# LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models

arXiv: https://arxiv.org/abs/2505.09659 · HTML: https://mlsanity.com/paper/2505.09659/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2025.

## Built on by (most cited first, 2 of 2)

- [Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers](https://mlsanity.com/paper/2605.20289/) (2026)
- [QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models](https://mlsanity.com/paper/2609.34259/) (2026)

## Abstract (arXiv)

Spiking Large Language Models (LLMs) have emerged as an energy-efficient alternative to conventional LLMs through their event-driven computation. To effectively obtain spiking LLMs, researchers develop different ANN-to-SNN conversion methods by leveraging pre-trained ANN parameters while inheriting the energy efficiency of SNN. However, existing conversion methods struggle with extreme activation outliers and incompatible nonlinear operations of ANN-based LLMs. To address this, we propose a loss-less ANN-SNN conversion for fully spike-driven LLMs, termed LAS. Specifically, LAS introduces two novel neurons to convert the activation outlier and nonlinear operation of ANN-based LLMs. Moreover, LAS tailors the spike-equivalent Transformer components for spiking LLMs, which can ensure full spiking conversion without any loss of performance. Experimental results on six language models and two vision-language models demonstrate that LAS achieves loss-less conversion. Notably, on OPT-66B, LAS even improves the accuracy of 2% on the WSC task. In addition, the parameter and ablation studies further verify the effectiveness of LAS. The source code is available at https://github.com/lc783/LAS