support language modeling on 16 datasets with spike-driven, energy-efficient architectures.

  4. SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks

    cs.RO 2026-06 unverdicted novelty 6.0

    SpikeVLA replaces transformer components in VLA models with spiking vision encoder, multi-modal LLM, and action policy network to reduce energy consumption while maintaining competitive performance on navigation tasks.

  5. Representation Capacity-Matched QNN-SNN Twin Construction for Rate-Encoded SNNs

    cs.NE 2024-08 unverdicted novelty 6.0

    Rate-encoded SNNs with T timesteps outperform bit-equivalent QNNs in energy only when average spike rate falls below 6.4% for T in [5,10] under typical neuromorphic hardware, per an analytical model covering computati...

  6. Adaptive Spiking Neurons for Vision and Language Modeling

    cs.NE 2026-04 unverdicted novelty 5.0

    ASN uses trainable parameters for adaptive membrane dynamics and firing in SNNs, with NASN adding normalization, and reports effectiveness across 19 vision and language datasets.

  7. SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba

    cs.NE 2025-10 unverdicted novelty 5.0

    SpikingMamba distills Mamba into an SNN LLM achieving 4.76x energy savings with a 4.78% zero-shot accuracy gap that narrows to 2.23% after RL.